WO2021048583A1

WO2021048583A1 - Action deciding method of traveling support device, and traveling support device

Info

Publication number: WO2021048583A1
Application number: PCT/IB2019/001099
Authority: WO
Inventors: 辻正文; 黒川貴都; 後藤健文
Original assignee: 日産自動車株式会社; ルノーエス．ア．エス．
Priority date: 2019-09-09
Filing date: 2019-09-09
Publication date: 2021-03-18

Abstract

A traveling support device (1) comprises a controller (20). The controller (20) sets a first region for places intersecting with a route on which an own vehicle (40) travels, where movement of a moving object is permitted from the perspective of road structure, sets a second region in the proximity of the first region in the direction in which the moving object is advancing, decision is made to execute a stopping action of the own vehicle when a moving object is present in the first region, and decision is made to execute a decelerating action of the own vehicle when a moving object is present in the second region.

Description

Behavior decision method of driving support device and driving support device

The present invention relates to a method for determining the behavior of a driving support device and a driving support device.

There is known a method of detecting an obstacle by changing the detection area at a place where it is presumed that there is a high possibility of collision with an obstacle while the vehicle is traveling (Patent Document 1). In the method described in Patent Document 1, a detection area is set on a pedestrian crossing in front of the vehicle, and when an obstacle (pedestrian) is detected in the set detection area, braking control or the like is performed.

Japanese Unexamined Patent Publication No. 2009-271766

However, Patent Document 1 does not describe that the side of the pedestrian crossing is included in the detection area. Therefore, when there are pedestrians beside the pedestrian crossing, it is unclear what the proper driving behavior is.

The present invention has been made in view of the above problems, and an object of the present invention is a method for determining an action of a driving support device and a driving support device capable of performing an appropriate driving action according to a situation around the vehicle. Is to provide.

In the method of determining the behavior of the traveling support device according to one aspect of the present invention, a first region is set at a place where the moving object is allowed to move due to the road structure, which intersects the route on which the own vehicle travels, and the moving object. A second region close to the first region in the traveling direction of the vehicle is set, and when a moving object exists in the first region, it is determined to execute the stopping operation of the own vehicle, and the moving object exists in the second region. If so, it is decided to perform the deceleration operation of the own vehicle.

According to the present invention, it is possible to perform appropriate driving behavior according to the situation around the vehicle.

FIG. 1 is a block diagram of an autonomous driving architecture according to an embodiment of the present invention. FIG. 2 is a block diagram of a traveling support device according to an embodiment of the present invention. FIG. 3 is a diagram illustrating a method of setting a first region according to an embodiment of the present invention. FIG. 4 is a diagram illustrating a method of setting a second region according to an embodiment of the present invention. FIG. 5 is a diagram illustrating an example of the shape of a pedestrian crossing according to an embodiment of the present invention. FIG. 6 is a diagram illustrating another example of the shape of the pedestrian crossing according to the embodiment of the present invention. FIG. 7 is a diagram illustrating an example of a method for determining a driving behavior according to an embodiment of the present invention. FIG. 8 is a diagram illustrating another example of a method for determining a driving behavior according to an embodiment of the present invention. FIG. 9 is a diagram illustrating another example of a method for determining a driving behavior according to an embodiment of the present invention. FIG. 10 is a flowchart illustrating an operation example of the traveling support device according to the embodiment of the present invention. FIG. 11 is a diagram illustrating a modified example of the present invention. FIG. 12 is a diagram illustrating the shape of the second region according to the embodiment of the present invention. FIG. 13 is a diagram illustrating another example of a method for determining a driving behavior according to an embodiment of the present invention. FIG. 14 is a diagram illustrating another example of a method for determining a driving behavior according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the description of the drawings, the same parts are designated by the same reference numerals and the description thereof will be omitted.

(Self-driving architecture)
The traveling support device according to the present embodiment is used for a vehicle having an automatic driving function. The architecture of automatic driving in this embodiment will be described with reference to FIG.

In automatic driving, it is required to grasp the self-position and the information around the vehicle. With these grasps, the vehicle can change lanes, move in an appropriate direction at an intersection, and reach the destination. The architecture for grasping the self-position and the architecture for grasping the information around the vehicle are indicated by reference numerals 100 to 105 in FIG.

The sensor group (Sensors) represented by reference numeral 100 in FIG. 1 detects various information. The sensor group 100 includes a laser range finder that measures a distance using a light wave, a camera, a radar, a lidar, a sonar that measures a distance using ultrasonic waves, and the like. Further, the sensor group also includes a speed sensor for detecting the speed of the vehicle, an acceleration sensor for detecting the acceleration of the vehicle, a steering angle sensor for detecting the steering angle of the vehicle, and the like.

Multiple cameras are installed in front, side, rear, side mirrors, etc. of the own vehicle. The camera has an image sensor such as a CCD (charge-coupled device) or a CMOS (complementary metallic accessory semiconductor). The camera detects objects around the vehicle (pedestrians, bicycles, two-wheeled vehicles, other vehicles, etc.) and information around the vehicle (road boundaries, traffic lights, signs, pedestrian crossings, facility entrances, etc.). To do.

The radar emits radio waves to an object in front of its own vehicle and measures the reflected wave to measure the distance and direction to the object.

A lidar (LIDAR: Laser Imaging Detection and Ranger) scans with a laser beam in the horizontal and vertical directions to measure the position and shape of an object existing around the vehicle.

Further, the sensor group 100 includes a GPS receiver. The GPS receiver detects the position information (including latitude and longitude information) of the vehicle on the ground by receiving the radio waves from the artificial satellite. However, the method of detecting the position information of the vehicle is not limited to the GPS receiver. For example, the position may be estimated using a method called odometry. The odometry is a method of estimating the position of a vehicle by obtaining the amount of movement and the direction of movement of the vehicle according to the rotation angle and the rotation angular velocity of the vehicle. In this case, the sensor group 100 includes a steering angle sensor, a wheel speed sensor, and a gyro sensor.

The information detected by the sensor group 100 is transmitted to a controller (not shown) mounted on the vehicle and processed. The information detected by the sensor group 100 is localized to fit the detected area (reference numeral 103 in FIG. 1).

The information detected by the sensor group 100 and the map information are integrated, and the environment recognition unit 104 in the controller generates a world model. The world model here is the surrounding environment on a digital map that combines static map information or a high-precision map with lane information with dynamic position information such as self-position information, other vehicle information, and pedestrian information. Means information.

The high-precision map will be explained here. A high-precision map is a map that includes information such as the number of lanes on a road, road width information, road information such as road undulation information, road signs indicating speed limits, one-way streets, pedestrian crossings, and road signs indicating lane markings. To say. Further, the high-precision map may include equipment information such as road structures (for example, traffic lights, telegraph columns), buildings, and the like. These high-precision map information is provided in the HD map 102 shown in FIG. The environment recognition unit 104 reads a high-precision map around the self-position from the HD map 102, sets dynamic position information such as self-position information, other vehicle information, and pedestrian information on the read map, and sets the world model. Generate.

Note that various data such as road information and equipment information are not limited to those acquired from the HD map 102, and may be acquired using vehicle-to-vehicle communication and road-to-vehicle communication. When various data such as road information and equipment information are stored in a server installed outside, the controller may acquire these data from the cloud at any time by communication. In addition, the controller may periodically obtain the latest map information from a server installed outside and update the map information it holds.

The object recognition unit 105 in the controller generates recognition information of objects around the vehicle generated based on the information detected by the sensor group 100, and generates a local model. The local model includes other vehicle information, pedestrian information, and the like as object recognition information. The other vehicle information includes the speed, the direction of travel, the traveling lane, and the like of the other vehicle. Pedestrian information includes pedestrian attributes (adult or child), face orientation, direction of travel, and the like. The local model generated by the object recognition unit 105 is used to generate the world model.

Next, the driving control architecture for automatic driving will be described with reference to reference numerals 106 to 111 in FIG.

The user sets the destination using the navigation device 101 (Navigation) (reference code 106 in FIG. 1, Destination setting). The navigation device 101 reads out the HD map 102 and plans a route to reach the destination. If there is an intersection on the route to reach the destination, the timing of changing lanes to the lane entering the intersection is also planned (reference code 107 in FIG. 1, Route planning).

The action determination unit 108 in the controller determines the action when automatically traveling along the route set by using the information generated by the environment recognition unit 104 and the object recognition unit 105. Further, the action decision unit 108 makes a decision to advance or stop the own vehicle. For example, if the color of the traffic light is red, the vehicle is stopped, and if the color of the traffic light is blue, the vehicle is driven. Further, the action determining unit 108 determines the timing of turning on the direction indicator when changing lanes, the timing of operating the steering wheel, and the like.

Next, the controller reads the local model and the HD map 102 generated by the object recognition unit 105 to plan the drive zone (reference code 109 in FIG. 1, Drive Zone planning). The drive zone is defined as the area in which the vehicle can travel. While traveling, various obstacles (other vehicles, motorcycles, falling objects on the road, etc.) are detected by the sensor group 100. The controller plans the drive zone with these obstacles in mind.

Next, the controller generates a trajectory along the drive zone (reference numeral 110 in FIG. 1). The trajectory is composed of a plurality of points indicating the traveling locus of the vehicle, and each point is composed of the position information of the vehicle and the posture information of the vehicle at that position. The controller also generates a vehicle speed profile when traveling along the trajectory in accordance with the generation of the trajectory. In general, the larger the radius of curvature of the trajectory, the higher the vehicle speed can be set from the viewpoint of discomfort given to the occupants and the limit behavior of the vehicle. The controller may set the vehicle speed profile based on the radius of curvature of the trajectory, or conversely may generate the trajectory based on the vehicle speed profile.

Finally, the controller controls various actuators (brake actuator, accelerator actuator, steering actuator, etc.) so that the vehicle automatically travels along the set trajectory (reference numeral 111 in FIG. 1, Vehicle motion control). .. As a result, automatic operation is realized.

(Configuration example of driving support device)
Next, a configuration example of the traveling support device 1 will be described with reference to FIG. As shown in FIG. 2, the traveling support device 1 includes an environment recognition unit 104, an object recognition unit 105, and a controller 20. The environment recognition unit 104 and the object recognition unit 105 have been described with reference to FIG. The controller 20 shown in FIG. 2 corresponds to the controller described in FIG. As described above, the functions of the controller 20 include a route planning function, an action determination function (action determination unit 108), a trajectory generation function, and the like. Among such a plurality of functions, FIG. 2 describes the action determination unit 108.

The action determination unit 108 determines the driving behavior of the own vehicle based on the information acquired from the environment recognition unit 104 and the object recognition unit 105.

The controller 20 is a general-purpose microcomputer including a CPU (central processing unit), a memory, and an input / output unit. A computer program for functioning as the driving support device 1 is installed in the microcomputer. By executing the computer program, the microcomputer functions as a plurality of information processing circuits included in the travel support device 1. Here, an example of realizing a plurality of information processing circuits included in the travel support device 1 by software is shown, but of course, dedicated hardware for executing each of the following information processing is prepared for information processing. It is also possible to configure a circuit. Further, a plurality of information processing circuits may be configured by individual hardware. The controller 20 includes a first area setting unit 21, a second area setting unit 22, a determination unit 23, and a speed determination unit 24 as a plurality of information processing circuits. Each function of the first area setting unit 21, the second area setting unit 22, the determination unit 23, and the speed determination unit 24 is a classification of the functions of the action determination unit 108.

The first area setting unit 21 sets the first area in a place where the movement of moving objects (pedestrians, bicycles, etc.) is permitted due to the road structure. The details of the first region will be described later, but the first region is a region used for determining the driving behavior of the own vehicle. For example, when a moving object is detected in the first region, the own vehicle is controlled to stop before the first region. That is, the action determination unit 108 determines to execute the stop operation of the own vehicle when the moving object is detected in the first region. The first region may be rephrased as a region where the own vehicle and a moving object may come into contact with each other.

The second area setting unit 22 sets each of the second areas close to the first area. Like the first region, the second region is also an region used for determining the driving behavior of the own vehicle. For example, when a moving object is detected in the second region, the target speed of the own vehicle is lowered. Alternatively, the action determination unit 108 determines to execute the deceleration operation of the own vehicle when a moving object is detected in the second region.

In the present embodiment, the stop operation means the control to make the vehicle speed zero. On the other hand, although the deceleration operation is a control for decelerating the own vehicle, it does not include setting the vehicle speed to zero. That is, the stop operation and the deceleration operation mean different controls.

The determination unit 23 determines whether or not a moving object exists in the first region and the second region set by the first region setting unit 21 and the second region setting unit 22. For this determination, the detection result by the sensor group 100 (for example, camera, radar, rider) is used.

The speed determination unit 24 determines the speed of the own vehicle 40 based on the result of the determination unit 23. When it is determined that a moving object exists in the first region, the speed determination unit 24 determines the speed of the own vehicle 40 so that the own vehicle 40 stops before the first region. When it is determined that a moving object exists in the second region, the speed determination unit 24 lowers the target speed of the own vehicle 40. The speed determination unit 24 outputs the determined speed to the controller 20 (travel control function of the controller 20).

Next, the first area set by the first area setting unit 21 will be described with reference to FIG.

In the scene shown in FIG. 3, the own vehicle 40 is traveling on a road with one lane on each side. A pedestrian crossing 50 exists in front of the own vehicle 40. A stop line 51 is provided in front of the pedestrian crossing 50 (on the side of the own vehicle 40). A stop line 52 is provided at the back of the pedestrian crossing 50 (on the opposite lane side). The route on which the own vehicle 40 travels is set in advance using a navigation device.

The pedestrian crossing 50 is provided on the road so that moving objects such as pedestrians and bicycles can safely cross the road. That is, the pedestrian crossing 50 is a place where pedestrians, bicycles, and the like are allowed to move due to the road structure. Hereinafter, for the sake of simplicity, a moving object passing through the pedestrian crossing 50 will be described as a pedestrian, but the moving object also includes a bicycle and the like.

As shown in FIG. 3, the first area setting unit 21 sets the first area 60 on the pedestrian crossing 50 where the movement of pedestrians is permitted due to the road structure. The first area setting unit 21 sets the first area 60 so as to be larger than the pedestrian crossing 50 in consideration of the margin. The margin is not particularly limited, but is, for example, 50 cm to 1 m. The first area 60 may be set to have the same size as the pedestrian crossing 50.

Next, the second area set by the second area setting unit 22 will be described with reference to FIG.

As shown in FIG. 4, the second area setting unit 22 sets the

second areas

61 and 62 close to the first area 60, respectively. In the present embodiment, the proximity to the first region 60 includes the contact with the first region 60 without a gap, the overlap with the first region 60, or the contact with the first region 60 with a gap. Further, the second area setting unit 22 may set the

second areas

61 and 62 before and after the first area 60, respectively. The front and back of the first area 60 means the traveling direction of a pedestrian passing through the pedestrian crossing 50. In the example shown in FIG. 4, the front-rear direction of the first region 60 and the traveling direction of the own vehicle 40 intersect at right angles, but the present invention is not limited to this. The crossing angle is not limited as long as the front-rear direction of the first region 60 and the traveling direction of the own vehicle 40 intersect. Further, at least a part of the

second areas

61 and 62 may be set on a sidewalk different from the roadway. In the present embodiment, two (61, 62) second regions are set, but the present invention is not limited to this. Only one second region may be set.

Note that the

second regions

61 and 62 may be expressed as being set at both ends of the first region 60, respectively. Further, the

second regions

61 and 62 may be expressed as being set adjacent to the first region 60.

In the present embodiment, the

second areas

61 and 62 are set on the sidewalk adjacent to the pedestrian crossing 50 (beside the pedestrian crossing 50). Pedestrians in the

second areas

61 and 62 may enter the first area 60 (pedestrian crossing 50) within a predetermined time. Here, as an example, if the predetermined time is set to 2 seconds, the speed of a normal pedestrian is 4 km / h, so the length d shown in FIG. 4 is set to 2.2 m. The size of the second region 61 and the size of the second region 62 may be the same or different. In the present embodiment, the size of the second region 61 and the size of the second region 62 will be described as being the same.

The first area 60 and the

second areas

61 and 62 are areas used for determining the driving behavior of the own vehicle 40. For example, when a pedestrian 70 is detected in the first area 60, the own vehicle 40 is controlled to stop before the first area 60. This is to ensure the safety of the pedestrian 70. On the other hand, the

second regions

61 and 62 are regions for wait-and-see. When pedestrians are detected in the

second regions

61 and 62, it is unknown whether or not the pedestrians pass the pedestrian crossing 50. While pedestrians may pass through pedestrian crossing 50, pedestrians may travel in a different direction than pedestrian crossing 50. Therefore, when a pedestrian is detected in the

second regions

61 and 62, the speed determination unit 24 lowers the target speed of the own vehicle 40 in preparation for the case where the pedestrian passes the pedestrian crossing 50.

The line of the pedestrian crossing 50 (mainly the white line) shown in FIGS. 3 to 4 is inclined with respect to the traveling direction of the own vehicle 40, but is not limited to this. The white line of the pedestrian crossing 50 may be formed along the same direction as the traveling direction of the own vehicle 40 as shown in FIGS. 5 to 6.

Next, an example of the driving behavior determined by the driving support device 1 will be described with reference to FIGS. 7 to 9.

As shown in FIG. 7, when a pedestrian 70 is detected in the first region 60 in front of the own vehicle 40, the speed determination unit 24 determines the own vehicle so that the own vehicle 40 stops before the first region 60. Determine the speed of 40. The controller 20 stops the own vehicle 40 in front of the first region 60 using the speed determined by the speed determination unit 24. The front of the first region 60 is the position of the stop line 51. The reason for stopping the own vehicle 40 at the stop line 51 is to allow the pedestrian 70 to pass safely.

As shown in FIG. 8, when the pedestrian 70 is detected in the second region 61 in front of the own vehicle 40, the speed determination unit 24 lowers the target speed of the own vehicle 40. The controller 20 runs the own vehicle 40 using the speed lowered by the speed determination unit 24. As an example of how to reduce the target speed, the speed determination unit 24 may reduce the target speed to a speed at which the own vehicle 40 can be immediately stopped in front of the first region 60 (stop line 51). Alternatively, the speed determination unit 24 may reduce the target speed to the slow speed. Slow speed is defined as traveling at a speed at which the vehicle can stop immediately, and the slow speed is, for example, 10 or less km / h. That is, in the present embodiment, the slow-moving motion is a deceleration motion in which the target speed of the own vehicle 40 is set to zero or more and the vehicle travels. The slow-moving operation may be an operation in which the target speed of the own vehicle 40 is made larger than zero to travel. In areas (countries) where slow speed is not defined, the speed determination unit 24 may reduce the target speed to 10 km / h or less. That is, when the pedestrian 70 is detected in the second region 61, the speed determination unit 24 may determine the speed of the own vehicle 40 so as to be equal to or lower than the predetermined vehicle speed. Further, the speed determination unit 24 may lower the target speed of the own vehicle 40 from the current vehicle speed of the own vehicle 40.

Here, I will explain the merits of running at a lower target speed. The target speed here means the legal speed. When the pedestrian 70 is detected in the second region 61 as described above, it is unknown whether or not the pedestrian 70 passes the pedestrian crossing 50. If the pedestrian 70 enters the pedestrian crossing 50 and passes through the pedestrian crossing 50, the own vehicle 40 needs to stop at the stop line 51. On the other hand, if the pedestrian 70 travels in a direction different from that of the pedestrian crossing 50, the deceleration of the own vehicle 40 is unnecessary.

When the pedestrian 70 is detected in the second region 61, the own vehicle 40 travels at a reduced target speed. Therefore, even if the pedestrian 70 tries to pass the pedestrian crossing 50 and enters the pedestrian crossing 50, the own vehicle 40 Can stop immediately at the stop line 51. As a result, the pedestrian 70 can safely pass through the pedestrian crossing 50.

In addition, since the own vehicle 40 travels at a reduced target speed, it is possible to acquire more information than when traveling at the legal speed. As a result, information such as the orientation of the face and the orientation of the body of the pedestrian 70 can be obtained, and the direction of travel of the pedestrian 70 can be estimated accurately. That is, regarding the behavior of the pedestrian 70, which is difficult to estimate from a distance, the closer to the pedestrian crossing 50, the more information can be obtained, so that the behavior of the pedestrian 70 can be estimated accurately. As a result, the estimation accuracy of whether or not the pedestrian 70 passes the pedestrian crossing 50 can be improved.

Based on the information obtained while traveling at a reduced target speed, the face of the pedestrian 70 is not facing the pedestrian crossing 50, the body of the pedestrian 70 is not facing the pedestrian crossing 50, etc. It is assumed that the characteristics of the pedestrian 70 can be detected. In this case, since it is estimated that the pedestrian 70 does not pass through the pedestrian crossing 50, the speed determination unit 24 may restore the lowered target speed. That is, the speed determination unit 24 may return the lowered target speed to the legal speed. If the pedestrian 70 does not pass the pedestrian crossing 50, it is not necessary to decelerate the own vehicle 40. Therefore, it is possible to reduce the unnecessary deceleration by returning the lowered target speed to the original speed.

However, in order to ensure the safety of the pedestrian 70, even if it is estimated that the pedestrian 70 does not pass through the pedestrian crossing 50, the pedestrian 70 advances in a direction different from that of the pedestrian crossing 50, and the second area Until the distance from 61 is reached, the controller 20 may drive the own vehicle 40 in a state where the target speed is lowered (see FIG. 9). When it is detected that the pedestrian 70 moves in a direction different from that of the pedestrian crossing 50 and leaves the second region 61, the speed determination unit 24 may restore the lowered target speed.

Next, an operation example of the traveling support device 1 will be described with reference to the flowchart of FIG.

In step S101, the environment recognition unit 104 acquires information about the structure around the own vehicle based on the detection result by the sensor group 100 (for example, a camera, radar, rider, etc.). The structure is, for example, a pedestrian crossing 50 as shown in FIG. The environment recognition unit 104 acquires the position, size, and the like of the pedestrian crossing 50.

The process proceeds to step S103, and the environment recognition unit 104 acquires the position information of the own vehicle based on the detection result by the GPS receiver.

When the pedestrian crossing 50 is detected in front of the own vehicle 40 (YES in step S105), the process proceeds to step S107, and the first area setting unit 21 sets the first area 60 on the pedestrian crossing 50 (FIG. 3). reference). After that, the process proceeds to step S109, and the second area setting unit 22 sets the

second areas

61 and 62 close to the first area 60, respectively (see FIG. 4). On the other hand, if the pedestrian crossing 50 is not detected in front of the own vehicle 40 (NO in step S105), the process returns to step S101.

When a pedestrian 70 is detected in the first region 60 in front of the own vehicle 40 (YES in step S111), the process proceeds to step S113, and the speed determination unit 24 moves the own vehicle 40 in front of the first region 60. The speed of the own vehicle 40 is determined so as to stop (see FIG. 7). Then, the controller 20 stops the own vehicle 40 in front of the first region 60 using the speed determined by the speed determination unit 24 (first speed control). After stopping, the own vehicle 40 waits until the passage of the pedestrian 70 is completed (NO in step S115). After the passage of the pedestrian 70 is completed (YES in step S115), the speed determination unit 24 determines the starting speed for starting the own vehicle 40. The starting speed is not particularly limited, but is, for example, a speed of reaching 20 km / h in 5 seconds after starting. The controller 20 starts the own vehicle 40 using the speed determined by the speed determination unit 24 (second speed control).

On the other hand, when the pedestrian 70 is not detected in the first region 60 in front of the own vehicle 40 and the pedestrian 70 is detected in the second region 61 (NO in step S111 and YES in step S119), the process is a step. Proceeding to S121, the speed determination unit 24 lowers the target speed of the own vehicle 40. Then, the controller 20 runs the own vehicle 40 using the speed lowered by the speed determination unit 24 (third speed control). As a result, when the own vehicle 40 travels toward the pedestrian crossing 50, it travels at a speed lower than the legal speed, so that more information can be acquired. As a result, information such as the orientation of the face and the orientation of the body of the pedestrian 70 can be obtained, and the direction of travel of the pedestrian 70 can be estimated accurately.

When it is detected that the pedestrian 70 moves in a direction different from the pedestrian crossing 50 and leaves the second area 61 (NO in step S123), the speed determination unit 24 restores the lowered target speed. Then, the controller 20 runs the own vehicle 40 using the speed restored by the speed determination unit 24 (fourth speed control). If it is estimated in step S123 that the pedestrian 70 does not pass through the pedestrian crossing 50 based on the information of the pedestrian 70 (face orientation, body orientation), the process may proceed to step S125.

On the other hand, when it is detected that the pedestrian 70 has entered the pedestrian crossing 50 (YES in step S123), the process proceeds to step S113.

(Action effect)
As described above, according to the traveling support device 1 according to the embodiment, the following effects can be obtained.

The first area setting unit 21 sets the first area 60 at a place where the movement of the pedestrian 70 (moving object) is permitted due to the road structure, which intersects the route on which the own vehicle 40 travels. The second area setting unit 22 sets the

second areas

61 and 62 close to the first area 60 in the traveling direction of the pedestrian 70, respectively. The determination unit 23 determines whether or not a pedestrian 70 exists in the first region 60 or the

second regions

61 and 62 using the detection result of the sensor group 100. The speed determination unit 24 determines the speed (driving behavior) of the own vehicle 40 based on the determination result. As a result, it becomes possible to perform an appropriate driving action corresponding to the surrounding situation of the own vehicle 40.

The second area setting unit 22 sets the

second areas

61 and 62 close to the first area 60 in the traveling direction of the pedestrian 70. The determination unit 23 determines whether or not the pedestrian 70 exists in the

second regions

61 and 62. When the pedestrian 70 is present in the

second regions

61 and 62, the speed determination unit 24 (action determination unit 108) determines to execute the deceleration operation of the own vehicle 40. As a result, it becomes possible to perform an appropriate driving action corresponding to the surrounding situation of the own vehicle 40. The deceleration operation may be a slow-moving operation in which the target speed of the own vehicle 40 is set to zero or more and the vehicle travels. Further, the deceleration operation may be an operation of traveling at a predetermined vehicle speed or lower. Further, the deceleration operation may be an operation in which the target speed of the own vehicle 40 is lowered from the current vehicle speed of the own vehicle 40 to travel.

If the own vehicle 40 is traveling at a slow speed in advance, even if the pedestrian 70 is detected in the

second regions

61 and 62, further deceleration is unnecessary.

Further, when it is determined that the pedestrian 70 exists in the first area 60, the speed determination unit 24 may determine the speed at which the own vehicle 40 is stopped before the first area 60 (see FIG. 7). This enables automatic driving in consideration of the safety of the pedestrian 70.

When it is determined that the pedestrian 70 exists in the second region 61, the speed determination unit 24 may lower the target speed (see FIG. 8). When it is determined that the pedestrian 70 exists in the second region 61, it is unknown whether or not the pedestrian 70 passes the pedestrian crossing 50. Therefore, by lowering the target speed, even if the pedestrian 70 enters the pedestrian crossing 50 in an attempt to pass the pedestrian crossing 50, the own vehicle 40 can immediately stop at the stop line 51. As a result, the pedestrian 70 can safely pass through the pedestrian crossing 50.

In addition, since the own vehicle 40 travels at a reduced target speed, it is possible to acquire more information than when traveling at the legal speed. As a result, information such as the orientation of the face and the orientation of the body of the pedestrian 70 can be obtained, and the direction of travel of the pedestrian 70 can be estimated accurately. That is, regarding the behavior of the pedestrian 70, which is difficult to estimate from a distance, the closer to the pedestrian crossing 50, the more information can be obtained, so that the behavior of the pedestrian 70 can be estimated accurately. As a result, the estimation accuracy of whether or not the pedestrian 70 passes the pedestrian crossing 50 can be improved. As a result, highly accurate automatic driving corresponding to the surrounding conditions of the own vehicle 40 can be realized.

Further, according to this embodiment, the processing load of the computer is reduced. When the

second regions

61 and 62 are not set, it is necessary to recognize the behavior of the moving object (pedestrian 70) in detail, and the processing load increases. However, according to the present embodiment, by setting the

second regions

61 and 62, it is not necessary to recognize the behavior of the moving object in detail. As a result, the action of the own vehicle 40 can be determined only by the position of the moving object, and the processing load for determining the action of the own vehicle 40 is reduced.

When it is determined that the pedestrian 70 is present in the second region 61, the speed determination unit 24 lowers the target speed to a speed at which the own vehicle 40 can be immediately stopped in front of the first region 60 (FIG. 8). reference). When it is determined that the pedestrian 70 exists in the second region 61, it is unknown whether or not the pedestrian 70 passes the pedestrian crossing 50. Therefore, by lowering the target speed, even if the pedestrian 70 enters the pedestrian crossing 50 in an attempt to pass the pedestrian crossing 50, the own vehicle 40 can immediately stop at the stop line 51. As a result, the pedestrian 70 can safely pass through the pedestrian crossing 50.

If it is estimated that the pedestrian 70 does not pass the pedestrian crossing 50, the speed determination unit 24 restores the lowered target speed. This makes it possible to reduce unnecessary deceleration.

(Modification example)
In the above example, a pedestrian crossing has been described as an example of a place where pedestrians are allowed to move due to the road structure, but such a place is not limited to the pedestrian crossing. For example, as shown in FIG. 11, a sidewalk that crosses the entrance / exit of a facility can be mentioned as a place where pedestrians are allowed to move due to the road structure. The scene shown in FIG. 11 is a scene in which the own vehicle 40 moves to the roadway through a sidewalk that crosses the entrance / exit of the store. Although a store is shown as an example of a facility in FIG. 11, the facility is not limited as long as the entrance / exit is provided on the sidewalk such as a library, a school, or a hotel.

On the sidewalk that crosses the doorway of the store, the processing of the controller 20 is the same as the above example. When a sidewalk that crosses the entrance / exit of the store is detected in front of the own vehicle 40, the first area setting unit 21 sets the first area 60 on the sidewalk that crosses the entrance / exit of the store.

The second area setting unit 22 sets the

second areas

61 and 62, which are close to the first area 60, respectively. In the example shown in FIG. 11, the direction close to the first area 60 means the traveling direction of the pedestrian 70 passing through the sidewalk crossing the entrance / exit of the store.

The speed determination and speed control are the same as in the above example. When a pedestrian is detected in the first area 60, the controller 20 stops the own vehicle 40 in front of the first area 60. When the pedestrian 70 is detected in the second region 62, the controller 20 drives the own vehicle 40 using the speed lowered by the speed determining unit 24. As a result, it becomes possible to perform an appropriate driving action corresponding to the surrounding situation of the own vehicle 40.

Each function described in the above-described embodiment can 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 circuits also include devices such as application specific integrated circuits (ASICs) and circuit components arranged to perform the described functions.

As described above, embodiments of the present invention have been described, but the statements and drawings that form part of this disclosure should not be understood to limit the invention. Various alternative embodiments, examples and operational techniques will be apparent to those skilled in the art from this disclosure.

In the examples shown in FIGS. 4 and 11, the shapes of the

second regions

61 and 62 have been described as being square, but the shape is not limited to the square. For example, as shown in FIG. 12, the shapes of the

second regions

61 and 62 may be semicircular.

Further, as shown in FIG. 13, when pedestrians (pedestrians 70 and 71) are detected in both the first region 60 and the second region 61, the speed determination unit 24 owns the vehicle in front of the first region 60. Determine the speed at which 40 is stopped. Then, the controller 20 stops the own vehicle 40 before the first region 60. This enables automatic driving in consideration of the safety of the pedestrian 70.

As shown in FIG. 14, a part of the first region 60 and a part of the

second regions

61 and 62 may overlap. When a pedestrian 70 is detected in a portion where a part of the first region 60 and a part of the second region 61 overlap, the speed determination unit 24 determines the speed at which the own vehicle 40 is stopped before the first region 60. decide. Then, the controller 20 stops the own vehicle 40 before the first region 60. This enables automatic driving in consideration of the safety of the pedestrian 70.

1 Travel support device 20 Controller 21 1st area setting unit 22 2nd area setting unit 23 Judgment unit 24 Speed determination unit 40 Own vehicle

Claims

A first region is set at a place where the movement of a moving object is permitted due to the road structure that intersects the route on which the own vehicle travels, and it is determined whether or not the moving object exists in the first region. In the action determination method of the travel support device including the controller that determines to execute the stop operation of the own vehicle when the moving object is present in the first region.
A second region close to the first region in the traveling direction of the moving object is set.
It is determined whether or not the moving object exists in the second region, and
A method of determining an action of a traveling support device, which determines that the deceleration operation of the own vehicle is executed when the moving object is present in the second region.
The method for determining an action of a traveling support device according to claim 1, wherein the deceleration operation is a slow-moving operation in which the vehicle travels with the target speed of the own vehicle set to zero or more.
The method for determining an action of a traveling support device according to claim 1 or 2, wherein the deceleration operation is an operation of traveling at a predetermined vehicle speed or lower.
The action of the traveling support device according to any one of claims 1 to 3, wherein the deceleration operation is an operation of traveling by lowering the target speed of the own vehicle from the current vehicle speed of the own vehicle. How to decide.
When the moving object is present in the second region, it is determined to reduce the target speed to a speed at which the own vehicle can be immediately stopped in front of the first region to run the own vehicle. The method for determining the behavior of the traveling support device according to claim 4, wherein the vehicle is driven by the vehicle.
The traveling support according to any one of claims 1 to 4, wherein when it is estimated that the moving object does not pass through the place where the movement is permitted, the lowered target speed is restored. How to determine the behavior of the device.
A first aspect of the present invention, wherein when the moving object is present in both the first region and the second region, it is determined to execute the stop operation of the own vehicle in front of the first region. The method for determining the behavior of the traveling support device according to any one of 6.
When a part of the second region is set to overlap a part of the first region, the moving object is in a region where a part of the second region and a part of the first region overlap. The method for determining the action of the traveling support device according to any one of claims 1 to 7, wherein when is present, it is determined to execute the stop operation of the own vehicle in front of the first region. ..
The method for determining the behavior of a traveling support device according to any one of claims 1 to 8, wherein the place where the moving object is allowed to move is a pedestrian crossing or an entrance / exit of a facility.
The method for determining an action of a traveling support device according to any one of claims 1 to 9, wherein at least a part of the second region is set on a sidewalk different from the roadway.
A first region is set at a place where the movement of a moving object is permitted due to the road structure that intersects the route on which the own vehicle travels, and it is determined whether or not the moving object exists in the first region. In a traveling support device including a controller that determines to execute the stop operation of the own vehicle when the moving object is present in the first region.
The controller
A second region close to the first region in the traveling direction of the moving object is set.
It is determined whether or not the moving object exists in the second region, and
A traveling support device characterized in that when the moving object is present in the second region, it is determined to execute the deceleration operation of the own vehicle.