JP7322845B2 - self-driving device - Google Patents

Description

The present invention relates to an automatic driving device.

In recent years, there has been proposed a technique of setting a travel trajectory on which a vehicle should travel using a potential field (see Patent Literature 1 below). In addition, technology that applies probabilistic position estimation methods such as the Kalman filter to predict the future positions of the vehicle and surrounding objects (other vehicles, etc.), and estimates the collision probability of the vehicle from the probability distribution to avoid collisions. is proposed.

JP 2018-192954 A

However, with the above technology, the position of surrounding objects is updated every time, so the risk of surrounding objects whose relative speed to the vehicle is close to 0 cannot be properly estimated, and it is difficult to secure a distance between vehicles during autonomous driving. becomes difficult.

Therefore, the present invention has been made in view of these points, and an object of the present invention is to obtain a driving behavior that can appropriately secure an inter-vehicle distance based on risk estimation during automatic driving.

In one aspect of the present invention, an automatic driving device that determines the driving behavior of a vehicle based on a potential field obtained in a predetermined prediction period, the object acquiring speed information of objects around the vehicle. an information acquisition unit; a potential generation unit that generates a potential for extending an object corresponding to the object in a moving direction according to the moving speed of the object and the prediction period; and a risk evaluation unit that evaluates the risk of collision of the own vehicle during the prediction period.

Further, the risk evaluation unit evaluates the risk in a state in which the object for which the potential is generated is moving until a first time in the prediction period, and after the first time, the potential is The risk may be evaluated assuming that the generated object is stopped.

Further, the object determination unit determines an object whose speed is equal to or less than a predetermined value among the objects corresponding to the objects around the own vehicle as a static object, and determines an object whose speed is greater than the predetermined value as a dynamic object. and the potential generation unit may generate a potential for extending the object determined to be the dynamic object by the object determination unit in a moving direction.

Further, the potential generating section may generate a potential for each of a plurality of objects around the own vehicle, and the risk evaluating section may evaluate the risk of collision with respect to the object with the maximum potential.

Further, the object information acquisition unit may predict the future position of the object based on at least the velocity out of the velocity and acceleration of the surrounding object.

Further, when the surrounding object is traveling in the lane, the object information acquisition unit may predict the future position of the object based on the information about the shape of the lane.

Further, the collision risk potential evaluated by the risk evaluation unit and the potential for maintaining the speed or driving lane of the own vehicle are applied to a cost function to determine the driving behavior of the own vehicle. It is good also as further providing the driving action determination part which carries out.

ADVANTAGE OF THE INVENTION According to this invention, it is effective in the ability to obtain the driving behavior which can ensure an appropriate inter-vehicle distance automatically at the time of automatic driving.

BRIEF DESCRIPTION OF THE DRAWINGS It is a schematic diagram for demonstrating an example of a structure of the automatic driving apparatus 1 which concerns on one embodiment. 2 is a block diagram for explaining an example of the detailed configuration of the control device 10; FIG. FIG. 4 is a schematic diagram for explaining an example of potential generation for an object; FIG. 4 is a schematic diagram for explaining the magnitude of static potential; FIG. 4 is a schematic diagram for explaining the magnitude of dynamic potential; FIG. 10 is a schematic diagram for explaining an example of risk evaluation for a dynamic object during short-term prediction; 4 is a flowchart for explaining an operation example of the automatic driving device 1;

<Configuration of automatic driving device>
A configuration of an automatic driving device according to one embodiment of the present invention will be described with reference to FIG.

FIG. 1 is a schematic diagram for explaining an example of the configuration of an automatic driving device 1 according to one embodiment. The automatic driving device 1 is mounted on a vehicle such as a truck, for example, and assists the driving of the own vehicle. The automatic driving device 1 sets the driving behavior of the own vehicle and determines the driving route based on the set driving behavior, for example, during automatic driving. The automatic driving device 1 sets the driving behavior of the own vehicle based on the potential field including the basic driving potential. The own vehicle runs according to the driving behavior set by the automatic driving device 1 . Also, the own vehicle can travel along the driving route determined by the automatic driving device 1 .

The automatic driving device 1 includes a vehicle detection unit 2, an environment recognition unit 4, a map database 6, and a control device 10, as shown in FIG.
The vehicle detection unit 2 detects the state of the own vehicle. A vehicle detection unit 2 detects the position and speed of the own vehicle. For example, the vehicle detection unit 2 has a GPS (Global Positioning System) receiver, and detects the position of the vehicle from radio waves received by the GPS receiver.

The environment recognition unit 4 recognizes the environmental conditions around the own vehicle. For example, the environment recognition unit 4 has an external sensor such as a camera or radar. The environment recognition unit 4 recognizes objects (for example, other vehicles, bicycles, pedestrians, etc.) around the own vehicle based on the output of the external sensor. The environment recognition unit 4 also recognizes, for example, the position and width of the lane on which the vehicle is traveling.

The map database 6 stores road map information. The road map information includes, for example, data indicating three-dimensional coordinates of latitude, longitude and altitude of roads. The road map information also includes information on the number of lanes and lane structure of the road on which the vehicle is traveling. Further, the map database 6 can instead obtain lane information recognized by the environment recognition unit 4 based on the position of the host vehicle detected by the vehicle detection unit 2 .

The control device 10 controls the operation of the automatic driving device 1 . The control device 10 uses the potential field obtained in the short-term prediction period to determine the driving behavior of the own vehicle. The potential field is obtained, for example, by adding the basic running potential and the actual risk potential, as is well known. Although the details will be described later, the control device 10 of the present embodiment generates a potential for extending the object corresponding to the object in the moving direction according to the moving speed of the object around the own vehicle and the prediction period. Then, the automatic driving device 1 evaluates the risk of collision of the own vehicle with the object for which the potential is generated during the prediction period, depending on the prediction time, with or without considering the movement of the object. At that time, in order not to underestimate the risk in the moving direction of the object when it does not move, the object potential extended in the moving direction is used for the risk evaluation. As a result, it becomes possible to appropriately estimate the risk of surrounding objects whose relative speed to the own vehicle is close to 0, and to obtain driving behavior that automatically secures an appropriate inter-vehicle distance during automatic driving.

<Detailed Configuration of Control Device 10>
A detailed configuration of the control device 10 will be described with reference to FIG.
FIG. 2 is a block diagram for explaining an example of the detailed configuration of the control device 10. As shown in FIG. The control device 10 has a storage unit 12 and a control unit 14, as shown in FIG.

The storage unit 12 includes, for example, ROM (Read Only Memory) and RAM (Random Access Memory). The storage unit 12 stores programs and various data for the control unit 14 to execute.

The control unit 14 is, for example, a CPU (Central Processing Unit). The control unit 14 functions as an object information acquisition unit 142 , an object determination unit 144 , a potential generation unit 145 , a risk evaluation unit 146 and a driving action determination unit 148 by executing programs stored in the storage unit 12 .

The object information acquisition unit 142 acquires information about objects around the vehicle. For example, the object information acquisition unit 142 acquires information on an object (for example, another vehicle) recognized by the environment recognition unit 4 . The object information acquisition unit 142 also acquires speed information related to acceleration in addition to the moving direction and moving speed of the object. That is, the object information acquisition unit 142 has the function of a speed information acquisition unit that acquires speed information of an object.

The object information acquisition unit 142 may predict the future position of the object based on at least the velocity of the velocity and acceleration of the surrounding object. For example, when the environment recognition unit 4 can detect both the velocity and acceleration of the object, the object information acquisition unit 142 predicts the future position of the object based on the velocity and acceleration. In addition, when a surrounding object (for example, a preceding vehicle) is traveling in the lane, the object information acquiring unit 142 may predict the future position of the object based on information regarding the shape of the lane. For example, the object information acquisition unit 142 predicts the future position of the object based on the lane position and curvature recognized by the environment recognition unit 4 .

The object determination unit 144 determines whether the object corresponding to the object for which the object information acquisition unit 142 has acquired information such as velocity information and future position is a static object or a dynamic object. Specifically, the object determination unit 144 determines an object whose speed is equal to or less than a predetermined value among objects around the own vehicle as a static object. On the other hand, the object determination unit 144 determines that an object whose speed is greater than a predetermined value is a dynamic object. A static object is, for example, a stationary vehicle, and a dynamic object is, for example, another vehicle in motion.

The potential generator 145 generates potentials for objects around the vehicle. The potential generator 145 generates a potential for each of the multiple objects when there are multiple objects around the vehicle. The potential generated by the potential generation unit 145 is an actual risk potential for preventing collision with the host vehicle.

The potential generating section 145 generates a potential corresponding to the object determined by the object determining section 144 . That is, the potential generation unit 145 generates a static object potential (hereinafter simply referred to as static potential) when the object is determined to be a static object, and generates a dynamic object potential when the object is determined to be a dynamic object. (hereinafter simply referred to as dynamic potential).

FIG. 3 is a schematic diagram for explaining an example of potential generation for an object. If the object is a static object, a static potential 112 is generated for the static object 110, as shown in FIG. 3(a). Specifically, static potential 112 is generated to surround static object 110 . On the other hand, when the object is a dynamic object, unlike the static potential generated in the static object 110, as shown in FIG. direction) is generated. The extent to which the dynamic potential 122 extends in the direction of movement is proportional to the speed of the dynamic object 120 and the predicted time corresponding to the time corresponding to the inter-vehicle distance to the object.

Here, the magnitudes of the static potential and the dynamic potential will be described with reference to FIGS. 4 and 5. FIG.
FIG. 4 is a schematic diagram for explaining the magnitude of static potential. It is assumed that the X-axis direction shown in FIG. 4 is the forward direction of the static object. If the X-axis direction and Y-axis direction of the object do not match the X-axis direction and Y-axis direction of the potential map, the following calculations are performed after the coordinate transformation is performed using the azimuth angle of the object. Here, it is assumed that the static object is located in region R5. In this case, the magnitude of the static potential differs depending on the regions R1-R9. The static potential of region R1 is expressed by the following equation (1), the static potential of region R2 is expressed by equation (2), the static potential of region R3 is expressed by equation (3), and the static potential of region R4 is expressed by equation (3). The static potential is given by equation (4), the static potential of region R5 is given by equation (5), the static potential of region R6 is given by equation (6), and the static potential of region R7 is given by equation (7), the static potential of region R8 is given by equation (8), and the static potential of region R9 is given by equation (9).

FIG. 5 is a schematic diagram for explaining the magnitude of the dynamic potential. It is assumed that the X-axis direction shown in FIG. 5 is the moving direction of the dynamic object. If the X-axis direction and Y-axis direction of the object do not match the X-axis direction and Y-axis direction of the potential map, the following calculations are performed after performing coordinate conversion using the azimuth angle of the object. Here, it is assumed that the dynamic object is located in region R5. In this case, the magnitude of the dynamic potential differs depending on R1-R9. The dynamic potential of the region R1 is expressed by the following formula (10), the dynamic potential of the region R2 is expressed by the formula (11), the dynamic potential of the region R3 is expressed by the formula (12), and the dynamic potential of the region R4 is expressed by the formula (12). The dynamic potential of region R5 is shown by equation (13), the dynamic potential of region R5 is shown by equation (14), the dynamic potential of region R6 is shown by equation (15), and the dynamic potential of region R7 is shown by equation (16), the dynamic potential of region R8 is given by equation (17), and the dynamic potential of region R9 is given by equation (18).

It is defined by equations (19) and (20).

According to equations (19) and (20), the variance reflects the velocity of the object (V _x,i , V _y,i ) and the predicted time (Δt _s ). Therefore, a potential is generated that extends in the direction of movement in proportion to the magnitude of the velocity and the length of the predicted time. It should be noted that <> in formulas (19) and (20) means Macaulay parentheses, and if the value inside the parentheses is positive, the value inside the parentheses

The risk evaluation unit 146 evaluates the collision risk of the own vehicle with respect to objects during short-term prediction for determining driving behavior. The risk evaluation unit 146 evaluates the risk of the host vehicle colliding with an object based on the potential generated by the potential generation unit 145 . For example, the risk evaluation unit 146 evaluates the risk of collision of the own vehicle with a dynamic object based on the dynamic potential generated by the potential generation unit 145 . Also, the risk evaluation unit 146 evaluates the risk of collision with an object having the largest potential magnitude during the short-term prediction period. As a result, when there are a plurality of objects around the own vehicle, it is possible to evaluate an object with a higher collision risk without depending on the size of the object.

The risk evaluator 146 adjusts the motion state of the dynamic object 120 during short-term prediction to evaluate the risk of collision. Specifically, the risk evaluation unit 146 evaluates the risk while the dynamic object 120 for which the dynamic potential 122 is generated is moving until the first time of the short-term prediction period. On the other hand, after the first time, the risk evaluation unit 146 evaluates the risk assuming that the dynamic object 120 for which the dynamic potential 122 is generated is stationary. As a result, it is possible to maintain the distance to the object whose relative velocity to the own vehicle is close to zero. Therefore, collisions when the dynamic object 120 comes to a sudden stop can be considered.

FIG. 6 is a schematic diagram for explaining an example of risk evaluation for dynamic objects during short-term prediction. Here, it is assumed that the dynamic object 120 for which the dynamic potential 122 is generated is the preceding vehicle that is separated from the host vehicle 100 by a distance L1, as shown in FIG. 6(a). Also, the dynamic object 120 is assumed to be moving until the first time in the prediction period, and the distance L1 between the host vehicle 100 and the dynamic object 120 is maintained as shown in FIG. 6(b). Therefore, if only the movement of the dynamic object is taken into account, there is no risk of collision during future prediction, and it becomes easier to take driving behavior that reduces the inter-vehicle distance. On the other hand, after the first time in the prediction period, the dynamic object 120 is assumed to be stationary, and the distance L2 between the host vehicle 100 and the dynamic object 120 is shortened as shown in FIG. 6(c). . In this case, since the risk of collision increases during future prediction, it becomes easier to secure a distance between vehicles as an actual driving behavior.

The driving behavior determining unit 148 determines the driving behavior of the own vehicle as short-term prediction. The driving behavior determining unit 148 determines the driving behavior of the own vehicle during the short-term prediction period based on the potential field including the potential of the own vehicle speed maintenance or lane keeping and the risk potential evaluated by the risk evaluation unit 146. do. Driving behavior determination unit 148 applies the potential field to the cost function to determine the optimal driving behavior of the host vehicle. The driving behavior determining unit 148 determines the optimum driving behavior by obtaining the value that minimizes the cost function. The driving behavior determination unit 148 determines the acceleration/deceleration and yaw rate of the host vehicle as the driving behavior.

<Operation example of automatic driving device>
An operation example of the automatic driving device 1 will be described with reference to FIG.

FIG. 7 is a flowchart for explaining an operation example of the automatic driving device 1. FIG. The processing shown in this flowchart is performed while the vehicle is running. Here, it is assumed that the vehicle is automatically driving at high speed.

First, the object information acquisition unit 142 of the control device 10 acquires speed information of objects around the host vehicle (step S102). Specifically, the object information acquisition unit 142 acquires the moving direction and moving speed of the object recognized by the environment recognition unit 4 .

Next, the object determination unit 144 determines an object corresponding to the object for which speed information has been acquired (step S104). Specifically, the object determination unit 144 determines whether the object is a static object or a dynamic object based on the speed information.

Next, the potential generator 145 generates a potential for the object (step S106). For example, the potential generation unit 145 generates a dynamic potential that stretches an object determined as a dynamic object in the movement direction.

Next, the risk evaluation unit 146 evaluates the collision risk of the own vehicle with respect to the object for which the potential has been generated (step S108). For example, when evaluating the collision risk with respect to the dynamic object for which the dynamic potential is generated, the risk evaluation unit 146 evaluates the collision risk with the dynamic object moving until the first time in the prediction period. After the first time, the collision risk is evaluated assuming that the dynamic object has stopped.

Next, the driving behavior determination unit 148 determines the driving behavior of the own vehicle based on the potential field including the potential generated by the potential generation unit 145 (step S110). For example, the driving behavior determination unit 148 applies a so-called cost function to the potential field obtained by adding the basic driving potential and the manifested risk potential (potential generated by the potential generation unit 145) to set the driving behavior of the host vehicle. As a result, the optimum driving behavior (acceleration/deceleration and yaw rate) of the own vehicle is determined based on short-term prediction.

<Effects of this embodiment>
The automatic driving device 1 of the embodiment described above generates a potential that extends the object corresponding to the object in the moving direction according to the moving speed of the object around the own vehicle and the prediction period. Then, the automatic driving device 1 evaluates the risk of collision of the own vehicle with the object for which the potential is generated during the prediction period, depending on the prediction time, with or without considering the movement of the object.
At that time, in order not to underestimate the risk in the moving direction of the object when it does not move, the object potential extended in the moving direction is used for the risk evaluation. As a result, it is possible to obtain a driving behavior that automatically secures an appropriate inter-vehicle distance during automatic driving.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist thereof. be. For example, all or part of the device can be functionally or physically distributed and integrated in arbitrary units. In addition, new embodiments resulting from arbitrary combinations of multiple embodiments are also included in the embodiments of the present invention. The effect of the new embodiment caused by the combination has the effect of the original embodiment.

1 Automatic Driving Device 100 Own Vehicle 120 Dynamic Object 122 Dynamic Potential 142 Object Information Acquisition Unit 144 Object Judgment Unit 145 Potential Generation Unit 146 Risk Evaluation Unit

Claims (6)

An automatic driving device that determines the driving behavior of the own vehicle based on the potential field obtained in a predetermined prediction period,
an object information acquisition unit that acquires speed information of objects around the own vehicle;
a potential generating unit that generates a potential for extending an object corresponding to the object in a moving direction according to the moving speed of the object and the prediction period;
a risk evaluation unit that evaluates a risk of collision of the host vehicle against the object for which the potential is generated during the prediction period;
with
The risk assessment unit
evaluating the risk while the object for which the potential is generated is moving until a first time in the prediction period;
After the first time, the automatic driving device evaluates the risk assuming that the object for which the potential is generated is stationary . Further an object determination unit for determining an object having a speed equal to or less than a predetermined value as a static object and determining an object having a speed greater than the predetermined value as a dynamic object among the objects corresponding to the objects around the own vehicle. prepared,
The potential generation unit generates a potential that extends the object determined to be the dynamic object by the object determination unit in a moving direction.
The automatic driving device according to claim 1 . The potential generation unit generates a potential for each of a plurality of objects around the own vehicle,
wherein the risk assessment unit assesses the risk of collision for objects with maximum potential;
The automatic driving device according to claim 1 or 2 . The object information acquisition unit predicts the future position of the object based on at least the velocity of the velocity and acceleration of the surrounding object.
The automatic driving device according to any one of claims 1 to 3 . The object information acquisition unit predicts the future position of the object based on information about the shape of the lane when the surrounding object is traveling in the lane.
The automatic driving device according to claim 4 . driving that determines the driving behavior of the own vehicle by applying the collision risk potential evaluated by the risk evaluation unit and the potential for maintaining the speed of the own vehicle or maintaining the driving lane to a cost function; further comprising an action determination unit;
The automatic driving device according to any one of claims 1 to 5 .