JPWO2020053612A1 - Vehicle behavior prediction method and vehicle behavior prediction device - Google Patents

Abstract

The vehicle behavior prediction method and the vehicle behavior prediction device of the present invention detect an object outside the own vehicle, identify an intersecting vehicle having a planned travel route that intersects the planned travel route of the own vehicle from the detected object, and own the vehicle. The preceding vehicle traveling on the planned travel route of the vehicle is identified, and the index value indicating the distance between the preceding vehicle and the own vehicle is indicated, and the first threshold value set based on the behavior change of the preceding vehicle is used. , Predict the entry of crossing vehicles into the planned travel route of the own vehicle.

Description

The present invention relates to a vehicle behavior prediction method and a vehicle behavior prediction device.

In Patent Document 1, the distance between the own vehicle and the oncoming right-turning vehicle, the own vehicle speed, and the head time with the preceding vehicle are obtained from the sensing device, and the distance between the own vehicle and the oncoming right-turning vehicle is divided by the own vehicle speed. There has been proposed a traveling support device that slows down the speed according to the judgment criteria and applies a sudden brake when the right-turning vehicle actually turns right.

Japanese Unexamined Patent Publication No. 2001-52297

However, the technique described in Patent Document 1 is configured to determine the right turn timing of an oncoming right-turning vehicle only from the distance between the own vehicle and the right-turning vehicle, the own vehicle speed, and the head time of the preceding vehicle. Therefore, the behavior of the oncoming right-turning vehicle, which changes due to the change in the behavior of the preceding vehicle, is not reflected in the judgment, and the deceleration of the own vehicle may be delayed.

The present invention has been made in view of the above problems, and an object of the present invention is that the behavior of a crossing vehicle having a planned travel route that intersects the planned travel route of the own vehicle changes due to a change in the behavior of the preceding vehicle. Even in this case, it is an object of the present invention to provide a vehicle behavior prediction method and a vehicle behavior prediction device capable of predicting the behavior of a crossing vehicle.

In order to solve the above-mentioned problems, the vehicle behavior prediction method and the vehicle behavior prediction device according to one aspect of the present invention detect an object outside the own vehicle, and the detected object intersects with the planned travel route of the own vehicle. The crossing vehicle having the planned travel route is specified, the preceding vehicle traveling on the planned travel route of the own vehicle is specified, the index value indicating the distance between the preceding vehicle and the section between the own vehicle, and the behavior of the preceding vehicle. Based on the first threshold value set based on the change, the approach of the crossing vehicle to the planned travel route of the own vehicle is predicted.

According to the present invention, even when the behavior of a crossing vehicle having a planned travel route intersecting the planned travel route of the own vehicle changes due to a change in the behavior of the preceding vehicle, the behavior of the crossing vehicle can be predicted. ..

FIG. 1 is a block diagram showing a configuration of a vehicle behavior prediction device according to an embodiment of the present invention. FIG. 2 is a flowchart showing a processing procedure for vehicle behavior prediction according to an embodiment of the present invention. FIG. 3 is a graph showing the relationship between the index value and the approach probability. FIG. 4 is a plan view showing the first running scene. FIG. 5 is a plan view showing a second running scene. FIG. 6 is a plan view showing a third running scene.

Next, embodiments of the present invention will be described in detail with reference to the drawings. In the description, the same reference numerals are given and duplicate description is omitted.

[Configuration of vehicle behavior prediction device]
The configuration of the vehicle behavior prediction device will be described with reference to FIG. The vehicle behavior prediction device includes an object detection unit 21, an own vehicle position estimation unit 23, a map information acquisition unit 25, and a processing unit 100 (controller).

The vehicle behavior prediction device may be applied to a vehicle having an automatic driving function, or may be applied to a vehicle having no automatic driving function. Further, the vehicle behavior prediction device may be applied to a vehicle capable of switching between automatic driving and manual driving.

The automatic driving in the present embodiment means, for example, a state in which at least one of the actuators such as the brake, the accelerator, and the steering is controlled without the operation of the occupant. Therefore, other actuators may be operated by the operation of the occupant. Further, the automatic operation may be a state in which any control such as acceleration / deceleration control or lateral position control is executed. Further, the manual operation in the present embodiment means, for example, a state in which the occupant is operating the brake, the accelerator, and the steering.

The object detection unit 21 includes an object detection sensor such as a laser radar, a millimeter wave radar, and a camera mounted on the own vehicle. The object detection unit 21 detects an object outside the own vehicle by using a plurality of object detection sensors. Further, the object detection unit 21 detects an object in front of or to the side of the own vehicle. The object detection unit 21 detects other vehicles, motorcycles, bicycles, moving objects including pedestrians, and stationary objects including parked vehicles and buildings. For example, the object detection unit 21 detects the position, posture (yaw angle), size, speed, acceleration, jerk, deceleration, and yaw rate of a moving object and a stationary object with respect to the own vehicle. The position, posture (yaw angle), size, speed, acceleration, deceleration, and yaw rate of the object are collectively called the "behavior" of the object.

The own vehicle position estimation unit 23 includes a position detection sensor mounted on the own vehicle to measure the absolute position of the own vehicle such as GPS (Global Positioning System) and odometry. The own vehicle position estimation device 2 measures the absolute position of the own vehicle, that is, the position, vehicle speed, acceleration, steering angle, and posture of the own vehicle with respect to a predetermined reference point by using the position detection sensor. The vehicle position estimation unit 23 includes an inertial navigation system (INS), sensors provided on the brake pedal and accelerator pedal, sensors for acquiring vehicle behavior such as wheel side sensors and yaw rate sensors, and lasers. A radar, a camera, etc. may be included.

The map information acquisition unit 25 acquires map information indicating the structure of the road on which the own vehicle travels. The map information acquired by the map information acquisition unit 25 includes road structure information such as absolute lane positions, lane connection relationships, and relative positional relationships. Further, the map information acquired by the map information acquisition unit 25 includes facility information such as a parking lot and a gas station. In addition, the map information includes the position information of the traffic light, the type of the traffic light, and the like. The map information acquisition unit 25 may own a map database storing map information, or may acquire map information from an external map data server by cloud computing. Further, the map information acquisition unit 25 may acquire map information by using vehicle-to-vehicle communication and road-to-vehicle communication.

In addition, the map information acquisition unit 25 may acquire the position of the own vehicle from GPS and detect the intersection in front of the own vehicle from the map information in which the lane information is described. In addition, an inertial navigation system or an odometry of the own vehicle may be used instead of the GPS to acquire the position of the own vehicle, or they may be used together with the GPS. The road structure may be estimated using a sensor that detects the front such as LiDAR.

The processing unit 100 predicts the operation of another vehicle based on the detection result by the object detection unit 21, the own vehicle position estimation unit 23, and the information acquired by the map information acquisition unit 25, and the operation of the own vehicle is based on the movement of the other vehicle. A planned travel route is generated, and the own vehicle is controlled according to the generated planned travel route.

The processing unit 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 (vehicle behavior prediction program) for functioning as a vehicle behavior prediction device is installed in the processing unit 100. By executing the computer program, the processing unit 100 functions as a plurality of information processing circuits (41, 43, 45, 50, 70, 80, 90) included in the vehicle behavior prediction device.

Here, an example is shown in which a plurality of information processing circuits (41, 43, 45, 50, 70, 80, 90) included in the vehicle behavior prediction device are realized by software. However, it is also possible to prepare information processing circuits (41, 43, 45, 50, 70, 80, 90) by preparing dedicated hardware for executing each of the following information processing. Further, a plurality of information processing circuits (41, 43, 45, 50, 70, 80, 90) may be configured by individual hardware. Further, the information processing circuit (41, 43, 45, 50, 70, 80, 90) may also be used as an electronic control unit (ECU) used for other control related to the vehicle.

The processing unit 100, as a plurality of information processing circuits (41, 43, 45, 50, 70, 80, 90), includes a detection integration unit 41, an object tracking unit 43, a road structure specifying unit 45, a vehicle behavior prediction unit 50, and itself. It includes a vehicle route generation unit 70, a speed profile generation unit 80, and a vehicle control unit 90. Further, the vehicle behavior prediction unit 50 includes a crossing vehicle identification unit 51, a preceding vehicle identification unit 53, a behavior change detection unit 55, a behavior prediction threshold value change unit 57, and a behavior prediction unit 59.

The detection integration unit 41 integrates a plurality of detection results obtained from each of the plurality of object detection sensors included in the object detection unit 21, 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 to obtain more accurate detection results.

In addition, when the detected object is a vehicle, the detection integration unit 41 may detect the presence or absence of the turn signal lighting of the vehicle and detect the behavior of the vehicle.

The object tracking unit 43 tracks the object detected by the detection integration unit 41. Specifically, the object tracking unit 43 verifies (associates) the identity of the object between different times from the behavior of the object output at different times, and tracks the object based on the association. do.

The road structure specifying unit 45 determines the type of road structure on the planned travel route of the own vehicle from the absolute position of the own vehicle obtained by the own vehicle position estimation unit 23 and the map data acquired by the map information acquisition unit 25. Identify. For example, the road structure specifying unit 45 specifies an intersection on the planned travel route of the own vehicle, a merging point with a merging lane, a T-junction, and the like. In addition, the road structure specifying unit 45 may specify the position and type of the traffic light installed at the intersection, and specifies priority lanes and non-priority lanes from the lanes in the road structure. It may be a thing.

The crossing vehicle identification unit 51 travels the own vehicle from the object detected by the object detection unit 21 based on the object information acquired from the object tracking unit 43 and the type of the road structure specified by the road structure identification unit 45. Identify crossing vehicles that have a planned travel route that intersects the planned route. It is assumed that the planned travel route of the own vehicle has already been generated as a premise for specifying the crossing vehicle in the crossing vehicle specifying unit 51. Further, it is assumed that the planned travel route of the crossing vehicle is also provisionally generated based on the object information, the road information, and the like acquired from the object tracking unit 43. The planned travel route of the crossing vehicle is, for example, an object on the right turn lane of the oncoming lane at an intersection on the planned travel route of the own vehicle, or when an object is detected at a position on an extension of the right turn lane in the intersection. And the crossing vehicle can generate a right turn route from the right turn lane in the oncoming lane as a planned travel route.

The preceding vehicle identification unit 53 determines the planned travel route of the own vehicle from the object information acquired from the object tracking unit 43 and the object detected by the object detection unit 21 based on the type of the road structure by the road structure identification unit 45. Identify the vehicle in front that is running. For example, the preceding vehicle traveling in front of the own vehicle is specified.

The behavior change detection unit 55 detects the behavior change of the preceding vehicle based on the time change of the object information acquired from the object tracking unit 43 with respect to the preceding vehicle specified by the preceding vehicle specifying unit 53.

The above-mentioned method for specifying a crossing vehicle, a method for specifying a preceding vehicle, and a method for detecting a change in the behavior of the preceding vehicle are variously changed based on the type of road structure.

The behavior prediction threshold value changing unit 57 includes the presence / absence of a preceding vehicle, the positional relationship between the own vehicle and other vehicles (including the preceding vehicle and the crossing vehicle), road information, the behavior change of the preceding vehicle detected by the behavior change detecting unit 55, and the like. The behavior prediction threshold value T (first threshold value) is set based on the above. The details of setting the behavior prediction threshold value T in the behavior prediction threshold value changing unit 57 will be described later.

The behavior prediction unit 59 calculates an index value for predicting the approach of a crossing vehicle to the planned travel route of the own vehicle based on the object information acquired from the object tracking unit 43. For example, when the preceding vehicle does not exist, the time required for the own vehicle to reach the intersection of the planned travel route of the own vehicle and the planned travel route of the crossing vehicle is calculated as an index value. If there is a preceding vehicle, it is a section on the planned travel route of the own vehicle such as the headway time (THW: Time Headway) and collision margin time (TTC: Time to Collection) with respect to the preceding vehicle. Calculate an index value indicating the distance between the vehicle and the section between the vehicle and the vehicle.

Then, the behavior prediction unit 59 determines whether or not the crossing vehicle enters the planned travel route of the own vehicle based on the behavior prediction threshold value T set in the behavior prediction threshold value change unit 57 and the calculated index value. Predict. The details of the approach prediction of the crossing vehicle in the behavior prediction unit 59 will be described later.

The own vehicle route generation unit 70 generates a planned travel route of the own vehicle based on the object information acquired from the object tracking unit 43, the map information acquired by the map information acquisition unit 25, and the position of the own vehicle.

Here, when the vehicle behavior prediction unit 50 predicts whether or not a crossing vehicle will enter the planned travel route of the own vehicle, the own vehicle route generation unit 70 uses object information, map information, and self. In addition to the position, the planned travel route of the own vehicle is generated based on the prediction result by the vehicle behavior prediction unit 50.

The speed profile generation unit 80 obtains a speed profile when the own vehicle travels on the planned travel route based on the object information acquired from the object tracking unit 43, the map information acquired by the map information acquisition unit 25, and the position of the own vehicle. Generate. Here, the speed profile is data showing a state of change in the speed of the own vehicle when the own vehicle moves along the planned traveling route.

Here, when the vehicle behavior prediction unit 50 predicts whether or not a crossing vehicle will enter the planned travel route of the own vehicle, the own vehicle route generation unit 70 uses object information, map information, and self. In addition to the position, the speed profile when the own vehicle travels on the planned travel route is generated based on the prediction result by the vehicle behavior prediction unit 50.

The vehicle control unit 90 controls the vehicle for the own vehicle based on the planned travel route generated by the own vehicle route generation unit 70 and the speed profile generated by the speed profile generation unit 80.

[Vehicle behavior prediction processing procedure]
Next, a processing procedure for vehicle behavior prediction according to the present embodiment will be described with reference to the flowchart of FIG. The vehicle behavior prediction process shown in FIG. 2 is started when the ignition of the own vehicle is turned on, and is repeatedly executed while the ignition is turned on.

First, in step S101, the crossing vehicle specifying unit 51 identifies the crossing vehicle. If the planned travel route of the own vehicle is not generated, such as immediately after the ignition of the own vehicle is turned on, the crossing vehicle specifying unit 51 does not specify the crossing vehicle.

Next, in step S103, the vehicle behavior prediction unit 50 determines whether or not the specified crossing vehicle exists. If the specified crossing vehicle exists (YES in step S103), the process of FIG. 2 proceeds to step S105. On the other hand, when the specified crossing vehicle does not exist (NO in step S103), the process of predicting the vehicle behavior of the crossing vehicle is terminated.

In step S105, the preceding vehicle specifying unit 53 identifies the preceding vehicle.

In step S107, the vehicle behavior prediction unit 50 determines whether or not the specified preceding vehicle exists. If the specified preceding vehicle exists (YES in step S107), the process of FIG. 2 proceeds to step S109. On the other hand, if the specified preceding vehicle does not exist (NO in step S107), the process proceeds to step S115.

In step S109, the behavior change detection unit 55 detects the behavior change of the preceding vehicle.

In step S111, the vehicle behavior prediction unit 50 determines whether or not there is a change in the behavior of the preceding vehicle. If there is a change in the behavior of the preceding vehicle (YES in step S111), the process of FIG. 2 proceeds to step S113. On the other hand, if there is no change in the behavior of the preceding vehicle (NO in step S111), the process proceeds to step S115.

In step S113, the behavior prediction threshold value changing unit 57 changes the behavior prediction threshold value T based on the detected behavior change of the preceding vehicle and the like.

In step S115, the behavior prediction unit 59 predicts the behavior of the crossing vehicle. As the behavior of the crossing vehicle, for example, it is predicted whether or not the crossing vehicle enters the planned travel route of the own vehicle.

Based on the behavior of the crossing vehicle predicted based on the above-mentioned processing, the own vehicle route generation unit 70 generates the planned travel route of the own vehicle, and the speed profile generation unit 80 generates the planned travel route of the own vehicle when the own vehicle travels on the planned travel route. Generate a speed profile for. Further, the vehicle control unit 90 controls the vehicle with respect to the own vehicle based on the generated planned travel route and speed profile of the own vehicle.

[Setting threshold for behavior prediction]
Next, the setting of the behavior prediction threshold value T in the behavior prediction threshold value changing unit 57 will be specifically described.

The behavior prediction threshold T (first threshold) is the presence or absence of the preceding vehicle, the positional relationship between the own vehicle and other vehicles (including the preceding vehicle and the crossing vehicle), road information, and the preceding vehicle detected by the behavior change detection unit 55. It is set based on the disturbance factor such as the behavior change of. This is because the approach probability of the crossing vehicle to the planned travel route of the own vehicle can be changed by such a disturbance factor.

For example, as shown by the curve F1 in FIG. 3, the approach probability of the crossing vehicle to the planned travel route of the own vehicle is until the own vehicle reaches the position where the planned travel route of the own vehicle and the planned travel route of the crossing vehicle intersect. It changes depending on the time and the index value such as THW and TTC of the own vehicle with respect to the preceding vehicle. As the index value becomes larger, the crossing vehicle can enter the planned travel route of the own vehicle more safely, so that the approach probability of the crossing vehicle tends to increase.

Therefore, when the preceding vehicle does not exist, the behavior prediction threshold value changing unit 57 determines the planned travel route of the own vehicle and the intersecting vehicle when the approach probability of the intersecting vehicle to the planned travel route of the own vehicle is 50%. The time required for the own vehicle to reach the intersection of the planned travel routes is set as the behavior prediction threshold value T.

Further, when there is no change in the behavior of the preceding vehicle, the behavior prediction threshold value changing unit 57 may use the THW of the own vehicle or THW of the own vehicle with respect to the preceding vehicle when the approach probability of the crossing vehicle to the planned travel route of the own vehicle is 50%. TTC is set as the behavior prediction threshold value T.

As shown by the curve F1 in FIG. 3, the approach probability of the crossing vehicle when the index value is equal to or higher than the behavior prediction threshold T is equal to or higher than the approach probability when the index value is equal to the behavior prediction threshold T. Therefore, when the index value is equal to or higher than the behavior prediction threshold value T, it can be predicted that the crossing vehicle will enter the planned travel route of the own vehicle.

On the other hand, the approach probability of the crossing vehicle when the index value is less than the behavior prediction threshold T is less than the approach probability when the index value is equal to the behavior prediction threshold T. Therefore, when the index value is less than the behavior prediction threshold value T, it can be predicted that the crossing vehicle will not enter the planned travel route of the own vehicle.

In this way, by comparing the index value and the behavior prediction threshold value T, it is possible to predict whether or not the crossing vehicle will enter the planned travel route of the own vehicle.

The behavior prediction threshold value T set as described above includes the positional relationship between the own vehicle and other vehicles (including the preceding vehicle and the crossing vehicle), road information, the behavior change of the preceding vehicle detected by the behavior change detection unit 55, and the like. It is changed by the behavior prediction threshold value changing unit 57 based on the disturbance factor.

For example, it is assumed that the relationship between the index value and the approach probability changes from the curve F1 in FIG. 3 to the curve F2 due to the influence of the disturbance factor. Here, it is assumed that the value of the behavior prediction threshold T determined based on the curve F1 is "Tc", and the value of the behavior prediction threshold T determined based on the curve F2 is "Tc-Δ".

When predicting the approach of a crossing vehicle under the influence of a disturbance factor, the value of the behavior prediction threshold T is set to "Tc" even though the relationship between the index value and the approach probability changes from the curve F1 to the curve F2. If it is left set to "", the accuracy of the approach prediction of the crossing vehicle will be lost. Therefore, the behavior prediction threshold value changing unit 57 determines the correction amount Δ based on the type of the disturbance factor and the degree of influence, and changes the value of the behavior prediction threshold value T from “Tc” to the correct “Tc−Δ”. .. As is clear from the direction of the sign, as the correction amount Δ is increased, the changed behavior prediction threshold value T decreases.

In this way, by changing the value of the behavior prediction threshold value T according to the correction amount Δ, it is possible to improve the accuracy of the approach prediction of the crossing vehicle when there is an influence of the disturbance factor.

It should be noted that the timing at which the behavior of the preceding vehicle changes does not always match the reference time for predicting the approach of the crossing vehicle. For example, after a change in the behavior of the preceding vehicle occurs, a change in the vehicle speed of the preceding vehicle may occur, and the positional relationship between the own vehicle and another vehicle may change. In order to improve the accuracy of the approach prediction of the crossing vehicle, it is preferable to consider the positional relationship between the own vehicle and other vehicles, road information, etc. at the reference time of the approach prediction of the crossing vehicle when determining the correction amount Δ.

[Forecasting approach of crossing vehicles]
Next, the approach prediction of the crossing vehicle in the behavior prediction unit 59 will be specifically described.

The behavior prediction unit 59 calculates index values such as the time required for the own vehicle to reach the intersection of the planned travel route of the own vehicle and the planned travel route of the crossing vehicle, THW of the own vehicle with respect to the preceding vehicle, and TTC.

In order to improve the accuracy of the approach prediction of the crossing vehicle, it is preferable that the reference time for calculating the index value and the reference time for the approach prediction of the crossing vehicle match and are as close as possible. This is because if the vehicle speed of the preceding vehicle changes between the reference time for calculating the index value and the reference time for the approach prediction of the crossing vehicle, the accuracy of the approach prediction of the crossing vehicle may be affected. ..

The behavior prediction unit 59 predicts that the crossing vehicle will enter the planned travel route of the own vehicle when the calculated index value is equal to or higher than the behavior prediction threshold value T. On the other hand, the behavior prediction unit 59 predicts that the crossing vehicle will not enter the planned travel route of the own vehicle when the calculated index value is less than the behavior prediction threshold value T.

In addition, the behavior prediction unit 59 may predict the time when the crossing vehicle starts approaching the planned travel route of the own vehicle based on the calculated index value and the behavior prediction threshold value T.

For example, when the calculated index value is equal to or higher than the behavior prediction threshold value T, the crossing vehicle crosses the position before the own vehicle passes the position where the planned travel route of the own vehicle and the planned travel route of the crossing vehicle intersect. Is thought to pass. Therefore, the behavior prediction unit 59 may predict a time that is a predetermined time before the scheduled time when the own vehicle passes through the position as a time when the crossing vehicle starts approaching.

If the calculated index value is less than the behavior prediction threshold value T, the crossing vehicle passes through the intersection of the planned travel route of the own vehicle and the planned travel route of the crossing vehicle, and then the crossing vehicle passes through the position. It is thought that it will pass. Therefore, the behavior prediction unit 59 may predict a time in the future by a predetermined time from the scheduled time when the own vehicle passes through the position as a time when the crossing vehicle starts approaching.

[Control based on the approach prediction result of crossing vehicles]
When the vehicle behavior prediction unit 50 predicts whether or not a crossing vehicle will enter the planned travel route of the own vehicle, the own vehicle route generation unit 70 adds to the object information, the map information, and the self-position. Then, based on the prediction result by the vehicle behavior prediction unit 50, the planned travel route of the own vehicle is generated. For example, if the probability of a crossing vehicle entering the planned travel route of the own vehicle is equal to or higher than the danger level value, the own vehicle must travel at the intersection of the planned travel route of the own vehicle and the planned travel route of the crossing vehicle. The vehicle control unit 90 may control the own vehicle so as to decelerate the vehicle.

Further, when it is predicted that the crossing vehicle will not enter the planned travel route of the own vehicle, the vehicle control unit 90 avoids the situation where the crossing vehicle enters the planned travel route of the own vehicle contrary to the prediction result. It may be the one that controls. Specifically, when the calculated index value is less than the behavior prediction threshold value T and the absolute value of the difference between the index value and the behavior prediction threshold value T is not more than a predetermined value, the vehicle control unit 90 is different from the preceding vehicle. Control may be performed to reduce the inter-vehicle distance between the own vehicles. By reducing the inter-vehicle distance between the preceding vehicle and the own vehicle, the approach probability of the crossing vehicle is reduced, so that the possibility of a situation contrary to the prediction result can be suppressed.

Further, when it is predicted that the crossing vehicle will enter the planned travel route of the own vehicle, the vehicle control unit 90 sets the own vehicle so as to avoid a situation in which the crossing vehicle does not enter the planned travel route of the own vehicle contrary to the prediction result. It may be controlled. Specifically, when the calculated index value is equal to or greater than the behavior prediction threshold value T and the absolute value of the difference between the index value and the behavior prediction threshold value T is equal to or less than a predetermined value, the vehicle control unit 90 is different from the preceding vehicle. Control may be performed to increase the inter-vehicle distance between the own vehicles. By increasing the inter-vehicle distance between the preceding vehicle and the own vehicle, the approach probability of the crossing vehicle increases, so that the possibility of a situation contrary to the prediction result can be suppressed.

[Example of vehicle behavior prediction for each driving scene]
Next, an example of vehicle behavior prediction for each driving scene will be described with reference to FIGS. 4 to 6.

(1st driving scene)
First, the vehicle behavior prediction will be described based on the "first driving scene" of FIG. In FIG. 4, the own vehicle VS and the vehicle VB are traveling in the lane TL1 in front of the intersection, and the vehicle VC is entering the intersection and traveling from the lane TL3 toward the lane TL5 or the lane TL6. It is shown.

In FIG. 4, lane TL1 and lane TL3 are lanes capable of turning left or going straight, and lane TL2 and lane TL4 are lanes dedicated to turning right.

The road structure specifying unit 45 identifies an intersection existing on the planned travel route of the own vehicle VS based on the road information. In FIG. 4, lanes TL1 to TL4 and lanes TL5 and TL6 intersect at the intersection. Further, it indicates whether or not it is possible to turn in one direction, which is the direction from the oncoming road to the own vehicle road, to the oncoming road (lane TL3, lane TL4) facing the own vehicle road (lane TL1, TL2) on which the own vehicle VS travels. Identify that there is no right / left turn signal. Here, the "one direction" is a left turn direction for the own vehicle VS and the vehicle VB, and a right turn direction for the vehicle VC.

If there is no left / right turn signal on the oncoming road indicating whether or not to turn in one direction, the behavior of the vehicle VC that travels on the oncoming road and makes a one-way turn within the intersection is to drive on the own road and enter the intersection. It is considered to be affected by the behavior of the vehicle VB.

The intersection vehicle identification unit 51 determines whether or not the vehicle VC is scheduled to turn in the intersection based on the behavior of the vehicle VC traveling on the oncoming road acquired from the object tracking unit 43. Then, the crossing vehicle specifying unit 51 identifies the vehicle VC as a crossing vehicle to be targeted for vehicle behavior prediction when the vehicle VC is scheduled to turn in one direction (scheduled to turn right).

The vehicle VC may be specified as a target crossing vehicle based on the fact that the vehicle VC is traveling in the lane TL4, which is a lane dedicated to turning right. The absolute value of the difference between the arrival time of the vehicle VC to the intersection of the planned travel route of the vehicle VC and the planned travel route of the own vehicle VS and the arrival time of the own vehicle VS to the position is a predetermined value (for example, 1 second). ) The vehicle VC may be specified as a crossing vehicle based on the following.

Further, when the vehicle VC moves in one direction (movement operation) from the center of the lane of the lane TL4, when the vehicle VC decelerates, or when the vehicle VC makes a turn in one direction. The vehicle VC may be specified as a crossing vehicle when the indicated winker display operation is performed. Further, the vehicle VC may be specified as an intersection vehicle based on the arrival time of the vehicle VC to the intersection.

The preceding vehicle identification unit 53 calculates the THW of the vehicle VS with respect to the vehicle VB and the arrival time to the intersection of the vehicle VB based on the behavior of the vehicle VB traveling on the vehicle road acquired from the object tracking unit 43. .. Then, in the preceding vehicle identification unit 53, the THW of the own vehicle VS with respect to the vehicle VB is equal to or less than the filtering threshold value A1 (second threshold value), and the arrival time to the intersection of the vehicle VB is the filtering threshold value A2 (third threshold value). ) When the following, the vehicle VB is specified as the preceding vehicle to be the target of the vehicle behavior prediction. Further, the preceding vehicle identification unit 53 determines that the vehicle VB is in front of the own vehicle VS.

Here, the reason for the determination using the filtering threshold value A1 is that the vehicle behavior prediction process is performed only for the preceding vehicle that may affect the behavior of the own vehicle. The filtering threshold value A1 is preferably about 7 to 8 seconds from the statistical results.

Further, the reason for the determination using the filtering threshold value A2 is that the vehicle behavior prediction process is performed only for the preceding vehicle that may affect the behavior of the crossing vehicle. The filtering threshold value A2 is determined based on the driving scene, and is preferably set to about 10 seconds.

The behavior change detection unit 55 detects the behavior change of the vehicle VB specified as the preceding vehicle based on the time change of the object information acquired from the object tracking unit 43. Specifically, the behavior change detection unit 55 detects the turning preliminary operation of the vehicle VB.

For example, the movement of the vehicle VB in one direction from the center of the lane of the lane TL1 (movement movement) may be detected as a turning preliminary movement of the vehicle VB. Here, in the operation of moving to the one-way side, a value obtained by dividing the distance from the center of the lane of the lane TL1 to the center of the vehicle VB measured in the lane width direction by the lane width is a predetermined threshold value (for example, 0.3). It may be determined based on whether it is the above.

Further, the vehicle VB may detect a deceleration operation (for example, a deceleration operation in which the acceleration of the vehicle VB is equal to or less than the threshold value "-20 km / h ^ 2") as a turning preliminary operation of the vehicle VB.

Further, the operation of the winker display indicating that the vehicle VB turns in one direction may be detected as a turning preliminary operation of the vehicle VB.

The behavior prediction threshold value changing unit 57 includes the presence / absence of a preceding vehicle, the positional relationship between the own vehicle and other vehicles (including the preceding vehicle and the crossing vehicle), road information, the behavior change of the preceding vehicle detected by the behavior change detecting unit 55, and the like. The correction amount Δ is determined based on the disturbance factor, and the value of the behavior prediction threshold value T is increased or decreased.

In the "first traveling scene" of FIG. 4, since the vehicle VB specified as the preceding vehicle exists, the behavior prediction threshold value changing unit 57 reduces the behavior prediction threshold value T (for example, the correction amount Δ is set to only 1 second). increase).

The lanes in which the vehicle VB and the vehicle VC can enter after passing the intersection are lane TL5 and lane TL6. Therefore, it can be determined that the number of lanes that the vehicle VB and the vehicle VC can enter after passing through the intersection is two or more lanes, and that there is sufficient space at the entry destination of the vehicle VC. Therefore, it is considered that the approach probability of the vehicle VC will be large. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

Furthermore, if there are two or more lanes on the own lane excluding lane TL2, which is the lane in which the vehicle scheduled to turn in the opposite direction to one direction travels, the vehicle VC intersects within the intersection. Since the number of lanes to be used increases, the time required for the vehicle VC to pass through the intersection becomes longer. In this case, since the approach probability of the vehicle VC is considered to be small, the behavior prediction threshold value changing unit 57 increases the behavior prediction threshold value T (for example, the correction amount Δ is reduced by 0.5 seconds).

Further, if two or more vehicles scheduled to enter the intersection are waiting behind the vehicle VC, the probability of the vehicle VC entering is increased in order to eliminate the standby state of the vehicle behind the vehicle VC. Conceivable. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

Further, if the oncoming road is a road with one lane on each side and a vehicle planning to enter the intersection is waiting behind the vehicle VC, the standby state of the vehicle behind the vehicle VC is set. In order to eliminate this, it is considered that the approach probability of the vehicle VC will increase. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

If five or more vehicles that are scheduled to enter the intersection are waiting behind the vehicle VB, the vehicle VC will wait to avoid waiting for the vehicle VC due to the vehicle entering the intersection behind the vehicle VB. The approach probability is expected to increase. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

The behavior prediction threshold value changing unit 57 confirms that the value of the behavior prediction threshold value T after the increase / decrease change as described above is within an appropriate range for use in the approach prediction of the crossing vehicle ( For example, confirm that the behavior prediction threshold T is the upper limit value of 8 seconds or less and the lower limit value of 4 seconds or more). Then, if it is within an appropriate range, the process of changing the behavior prediction threshold value T is terminated.

The behavior prediction threshold value T may be dynamically determined by calculation using the positions, postures, speeds, accelerations, and road structures of the own vehicle and other vehicles.

As described above, in the "first driving scene", the shape of the road is described as two lanes on each side, but the present invention is not limited to this, and an intersection may have one lane on each side, three or more lanes on each side, and no lane. In addition, although the description is based on the premise of left-hand traffic, the description is not limited to this, and in a country where right-hand traffic is legally established, the preceding vehicle may be a right-turn vehicle and the crossing vehicle may be a left-turn vehicle. Further, although the object is described on the premise of an automobile, it may be a two-wheeled vehicle or a light vehicle. Further, it may be an intersection without a traffic signal or an intersection with a traffic signal.

(Second driving scene)
Next, vehicle behavior prediction will be described based on the "second driving scene" of FIG. FIG. 5 shows how the lane TL7 in which the own vehicle VS and the vehicle VB travel and the lane TL8 in which the vehicle VC travels merge.

The road structure specifying unit 45 specifies the lane TL8 that merges with the lane TL7 in which the own vehicle VS travels at the merging point as the merging lane based on the road information. Then, the crossing vehicle specifying unit 51 identifies the vehicle VC traveling in the lane TL8 specified as the merging lane as the crossing vehicle to be the target of vehicle behavior prediction.

The absolute value of the difference between the arrival time of the vehicle VC up to the intersection of the planned travel route of the vehicle VC and the planned travel route of the own vehicle VS and the arrival time of the own vehicle VS up to the position is a predetermined value (for example). 1 second) The vehicle VC may be specified as a crossing vehicle based on the following.

The preceding vehicle identification unit 53 determines the THW of the vehicle VS with respect to the vehicle VB and the arrival time to the confluence of the vehicle VB based on the behavior of the vehicle VB in front of the vehicle VS acquired from the object tracking unit 43. Is calculated. Then, in the preceding vehicle identification unit 53, the THW of the own vehicle VS with respect to the vehicle VB is equal to or less than the filtering threshold value A1 (second threshold value), and the arrival time to the intersection of the vehicle VB is the filtering threshold value A2 (third threshold value). ) When the following, the vehicle VB is specified as the preceding vehicle to be the target of the vehicle behavior prediction. The reason for determining using the filtering threshold value A1 and the filtering threshold value A2 is the same as in the case of the “first running scene”.

Instead of making a determination using the filtering threshold value A1 and the filtering threshold value A2, the preceding vehicle identification unit 53 is the vehicle VB before passing through the confluence point, and the head time with respect to the vehicle VB when passing through the confluence point or A vehicle VB whose collision margin time is equal to or less than the filtering threshold value B1 (fourth threshold value) may be specified as a preceding vehicle to be targeted for vehicle behavior prediction.

The behavior change detection unit 55 detects the behavior change of the vehicle VB specified as the preceding vehicle based on the time change of the object information acquired from the object tracking unit 43.

For example, the vehicle VB may detect an acceleration operation (for example, an operation in which the acceleration of the vehicle VB is at least the threshold value “10 km / h ^ 2”) as a behavior change of the vehicle VB.

The behavior prediction threshold value changing unit 57 includes the presence / absence of a preceding vehicle, the positional relationship between the own vehicle and other vehicles (including the preceding vehicle and the crossing vehicle), road information, the behavior change of the preceding vehicle detected by the behavior change detecting unit 55, and the like. The correction amount Δ is determined based on the disturbance factor, and the value of the behavior prediction threshold value T is increased or decreased.

In the "second driving scene" of FIG. 5, since the vehicle VB specified as the preceding vehicle exists, the behavior prediction threshold value changing unit 57 reduces the behavior prediction threshold value T (for example, the correction amount Δ is set to only 1 second). increase).

Further, the behavior prediction threshold value changing unit 57 detects the merging preliminary operation of the vehicle VC.

For example, the operation (movement operation) in which the vehicle VC moves to the side of the lane TL7, which is the lane to be merged, from the center of the lane of the lane TL8 may be detected as the merging preliminary operation of the vehicle VC. Here, in the operation of moving to the side of the lane to be merged, a value obtained by dividing the distance from the center of the lane of the lane TL8 to the center of the vehicle VC measured in the lane width direction by the lane width is a predetermined threshold value (for example, 0. 3) It may be judged based on whether it is the above.

Further, the vehicle VC may detect the acceleration operation (for example, the operation in which the acceleration of the vehicle VC is the threshold value “10 km / h ^ 2” or more) as the merging preliminary operation of the vehicle VC.

Further, the operation of the winker display indicating that the vehicle VC turns to the side of the lane to be merged may be detected as the merging preliminary operation of the vehicle VC.

When the vehicle VC indicates the merging preliminary operation as described above, the approach probability of the vehicle VC is considered to be large. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

Even when the vehicle VC does not indicate the merging preliminary operation as described above, the time until the vehicle VC reaches the merging point as a result of the vehicle VC approaching the ending point of the merging lane is the filtering threshold value B2. When it becomes less than (fifth threshold value), it is considered that the approach probability of the vehicle VC increases. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

Further, when the speed of the vehicle VC is higher than the speed of the own vehicle VS by a predetermined ratio or more (for example, when the speed is 20% or more higher), the approach probability of the vehicle VC is considered to be large. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

The behavior prediction threshold value changing unit 57 confirms that the value of the behavior prediction threshold value T after the increase / decrease change as described above is within an appropriate range for use in the approach prediction of the crossing vehicle ( For example, confirm that the behavior prediction threshold T is the upper limit value of 8 seconds or less and the lower limit value of 4 seconds or more). Then, if it is within an appropriate range, the process of changing the behavior prediction threshold value T is terminated.

The behavior prediction threshold value T may be dynamically determined by calculation using the positions, postures, speeds, accelerations, and road structures of the own vehicle and other vehicles.

As described above, in the "second driving scene", the case of merging between lanes has been described, but the present invention is not limited to this, and the road width is reduced due to the presence of construction vehicles and parked vehicles on the road, for example. It may be the case.

(Third driving scene)
Next, the "third running scene" will be described as an example. In FIG. 6, the own vehicle VS and the vehicle VB are traveling in the lane TL9 in front of the T-junction, and the vehicle VC enters the intersection of the T-junction and heads from the lane TL12 to the lane TL13 or the lane TL14. It is shown that the vehicle is running.

In FIG. 6, the lane TL9 is a lane capable of turning left or going straight, and the lane TL10 is a lane dedicated to going straight.

The road structure specifying unit 45 identifies a T-junction existing on the planned travel route of the own vehicle VS based on the road information. In FIG. 6, lane TL9, lane TL10, lane TL13, and lane TL14 are priority lanes at the intersection of the T-shaped road, while lane TL11 and lane TL12 have lower priority than the priority lane. It is a priority lane.

The crossing vehicle identification unit 51 determines whether or not the vehicle VC is scheduled to enter the intersection of the T-junction based on the behavior of the vehicle VC traveling in the lane TL12 which is the non-priority lane acquired from the object tracking unit 43. If it is determined that the vehicle VC is scheduled to enter the intersection of the T-junction,
The crossing vehicle specifying unit 51 identifies the vehicle VC as a crossing vehicle to be targeted for vehicle behavior prediction.

It should be noted that the vehicle VC may be specified as a target crossing vehicle based on the fact that the vehicle VC is traveling in the lane TL12 which is a non-priority lane. The absolute value of the difference between the arrival time of the vehicle VC to the intersection of the planned travel route of the vehicle VC and the planned travel route of the own vehicle VS and the arrival time of the own vehicle VS to the position is a predetermined value (for example, 1 second). ) The vehicle VC may be specified as a crossing vehicle based on the following.

Further, when the vehicle VC deviates from the center of the lane of the lane TL12 and moves to the end of the lane TL12 (movement operation), the vehicle VC decelerates, or the vehicle VC indicates a turn signal. The vehicle VC may be specified as a crossing vehicle when the vehicle is operated. Further, the vehicle VC may be specified as an intersection vehicle based on the arrival time of the vehicle VC to the intersection.

The preceding vehicle identification unit 53 calculates the THW of the vehicle VS with respect to the vehicle VB and the arrival time to the intersection of the vehicle VB based on the behavior of the vehicle VB traveling on the vehicle road acquired from the object tracking unit 43. .. Then, in the preceding vehicle identification unit 53, the THW of the own vehicle VS with respect to the vehicle VB is equal to or less than the filtering threshold value A1 (second threshold value), and the arrival time of the vehicle VB to the intersection of the T-shaped road is the filtering threshold value A2. When it is equal to or less than (third threshold value), the vehicle VB is specified as the preceding vehicle to be the target of vehicle behavior prediction. Further, the preceding vehicle identification unit 53 determines that the vehicle VB is in front of the own vehicle VS. The reason for determining using the filtering threshold value A1 and the filtering threshold value A2 is the same as in the case of the “first running scene”.

The behavior change detection unit 55 detects the behavior change of the vehicle VB specified as the preceding vehicle based on the time change of the object information acquired from the object tracking unit 43, as in the case of the “first traveling scene”.

The behavior prediction threshold value changing unit 57 includes the presence / absence of a preceding vehicle, the positional relationship between the own vehicle and other vehicles (including the preceding vehicle and the crossing vehicle), road information, the behavior change of the preceding vehicle detected by the behavior change detecting unit 55, and the like. The correction amount Δ is determined based on the disturbance factor, and the value of the behavior prediction threshold value T is increased or decreased.

In the "third running scene" of FIG. 6, since the vehicle VB specified as the preceding vehicle exists, the behavior prediction threshold value changing unit 57 reduces the behavior prediction threshold value T (for example, the correction amount Δ is set to only 1 second). increase).

The lanes that the vehicle VC can enter after passing through the intersection of the T-junction are lane TL9, lane TL10, lane TL13, and lane TL14. Therefore, it can be determined that the number of roads that the vehicle VC can enter after passing through the intersection of the T-junction is two or more lanes, and that there is sufficient space at the entry destination of the vehicle VC. Therefore, it is considered that the approach probability of the vehicle VC will be large. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

Further, if two or more vehicles scheduled to enter the intersection of the T-junction are waiting behind the vehicle VC, the vehicle VC enters in order to eliminate the standby state of the vehicle behind the vehicle VC. The probability is expected to increase. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

If the non-priority lane is a road with one lane on each side and a vehicle planning to enter the intersection of the T-junction is waiting behind the vehicle VC, the vehicle behind the vehicle VC is waiting. It is considered that the approach probability of the vehicle VC will be increased in order to eliminate the waiting state. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

Furthermore, if there are five or more vehicles waiting at the intersection of the T-junction behind the vehicle VB, in order to avoid waiting for the vehicle VC due to the vehicle entering the intersection behind the vehicle VB. , It is considered that the approach probability of the vehicle VC will increase. Therefore, the behavior prediction threshold change unit 57 reduces the behavior prediction threshold T (for example, increases the correction amount Δ by 0.5 seconds).

The behavior prediction threshold value changing unit 57 confirms that the value of the behavior prediction threshold value T after the increase / decrease change as described above is within an appropriate range for use in the approach prediction of the crossing vehicle ( For example, confirm that the behavior prediction threshold T is the upper limit value of 8 seconds or less and the lower limit value of 4 seconds or more). Then, if it is within an appropriate range, the process of changing the behavior prediction threshold value T is terminated.

The behavior prediction threshold value T may be dynamically determined by calculation using the positions, postures, speeds, accelerations, and road structures of the own vehicle and other vehicles.

As described above, in the "third driving scene", the shape of the road is described as two lanes on each side, but the present invention is not limited to this, and a T-junction having one lane on each side, three or more lanes on each side, and no lane may be used. Further, although the description is based on the premise of left-hand traffic, the description is not limited to this, and right-hand traffic may be used. Further, although the object is described on the premise of an automobile, it may be a two-wheeled vehicle or a light vehicle. Further, it may be an intersection without a traffic signal or an intersection with a traffic signal.

[Effect of embodiment]
As described in detail above, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment detect an object outside the own vehicle, and from the detected object, the traveling schedule intersects with the planned traveling route of the own vehicle. The crossing vehicle having a route and the preceding vehicle traveling on the planned travel route of the own vehicle are identified, the behavior change of the preceding vehicle is detected, the first threshold value is set based on the behavior change, and the traveling of the own vehicle is performed. Based on the index value indicating the distance between the preceding vehicle and the section sandwiched between the own vehicle on the planned route and the first threshold value, the entry of the crossing vehicle into the planned travel route of the own vehicle is predicted.

As a result, the prediction is performed in consideration of the influence of the behavior change of the preceding vehicle in front of the traveling direction, so that the accuracy of the approach prediction of the crossing vehicle is improved. Furthermore, by improving the accuracy of approach prediction, it is possible to reduce the possibility of sudden deceleration of the own vehicle in the control of the own vehicle based on the approach prediction of the crossing vehicle.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may predict that a crossing vehicle will enter the planned travel route of the own vehicle when the index value is equal to or higher than the first threshold value. .. Therefore, the approach prediction of the crossing vehicle can be realized by a method of comparing the index value with the first threshold value, which has a low calculation cost.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment predict the time when the crossing vehicle starts approaching the planned travel route of the own vehicle based on the index value and the first threshold value. May be good. Therefore, it is possible to obtain information on the approach start time together with the approach prediction result, and it is possible to perform more accurate control of the own vehicle when controlling the own vehicle based on the approach prediction of the crossing vehicle.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment are intersections on the planned travel route of the own vehicle based on the map information, and are oncoming roads facing the own road on which the own vehicle travels. In addition, an intersection that does not have a right / left turn signal indicating whether or not to turn in one direction, which is the direction from the oncoming road to the own vehicle road, may be specified. As a result, it is possible to predict the approach of the crossing vehicle in a driving scene where sudden deceleration of the own vehicle is likely to occur. As a result, the possibility of sudden deceleration of the own vehicle can be reduced.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may specify a vehicle that travels on an oncoming road and is scheduled to turn in one direction at an intersection as an intersection vehicle. Therefore, it is possible to predict the approach of the crossing vehicle which may cause the sudden deceleration of the own vehicle. Furthermore, the possibility of sudden deceleration of the own vehicle can be reduced.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may detect a change in the behavior of the preceding vehicle based on the turning preliminary operation of the preceding vehicle before entering the intersection. For example, the turning preliminary operation includes a deceleration operation of the preceding vehicle, an operation of moving the preceding vehicle in one direction in the lane in which the preceding vehicle travels, an operation of displaying a right / left turn signal of the preceding vehicle, and the like.

Such a turning preliminary movement of the preceding vehicle can occur at a timing earlier than the actual turning behavior change of the preceding vehicle, and the behavior change of the preceding vehicle is detected based on the turning preliminary movement of the preceding vehicle. Therefore, it is possible to predict the approach of a crossing vehicle at an earlier timing.

Further, in the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment, the time until the preceding vehicle starts approaching the intersection is equal to or less than the second threshold value, and the collision margin time of the own vehicle with the preceding vehicle is equal to or less than the second threshold value. It may specify the preceding vehicle such that it is equal to or less than the third threshold value. As a result, the preceding vehicle that is clearly not affected by the own vehicle can be excluded from the target used for approach prediction. As a result, it is possible to reduce the calculation cost when predicting the approach of the crossing vehicle.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment have a first threshold value when the road that the preceding vehicle and the crossing vehicle enter after passing through the intersection is a road having two or more lanes on each side. May be reduced. If the approach destination of the crossing vehicle and the preceding vehicle is a road with two or more lanes on each side, it can be assumed that there is sufficient space at the approach destination of the crossing vehicle, and it is expected that the approach probability of the crossing vehicle will increase. Will be done. Since the relationship between the road structure and the approach probability of the crossing vehicle can be used for the approach prediction of the crossing vehicle, the accuracy of the approach prediction can be improved.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment are used when two or more vehicles scheduled to enter the intersection are waiting behind the traveling direction of the intersection vehicle before entering the intersection. , The first threshold value may be reduced. In such a case, it is considered that the approach probability of the crossing vehicle is increased in order to eliminate the waiting state of the vehicle behind the crossing vehicle. Since the relationship between the standby state of the vehicle and the approach probability of the crossing vehicle can be used for the approach prediction of the crossing vehicle, the accuracy of the approach prediction can be improved.

Further, in the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment, when a predetermined number or more of vehicles scheduled to enter the intersection are waiting behind the traveling direction of the preceding vehicle before entering the intersection. In addition, the first threshold value may be reduced. In such a case, it is considered that the approach probability of the crossing vehicle is increased in order to avoid the waiting of the crossing vehicle due to the approach of the vehicle behind the preceding vehicle at the intersection. Since the relationship between the standby state of the vehicle and the approach probability of the crossing vehicle can be used for the approach prediction of the crossing vehicle, the accuracy of the approach prediction can be improved.

Further, in the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment, a vehicle scheduled to enter the intersection is waiting behind the traveling direction of the crossing vehicle before entering the intersection, and an oncoming road is present. When there is one lane on each side, the first threshold value may be reduced. In such a case, it is considered that the approach probability of the crossing vehicle is increased in order to eliminate the waiting state of the vehicle behind the crossing vehicle. Since the relationship between the road structure and the standby state of the vehicle and the approach probability of the crossing vehicle can be used for the approach prediction of the crossing vehicle, the accuracy of the approach prediction can be improved.

Further, in the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment, the road on which the preceding vehicle and the own vehicle travel is two lanes on each side except for the lane in which the vehicle scheduled to turn in the opposite direction to one direction travels. When the vehicle consists of the above lanes, the first threshold value may be increased. In this case, since the number of lanes in which the crossing vehicle intersects in the intersection increases, the time for the vehicle VC to pass through the intersection becomes long. In this case, the approach probability of the vehicle VC is considered to be small. Since the relationship between the road structure and the approach probability of the crossing vehicle can be used for the approach prediction of the crossing vehicle, the accuracy of the approach prediction can be improved.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may specify a merging lane that merges with the lane in which the preceding vehicle and the own vehicle travel at the merging point based on the map information. .. As a result, it is possible to predict the approach of the crossing vehicle in a driving scene where sudden deceleration of the own vehicle is likely to occur. As a result, the possibility of sudden deceleration of the own vehicle can be reduced.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may detect a change in the behavior of the preceding vehicle based on the acceleration operation of the preceding vehicle before passing through the confluence. By detecting a change in the behavior of the preceding vehicle based on the acceleration motion of the preceding vehicle, it is possible to predict the approach of the crossing vehicle at an earlier timing.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment are preceding vehicles before passing through the confluence, and the head time for the own vehicle when passing through the confluence is the fourth threshold value or less. It may specify such a preceding vehicle. As a result, the preceding vehicle that is clearly not affected by the own vehicle can be excluded from the target used for approach prediction. As a result, it is possible to reduce the calculation cost when predicting the approach of the crossing vehicle.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment are preceding vehicles before passing through the confluence point, and the collision margin time with respect to the own vehicle when passing through the confluence point is equal to or less than the fourth threshold value. It may identify a certain preceding vehicle. As a result, the preceding vehicle that is clearly not affected by the own vehicle can be excluded from the target used for approach prediction. In particular, since the preceding vehicle is specified by using the collision margin time instead of the head time, the preceding vehicle that is clearly not affected by the speed change of the preceding vehicle is used for the approach prediction. It can be excluded from the target to be used. As a result, it is possible to reduce the calculation cost when predicting the approach of the crossing vehicle.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may specify a vehicle traveling in the merging lane before passing through the merging point as a crossing vehicle. Therefore, it is possible to predict the approach of the crossing vehicle which may cause the sudden deceleration of the own vehicle. Furthermore, the possibility of sudden deceleration of the own vehicle can be reduced.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment set the first threshold value when the crossing vehicle whose time to reach the merging point is equal to or less than the fifth threshold value does not show the merging preliminary operation. It may be something to reduce. When the crossing vehicle approaches the end point of the merging lane, it is considered that the approach probability of the crossing vehicle increases even if the crossing vehicle does not show the merging preliminary operation. Since the relationship between the road structure and the approach probability of the crossing vehicle can be used for the approach prediction of the crossing vehicle, the accuracy of the approach prediction can be improved.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may reduce the first threshold value when the speed of the crossing vehicle is higher than the speed of the own vehicle by a predetermined ratio or more. .. In this case, the approach probability of the crossing vehicle is considered to be large. Since the property that the speed relationship between the own vehicle and the crossing vehicle gives to the approach probability of the crossing vehicle can be used for the approach prediction of the crossing vehicle, the accuracy of the approach prediction can be improved.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may specify a T-junction on the planned travel route of the own vehicle based on the map information. As a result, it is possible to predict the approach of the crossing vehicle in a driving scene where sudden deceleration of the own vehicle is likely to occur. As a result, the possibility of sudden deceleration of the own vehicle can be reduced.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment travel in a non-priority lane having a lower priority than the lane in which the own vehicle travels among a plurality of roads merging at a T-junction. Vehicles scheduled to enter the road may be specified as crossing vehicles. Therefore, it is possible to predict the approach of the crossing vehicle which may cause the sudden deceleration of the own vehicle. Furthermore, the possibility of sudden deceleration of the own vehicle can be reduced.

Further, the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment may detect a change in the behavior of the preceding vehicle based on the turning preliminary operation of the preceding vehicle before entering the T-junction. .. For example, the turning preliminary operation includes a deceleration operation of the preceding vehicle, an operation of moving the preceding vehicle in one direction in the lane in which the preceding vehicle travels, an operation of displaying a right / left turn signal of the preceding vehicle, and the like.

Such a turning preliminary movement of the preceding vehicle can occur at a timing earlier than the actual turning behavior change of the preceding vehicle, and the behavior change of the preceding vehicle is detected based on the turning preliminary movement of the preceding vehicle. Therefore, it is possible to predict the approach of a crossing vehicle at an earlier timing.

Further, in the vehicle behavior prediction method and the vehicle behavior prediction device according to the present embodiment, the time until the preceding vehicle starts approaching the T-shaped road is equal to or less than the second threshold value, and the collision margin of the own vehicle with the preceding vehicle is sufficient. It may specify the preceding vehicle whose time is equal to or less than the third threshold value. As a result, the preceding vehicle that is clearly not affected by the own vehicle can be excluded from the target used for approach prediction. As a result, it is possible to reduce the calculation cost when predicting the approach of the crossing vehicle.

Further, in the vehicle control method using the vehicle behavior prediction method according to the present embodiment and the vehicle control device using the vehicle behavior prediction device, the probability of the crossing vehicle entering the planned travel route of the own vehicle is equal to or higher than the danger level value. In this case, the vehicle may be decelerated before traveling at a position where the planned travel route of the own vehicle and the planned travel route of the intersecting vehicle intersect. As a result, it is possible to decelerate the own vehicle in advance before the crossing vehicle actually starts approaching the planned travel route of the own vehicle, and it is possible to avoid sudden deceleration of the own vehicle.

Further, in the vehicle control method using the vehicle behavior prediction method according to the present embodiment and the vehicle control device using the vehicle behavior prediction device, the index value is less than the first threshold value, and the difference between the index value and the first threshold value is When the absolute value is not more than a predetermined value, the control may be performed to reduce the inter-vehicle distance between the preceding vehicle and the own vehicle. By reducing the inter-vehicle distance between the preceding vehicle and the own vehicle, the approach probability of the crossing vehicle is reduced, so that the possibility of a situation contrary to the prediction result can be suppressed and the sudden deceleration of the own vehicle can be avoided.

Further, in the vehicle control method using the vehicle behavior prediction method according to the present embodiment and the vehicle control device using the vehicle behavior prediction device, the index value is equal to or higher than the first threshold value, and the difference between the index value and the first threshold value is set. When the absolute value is not more than a predetermined value, the control may be performed to increase the inter-vehicle distance between the preceding vehicle and the own vehicle. By increasing the inter-vehicle distance between the preceding vehicle and the own vehicle, the approach probability of the crossing vehicle increases, so the possibility of a situation contrary to the prediction result can be suppressed, and the own vehicle wastefully enters the crossing vehicle. You can avoid the situation of waiting for.

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 according to the reasonable claims from the above description.

Each function shown in the above-described embodiment may be implemented by one or more processing circuits. The processing circuit includes a programmed processing device such as a processing device including an electric circuit. Processing devices also include devices such as application specific integrated circuits (ASICs) and conventional circuit components arranged to perform the functions described in the embodiments.

21 Object detection unit 23 Own vehicle position estimation unit 25 Map information acquisition unit 50 Vehicle behavior prediction unit 51 Crossing vehicle identification unit 53 Leading vehicle identification unit 55 Behavior change detection unit 57 Behavior prediction threshold change unit 59 Behavior prediction unit 70 Own vehicle route Generation unit 80 Speed profile generation unit 90 Vehicle control unit 100 Processing unit (controller)

The own vehicle position estimation unit 23 includes a position detection sensor mounted on the own vehicle to measure the absolute position of the own vehicle such as GPS (Global Positioning System) and odometry. The own vehicle position estimation unit 23 measures the absolute position of the own vehicle, that is, the position, vehicle speed, acceleration, steering angle, and posture of the own vehicle with respect to a predetermined reference point by using the position detection sensor. The vehicle position estimation unit 23 includes an inertial navigation system (INS), sensors provided on the brake pedal and accelerator pedal, sensors for acquiring vehicle behavior such as wheel side sensors and yaw rate sensors, and lasers. A radar, a camera, etc. may be included.

Road structure identification unit 45, the absolute position of the vehicle obtained by the vehicle position estimating section 23, and the map information acquired by the map information acquisition unit 25, the type of the road structure on the planned travel route of the vehicle Identify. For example, the road structure specifying unit 45 specifies an intersection on the planned travel route of the own vehicle, a merging point with a merging lane, a T-junction, and the like. In addition, the road structure specifying unit 45 may specify the position and type of the traffic light installed at the intersection, and specifies priority lanes and non-priority lanes from the lanes in the road structure. It may be a thing.

(1st driving scene)
First, the vehicle behavior prediction will be described based on the "first driving scene" of FIG. In FIG. 4, the own vehicle VS and the vehicle VB are traveling in the lane TL1 in front of the intersection, and the vehicle VC is entering the intersection and traveling from the lane TL4 toward the lane TL5 or the lane TL6. It is shown.

The preceding vehicle identification unit 53 determines the THW of the vehicle VS with respect to the vehicle VB and the arrival time to the confluence of the vehicle VB based on the behavior of the vehicle VB in front of the vehicle VS acquired from the object tracking unit 43. Is calculated. Then, in the preceding vehicle identification unit 53, the THW of the own vehicle VS with respect to the vehicle VB is equal to or less than the filtering threshold value A1 (second threshold value), and the arrival time to the confluence of the vehicle VB is the filtering threshold value A2 (third). When it is equal to or less than the threshold value), the vehicle VB is specified as the preceding vehicle to be the target of vehicle behavior prediction. The reason for determining using the filtering threshold value A1 and the filtering threshold value A2 is the same as in the case of the “first running scene”.

Claims (28)

Detects objects outside your vehicle and
From the object
Identify a crossing vehicle that has a planned travel route that intersects the planned travel route of the own vehicle.
Identify the preceding vehicle that is traveling on the planned travel route of the own vehicle,
Detecting changes in the behavior of the preceding vehicle,
A first threshold is set based on the behavior change,
Predicting the entry of the crossing vehicle into the planned travel route of the own vehicle based on the index value indicating the distance between the preceding vehicle and the section sandwiched between the own vehicle and the first threshold value in the planned travel route of the own vehicle. A vehicle behavior prediction method characterized by doing so. The vehicle behavior prediction method according to claim 1.
A vehicle behavior prediction method for predicting that the crossing vehicle will enter the planned travel route of the own vehicle when the index value is equal to or higher than the first threshold value. The vehicle behavior prediction method according to claim 1 or 2.
A vehicle behavior prediction method, characterized in that the time at which the crossing vehicle starts approaching the planned travel route of the own vehicle is predicted based on the index value and the first threshold value. The vehicle behavior prediction method according to any one of claims 1 to 3.
Based on the map information, it is an intersection on the planned travel route of the own vehicle, and is a direction toward the oncoming road facing the own vehicle road on which the own vehicle travels from the oncoming road toward the own vehicle road. A vehicle behavior prediction method for identifying an intersection that does not have a right / left turn signal indicating whether or not a vehicle can turn in a direction. The vehicle behavior prediction method according to claim 4.
A vehicle behavior prediction method, characterized in that a vehicle traveling on an oncoming road and scheduled to turn in one direction at an intersection is specified as the intersection vehicle. The vehicle behavior prediction method according to claim 4 or 5.
A vehicle behavior prediction method comprising detecting a change in the behavior of the preceding vehicle based on a turning preliminary motion of the preceding vehicle before entering the intersection. The vehicle behavior prediction method according to claim 6.
The turning preliminary operation is at least one of a deceleration operation of the preceding vehicle, an operation of moving the preceding vehicle in one direction in the lane in which the preceding vehicle travels, and an operation of displaying a right / left turn signal of the preceding vehicle. A vehicle behavior prediction method characterized by this. The vehicle behavior prediction method according to any one of claims 4 to 7.
The time until the preceding vehicle starts approaching the intersection is equal to or less than the second threshold value, and
A vehicle behavior prediction method for identifying a preceding vehicle such that the collision margin time of the own vehicle with respect to the preceding vehicle is equal to or less than a third threshold value. The vehicle behavior prediction method according to any one of claims 4 to 8.
A vehicle behavior prediction method, characterized in that the first threshold value is reduced when the preceding vehicle and the crossing vehicle enter after passing through the intersection is a road having two or more lanes on each side. The vehicle behavior prediction method according to any one of claims 4 to 9.
Vehicle behavior characterized in that the first threshold value is reduced when two or more vehicles scheduled to enter the intersection are waiting behind the traveling direction of the crossing vehicle before entering the intersection. Prediction method. The vehicle behavior prediction method according to any one of claims 4 to 10.
A vehicle characterized in that the first threshold value is reduced when a predetermined number or more of vehicles scheduled to enter the intersection are waiting behind the traveling direction of the preceding vehicle before entering the intersection. Behavior prediction method. The vehicle behavior prediction method according to any one of claims 4 to 11.
The first threshold value is reduced when a vehicle planning to enter the intersection is waiting behind the traveling direction of the crossing vehicle before entering the intersection and the oncoming road has one lane on each side. A vehicle behavior prediction method characterized by making the vehicle behave. The vehicle behavior prediction method according to any one of claims 4 to 12.
The first threshold value is increased when the preceding vehicle and the road on which the own vehicle travels consist of two or more lanes on each side except for the lane in which the vehicle scheduled to turn in the opposite direction to the one direction travels. A vehicle behavior prediction method characterized by this. The vehicle behavior prediction method according to any one of claims 1 to 3.
A vehicle behavior prediction method, characterized in that a merging lane that merges with the preceding vehicle and the lane in which the own vehicle travels at a merging point is specified based on map information. The vehicle behavior prediction method according to claim 14.
A vehicle behavior prediction method comprising detecting a change in the behavior of the preceding vehicle based on the acceleration operation of the preceding vehicle before passing through the confluence. The vehicle behavior prediction method according to claim 14 or 15.
A vehicle that is the preceding vehicle before passing through the merging point and is characterized in that the preceding vehicle is specified such that the head time with respect to the own vehicle when passing through the merging point is equal to or less than the fourth threshold value. Behavior prediction method. The vehicle behavior prediction method according to claim 14 or 15.
It is characterized in that the preceding vehicle before passing through the merging point is specified such that the collision margin time with respect to the own vehicle when passing through the merging point is equal to or less than the fourth threshold value. Vehicle behavior prediction method. The vehicle behavior prediction method according to any one of claims 14 to 17.
A vehicle behavior prediction method, characterized in that a vehicle traveling in the merging lane before passing through the merging point is specified as the crossing vehicle. The vehicle behavior prediction method according to claim 18.
A vehicle behavior prediction method, characterized in that the first threshold value is reduced when the crossing vehicle does not show a merging preliminary operation in which the time until reaching the merging point is equal to or less than the fifth threshold value. The vehicle behavior prediction method according to claim 18 or 19.
A vehicle behavior prediction method, characterized in that the first threshold value is reduced when the speed of the crossing vehicle is higher than the speed of the own vehicle by a predetermined ratio or more. The vehicle behavior prediction method according to any one of claims 1 to 3.
A vehicle behavior prediction method characterized by specifying a T-junction on a planned travel route of the own vehicle based on map information. The vehicle behavior prediction method according to claim 21.
Of the plurality of roads merging on the T-junction, a vehicle that is scheduled to enter the T-junction by traveling in a non-priority lane having a lower priority than the lane in which the own vehicle is traveling is specified as the crossing vehicle. A vehicle behavior prediction method characterized by. The vehicle behavior prediction method according to claim 21 or 22.
A vehicle behavior prediction method comprising detecting a change in the behavior of the preceding vehicle based on a turning preliminary motion of the preceding vehicle before entering the T-junction. The vehicle behavior prediction method according to any one of claims 21 to 23.
The time until the preceding vehicle starts approaching the T-junction is equal to or less than the second threshold value, and
A vehicle behavior prediction method for identifying a preceding vehicle such that the collision margin time of the own vehicle with respect to the preceding vehicle is equal to or less than a third threshold value. A vehicle control method using the vehicle behavior prediction method according to any one of claims 4 to 24.
When the probability of the crossing vehicle entering the planned travel route of the own vehicle is equal to or higher than the danger level value, before traveling at the intersection of the planned travel route of the own vehicle and the planned travel route of the crossing vehicle. A vehicle control method comprising decelerating the own vehicle. A vehicle control method using the vehicle behavior prediction method according to any one of claims 4 to 24.
Control to reduce the inter-vehicle distance between the preceding vehicle and the own vehicle when the index value is less than the first threshold value and the absolute value of the difference between the index value and the first threshold value is not more than a predetermined value. A vehicle control method characterized by performing. A vehicle control method using the vehicle behavior prediction method according to any one of claims 4 to 24.
When the index value is equal to or higher than the first threshold value and the absolute value of the difference between the index value and the first threshold value is equal to or less than a predetermined value, control for increasing the inter-vehicle distance between the preceding vehicle and the own vehicle. A vehicle control method characterized by performing. Equipped with a sensor that detects an object outside the vehicle and a controller,
The controller
From the object
Identify a crossing vehicle that has a planned travel route that intersects the planned travel route of the own vehicle.
Identify the preceding vehicle that is traveling on the planned travel route of the own vehicle,
Detecting changes in the behavior of the preceding vehicle,
A first threshold is set based on the behavior change,
Based on the index value indicating the distance between the preceding vehicle and the section sandwiched between the own vehicle in the planned travel route of the own vehicle and the first threshold value, the crossing vehicle enters the planned travel route of the own vehicle. A vehicle behavior prediction device characterized by making predictions.

Images