JP6984172B2 - Driving support method and driving support device - Google Patents

Description

The present invention relates to a traveling support method and a traveling support device.

Conventionally, a vehicle control device that predicts the operation of another vehicle and changes the operation of the own vehicle based on the reliability of the prediction has been known (see Patent Document 1). The vehicle control device of Patent Document 1 predicts the operation of another vehicle based on the current state of the own vehicle and the current state of the environment in which the own vehicle is placed, and determines the reliability of the prediction.

U.S. Pat. No. 8,457,827

However, the vehicle control device of Patent Document 1 does not select an appropriate prediction method according to a driving scene, and cannot predict the operation of another vehicle with sufficient accuracy. In particular, the vehicle control device of Patent Document 1 makes a prediction targeting a traveling scene in which another vehicle is located in front of the own vehicle for the purpose of avoiding a collision between the own vehicle and the other vehicle. However, it does not make a prediction targeting a driving scene in which another vehicle (rear vehicle) located behind the vehicle exists. Therefore, in consideration of the movement of the rear vehicle, it is not possible to smoothly support the traveling of the own vehicle.

The present invention has been made to solve such a conventional problem, and an object of the present invention is to predict the movement of a rear vehicle in a driving scene in which a rear vehicle exists, and to predict the movement of the rear vehicle. It is an object of the present invention to provide a travel support method and a travel support device that support the travel of the own vehicle based on a prediction.

The traveling support method and the traveling support device according to the present invention detect a rear vehicle located behind the own vehicle, detect an environment in which the rear vehicle is placed, and based on the environment in which the rear vehicle is placed, the rear vehicle It predicts the movement and supports the running of the own vehicle based on the prediction result.

According to the present invention, in a traveling scene in which a rear vehicle exists, it is possible to predict the movement of the rear vehicle and support the traveling of the own vehicle based on the prediction of the movement of the rear vehicle.

FIG. 1 is a block diagram showing a configuration of a traveling support device according to an embodiment of the present invention. FIG. 2 is a flowchart showing an example of the operation of the traveling support device of FIG. FIG. 3 is a flowchart showing an example of the detailed procedure of step S06 of FIG. FIG. 4A is a plan view showing a traveling scene (first traveling scene) immediately before the own vehicle enters an intersection on a road having two lanes on each side. FIG. 4B is a plan view showing a traveling scene immediately after the time has passed from the traveling scene shown in FIG. 4A and the own vehicle has passed the intersection. FIG. 5 is a plan view showing a traveling scene (second traveling scene) in which the own vehicle crosses an adjacent lane. FIG. 6 is a plan view showing a traveling scene (third traveling scene) when the own vehicle changes lanes toward the adjacent lane. FIG. 7 is a plan view showing a traveling scene (fourth traveling scene) when the stopped own vehicle is about to start on a road with one lane on each side. FIG. 8 is a plan view showing a traveling scene (fifth traveling scene) when the own vehicle tries to stop on the shoulder of the road. FIG. 9 is a plan view showing a traveling scene (sixth traveling scene) when the own vehicle has passed the intersection on a road with two lanes on each side and another vehicle tries to enter the intersection from the lane intersecting at the intersection. Is. FIG. 10 is a plan view showing a traveling scene (seventh traveling scene) in which a road confluence exists in front of the own vehicle. FIG. 11 is a plan view showing a traveling scene (eighth traveling scene) in which a traffic prohibited area exists in an adjacent lane in front of the own vehicle. FIG. 12 is a plan view showing a traveling scene (9th traveling scene) in which the rear vehicle exists at the position of the stop line behind the own vehicle when the own vehicle tries to stop on the shoulder of the road. FIG. 13 is a plan view showing a visible area and an invisible area behind the own vehicle.

Hereinafter, an embodiment to which the present invention is applied will be described with reference to the drawings.

[Configuration of driving support device]
FIG. 1 is a block diagram showing a configuration of a traveling support device according to the present embodiment. As shown in FIG. 1, the traveling support device according to the present embodiment includes an object detection device 1, an own vehicle position estimation device 3, a map acquisition device 4, and a microcomputer 100.

The object detection device 1 includes a plurality of different types of object detection sensors mounted on the own vehicle 51 to detect objects existing around the own vehicle 51 such as a laser radar, a millimeter wave radar, and a camera. The object detection device 1 detects an object around the own vehicle 51 by using a plurality of object detection sensors. The object detection device 1 detects a moving object including another vehicle, a motorcycle, a bicycle, a pedestrian, and a stationary object including a parked vehicle. For example, the position, posture, size, speed, acceleration, deceleration, and yaw rate of a moving object and a stationary object with respect to the own vehicle 51 are detected. The position, posture (yaw angle), size, speed, acceleration, deceleration, and yaw rate of the object are collectively called the "behavior" of the object. As a detection result, the object detection device 1 outputs, for example, the behavior of a two-dimensional object in a zenith view (also referred to as a plan view) viewed from the air above the own vehicle 51.

The own vehicle position estimation device 3 includes a position detection sensor mounted on the own vehicle 51 to measure the absolute position of the own vehicle 51 such as GPS (Global Positioning System) and odometry. The own vehicle position estimation device 3 measures the absolute position of the own vehicle 51, that is, the position, posture, and speed of the own vehicle 51 with respect to a predetermined reference point by using the position detection sensor.

The map acquisition device 4 acquires map information indicating the structure of the road on which the own vehicle 51 travels. The map acquisition device 4 may own a map database storing map information, or may acquire map information from an external map data server by cloud computing. The map information acquired by the map acquisition device 4 includes information on the road structure such as the absolute position of the lane, the connection relationship of the lanes, and the relative positional relationship.

Further, the map acquisition device 4 acquires map information (for example, information embedded in a dynamic map) that is frequently updated. Specifically, the map acquisition device 4 has dynamic information updated at a frequency of 1 second or less, quasi-dynamic information updated at a frequency of 1 minute or less, and quasi-static information updated at a frequency of 1 hour or less. Information is acquired from the outside of the own vehicle 51 by wireless communication. For example, dynamic information includes information on surrounding vehicles, pedestrians, and traffic lights, quasi-static information includes accident information, traffic congestion information, and narrow-area weather information, and quasi-static information includes traffic. Includes regulatory information, road construction information, and wide area weather information. On the other hand, the above-mentioned "map information showing the structure of the road" corresponds to static information updated at a frequency of one hour or less.

The microcomputer 100 (an example of the control unit) predicts the operation of another vehicle based on the detection result by the object detection device 1 and the own vehicle position estimation device 3 and the information acquired by the map acquisition device 4, and from the operation of the other vehicle. The route of the own vehicle 51 is generated, and the own vehicle 51 is controlled according to the generated route.

The microcomputer 100 (an example of a control unit or a controller) is a general-purpose microcomputer including a CPU (central processing unit), a memory, and an input / output unit. A computer program (driving support program) for functioning as a driving support device is installed in the microcomputer 100. By executing the computer program, the microcomputer 100 functions as a plurality of information processing circuits (2a, 2b, 5, 10, 31, 32) included in the traveling support device. Here, an example is shown in which a plurality of information processing circuits (2a, 2b, 5, 10, 31, 32) included in the travel support device are realized by software. However, it is also possible to prepare an information processing circuit (2a, 2b, 5, 10, 31, 32) by preparing dedicated hardware for executing each of the following information processing. Further, a plurality of information processing circuits (2a, 2b, 5, 10, 31, 32) may be configured by individual hardware. Further, the information processing circuit (2a, 2b, 5, 10, 31, 32) may also be used as an electronic control unit (ECU) used for other control related to the vehicle.

The microcomputer 100 includes a detection integration unit 2a, an object tracking unit 2b, a map position calculation unit 5, and an operation prediction unit 10 as a plurality of information processing circuits (2a, 2b, 5, 10, 31, 32). , Own vehicle route generation unit 31 and vehicle control unit 32. Further, the motion prediction unit 10 includes a behavior determination unit 11, an operation candidate prediction unit 12, a rear vehicle extraction unit 13, a track prediction unit 16, a likelihood estimation unit 17, and a rear prediction necessity determination unit 21. It includes an environment information extraction unit 25 and a prediction method selection unit 26.

The detection integration unit 2a integrates a plurality of detection results obtained from each of the plurality of object detection sensors included in the object detection device 1 and outputs one detection result for each object. Specifically, from the behavior of the object obtained from each of the object detection sensors, the behavior of the most rational object with the least error is calculated in consideration of the error characteristics of each object detection sensor. Specifically, by using a known sensor fusion technique, the detection results acquired by a plurality of types of sensors are comprehensively evaluated, and more accurate detection results are acquired.

The object tracking unit 2b tracks the object detected by the object detection device 1. Specifically, the identity of the object is verified (association) between different times from the behavior of the object output at different times from the detection result integrated by the detection integration unit 2a, and the association is performed. Based on this, the behavior of the object is predicted. The behavior of the object output at different times is stored in the memory in the microcomputer 100.

The position calculation unit 5 in the map estimates the position and posture of the own vehicle 51 on the map from the absolute position of the own vehicle 51 obtained by the own vehicle position estimation device 3 and the map data acquired by the map acquisition device 4. do. For example, the road on which the own vehicle 51 is traveling and the lane on which the own vehicle 51 is traveling are specified.

The motion prediction unit 10 predicts the motion of a moving object around the own vehicle 51 based on the detection result obtained by the detection integration unit 2a and the position of the own vehicle 51 specified by the position calculation unit 5 in the map. .. The specific configuration of the motion prediction unit 10 will be described below.

The behavior determination unit 11 identifies the position and behavior of the object on the map from the position of the own vehicle 51 on the map and the behavior of the object obtained by the detection integration unit 2a. Further, the behavior determination unit 11 determines that the object is a "moving object" when the position of the object on the map changes with the passage of time, and the attribute of the moving object is determined from the size and speed of the moving object. Judge (other running vehicles, pedestrians). Then, when it is determined that the moving object is a traveling "other vehicle", the behavior determination unit 11 determines the road and lane in which the other vehicle is traveling.

If the position of the object on the map does not change with the passage of time, it is judged to be a stationary object, and the attributes of the stationary object (other vehicles that are stopped, etc.) are determined from the position, posture, and size of the stationary object on the map. Judge parked vehicles, pedestrians, etc.).

The motion candidate prediction unit 12 predicts motion candidates of other vehicles based on the map. The motion candidate prediction unit 12 predicts the motion intention of how the other vehicle will travel next from the road structure included in the map information and the lane information to which the other vehicle belongs, and the motion candidate prediction unit 12 predicts the motion intention based on the motion intention. The basic track of is calculated based on the road structure. The "movement candidate" is a superordinate concept including the movement intention and the basic trajectory. The "basic track" indicates not only the profile of the position of the other vehicle at different times, but also the profile of the speed of the other vehicle at each position.

For example, when another vehicle travels on a single lane or a curved road, the motion candidate prediction unit 12 predicts the motion intention (straight ahead) to travel along the shape of the lane, and uses the lane on the map as the basic track. Calculate the trajectory along. Further, when another vehicle travels on a single road or a curved road with a plurality of lanes, the motion candidate prediction unit 12 predicts an motion intention to go straight (straight ahead) and an motion intention to change lanes to the right or left side (lane change). .. The basic track of another vehicle in the operation intention (lane change) is a track that changes lanes based on the road structure and a predetermined lane change time. Further, when traveling at an intersection, the motion candidate prediction unit 12 predicts the motion intentions of stopping, going straight, turning right and turning left, and based on the road structure at the intersection on the map, the motion candidate prediction unit 12 stops before the intersection. Calculate using the "straight track", "right turn track", and "left turn track" that enter the intersection as the basic track. In the calculation of the "basic track", the road structure is taken into consideration, but the behavior of other vehicles integrated by the detection integration unit 2a is not taken into consideration.

The rear prediction necessity determination unit 21 needs to predict the operation of the rear vehicle 61 (another vehicle located behind the own vehicle 51 in the traveling direction of the own vehicle 51) based on the operation intention of the own vehicle 51. Judge whether or not. The operation intention of the own vehicle 51 is that the own vehicle 51 goes straight on the own lane TL1, the operation intention of changing the lane from the own lane TL1 to the adjacent lane TL2, the operation intention of the running own vehicle 51 stopping on the shoulder, or the operation intention. , The operation intention of the stopped own vehicle 51 to start, and the like. That is, the rear prediction necessity determination unit 21 assumes that the rear vehicle 61 exists, and when the own vehicle 51 has an operation intention that may affect the basic track of the rear vehicle 61, the rear vehicle 51 It is determined that it is necessary to predict the operation of the vehicle 61.

When the rear vehicle extraction unit 13 determines that the operation of the rear vehicle 61 needs to be predicted by the rear prediction necessity determination unit 21, the rear vehicle extraction unit 13 owns the vehicle 51 from the moving objects detected by the object detection device 1. Other vehicles located behind the vehicle are extracted as the rear vehicle 61. The rear vehicle 61 extracted by the rear vehicle extraction unit 13 travels not only to other vehicles existing in the own lane TL1 but also to the adjacent lane TL2 which is in the same traveling direction as the own lane TL1 and is adjacent to the own lane TL1. This includes other vehicles traveling in the merging lane TL7, which merges with the own lane TL1 in front of the own vehicle 51. In this way, the rear vehicle extraction unit 13 extracts the rear vehicle 61 having a basic track on which the own vehicle 51 can interfere.

The environment information extraction unit 25 includes the environment such as the road structure included in the map information, the condition of the lane in which the other vehicle is located, the state of the surrounding traffic lights, the vehicle type of the other vehicle, and the positional relationship between the own vehicle and the other vehicle. From the information, the driving scene (the type of environment in which the vehicle behind is placed) is extracted. The environmental information extraction unit 25 may extract not only one driving scene but also a plurality of driving scenes at the same time. As the traveling scenes extracted by the environmental information extraction unit 25, those shown in FIGS. 4A, 4B, and 5 to 12 can be mentioned as described later.

The prediction method selection unit 26 selects a prediction method corresponding to the driving scene extracted by the environment information extraction unit 25. The prediction method selection unit 26 may select not only one prediction method but also a plurality of prediction methods at the same time.

The track prediction unit 16 uses the prediction method selected by the prediction method selection unit 26 to extract motion candidates that are the targets of the selected prediction method from the motion candidates of the rear vehicle 61, and sets them as prediction motions. .. In particular, when a plurality of prediction methods are selected, the trajectory prediction unit 16 extracts operation candidates to be predicted for each selected prediction method and sets them as prediction operations. The details of the prediction method will be described later together with the description of each driving scene shown in FIGS. 4A, 4B, and 5 to 12.

The likelihood estimation unit 17 obtains the likelihood of each set prediction operation based on the selected prediction method and environmental information. The likelihood is an example of an index showing the possibility that the predicted operation of the rear vehicle 61 actually occurs, and may be an expression other than the likelihood.

As described above, the motion prediction unit 10 predicts the motion of other vehicles including the rear vehicle 61 around the own vehicle 51 based on the likelihood of each motion candidate assumed by the likelihood estimation unit 17. .. The "operation of other vehicles" includes profiles of the tracks and speeds of other vehicles. The track of another vehicle indicates a profile of the position of another vehicle at a different time.

The own vehicle route generation unit 31 generates a route of the own vehicle 51 based on the movement of another vehicle predicted by the motion prediction unit 10. When the action of avoiding obstacles is predicted, it is possible to generate a route after predicting the existence of obstacles. Therefore, it is possible to generate a smooth route of the own vehicle 51 that does not collide with another vehicle and that the own vehicle 51 does not suddenly decelerate or steer due to the behavior of the other vehicle. The "route of the own vehicle 51" indicates not only the profile of the position of the own vehicle 51 at different times but also the profile of the speed of the own vehicle 51 at each position.

In the vehicle control unit 32, the steering actuator, the accelerator pedal actuator, and the accelerator pedal actuator, based on the self-position calculated by the position calculation unit 5 in the map, so that the own vehicle 51 travels according to the route generated by the own vehicle route generation unit 31. And the brake pedal drives at least one of the actuators. In the embodiment, the control is performed according to the route of the own vehicle 51, but the own vehicle 51 may be controlled without generating the route of the own vehicle 51.

[Driving support method]
A traveling support method according to an embodiment will be described with reference to FIGS. 2 and 3. FIG. 2 is a flowchart showing an example of the operation of the traveling support device of FIG. FIG. 3 is a flowchart showing an example of the detailed procedure of step S06 of FIG.

First, in step S01, the object detection device 1 detects the behavior of an object around the own vehicle 51 by using a plurality of object detection sensors. Proceeding to step S02, the detection integration unit 2a integrates a plurality of detection results obtained from each of the plurality of object detection sensors, and outputs one detection result for each object. Then, the object tracking unit 2b tracks each detected and integrated object.

Proceeding to step S03, the own vehicle position estimation device 3 measures the position, posture, and speed of the own vehicle 51 with respect to a predetermined reference point by using the position detection sensor. Proceeding to step S04, the map acquisition device 4 acquires map information indicating the structure of the road on which the own vehicle 51 travels.

Proceeding to step S05, the position calculation unit 5 in the map estimates the position and posture of the own vehicle 51 on the map from the position of the own vehicle 51 measured in step S03 and the map data acquired in step S04. Proceeding to step S06, the motion prediction unit 10 determines the other vehicle around the own vehicle 51 based on the detection result (behavior of the other vehicle) obtained in step S02 and the position of the own vehicle 51 specified in step S05. Predict the behavior of.

The details of step S06 will be described with reference to FIG. First, in step S610, the rear prediction necessity determination unit 21 operates the rear vehicle 61 (another vehicle located behind the own vehicle 51 in the traveling direction of the own vehicle 51) based on the operation intention of the own vehicle 51. Determine if it is necessary to predict. When it is determined by the rearward prediction necessity determination unit 21 that it is necessary to predict the operation of the rear vehicle 61, the process proceeds to step S612, and the rear vehicle extraction unit 13 determines that the moving object detected by the object detection device 1 Another vehicle located behind the own vehicle 51 is extracted as the rear vehicle 61.

Proceeding to step S614, the environment information extraction unit 25 detects a traveling scene (type of environment in which the rear vehicle is placed) in which the rear vehicle 61 is placed for all the rear vehicles 61 extracted in step S612. The environmental information extraction unit 25 may extract not only one driving scene but also a plurality of driving scenes for each rear vehicle 61 at the same time. After that, the process proceeds to step S616, and the prediction method selection unit 26 selects a prediction method corresponding to each extracted driving scene. The prediction method selection unit 26 may select not only one prediction method but also a plurality of prediction methods at the same time.

Proceeding to step S618, the track prediction unit 16 predicts the movement of the rear vehicle 61 by using one or more prediction methods selected by the prediction method selection unit 26.

Proceeding to step S620, the trajectory prediction unit 16 extracts an operation candidate to be predicted for each selected prediction method and sets it as a prediction operation.

Proceeding to step S622, the likelihood estimation unit 17 estimates the likelihood of each set prediction operation set in S618 based on the selected prediction method and environmental information. As a result, step S06 in FIG. 2 ends.

Proceeding to step S07 of FIG. 2, the own vehicle route generation unit 31 generates the route of the own vehicle 51 based on the operation of the other vehicle predicted in step S06. Proceeding to step S08, the vehicle control unit 32 controls the own vehicle 51 so that the own vehicle 51 travels according to the route generated in step S07.

[Driving scene and prediction method]
Next, with reference to FIGS. 4A, 4B, and 5 to 12, the driving scenes extracted by the environmental information extraction unit 25 and selected by the prediction method selection unit 26 corresponding to each driving scene. The prediction method will be explained.

(1st driving scene)
First, the "first driving scene" will be described. FIG. 4A is a plan view showing a traveling scene (first traveling scene) immediately before the own vehicle 51 enters an intersection on a road having two lanes on each side. Further, FIG. 4B is a plan view showing a traveling scene immediately after the own vehicle 51 has passed the intersection after a lapse of time from the traveling scene shown in FIG. 4A.

As shown in FIGS. 4A and 4B, it is assumed that in the own lane TL1 in which the own vehicle 51 travels, a no-traffic area 101 surrounded by, for example, a traffic cone exists in front of the own vehicle 51.

In such a situation, when the own vehicle 51 has an operation intention of changing the lane from the own lane TL1 to the adjacent lane TL2, the operation of the own vehicle 51 is on the basic track of the rear vehicle 61 traveling in the adjacent lane TL2. May affect. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the adjacent lane TL2 as shown in FIG. 4A.

As shown in FIGS. 4A and 4B, there is an intersection in front of the own vehicle 51 and the rear vehicle 61 in the traveling direction, and the vehicle traveling in the own lane TL1 and the adjacent lane TL2 enters the intersection according to the traffic light 201. I do. On the other hand, it is assumed that a vehicle traveling in an intersection lane that intersects the own lane TL1 and the adjacent lane TL2 at the intersection performs an approach operation to the intersection according to the traffic light 202. When the environmental information extraction unit 25 determines that there is an intersection in front of the own vehicle 51 and the rear vehicle 61 and the operation of the own vehicle 51 and the rear vehicle 61 is determined according to the traffic light 201, the environment information extraction unit 25 is behind. It is determined that the vehicle 61 is placed in the "first traveling scene". That is, the environmental information extraction unit 25 extracts the first traveling scene in association with the rear vehicle 61 based on the environmental information.

When the first traveling scene is extracted, the prediction method selection unit 26 selects a prediction method based on the state of the traffic light 201 as a prediction method of the operation of the rear vehicle 61.

The motion candidates of the rear vehicle 61 assumed in FIG. 4A are considered to be one of a "stop track" that stops before the intersection, a "straight track" that enters the intersection, a "right turn track", and a "left turn track". .. Of these motion candidates, the track prediction unit 16 selects "stop track" and "straight track" as motion candidates that may affect the lane change of the own vehicle 51, and predicts the motion of the rear vehicle 61. Set as. Since the “right turn track” and the “left turn track” are less likely to affect the lane change of the own vehicle 51 than the “stop track” and the “straight track”, there is little need to predict them. Therefore, in this embodiment, "right turn trajectory" and "left turn trajectory" are not selected as predictive actions.

The likelihood estimation unit 17 estimates the likelihood of the predicted operation of the rear vehicle 61 by using the state change of the traffic light 201 before and after the own vehicle 51 passes through the intersection.

Generally, the lighting color of the traffic light 201 is (1) "blue" (or "green"), which means that it is possible to enter an intersection, and (2) entry to an intersection is prohibited. "Yellow", which means that you are allowed to enter the intersection when it is difficult to stop safely at the stop position of the intersection, (3) "Red", which means that you are prohibited from entering the intersection. There are three types.

The lighting color of the traffic light 201 is "blue" in the state immediately before the own vehicle 51 enters the intersection as shown in FIG. 4A.

It is assumed that time has passed from the state shown in FIG. 4A and the state immediately after the own vehicle 51 has passed the intersection as shown in FIG. 4B. In this state, it is assumed that the lighting color of the traffic light 201 becomes "blue" (pattern 1-1). In the case of this pattern 1-1, it is considered that the rear vehicle 61 starts approaching the intersection and goes straight on the adjacent lane TL2 as it is. That is, it is considered that the probability that the rear vehicle 61 passes through the intersection is high. Therefore, the likelihood estimation unit 17 estimates that the likelihood of the "straight orbit" is larger than the likelihood of the "stop orbit".

It is assumed that the lighting color of the traffic light 201 becomes "yellow" immediately after the own vehicle 51 has passed the intersection (Pattern 1-2). In the case of this pattern 1-2, the probability that the rear vehicle 61 passes through the intersection is considered to be lower than the probability in the above-mentioned pattern 1-1. Therefore, the likelihood estimation unit 17 estimates the likelihood of the “straight orbit” to be smaller than the likelihood of the “straight orbit” estimated by the pattern 1-1. Further, the likelihood estimation unit 17 estimates the likelihood of the "stop trajectory" larger than the likelihood of the "stop trajectory" estimated by the pattern 1-1.

It is assumed that the lighting color of the traffic light 201 becomes "red" immediately after the own vehicle 51 has passed the intersection (Pattern 1-3). In the case of this pattern 1-3, it is considered that the rear vehicle 61 does not start approaching the intersection and stops before the intersection. That is, the probability that the rear vehicle 61 passes through the intersection is considered to be even lower than the probability in the above-mentioned pattern 1-2. Therefore, the likelihood estimation unit 17 estimates the likelihood of the "straight orbit" to be smaller than the likelihood of the "straight orbit" estimated by the pattern 1-2. Further, the likelihood estimation unit 17 estimates the likelihood of the "stop trajectory" to be larger than the likelihood of the "stop trajectory" estimated by the pattern 1-2.

In this way, the likelihood estimation unit 17 rearward in this order depending on whether the lighting color of the traffic light 201 is "blue", "yellow", or "red" in the state immediately after the own vehicle 51 has passed the intersection. It is estimated that the likelihood of the "straight track" of the vehicle 61 becomes smaller in order. Further, it is estimated that the likelihood of the "stop track" of the rear vehicle 61 increases in this order.

In this way, the motion prediction unit 10 predicts the motion of the rear vehicle 61 based on the state change of the traffic light 201. Therefore, for example, as shown in FIG. 4B, the other vehicle 71 approaches behind the own vehicle 51 and rearward. Even when the vehicle 61 is hidden in an invisible position, the operation of the rear vehicle 61 can be predicted.

Since the prediction method based on the driving scene is selected and the prediction motion of the rear vehicle 61 and the likelihood of the prediction motion are estimated, the own vehicle route generation unit 31 uses a safer and more appropriate route as the route of the own vehicle 51. Can be generated. Specifically, the own vehicle route generation unit 31 can generate a route away from the no-traffic area 101 as a route of the own vehicle 51 as the likelihood of the “straight track” of the rear vehicle 61 is smaller. FIG. 4B shows how the route R1, the route R2, and the route R3 are generated as the route of the own vehicle 51. The route R1, the route R2, and the route R3 are generated corresponding to the cases of the above-mentioned patterns 1-1, 1-2, and 1-3, respectively.

It should be noted that various methods can be used to acquire the state of the traffic light 201. For example, when the own vehicle 51 can communicate with the infrastructure, the lighting color of the traffic light 201 may be acquired as environmental information directly from the infrastructure by communication. Further, even when communication with the infrastructure is not possible, the traffic light 201 may be detected by the camera mounted on the own vehicle 51 to identify the lighting color. Further, even if the lighting color of the traffic light 201 cannot be identified, the traffic light 201 is based on the traveling time zone, the cycle of the traffic flow before the intersection, the movement of other vehicles traveling in the intersection lane intersecting with the own lane TL1, and the like. You may predict the lighting color of.

Various methods can be used to detect the restricted area. For example, when the own vehicle 51 can communicate with the infrastructure, the position of the restricted area may be acquired directly from the infrastructure by communication. Further, the traffic cones arranged on the road may be detected by image recognition, and the area surrounded by the traffic cones may be detected as a no-traffic area. Alternatively, the headrace zone (zebra zone) marked on the road surface may be detected by image recognition and detected as a no-passage area.

(Second driving scene)
Next, the "second running scene" will be described. FIG. 5 is a plan view showing a traveling scene (second traveling scene) in which the own vehicle 51 crosses the adjacent lane TL2.

As shown in FIG. 5, when the own vehicle 51 turns from the own lane TL1 and has an intention to cross the adjacent lane TL2 (for example, when entering a parking lot adjacent to the building 105). The operation of the own vehicle 51 may affect the basic track of the rear vehicle 61 traveling in the adjacent lane TL2. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the adjacent lane TL2 as shown in FIG.

When it is determined that the obstacle 102 exists in the adjacent lane TL2 as shown in FIG. 5, the environmental information extraction unit 25 determines that the rear vehicle 61 is placed in the "second traveling scene". .. That is, the environmental information extraction unit 25 extracts the second traveling scene in association with the rear vehicle 61 based on the environmental information.

When the second traveling scene is extracted, the prediction method selection unit 26 selects a prediction method based on the situation of the obstacle 102 as a prediction method of the movement of the rear vehicle 61.

The operation candidates of the rear vehicle 61 assumed in FIG. 5 are "straight track" that ignores the obstacle 102 and goes straight on the adjacent lane TL2, "deceleration track" that decelerates in front of the obstacle 102, and own from the adjacent lane TL2. It is considered to be one of the "LC tracks" that change lanes to lane TL1. Among these motion candidates, the track prediction unit 16 selects "straight track" and "deceleration track" as motion candidates that may affect the motion of the own vehicle 51, and as the predictive motion of the rear vehicle 61. Set. The "LC track" will be dealt with in the "eighth running scene" described later, and will not be described here.

The likelihood estimation unit 17 determines the likelihood of the predicted operation of the rear vehicle 61 based on the ratio of the width ΔK of the obstacle 102 measured along the width direction of the adjacent lane TL2 to the lane width ΔW of the adjacent lane TL2. presume.

It is expected that the larger the ratio of the obstacle 102 occupying the adjacent lane TL2, the more difficult it is for the rear vehicle 61 to ignore the obstacle 102 and go straight. Therefore, the likelihood estimation unit 17 estimates that the larger the ratio ΔK / ΔW, the smaller the likelihood of the “straight track” in the predicted operation of the rear vehicle 61. On the contrary, the likelihood estimation unit 17 estimates that the larger the ratio ΔK / ΔW, the greater the likelihood of the “deceleration trajectory”.

Since the prediction method based on the driving scene is selected and the prediction motion of the rear vehicle 61 and the likelihood of the prediction motion are estimated, the own vehicle route generation unit 31 uses a safer and more appropriate route as the route of the own vehicle 51. Can be generated. Specifically, the own vehicle route generation unit 31 can generate a route in which the own vehicle 51 temporarily stops before crossing the adjacent lane TL2 as the likelihood of the “straight track” of the rear vehicle 61 increases. By taking such a route in which the own vehicle 51 temporarily stops, it is possible to control the own vehicle 51 so that the own vehicle 51 crosses the adjacent lane TL2 after the rear vehicle 61 passes by the side of the own vehicle 51. can.

Further, the own vehicle route generation unit 31 may generate a route in which the own vehicle 51 crosses the adjacent lane TL2 in a shorter time as the likelihood of the “straight track” of the rear vehicle 61 increases. By taking such a route across the adjacent lane TL2 in a short time, the own vehicle 51 completes the operation of crossing the adjacent lane TL2 before the rear vehicle 61 approaches the own vehicle 51. The own vehicle 51 can be controlled.

(Third driving scene)
Next, the "third running scene" will be described. FIG. 6 is a plan view showing a traveling scene (third traveling scene) when the own vehicle 51 changes lanes toward the adjacent lane TL2.

As shown in FIG. 6, when the own vehicle 51 has an operation intention of changing the lane from the own lane TL1 to the adjacent lane TL2, the operation of the own vehicle 51 is the basic track of the rear vehicle 61 traveling in the adjacent lane TL2. May affect. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 that travels in the adjacent lane TL2 and travels behind the stop BS, as shown in FIG. That is, the rear vehicle extraction unit 13 extracts the rear vehicle 61 that has not yet passed the stop BS.

When it is determined that the stop BS exists in the adjacent lane TL2 as shown in FIG. 6, the environmental information extraction unit 25 determines that the rear vehicle 61 is placed in the "third traveling scene". That is, the environmental information extraction unit 25 extracts the third traveling scene in association with the rear vehicle 61 based on the environmental information.

When the third traveling scene is extracted, the prediction method selection unit 26 is based on the state of the stop BS, the vehicle type of the rear vehicle 61, the position of the rear vehicle 61, and the behavior as a method of predicting the operation of the rear vehicle 61. Select a prediction method.

It is considered that the operation candidate of the rear vehicle 61 assumed in FIG. 6 is either a "stop track" that stops at the stop BS or a "straight track" that goes straight on the adjacent lane TL2 without stopping at the stop BS. In particular, when the rear vehicle 61 is a vehicle related to the passenger vehicle transportation business corresponding to the stop BS, the rear vehicle 61 has a "stop track" that stops at the stop BS as an operation candidate. The track prediction unit 16 selects "stop track" and "straight track" as motion candidates that may affect the lane change of the own vehicle 51, and sets them as the predictive motion of the rear vehicle 61.

The likelihood estimation unit 17 predicts the rear vehicle 61 based on whether the rear vehicle 61 is a vehicle related to the passenger vehicle transportation business corresponding to the stop BS, whether a person is waiting at the stop BS, and the like. Estimate the likelihood of.

Whether or not the rear vehicle 61 is a vehicle related to the passenger vehicle transportation business is determined by, for example, the length of the rear vehicle 61 detected by image recognition, the characters, figures, symbols, three-dimensional shapes, and colors on the surface of the rear vehicle 61. , In addition, the determination is made using the vehicle type information obtained based on the communication with the infrastructure and the communication between vehicles. Vehicles involved in the passenger car transportation business include fixed-route buses and taxis.

When it is determined with a probability whether the rear vehicle 61 is a vehicle related to the passenger vehicle transportation business, the higher the probability that the rear vehicle 61 is a vehicle related to the passenger vehicle transportation business, the higher the probability that the likelihood estimation unit 17 is the stop BS. It is estimated that the probability of the "stop track" that stops at is high.

Whether or not a person is waiting at the stop BS is determined by, for example, image recognition. In addition, the determination may be made based on the position information of the mobile terminal of the person at the stop BS.

When a person is waiting at the stop BS, it is considered that the rear vehicle 61 is likely to stop at the stop BS to carry the waiting person. Therefore, the likelihood estimation unit 17 estimates that the likelihood of the "stop orbit" is high when a person is waiting at the stop BS, and conversely, the "stop orbit" when a person is not waiting at the stop BS. It is estimated that the likelihood of is small.

In addition to the above, the likelihood estimation unit 17 may estimate the likelihood of the "stop track" based on the behavior of the rear vehicle 61. For example, the likelihood of the "stop track" may be estimated based on the acceleration of the rear vehicle 61 when the rear vehicle 61 approaches the stop BS. When the rear vehicle 61 tries to stop at the stop BS, the rear vehicle 61 slows down. Focusing on this point, the likelihood estimation unit 17 estimates that the likelihood of the "stop track" is high and the likelihood of the "straight track" is low when the acceleration of the rear vehicle 61 is in the direction of deceleration. You may. On the contrary, when the acceleration of the rear vehicle 61 is in the direction of acceleration, it may be estimated that the likelihood of the "stop track" is small and the likelihood of the "straight track" is high.

Further, assuming that the distance between the center position of the rear vehicle 61 and the stop BS measured along the width direction of the adjacent lane TL2 is the distance Δx1, the likelihood estimation unit 17 determines that the smaller the distance Δx1, the more likely the “stop track” is. It may be estimated that the degree is large and the likelihood of the "straight orbit" is small. On the contrary, the likelihood estimation unit 17 may estimate that the larger the distance Δx1, the smaller the likelihood of the “stop orbit” and the larger the likelihood of the “straight orbit”.

Since the prediction method based on the driving scene is selected and the prediction motion of the rear vehicle 61 and the likelihood of the prediction motion are estimated, the own vehicle route generation unit 31 uses a safer and more appropriate route as the route of the own vehicle 51. Can be generated. Specifically, the own vehicle route generation unit 31 uses a route away from the stop BS or the rear vehicle 61 as a route for lane change of the own vehicle 51 as the likelihood of the “straight track” of the rear vehicle 61 increases. Can be generated. The own vehicle 51 is set so as to prevent the own vehicle 51 from approaching the rear vehicle 61 and becoming a dangerous state at the time of a lane change by taking such a route away from the rear vehicle 61. Can be controlled.

The own vehicle route generation unit 31 may suppress the generation of a route for lane change of the own vehicle 51 as the likelihood of the “straight track” increases. By suppressing the lane change of the own vehicle 51, the own vehicle 51 can be controlled so as to prevent the own vehicle 51 from approaching the rear vehicle 61 and becoming a dangerous state.

(4th driving scene)
Next, the "fourth running scene" will be described. FIG. 7 is a plan view showing a traveling scene (fourth traveling scene) when the stopped own vehicle 51 is about to start on a road with one lane on each side.

As shown in FIG. 7, it is assumed that the own vehicle 51 is about to start from the state where the own vehicle 51 is stopped on the shoulder of the own lane TL1. The movement of the own vehicle 51 to start may affect the basic track of the rear vehicle 61 traveling in the own lane TL1 because it is behind the stop position of the own vehicle 51. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the own lane TL1 as shown in FIG. 7.

As shown in FIG. 7, the lane adjacent to the own lane TL1 is the oncoming lane TL3 whose traveling direction is opposite to that of the oncoming lane TL3. In the environmental information extraction unit 25, the lane adjacent to the own lane TL1 is the oncoming lane TL3, and there is another vehicle 72 (oncoming vehicle) in front of the own vehicle 51 and traveling in the oncoming lane TL3. When it is determined that the situation is such, it is determined that the rear vehicle 61 is placed in the "fourth traveling scene". That is, the environmental information extraction unit 25 extracts the fourth traveling scene in association with the rear vehicle 61 based on the environmental information.

When the fourth driving scene is extracted, the prediction method selection unit 26 determines the positional relationship between the own vehicle 51, the rear vehicle 61, and the other vehicle 72, and the rear vehicle 61 and the other vehicle as a method of predicting the operation of the rear vehicle 61. Select a prediction method based on the behavior of 72.

The operation candidates of the rear vehicle 61 assumed in FIG. 7 are a "detour track" that passes by the side of the own vehicle 51 stopped on the shoulder and advances toward the front of the own vehicle 51, and passes by the side of the own vehicle 51. Instead, it is considered to be one of the "following tracks" traveling behind the own vehicle 51 that has started. When the rear vehicle 61 takes a "detour track", when passing by the own vehicle 51, it protrudes from the own lane TL1 into the oncoming lane TL3 and then takes a track returning to the own lane TL1. The track prediction unit 16 selects "detour track" and "following track" as motion candidates that may affect the motion of the own vehicle 51, and sets them as the predicted motion of the rear vehicle 61.

Here, the distance from the head of the rear vehicle 61 to the head of the own vehicle 51 is the distance ΔL11, the distance from the head of the other vehicle 72 to the head of the own vehicle 51 is the distance ΔL12, and the speed of the rear vehicle 61 is the speed v61. The speed of the other vehicle 72 is defined as the speed v72. The likelihood estimation unit 17 estimates the likelihood of the predicted operation of the rear vehicle 61 based on the distance ΔL11, the distance ΔL12, the speed v61, and the speed v72.

When the rear vehicle 61 takes a "detour track", it is necessary to avoid contact with another vehicle 72 running in the oncoming lane TL3, so that the time t12 (= ΔL12 / v72) for the other vehicle 72 to run through the distance ΔL12 , The time t11 (= ΔL11 / v61) for the rear vehicle 61 to run through the distance ΔL11 needs to be shorter. Further, the section sandwiched between the other vehicle 72 and the own vehicle 51 must have a length that allows the rear vehicle 61 to safely enter.

Focusing on this point, in the likelihood estimation unit 17, the smaller the ratio t11 / t12 is and the smaller the ratio t11 / t12, the greater the likelihood of the “detour orbit” and the likelihood of the “following orbit”. It is estimated that the degree is small. When the ratio t11 / t12 is 1 or more, it is estimated that the likelihood of the "detour orbit" is small and the likelihood of the "following orbit" is large.

Further, the likelihood estimation unit 17 may estimate that the larger the distance ΔL12, the higher the likelihood of the “detour orbit” and the smaller the likelihood of the “following orbit”. This is because it is considered that the larger the distance ΔL12, the less likely the rear vehicle 61 and the other vehicle 72 will approach each other, and the rear vehicle 61 can safely take a “detour track”.

Since the prediction method based on the driving scene is selected and the prediction motion of the rear vehicle 61 and the likelihood of the prediction motion are estimated, the own vehicle route generation unit 31 uses a safer and more appropriate route as the route of the own vehicle 51. Can be generated. Specifically, the own vehicle route generation unit 31 generates a route for the own vehicle 51 to start when the likelihood of the "following track" of the rear vehicle 61 is high and the likelihood of the "detour track" is low. Can be done.

On the contrary, when the likelihood of the rear vehicle 61 "following track" is small and the likelihood of the "detour track" is large, the own vehicle 51 starts after waiting for the rear vehicle 61 to pass by the own vehicle 51. It is possible to generate a route that does. In this way, by generating the route of the own vehicle 51 in consideration of the operation candidate of the rear vehicle 61, it is possible to prevent the rear vehicle 61 from protruding into the oncoming lane TL3 more than necessary due to the operation of the own vehicle 51. This makes it possible to reduce the risk of collision between the rear vehicle 61 and another vehicle 72 traveling in the oncoming lane TL3.

(Fifth driving scene)
Next, the "fifth running scene" will be described. FIG. 8 is a plan view showing a traveling scene (fifth traveling scene) when the own vehicle 51 tries to stop on the shoulder of the road.

As shown in FIG. 8, it is assumed that the own vehicle 51 traveling in the own lane TL1 is about to stop at the position P1 on the shoulder of the own lane TL1. The operation of the own vehicle 51 stopping on the shoulder of the road may affect the basic track of the rear vehicle 61 traveling in the own lane TL1 because it is behind the stop position of the own vehicle 51. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the own lane TL1 as shown in FIG.

When the environmental information extraction unit 25 determines that another vehicle 73 (following vehicle) exists between the own vehicle 51 and the extracted rear vehicle 61 as shown in FIG. 8, the rear vehicle 61 "is". It is determined that the vehicle is placed in the "fifth driving scene". That is, the environmental information extraction unit 25 extracts the fifth traveling scene in association with the rear vehicle 61 based on the environmental information.

When the fifth traveling scene is extracted, the prediction method selection unit 26 selects a prediction method based on the position and behavior of the rear vehicle 61 as a method of predicting the operation of the rear vehicle 61.

In FIG. 8, as the rear vehicle 61, a small vehicle having a narrow width such as a motorcycle or a bicycle is assumed. Assumed motion candidates for the rear vehicle 61 pass through the side of the other vehicle 73, travel on the shoulder of the own lane TL1 and approach the own vehicle 51, and do not pass by the side of the other vehicle 73. , It is considered to be one of the "following tracks" traveling behind the other vehicle 73. The track prediction unit 16 selects "road shoulder traveling track" and "following track" as motion candidates that may affect the motion of the own vehicle 51, and sets them as the predicted motion of the rear vehicle 61.

Here, the distance from the center position of the other vehicle 73 measured along the width direction of the own lane TL1 to the end of the own lane TL1 is defined as the distance Δx2. The likelihood estimation unit 17 estimates the likelihood of the predicted operation of the rear vehicle 61 based on the vehicle width and the distance Δx2 of the rear vehicle 61.

The width of the rear vehicle 61 is detected, for example, by image recognition. It is considered that the smaller the width of the rear vehicle 61, the easier it is for the rear vehicle 61 to travel toward the front of the other vehicle 73 by traveling on the shoulder of the own lane TL1 and passing by the other vehicle 73. .. Further, it is considered that the larger the distance Δx2, the easier it is for the rear vehicle 61 to move toward the front of the other vehicle 73.

Focusing on this point, the likelihood estimation unit 17 has a larger likelihood of the "road shoulder traveling track" as the width of the rear vehicle 61 is smaller or the distance Δx2 is larger, and the likelihood of the “following track” is higher. Is estimated to be small.

Since the prediction method based on the driving scene is selected and the prediction motion of the rear vehicle 61 and the likelihood of the prediction motion are estimated, the own vehicle route generation unit 31 uses a safer and more appropriate route as the route of the own vehicle 51. Can be generated. Specifically, the own vehicle route generation unit 31 generates a route in which the own vehicle 51 stops when the likelihood of the “road shoulder traveling track” of the rear vehicle 61 is small and the likelihood of the “following track” is high. be able to.

On the contrary, when the likelihood of the "road shoulder traveling track" of the rear vehicle 61 is large and the likelihood of the "following track" is small, it is possible to suppress the generation of a route in which the own vehicle 51 stops. In this way, by generating the route of the own vehicle 51 in consideration of the operation candidate of the rear vehicle 61, it is possible to reduce the risk that the rear vehicle 61 approaches and collides with the own vehicle 51.

(6th driving scene)
Next, the "sixth running scene" will be described. FIG. 9 shows a traveling scene (sixth traveling scene) when the own vehicle 51 has just passed the intersection on a road with two lanes on each side and the other vehicle 74 tries to enter the intersection from the lane where the intersection intersects. It is a plan view.

FIG. 9 is similar to the state shown in FIG. 4B, but differs in that another vehicle 74 is approaching the intersection. Here, the crossing lanes that intersect the own lane TL1 and the adjacent lane TL2 at the intersection are shown as the crossing lane TL5 and the crossing lane TL6. The other vehicle 74 is about to turn left in the intersection from the intersection lane TL6 toward the adjacent lane TL2. Seen from the own vehicle 51 and the rear vehicle 61, the other vehicle 74 is a vehicle that approaches from the side with respect to the traveling direction of the own vehicle 51 and the rear vehicle 61.

It is assumed that the own vehicle 51 changes lanes from the own lane TL1 to the adjacent lane TL2. In this case, the rear prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the adjacent lane TL2 as shown in FIG.

The environmental information extraction unit 25 has an intersection in front of the own vehicle 51 and the rear vehicle 61, and another vehicle 74 (side vehicle) enters from the intersection lane TL5 and the intersection lane TL6 toward the intersection. When it is determined, it is determined that the rear vehicle 61 is placed in the "sixth traveling scene". That is, the environmental information extraction unit 25 extracts the sixth traveling scene in association with the rear vehicle 61 based on the environmental information.

When the sixth driving scene is extracted, the prediction method selection unit 26 is based on the movement of another vehicle 74 approaching the intersection from the intersection lane TL5 or the intersection lane TL6 as a prediction method of the movement of the rear vehicle 61. Select a prediction method.

Similar to the explanation in the first driving scene, the motion candidates of the rear vehicle 61 assumed in FIG. 9 are a "stop track" that stops before the intersection, a "straight track" that enters the intersection, a "right turn track", and a "left turn". It is considered to be one of the "orbits". Of these motion candidates, the track prediction unit 16 selects "stop track" and "straight track" as motion candidates that may affect the lane change of the own vehicle 51, and predicts the motion of the rear vehicle 61. Set as.

The likelihood estimation unit 17 estimates the likelihood of the predicted operation of the rear vehicle 61 based on the speed of the other vehicle 74.

When the rear vehicle 61 takes a "straight track", it is considered that the other vehicle 74 approaching from the side enters the intersection while decelerating in order to avoid contact with the rear vehicle 61. On the other hand, when the rear vehicle 61 takes a "stop track", the other vehicle 74 may enter the intersection without decelerating because it is not necessary to avoid contact with the rear vehicle 61.

Focusing on this point, the likelihood estimation unit 17 has a lower likelihood of the "straight track" of the rear vehicle 61 as the speed of the other vehicle 74 entering the intersection from the side increases, and the likelihood of the "stop track". It is estimated that the degree is large. On the contrary, it is estimated that the smaller the speed of the other vehicle 74, the higher the likelihood of the "straight track" of the rear vehicle 61, and the smaller the likelihood of the "stop track".

In this way, the motion prediction unit 10 predicts the motion of the rear vehicle 61 based on the speed of the other vehicle 74. Therefore, for example, the other vehicle 71 approaches behind the own vehicle 51 and the rear vehicle 61 cannot be visually recognized. Even if it is hidden behind, the operation of the rear vehicle 61 can be predicted.

Similar to the explanation in the first driving scene, in the sixth driving scene shown in FIG. 9, the prediction method based on the driving scene is selected, and the predictive motion of the rear vehicle 61 and the likelihood of the predictive motion are estimated. The own vehicle route generation unit 31 can generate a safer and more appropriate route as the route of the own vehicle 51.

(7th driving scene)
Next, the "seventh running scene" will be described. FIG. 10 is a plan view showing a traveling scene (seventh traveling scene) in which a road confluence exists in front of the own vehicle 51.

As shown in FIG. 10, when the own lane TL1 merges with the merging lane TL7 in front of the own vehicle 51, the operation of the own vehicle 51 affects the basic track of the rear vehicle 61 traveling in the merging lane TL7. there is a possibility. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the merging lane TL7 shown in FIG.

When the environmental information extraction unit 25 determines that the own lane TL1 in which the own vehicle 51 travels and the merging lane TL7 in which the rear vehicle 61 travels meet at the merging point in front of the own vehicle 51, the environment information extraction unit 25 determines. It is determined that the rear vehicle 61 is placed in the "seventh driving scene". That is, the environmental information extraction unit 25 extracts the seventh traveling scene in association with the rear vehicle 61 based on the environmental information.

When the seventh traveling scene is extracted, the prediction method selection unit 26 selects a prediction method based on the positional relationship and behavior of the own vehicle 51 and the rear vehicle 61 as the prediction method of the movement of the rear vehicle 61.

The operation candidates of the rear vehicle 61 assumed in FIG. 9 are the "first straight track" that goes straight and runs ahead of the own vehicle 51 and the "second straight track" that goes straight and runs behind the own vehicle 51. It is considered to be either. The track prediction unit 16 selects "first straight track" and "second straight track" as motion candidates that may affect the motion of the own vehicle 51, and sets them as the predicted motion of the rear vehicle 61.

Here, the distance from the head of the own vehicle 51 to the confluence is defined as the distance ΔL21, the distance from the head of the rear vehicle 61 to the confluence is defined as the distance ΔL22, the speed of the own vehicle 51 is the speed v51, and the speed of the rear vehicle 61 is the speed v51. The speed is v61. The likelihood estimation unit 17 estimates the likelihood of the predicted operation of the rear vehicle 61 based on the distance ΔL21, the distance ΔL22, the speed v51, and the speed v61.

When the time t22 (= ΔL22 / v61) for the rear vehicle 61 to run through the distance ΔL22 is shorter than the time t21 (= ΔL21 / v51) for the own vehicle 51 to run through the distance ΔL21, the rear vehicle 61 is shorter than the own vehicle 51. Is thought to reach the confluence first. On the contrary, when t22 is longer than t21, it is considered that the rear vehicle 61 reaches the confluence after the own vehicle 51.

Focusing on this point, the likelihood estimation unit 17 estimates that the smaller the ratio t21 / t22, the higher the likelihood of the "first straight orbit" and the smaller the likelihood of the "second straight orbit". On the contrary, the likelihood estimation unit 17 estimates that the larger the ratio t21 / t22, the smaller the likelihood of the "first straight orbit" and the larger the likelihood of the "second straight orbit".

Further, although not shown, when it is clear that there is a no-traffic area between the confluence point and the rear vehicle 61 and the rear vehicle 61 cannot reach the confluence point, the likelihood estimation unit 17 May be estimated assuming that the likelihood of the "first straight orbit" is extremely small.

Since the prediction method based on the driving scene is selected and the prediction motion of the rear vehicle 61 and the likelihood of the prediction motion are estimated, the own vehicle route generation unit 31 uses a safer and more appropriate route as the route of the own vehicle 51. Can be generated. Specifically, the own vehicle route generation unit 31 compares the likelihood of the "first straight track" of the rear vehicle 61 with the likelihood of the "second straight track", and when either of them is sufficiently large. Can determine that the possibility that the own vehicle 51 and the rear vehicle 61 are unlikely to come into contact with each other at the confluence is low, and can generate a route for the own vehicle 51 to reach the confluence while maintaining the speed.

Further, when the likelihood of the "first straight track" and the likelihood of the "second straight track" are about the same, it is determined that there is a high possibility that the own vehicle 51 and the rear vehicle 61 come into contact with each other at the confluence. Then, the own vehicle 51 can be decelerated or accelerated to generate a route to reach the confluence. Since the time required to reach the confluence changes due to deceleration or acceleration of the own vehicle 51, the risk of contact between the own vehicle 51 and the rear vehicle 61 at the confluence can be reduced.

(8th driving scene)
Next, the "eighth running scene" will be described. FIG. 11 is a plan view showing a traveling scene (eighth traveling scene) in which a traffic prohibited area 101 exists in the adjacent lane TL2 in front of the own vehicle 51.

As shown in FIG. 11, it is assumed that the own vehicle 51 is in front of the own vehicle 51 and is about to go straight past the side of the no-traffic area 101 existing in the adjacent lane TL2. Due to the existence of the no-traffic area 101, the rear vehicle 61 needs to change lanes from the adjacent lane TL2 to the own lane TL1 in which the own vehicle 51 travels. As operation candidates for the rear vehicle 61, a "first LC track" that overtakes the own vehicle 51 and changes lanes in front of the own vehicle 51, and a "second LC track" that changes lanes behind the own vehicle 51 without overtaking the own vehicle 51. It has two types of "LC orbits".

How the own vehicle 51 passes by the side of the restricted area 101 existing in the adjacent lane TL2 may affect the basic track of the rear vehicle 61 traveling in the adjacent lane TL2. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the adjacent lane TL2 as shown in FIG.

When the environmental information extraction unit 25 determines that the traffic prohibited area 101 exists in the adjacent lane TL2 as shown in FIG. 11, it is determined that the rear vehicle 61 is placed in the "eighth driving scene". do. That is, the environmental information extraction unit 25 extracts the eighth traveling scene in association with the rear vehicle 61 based on the environmental information.

When the eighth traveling scene is extracted, the prediction method selection unit 26 selects a prediction method based on the positional relationship and behavior of the own vehicle 51 and the rear vehicle 61 as the prediction method of the movement of the rear vehicle 61.

Here, the eighth running scene is in a situation similar to the seventh running scene described above. That is, if the position close to the prohibited area 101 on the own lane TL1 shown in FIG. 11 is regarded as the virtual confluence in the seventh driving scene, the own lane TL1 and the adjacent lane TL2 merge at the virtual confluence. It can be seen that it is.

Therefore, the track prediction unit 16 selects "first LC track" and "second LC track" as operation candidates that may affect the operation of the own vehicle 51, and sets them as the prediction operation of the rear vehicle 61.

The distance from the head of the own vehicle 51 to the prohibited area 101 is defined as the distance ΔL31, and the distance from the head of the rear vehicle 61 to the prohibited area 101 is defined as the distance ΔL32. In the prediction method described in the seventh driving scene, the distance ΔL31 and the distance ΔL32 are used instead of the distance ΔL21 and the distance ΔL22, respectively, so that the likelihood estimation unit 17 can use the rear vehicle 61 in the eighth driving scene. The likelihood of "1LC orbit" and "second LC orbit" is estimated.

Similar to the explanation in the 7th driving scene, in the 8th driving scene shown in FIG. 11, the prediction method based on the driving scene is selected, and the predictive motion of the rear vehicle 61 and the likelihood of the predictive motion are estimated. The own vehicle route generation unit 31 can generate a safer and more appropriate route as the route of the own vehicle 51.

(9th driving scene)
Next, the "9th running scene" will be described. FIG. 12 is a plan view showing a traveling scene (9th traveling scene) in which the rear vehicle 61 exists at the position of the stop line P10 behind the own vehicle 51 when the own vehicle 51 tries to stop on the shoulder.

As shown in FIG. 12, it is assumed that the own vehicle 51 traveling in the own lane TL1 is about to stop at the position P2 on the shoulder of the own lane TL1. The operation of the own vehicle 51 stopping on the shoulder of the road may affect the basic track of the rear vehicle 61 traveling in the own lane TL1 because it is behind the stop position of the own vehicle 51. Therefore, the rearward prediction necessity determination unit 21 determines that it is necessary to predict the operation of the rear vehicle 61. Based on this determination, the rear vehicle extraction unit 13 extracts the rear vehicle 61 traveling in the own lane TL1 as shown in FIG.

As shown in FIG. 12, when the environmental information extraction unit 25 determines that the rear vehicle 61 is in a situation where the rear vehicle 61 exists at the stop line P10 behind the own vehicle 51, the rear vehicle 61 is in the “9th traveling scene”. Judge that it is placed in. That is, the environmental information extraction unit 25 extracts the ninth traveling scene in association with the rear vehicle 61 based on the environmental information.

When the ninth traveling scene is extracted, the prediction method selection unit 26 predicts the movement of the rear vehicle 61 based on the good visibility of the front and side from the rear vehicle 61 at the position of the stop line P10. Select a method.

Among the operation candidates of the rear vehicle 61 assumed in FIG. 12, the track prediction unit 16 passes straight through the intersection and goes straight to the own vehicle 51 as an operation candidate that may affect the operation of the own vehicle 51. The approaching "first straight track" and the "second straight track" approaching the own vehicle 51 at a speed slower than the "first straight track" are set as prediction targets.

The good visibility of the rear vehicle 61 at the position of the stop line P10 is defined by the angle θ surrounded by the line of sight VL1 and the line of sight VL2 from the rear vehicle 61. Here, when trying to visually recognize the road connected to the intersection from the rear vehicle 61, the view from the rear vehicle 61 is obstructed by the buildings 110 and 120 existing on the left and right in the traveling direction of the rear vehicle 61. The lines representing the boundary between the area visible from the rear vehicle 61 and the area invisible are defined as line-of-sight VL1 and line-of-sight VL2.

In the absence of the building 110 and the building 120, the rear vehicle 61 can overlook the entire road connecting to the intersection. In this case, it can be said that the front and side visibility at the position of the stop line P10 is good.

On the other hand, when the visibility is obstructed by the building 110 and the building 120, it can be said that the front and side visibility at the position of the stop line P10 is poor. When the visibility is poor, the angle θ takes a smaller value than when the visibility is good. Further, it is considered that the rear vehicle 61 enters the intersection at a slow speed.

Focusing on this point, the likelihood estimation unit 17 uses the angle θ as an index indicating the goodness of the front and side visibility from the rear vehicle 61 at the position of the stop line P10, and the likelihood estimation unit 17 uses the angle θ. It is estimated that the larger θ is, the higher the likelihood of the “first straight orbit” is, and the smaller the likelihood of the “second straight orbit” is.

Since the prediction method based on the driving scene is selected and the prediction motion of the rear vehicle 61 and the likelihood of the prediction motion are estimated, the own vehicle route generation unit 31 uses a safer and more appropriate route as the route of the own vehicle 51. Can be generated. Specifically, the own vehicle route generation unit 31 sets the position farther from the intersection as the position P2 for the own vehicle 51 to stop as the likelihood of the "first straight track" of the rear vehicle 61 increases, and stops. You can generate a route to do so. When the rear vehicle 61 is predicted to pass through the intersection at high speed and approach the own vehicle 51, the own vehicle 51 can be suppressed from stopping at a position close to the intersection, so that the own vehicle 51 is the rear vehicle 61. The own vehicle 51 can be controlled so as to avoid getting close to the vehicle and becoming a dangerous state.

[Effect of embodiment]
As described in detail above, in the traveling support method and the traveling support device according to the present embodiment, the rear vehicle located behind the own vehicle is detected, the environment in which the rear vehicle is placed is detected, and the rear vehicle is placed. The movement of the rear vehicle is predicted based on the environment in which the vehicle is struck. Since the movement of the rear vehicle can be predicted using the environment in which the rear vehicle is placed, such as the situation of an object other than the rear vehicle, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as the prediction accuracy of the rear vehicle is improved, sudden changes in the behavior of the own vehicle due to the movement of the rear vehicle can be suppressed, and the discomfort given to the occupants can be reduced.

Further, in the traveling support method and the traveling support device according to the present embodiment, the traveling scene is extracted from the environment in which the rear vehicle is placed as the detection of the type of the environment in which the rear vehicle is placed. Then, the movement of the vehicle behind is predicted by using the prediction method corresponding to the driving scene. As a result, it is possible to predict the movement of the rear vehicle in consideration of the influence of the driving scene on the movement of the rear vehicle according to the driving scene, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, the number of driving scenes extracted from the environment in which the vehicle behind is placed is not limited to one, and a plurality of driving scenes can be extracted at the same time. Therefore, a plurality of prediction methods can be used at the same time corresponding to each of the plurality of traveling scenes, and as a result, the prediction accuracy of the movement of the vehicle behind is improved.

Further, as described in the first traveling scene, the state of the signal around the own vehicle is detected, and the operation of the rear vehicle is predicted based on the state of the signal. As a result, the movement of the rear vehicle can be predicted in consideration of the influence of the signal around the own vehicle on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as described in the second traveling scene, when there is an obstacle that affects the traveling of the rear vehicle around the rear vehicle, the movement of the rear vehicle is predicted based on the situation of the obstacle. As a result, the movement of the rear vehicle can be predicted in consideration of the influence of the obstacle on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as explained in the third driving scene, it is determined whether or not there is a stop place related to the passenger car transportation business around the own vehicle, and if there is a stop place, the rear vehicle is the passenger car transportation business. The movement of the vehicle behind is predicted based on whether or not the vehicle corresponds to. It is possible to predict the movement of the rear vehicle in consideration of the influence of the presence of the stop place on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as described in the 4th driving scene, the 5th driving scene, and the 6th driving scene, the attributes of other vehicles traveling around the rear vehicle (whether the oncoming vehicle, the following vehicle, or the side vehicle, and whether the vehicle is a side vehicle, and , The movement of other vehicles) is detected, and the movement of the rear vehicle is predicted based on the detected attributes of the other vehicle. As a result, the movement of the rear vehicle can be predicted in consideration of the influence of the attributes of the other vehicle on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as described in the sixth driving scene, when the own vehicle travels at the intersection, the predicted probability of the movement of the rear vehicle is determined by the other vehicle located in the intersection lane where the own vehicle intersects with the lane in which the own vehicle travels. It is calculated based on the running condition of. As a result, the movement of the rear vehicle can be predicted in consideration of the influence of other vehicles located in the crossing lane on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as described in the seventh traveling scene, the road structure around the rear vehicle is detected, and the movement of the rear vehicle is predicted based on the road structure. As a result, the movement of the rear vehicle can be predicted in consideration of the influence of the road structure on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as described in the eighth traveling scene, the traffic prohibited area around the rear vehicle is detected, and if there is a traffic prohibited area, the operation of the rear vehicle is predicted based on the traffic prohibited area. As a result, the movement of the rear vehicle can be predicted in consideration of the influence of the road structure on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, in the traveling support method and the traveling support device according to the present embodiment, the behavior of the rear vehicle is detected and recorded, and the movement of the rear vehicle is performed based on the behavior of the rear vehicle in the environment in which the rear vehicle is placed. It may be predictive. As a result, the movement of the rear vehicle can be predicted in consideration of the behavior of the rear vehicle itself, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, the traveling support method and the traveling support device according to the present embodiment may detect the front situation of the own vehicle and predict the operation of the rear vehicle based on the front situation. As a result, the movement of the rear vehicle can be predicted in consideration of the influence of the situation in front of the own vehicle on the rear vehicle, and as a result, the prediction accuracy of the movement of the rear vehicle is improved.

Further, as described in each driving scene, when predicting the movement of the rear vehicle, the likelihood of the motion candidate of the rear vehicle may be calculated based on the environment in which the rear vehicle is placed. .. This makes it possible to appropriately predict the movement of the vehicle behind. Furthermore, it becomes possible to provide appropriate driving support for the own vehicle corresponding to the movement candidates that the rear vehicle can take.

Further, as described in each traveling scene, after predicting the movement of the rear vehicle, the traveling of the own vehicle may be controlled based on the prediction result. As a result, the own vehicle can be controlled after accurately predicting the movement of the rear vehicle, so that the own vehicle can be appropriately controlled according to the surrounding conditions of the own vehicle and the rear vehicle.

[Other embodiments]
As another modification, the likelihood of the motion candidate of the rear vehicle 61 may be calculated based on the information on whether or not the rear vehicle 61 is visible from the own vehicle 51 in each traveling scene. ..

For example, as shown in FIG. 13, it is assumed that the rear vehicle 61 is located in the blind spot region DR2 due to the presence of another vehicle 71 traveling behind the own vehicle 51. As a region visible from the own vehicle 51, FIG. 13 shows a visible region DR1 and a visible region DR3.

In the figure viewed from above of the own vehicle 51 from above, the area area A1 which is the total area of the visible area DR1 and the visible area DR3 is compared with the area area A2 of the blind spot area DR2. Here, it is considered that the larger the ratio A1 / A2 is, the more the rear vehicle 61 is located at a place farther from the own vehicle 51. Therefore, the larger the ratio A1 / A2, the smaller the likelihood of the motion candidate that approaches the own vehicle 51 among the motion candidates that the rear vehicle 61 can take may be estimated.

In the embodiment, the lane in which the own vehicle 51 travels is exemplified as one lane on one side or two lanes on one side, but the vehicle may travel in three or more lanes. Further, in the embodiment, the case of right-hand traffic is illustrated, but the present invention can be applied even in the case of left-hand traffic.

In the embodiment, the case where the own vehicle 51 is an automatically driven vehicle is illustrated, but the own vehicle 51 may be a manually driven vehicle. In this case, instead of the vehicle control unit 32, a speaker, a display for guiding the operation of the steering, the accelerator, and the brake to the driver, and a controller for controlling these user interfaces are provided by using voice or an image. All you have to do is prepare.

Each of the described functions and processes may be implemented by one or more processing circuits. Processing circuits include programmed processors, electrical circuits, etc., as well as devices such as application specific integrated circuits (ASICs) and circuit components arranged to perform the described functions. Etc. are also included.

Although the contents of the present invention have been described above according to the embodiments, it is obvious to those skilled in the art that the present invention is not limited to these descriptions and can be modified and improved in various ways. The statements and drawings that form part of this disclosure should not be understood as limiting the invention. This disclosure will reveal to those skilled in the art various alternative embodiments, examples and operational techniques.

It goes without saying that the present invention includes various embodiments not described here. Therefore, the technical scope of the present invention is defined only by the matters specifying the invention relating to the reasonable claims from the above description.

1 Object detection device 2a Detection integration unit 2b Object tracking unit 3 Own vehicle position estimation device 4 Map acquisition device 5 In-map position calculation unit 10 Motion prediction unit 11 Behavior determination unit 12 Motion candidate prediction unit 13 Rear vehicle extraction unit 16 Track prediction unit 17 Probability estimation unit 21 Rear prediction necessity determination unit 25 Environmental information extraction unit 26 Prediction method selection unit 31 Own vehicle route generation unit 32 Vehicle control unit

Claims (13)

In the driving support method that predicts the surrounding situation of the own vehicle and supports the running of the own vehicle based on the prediction result.
Detecting the rear vehicle located behind the own vehicle,
Detects the environment in which the vehicle behind is placed and
Detecting the type of environment,
Select one or more prediction methods corresponding to the above type from a plurality of prediction methods, and select one or more prediction methods.
Predicting the movement of the rear vehicle based on the environment in which the rear vehicle is placed using the selected prediction method.
It is a driving support method characterized by
In a situation where there is a no-traffic area in front of the own lane in which the own vehicle travels, the own vehicle has an operation intention to change lanes from the own lane to an adjacent lane adjacent to the own lane, and the said When it is determined that there is an intersection in front of the own vehicle and the rear vehicle, and the operation of the own vehicle and the rear vehicle is determined according to a signal around the own vehicle.
Detecting the state of the signal,
A traveling support method comprising predicting the movement of the rear vehicle based on the state of the signal. The driving support method according to claim 1.
When it is determined that another vehicle is approaching the intersection from the intersection lane that intersects with the own lane and the own vehicle travels at the intersection.
A traveling support method comprising calculating a predicted likelihood of an operation of the rear vehicle based on the speed of the other vehicle. In the driving support method that predicts the surrounding situation of the own vehicle and supports the running of the own vehicle based on the prediction result.
Detecting the rear vehicle located behind the own vehicle,
Detects the environment in which the vehicle behind is placed and
Detecting the type of environment,
Select one or more prediction methods corresponding to the above type from a plurality of prediction methods, and select one or more prediction methods.
Predicting the movement of the rear vehicle based on the environment in which the rear vehicle is placed using the selected prediction method.
It is a driving support method characterized by
It is determined that the own vehicle has the intention of turning from the own lane in which the own vehicle travels and crosses the adjacent lane adjacent to the own lane, and there is an obstacle in the adjacent lane. In case,
A traveling support method characterized in that the predicted likelihood of the movement of the rear vehicle is calculated based on the ratio of the width of the obstacle measured along the width direction of the adjacent lane to the width of the adjacent lane. .. In the driving support method that predicts the surrounding situation of the own vehicle and supports the running of the own vehicle based on the prediction result.
Detecting the rear vehicle located behind the own vehicle,
Detects the environment in which the vehicle behind is placed and
Detecting the type of environment,
Select one or more prediction methods corresponding to the above type from a plurality of prediction methods, and select one or more prediction methods.
Predicting the movement of the rear vehicle based on the environment in which the rear vehicle is placed using the selected prediction method.
It is a driving support method characterized by
It is determined whether or not there is a stop place related to the passenger car transportation business around the own vehicle.
A traveling support method comprising predicting the operation of the rear vehicle based on whether or not the rear vehicle is a vehicle corresponding to the passenger vehicle transportation business when there is a stop location. In the driving support method that predicts the surrounding situation of the own vehicle and supports the running of the own vehicle based on the prediction result.
Detecting the rear vehicle located behind the own vehicle,
Detects the environment in which the vehicle behind is placed and
Detecting the type of environment,
Select one or more prediction methods corresponding to the above type from a plurality of prediction methods, and select one or more prediction methods.
Predicting the movement of the rear vehicle based on the environment in which the rear vehicle is placed using the selected prediction method.
It is a driving support method characterized by
In a situation where the own vehicle is about to start from a state where the own vehicle is stopped on the shoulder of the own lane in which the own vehicle is traveling, the vehicle travels in an oncoming lane in front of the own vehicle and adjacent to the own lane. When it is determined that there is another vehicle that is operating
Based on the ratio of the time from the head of the rear vehicle to the head of the own vehicle to the time to run through the rear vehicle with respect to the time for the other vehicle to run through the distance from the head of the other vehicle to the head of the own vehicle. A traveling support method characterized by calculating the predicted likelihood of the movement of the rear vehicle. In the driving support method that predicts the surrounding situation of the own vehicle and supports the running of the own vehicle based on the prediction result.
Detecting the rear vehicle located behind the own vehicle,
Detects the environment in which the vehicle behind is placed and
Detecting the type of environment,
Select one or more prediction methods corresponding to the above type from a plurality of prediction methods, and select one or more prediction methods.
Predicting the movement of the rear vehicle based on the environment in which the rear vehicle is placed using the selected prediction method.
It is a driving support method characterized by
When it is determined that another vehicle exists between the own vehicle and the rear vehicle in the situation where the own vehicle is about to stop on the shoulder of the own lane in which the own vehicle travels.
Based on the distance from the center position of the other vehicle to the end of the own lane measured along the width direction of the own lane, or the width of the rear vehicle measured along the width direction of the own lane. A traveling support method characterized by calculating the predicted likelihood of the movement of the rear vehicle. In the driving support method that predicts the surrounding situation of the own vehicle and supports the running of the own vehicle based on the prediction result.
Detecting the rear vehicle located behind the own vehicle,
Detects the environment in which the vehicle behind is placed and
Detecting the type of environment,
Select one or more prediction methods corresponding to the above type from a plurality of prediction methods, and select one or more prediction methods.
Predicting the movement of the rear vehicle based on the environment in which the rear vehicle is placed using the selected prediction method.
It is a driving support method characterized by
When the own lane in which the own vehicle travels merges with the merging lane at the merging point in front of the own vehicle.
The rear vehicle's A driving support method characterized by calculating the predicted likelihood of motion. In the driving support method that predicts the surrounding situation of the own vehicle and supports the running of the own vehicle based on the prediction result.
Detecting the rear vehicle located behind the own vehicle,
Detects the environment in which the vehicle behind is placed and
Detecting the type of environment,
Select one or more prediction methods corresponding to the above type from a plurality of prediction methods, and select one or more prediction methods.
Predicting the movement of the rear vehicle based on the environment in which the rear vehicle is placed using the selected prediction method.
It is a driving support method characterized by
When it is determined that the own vehicle is in a situation where it is about to go straight past the side of a no-traffic area existing in an adjacent lane adjacent to the own lane in which the own vehicle is traveling in front of the own vehicle.
The rear is based on the ratio of the time for the own vehicle to run through the distance from the head of the own vehicle to the forbidden area with respect to the time for the rear vehicle to run through the distance from the head of the rear vehicle to the forbidden area. A driving support method characterized by calculating the predicted likelihood of vehicle motion. The driving support method according to any one of claims 1 to 8.
Detecting the behavior of the vehicle behind,
A traveling support method comprising predicting the movement of the rear vehicle based on the behavior of the rear vehicle in the environment in which the rear vehicle is placed. The driving support method according to any one of claims 1 to 9.
As the surrounding situation of the own vehicle, the front situation of the own vehicle is detected.
A traveling support method comprising predicting the movement of the rear vehicle based on the front situation. The driving support method according to any one of claims 1 to 10.
A traveling support method characterized by calculating the predicted likelihood of the movement of the rear vehicle based on the environment. The driving support method according to any one of claims 1 to 11.
Predicting the movement of the rear vehicle based on the environment,
A traveling support method characterized in that the traveling of the own vehicle is controlled based on the prediction result. An object detection sensor that detects a vehicle behind the vehicle, and an object detection sensor that detects the vehicle behind the vehicle.
An environment information extraction unit that extracts the environment in which the rear vehicle is placed and detects the type of the environment,
A prediction method selection unit that selects one or more prediction methods corresponding to the above type from a plurality of prediction methods.
Using the selected prediction method, a motion prediction unit that predicts the motion of the rear vehicle based on the environment in which the rear vehicle is placed, and a motion prediction unit.
A control unit that controls the own vehicle based on the prediction result of the operation prediction unit,
A travel support apparatus characterized by comprising,
The operation prediction unit is
In a situation where there is a no-traffic area in front of the own lane in which the own vehicle travels, the own vehicle has an operation intention to change lanes from the own lane to an adjacent lane adjacent to the own lane, and the said When it is determined that there is an intersection in front of the own vehicle and the rear vehicle, and the operation of the own vehicle and the rear vehicle is determined according to a signal around the own vehicle.
Detecting the state of the signal,
Predicting the movement of the vehicle behind the vehicle based on the state of the signal.
A driving support device characterized by .

Images