JP7681504B2 - Pedestrian crossing prediction method and pedestrian crossing prediction device - Google Patents

Description

The present invention relates to a pedestrian crossing prediction method and a pedestrian crossing prediction device.

A method has been known for predicting the possibility of a crossing between a vehicle and a pedestrian when turning right or left at an intersection, based on the direction and speed of the vehicle after turning right or left and the direction and speed of the pedestrian (Patent Document 1).

JP 2014-232412 A

However, the invention described in Patent Document 1 does not take into account the possibility that pedestrians may accelerate in a hurry to cross the crosswalk if there is a shuttle bus across the road, which may result in reduced prediction accuracy.

The present invention has been made in consideration of the above problems, and its purpose is to provide a pedestrian crossing prediction method and a pedestrian crossing prediction device that can accurately predict whether a pedestrian will cross a road when a shuttle bus is present across the road.

In one embodiment of the present invention, when a shuttle vehicle is detected on the other side of the road based on the pedestrian's position, the pedestrian crossing prediction method determines whether the shuttle vehicle is stopped or about to stop, and when it is determined that the shuttle vehicle is stopped or about to stop, increases the likelihood compared to when a shuttle vehicle is not detected.

The present invention makes it possible to accurately predict whether a pedestrian will cross a road when a shuttle bus is on either side of the road.

FIG. 1 is a configuration diagram of a pedestrian crossing prediction device according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of a method for calculating the likelihood. FIG. 3 is a graph showing the relationship between the acceleration threshold and time. FIG. 4 is a graph showing the relationship between the speed threshold and time. FIG. 5 is a flowchart illustrating an example of an operation of the pedestrian crossing prediction device. FIG. 6 is a diagram illustrating an example of a method for calculating the likelihood. FIG. 7 is a diagram illustrating an example of a method for calculating the likelihood.

Embodiments of the present invention will be described below with reference to the drawings. In the description of the drawings, identical parts are given the same reference numerals and the description will be omitted.

An example of the configuration of a pedestrian crossing prediction device will be described with reference to FIG. 1. As shown in FIG. 1, the pedestrian crossing prediction device includes an object detection device 1, a vehicle position estimation device 2, a map database 3, and a controller 100.

The pedestrian crossing prediction device is installed in a vehicle (host vehicle). The pedestrian crossing prediction device may be installed in a vehicle with an automatic driving function, or in a vehicle without an automatic driving function. The pedestrian crossing prediction device may also be installed in a vehicle that can switch between automatic driving and manual driving. The automatic driving function may also be a driving assistance function that automatically controls only some of the vehicle control functions, such as steering control, braking force control, and driving force control, to assist the driver in driving.

The object detection device 1 is composed of object detection sensors such as a laser range finder, radar, lidar, camera, and sonar. The object detection device 1 detects objects around the vehicle using multiple object detection sensors. The object detection device 1 detects moving objects including other vehicles, buses, motorbikes, bicycles, and pedestrians, and stationary objects including crosswalks and bus stops. The object detection device 1 detects the position, attitude, size, speed, acceleration, etc. of moving and stationary objects relative to the vehicle. The object detection device 1 outputs information about the detected objects to the controller 100. Note that object detection methods using laser range finders, radar, lidar, cameras, sonar, etc. are well known, so detailed explanations will be omitted.

The vehicle position estimation device 2 detects the position (position information) of the vehicle on the ground. One example of the vehicle position estimation device 2 is a GPS receiver. The GPS receiver detects the vehicle's position information on the ground by receiving radio waves from an artificial satellite. The vehicle's position information detected by the GPS receiver includes latitude information and longitude information. The GPS receiver outputs the detected vehicle's position information to the controller 100. Note that the method of detecting the vehicle's position information is not limited to a GPS receiver. For example, the vehicle's position may be estimated using a method called odometry. Odometry is a method of estimating the vehicle's position by determining the amount and direction of movement of the vehicle according to the rotation angle and rotation angular velocity of the vehicle. Note that a GNSS receiver may be used instead of a GPS receiver.

The controller 100 is a general-purpose microcomputer equipped with a CPU (Central Processing Unit), a memory, and an input/output unit. A computer program for functioning as a pedestrian crossing prediction device is installed in the microcomputer. By executing the computer program, the microcomputer functions as multiple information processing circuits equipped in the pedestrian crossing prediction device. Note that here, an example is shown in which multiple information processing circuits equipped in the pedestrian crossing prediction device are realized by software, but it is of course possible to configure the information processing circuit by preparing dedicated hardware for performing each information processing shown below. In addition, the multiple information processing circuits may be configured by individual hardware. The controller 100 includes a detection integration unit 4, an object tracking unit 5, an in-map position estimation unit 6, a behavior prediction unit 10, and a vehicle control unit 20 as an example of multiple information processing circuits. Furthermore, the behavior prediction unit 10 is classified into a pedestrian detection unit 11, a pedestrian speed change detection unit 12, a face direction detection unit 13, a surrounding object detection unit 14, a shuttle vehicle detection unit 15, a bus departure time acquisition unit 16, a boarding waiting number measurement unit 17, and a likelihood calculation unit 18.

The detection integration unit 4 integrates the multiple detection results obtained from each of the multiple object detection sensors equipped in the object detection device 1, and outputs a single detection result for each object. Specifically, from the object behavior obtained from each object detection sensor, the most rational object behavior that will minimize error is calculated, taking into account the error characteristics of each object detection sensor. Specifically, by using well-known sensor fusion technology, the detection results obtained from multiple types of sensors are comprehensively evaluated to obtain more accurate detection results.

The object tracking unit 5 tracks the objects detected by the detection integration unit 4. Specifically, the object tracking unit 5 verifies (matches) the identity of objects between different times based on the behavior of the objects output at different times, and tracks the objects based on the matching.

The map position estimation unit 6 estimates the position of the vehicle on the map from the absolute position of the vehicle obtained by the vehicle position estimation device 2 and the map information obtained by the map database 3. The map database 3 is a database stored in a car navigation device or the like, and stores map information necessary for route guidance, such as road information and facility information. The road information is, for example, information on intersections, the number of lanes on a road, road boundaries, and lane connections. The map database 3 outputs the map information to the map position estimation unit 6 in response to a request from the map position estimation unit 6. In this embodiment, the pedestrian crossing prediction device is described as having the map database 3, but it is not necessarily required that the pedestrian crossing prediction device has the map database 3. The map information may be acquired by various sensors such as a camera, or may be acquired using vehicle-to-vehicle communication or road-to-vehicle communication. In addition, if the map information is stored in an external server, the pedestrian crossing prediction device may acquire the map information from the server at any time by communication. In addition, the pedestrian crossing prediction device may periodically acquire the latest map information from the server and update the map information it holds. The map information stored in the map database 3 may be high-precision map data (HD MAP) or normal map data (SD MAP).

Next, the function of the behavior prediction unit 10 will be described in detail with reference to Figures 2 to 7. The scene shown in Figure 2 is a scene in which the vehicle 50 is traveling toward an intersection. Reference numeral 60 indicates a pedestrian. Reference numeral 70 indicates a bus. Reference numerals 61 to 63 indicate people waiting for the bus to arrive. Reference numeral 80 indicates a bus stop.

As shown in FIG. 2, if a pedestrian 60 is in front of a crosswalk (near the crosswalk), the pedestrian 60 is detected by the pedestrian detection unit 11 (step S101 in FIG. 5). More specifically, the pedestrian detection unit 11 detects the pedestrian 60 using data acquired from the object tracking unit 5. If a pedestrian 60 is detected (YES in step S101 in FIG. 5), the pedestrian detection unit 11 detects the walking speed of the pedestrian 60 (step S103 in FIG. 5).

The shuttle vehicle detection unit 15 detects a shuttle vehicle on the other side of the road based on the position of the pedestrian 60. In this embodiment, a "shuttle vehicle" is a vehicle capable of transporting many passengers, such as a bus. When the shuttle vehicle detection unit 15 detects a bus 70 on the other side of the road based on the position of the pedestrian 60, it determines whether the bus 70 is about to stop or whether the bus 70 is stopped (step S105 in FIG. 5). Whether the detected object is a bus can be determined based on the width and size of the vehicle (step S107 in FIG. 5). Whether the bus 70 is stopped can be determined based on the detected speed of the bus 70. Specifically, when the detected speed of the bus 70 is 0 km/h or is a value small enough to be considered as 0 km/h, the shuttle vehicle detection unit 15 can determine that the bus 70 is stopped. Whether the bus 70 is about to stop can be determined based on the distance from the side of the bus 70 to the edge of the road. Specifically, if the distance from the side of the bus 70 to the road edge is equal to or less than a predetermined distance, the shuttle vehicle detection unit 15 can determine that the bus 70 is about to stop. Alternatively, if the bus 70 approaches the road edge while decelerating, the shuttle vehicle detection unit 15 may determine that the bus 70 is about to stop. The speed of the bus 70 and the distance from the side of the bus 70 to the road edge are detected by the object detection device 1. The information detected by the shuttle vehicle detection unit 15 is output to the bus departure time acquisition unit 16. In FIG. 2, "the bus 70 is stopped" means "the bus 70 is stopped at the bus stop 80." "The other side of the road based on the position of the pedestrian 60" may be expressed as "the other side of the road in the direction of travel of the pedestrian 60."

When the shuttle vehicle detection unit 15 detects a bus 70 that is stopped or about to stop (YES in steps S105 and S107 in FIG. 5), the bus departure time acquisition unit 16 acquires the departure time of the detected bus 70 and reads out the departure time closest to the current time (step S109 in FIG. 5). There is no particular limitation on the method of acquiring the departure time of the bus 70, but for example, if the departure time for each bus stop is stored in a storage device (not shown), the bus departure time acquisition unit 16 can acquire the departure time of the bus 70 by referring to the storage device. Alternatively, the departure time of the bus 70 may be acquired by road-to-vehicle communication. As another method, when it is detected that the bus 70 has stopped, the elapsed time (the time during which the bus 70 continues to stop) may be subtracted from a predetermined stop time to calculate the time until the bus 70 departs. By these methods, the remaining time from the current time when the bus 70 is detected until the bus 70 departs is calculated (step S111 in FIG. 5).

The likelihood that the pedestrian 60 will cross the crosswalk in a hurry changes depending on the time remaining until the bus 70 departs. In this embodiment, "likelihood" means plausibility and has the concept of high and low. For example, "the likelihood that the pedestrian 60 will cross the crosswalk is high" means "the pedestrian 60 is highly likely to cross the crosswalk." Consider a case in which the remaining time until the bus 70 departs is long in the scene of FIG. 2. In this case, the pedestrian 60 can still make it in time to board the bus 70 even if he waits for his own vehicle 50 to pass the crosswalk before crossing the crosswalk. Therefore, in this case, the likelihood that the pedestrian 60 will cross the crosswalk in a hurry is calculated to be low. On the other hand, if the remaining time until the bus 70 departs is short, if the pedestrian waits for his own vehicle 50 to pass the crosswalk, he will not be able to make it in time to board the bus 70. Therefore, the shorter the remaining time until the bus 70 departs, the higher the likelihood that the pedestrian 60 will cross the crosswalk in a hurry is calculated. However, if the time remaining until bus 70 departs is so short that the remaining time is less than a predetermined time (for example, less than 3 seconds), there is a high possibility that pedestrian 60 will give up on crossing the crosswalk in a hurry. In this case, the likelihood that pedestrian 60 will cross the crosswalk in a hurry is calculated to be low. The likelihood is calculated by likelihood calculation unit 18. Note that "the likelihood is calculated to be high" and "the likelihood is calculated to be low" mean, for example, compared to a case in which no causal event exists. Furthermore, "the likelihood that pedestrian 60 will cross the crosswalk in a hurry" may simply be rephrased as "the likelihood that pedestrian 60 will cross the crosswalk."

The boarding waiting number counting unit 17 counts the number of people waiting to board the bus 70 (step S113 in FIG. 5). The "number of people waiting to board the bus 70" refers to the number of people waiting for the arrival of the bus 70 at the bus stop 80 (three people, reference numbers 61 to 63, in FIG. 2). The boarding waiting number counting unit 17 counts the number of people waiting to board the bus 70 using information detected by the object detection device 1. In general bus operations, the bus 70 departs after all passengers have boarded, so the more people waiting to board, the longer the time left for the pedestrians 60. Conversely, the fewer the number of people waiting to board, the shorter the time left for the pedestrians 60. In other words, the fewer the number of people waiting to board, the more likely it is that the pedestrians 60 will cross the crosswalk in a hurry. Therefore, the fewer the number of people waiting to board, the higher the likelihood that the pedestrians 60 will cross the crosswalk in a hurry may be calculated.

The pedestrian speed change detection unit 12 calculates the speed change of the pedestrian 60 detected by the pedestrian detection unit 11 (step S115 in FIG. 5). If the pedestrian 60 starts accelerating in accordance with the timing of the bus 70 stopping or the action of the bus 70 trying to stop, there is a high possibility that the pedestrian 60 will cross the crosswalk. If the acceleration of the pedestrian 60 exceeds a predetermined value (threshold), the likelihood that the pedestrian 60 will cross the crosswalk may be calculated to be high. In addition, the threshold may be changed depending on the remaining time until the bus 70 departs. For example, as shown in FIG. 3, the threshold may be increased as the remaining time until the bus 70 departs is shorter. This is because the required acceleration is large. The vertical axis of FIG. 3 indicates the acceleration threshold, and the horizontal axis indicates the time when the bus departs. The closer the time when the bus departs is closer to the origin, the earlier the time when the bus departs. At times T1 and T2 (T1<T2), it indicates that time T1 departs before time T2. As shown in FIG. 3, in the case of time T1 when the remaining time until the bus 70 departs is shorter than time T2, the acceleration threshold may be set to A1, which is larger than A2. In addition, in the case where a speed change (acceleration) is not detected, if the speed at the time when the pedestrian 60 is detected is greater than a threshold (e.g., 10 km/h), the calculation may be performed so that the likelihood that the pedestrian 60 will cross the crosswalk in a hurry is higher. This is because the pedestrian 60 may have already accelerated at the time when the pedestrian 60 is detected. Note that, like the acceleration threshold, the speed threshold may be increased as the remaining time until the bus 70 departs is shorter. In FIG. 4, the vertical axis indicates the speed threshold, and the horizontal axis indicates the time when the bus departs. The closer the time when the bus departs is to the origin, the earlier the time when the bus departs. As shown in FIG. 4, in the case of time T1 when the remaining time until the bus 70 departs is shorter than time T2, the speed threshold may be set to V1, which is larger than V2. Note that the calculation may be performed so that the likelihood that the pedestrian 60 will cross the crosswalk in a hurry is higher as the acceleration of the pedestrian 60 is greater. In addition, the likelihood that a pedestrian 60 will cross the crosswalk in a hurry may be calculated to be higher as the speed of the pedestrian 60 increases.

The face direction detection unit 13 detects the face direction of the pedestrian 60 detected by the pedestrian detection unit 11 (step S117 in FIG. 5). The "detection of the face direction of the pedestrian 60" may be "detection of the line of sight of the pedestrian 60". A method for detecting the face direction from a camera image or the like is well known, so a detailed description is omitted. When the pedestrian 60 intends to board the bus 70, the pedestrian 60 often checks the direction of the bus 70 and decides to act according to the situation of the bus 70. As shown in FIG. 2, when the face direction of the pedestrian 60 is detected to be facing the direction of the bus 70 and the pedestrian 60 accelerates while looking in the direction of the bus 70, the likelihood that the pedestrian 60 will cross the crosswalk in a hurry may be calculated to be high. As shown in FIG. 6, even if the pedestrian 60 is not facing the direction of the bus 70 when the pedestrian is detected (in FIG. 6, the pedestrian 60 is facing upwards, not to the right, when the pedestrian is detected), if the pedestrian 60 accelerates while checking the direction of the bus 70 or is walking at a speed equal to or greater than a predetermined value, the likelihood of the pedestrian changing direction and crossing the crosswalk may be calculated to be high.

The surrounding object detection unit 14 detects other vehicles (hereinafter referred to as other vehicles) and other objects around the pedestrian 60 (step S119 in FIG. 5). The purpose of detecting other vehicles and other objects is that the likelihood of the pedestrian 60 crossing the crosswalk changes depending on whether there are other vehicles and other objects other than the vehicle 50 that make the pedestrian 60 wait. As an example, consider a case where there are other vehicles 51-52 (following vehicles 51-52) running behind the vehicle 50 as shown in FIG. 7. In this case, if the pedestrian 60 waits for the vehicle 50 to pass, he or she will also wait for the following vehicles 51-52 to pass, and will wait longer in front of the crosswalk. This will delay the time to reach the bus stop 80. If the remaining time until the bus 70 departs is longer than a predetermined time and there are other vehicles 51-52 other than the vehicle 50 that make the pedestrian 60 wait, the likelihood of the pedestrian 60 crossing the crosswalk in a hurry may be calculated to be higher than when there are no other vehicles 51-52.

The likelihood calculation unit 18 calculates the likelihood that the pedestrian 60 will cross the crosswalk based on the presence or absence of the bus 70, the remaining time until the bus 70 departs, the number of people waiting to board, the speed change of the pedestrian 60, the facial orientation of the pedestrian 60, the presence or absence of other vehicles, etc. (step S121 in FIG. 5). As described above, the likelihood calculation unit 18 changes the likelihood that the pedestrian 60 will cross the crosswalk based on each detected element, and adds the likelihood calculated based on each element. If the total value of the likelihood exceeds a predetermined value (0.7 as an example), the likelihood calculation unit 18 predicts that the pedestrian 60 will cross the crosswalk. The likelihood calculation unit 18 outputs the prediction result to the vehicle control unit 20. Note that when it is determined that the bus 70 is stopped or about to stop, the likelihood may be calculated to be higher than when the bus 70 is not detected.

When the likelihood calculation unit 18 predicts that the pedestrian 60 will cross the crosswalk, the vehicle control unit 20 accelerates the deceleration of the host vehicle 50 and stops the host vehicle 50 before the crosswalk. As a result, for example, when the host vehicle 50 is a vehicle equipped with an autonomous driving function, the discomfort felt by the occupants in the autonomous driving is eliminated or reduced. Note that "when the likelihood calculation unit 18 predicts that the pedestrian 60 will cross the crosswalk" may also be expressed as "when the likelihood calculated by the likelihood calculation unit 18 is greater than a predetermined value."

(Action and Effect)
As described above, the pedestrian crossing prediction device according to the present embodiment provides the following advantageous effects.

The pedestrian crossing prediction device includes a sensor (object detection device 1) that detects pedestrians, and a controller 100 that calculates the likelihood that a pedestrian detected by the sensor will cross a road. When a shuttle vehicle is detected on the other side of the road based on the position of a pedestrian 60 detected by the sensor, the controller 100 determines whether the shuttle vehicle is stopped or about to stop. When it is determined that the shuttle vehicle is stopped or about to stop, the controller 100 increases the likelihood compared to when a shuttle vehicle is not detected. This makes it possible to accurately predict whether a pedestrian 60 will cross a road when a shuttle vehicle is present across the road. In the above embodiment, a case where a pedestrian 60 crosses a crosswalk has been described, but the case where a shuttle vehicle is present across the road is not limited to a crosswalk, and the present invention can also be applied to a case where a pedestrian 60 crosses a road other than a crosswalk.

An example of a shuttle vehicle is a bus 70. The pedestrian 60 may be detected by a sensor around the crosswalk. The bus 70 may be detected by a sensor on the other side of the crosswalk that the pedestrian 60 is about to cross, based on the position of the pedestrian 60. The controller 100 may change the likelihood that the pedestrian 60 will cross the crosswalk depending on the time remaining until the bus 70 departs. By taking into account the time remaining until the bus 70 departs, it becomes possible to accurately predict whether the pedestrian 60 will cross the crosswalk.

The controller 100 may increase the likelihood the shorter the remaining time until the bus 70 departs. If the remaining time until the bus 70 departs is short, it is assumed that the pedestrian 60 is likely to be unable to catch the bus 70 and therefore is more likely to cross the crosswalk in a hurry. By increasing the likelihood the shorter the remaining time until the bus 70 departs, it becomes possible to accurately predict whether the pedestrian 60 will cross the crosswalk.

The controller 100 may increase the likelihood the fewer the number of people waiting to board the bus 70. The fewer the number of people waiting to board, the less time the pedestrian 60 has left. In other words, the fewer the number of people waiting to board, the more likely it is that the pedestrian 60 will cross the crosswalk in a hurry. By increasing the likelihood the fewer the number of people waiting to board the bus 70, it becomes possible to accurately predict whether or not the pedestrian 60 will cross the crosswalk.

When the remaining time until the bus 70 departs is less than or equal to a predetermined time, the controller 100 may lower the likelihood compared to when the remaining time until the bus 70 departs is longer than the predetermined time. When the remaining time is less than or equal to the predetermined time (for example, less than or equal to 3 seconds), there is a high possibility that the pedestrian 60 will give up on crossing the crosswalk in a hurry. In such a case, the likelihood may be lowered. This makes it possible to avoid unnecessary deceleration.

When the remaining time until the bus 70 departs is longer than a predetermined time, and when other vehicles 51-52 that may cause the pedestrian 60 to wait to cross the crosswalk are detected in addition to the vehicle 50, the controller 100 may increase the likelihood compared to when the other vehicles 51-52 are not detected. As shown in FIG. 7, when the pedestrian 60 waits for the vehicle 50 to pass, he or she will also have to wait for the following vehicles 51-52 to pass, and will end up waiting longer in front of the crosswalk. This will delay the time it takes to reach the bus stop 80. In such a case, it is assumed that the pedestrian 60 will want to cross the crosswalk in a hurry. Therefore, by increasing the likelihood in such a case, it becomes possible to accurately predict whether the pedestrian 60 will cross the crosswalk.

The facial orientation and walking acceleration of the pedestrian 60 may be detected by a sensor. When it is determined that the pedestrian 60 is accelerating while looking in the direction of the bus 70, the controller 100 may increase the likelihood according to the acceleration. This makes it possible to accurately predict whether the pedestrian 60 will cross the crosswalk.

If the acceleration value does not change from negative to positive within a predetermined time after it has changed from positive to negative, the controller 100 may lower the increased likelihood. A change in the acceleration value from positive to negative means that the pedestrian 60 has decelerated from an accelerating state. If acceleration is not detected again within a predetermined time after deceleration, it can be said that there is a high possibility that the pedestrian 60 has given up on boarding the bus 70. In such a case, the increased likelihood may be lowered. This makes it possible to avoid unnecessary deceleration.

If acceleration of pedestrian 60 is detected within a predetermined time after it is determined that bus 70 is stopped or about to stop, controller 100 may increase the likelihood according to the acceleration. "Acceleration of pedestrian 60 is detected within a predetermined time after it is determined that bus 70 is stopped or about to stop" can be interpreted as pedestrian 60 accelerating due to the presence of bus 70. Therefore, by increasing the likelihood in such a case, it becomes possible to accurately predict whether pedestrian 60 will cross the crosswalk. Note that even if acceleration of pedestrian 60 is detected after a predetermined time has elapsed, the acceleration is considered not to be due to the presence of bus 70. Therefore, even if acceleration of pedestrian 60 is detected after a predetermined time has elapsed, it is not necessary to increase the likelihood.

If the calculated likelihood is greater than a predetermined value, the controller 100 accelerates the deceleration of the vehicle 50 and stops the vehicle in front of the crosswalk. As a result, for example, if the vehicle 50 is a vehicle equipped with an autonomous driving function, the discomfort felt by the occupants regarding the autonomous driving is eliminated or reduced.

Each of the functions described in the above embodiments may be implemented by one or more processing circuits. Processing circuits include programmed processing devices, such as processors that include electrical circuitry. Processing circuits also include devices, such as application specific integrated circuits (ASICs) or circuit components, arranged to perform the described functions.

As described above, an embodiment of the present invention has been described, but the descriptions and drawings that form part of this disclosure should not be understood as limiting this invention. Various alternative embodiments, examples, and operating techniques will become apparent to those skilled in the art from this disclosure.

1 Object detection device, 2 Vehicle position estimation device, 3 Map database, 4 Detection integration unit, 5 Object tracking unit, 6 Map position estimation unit, 10 Behavior prediction unit, 11 Pedestrian detection unit, 12 Pedestrian speed change detection unit, 13 Face direction detection unit, 14 Surrounding object detection unit, 15 Shuttle bus detection unit, 16 Bus departure time acquisition unit, 17 Waiting passenger count unit, 18 Likelihood calculation unit, 20 Vehicle control unit, 100 Controller

Claims (11)

A pedestrian crossing prediction method for a pedestrian crossing prediction device including a controller that calculates a likelihood that a pedestrian detected by a sensor mounted on a vehicle will cross a road, the method comprising:
The controller:
When a shuttle vehicle is detected across the road based on the position of the pedestrian detected by the sensor, it is determined whether the shuttle vehicle is stopped or about to stop;
A pedestrian crossing prediction method characterized in that, when it is determined that the shuttle bus is stopped or about to stop, the likelihood is increased compared to when the shuttle bus is not detected. The shuttle vehicle is a bus,
The pedestrian is detected by the sensor around the crosswalk,
The bus is detected by the sensor on the other side of the crosswalk that the pedestrian is about to cross based on the position of the pedestrian,
The pedestrian crossing prediction method according to claim 1 , wherein the controller changes the likelihood that the pedestrian will cross the crosswalk depending on the remaining time until the bus departs. The pedestrian crossing prediction method according to claim 2 , wherein the controller increases the likelihood as the remaining time until the bus departs is shorter. The pedestrian crossing prediction method according to claim 2 or 3, wherein the controller increases the likelihood as the number of people waiting to board the bus decreases. The pedestrian crossing prediction method according to any one of claims 2 to 4, characterized in that the controller lowers the likelihood when the remaining time until the bus departs is equal to or shorter than a predetermined time, compared to when the remaining time until the bus departs is longer than the predetermined time. The pedestrian crossing prediction method according to claim 5, characterized in that when the remaining time until the bus departs is longer than the predetermined time and when another vehicle other than the host vehicle is detected that may cause the pedestrian to wait to cross the crosswalk, the controller increases the likelihood compared to when the other vehicle is not detected. The sensor detects the face direction and the acceleration related to the walking of the pedestrian,
The pedestrian crossing prediction method according to claim 5 , wherein when it is determined that the pedestrian is accelerating while looking in the direction of the bus, the controller increases the likelihood according to the acceleration. The pedestrian crossing prediction method according to claim 7, wherein the controller lowers the increased likelihood if the acceleration value does not change from negative to positive within a predetermined time after the acceleration value changes from positive to negative. The pedestrian crossing prediction method according to claim 7, characterized in that, when acceleration of the pedestrian is detected within a predetermined time after it is determined that the bus is stopped or about to stop, the controller increases the likelihood according to the acceleration. 10. The pedestrian crossing prediction method according to claim 1, wherein the controller accelerates deceleration of the host vehicle when the calculated likelihood is greater than a predetermined value. A sensor for detecting a pedestrian;
a controller for calculating a likelihood that a pedestrian detected by the sensor will cross a road;
The controller:
When a shuttle vehicle is detected across the road based on the position of the pedestrian, it is determined whether the shuttle vehicle is stopped or about to stop;
A pedestrian crossing prediction device characterized in that, when it is determined that the shuttle bus is stopped or about to stop, the likelihood is increased compared to a case in which the shuttle bus is not detected.

Images