Action plan device and mobile body control system

Abstract

To provide an action plan device for enabling a mobile body to appropriately decelerate, stop, and re-start or the like by detecting a traffic participant intending to cross a crosswalk by combining information obtained from mobile body sensors installed in the mobile body and a roadside sensor installed on a roadside.SOLUTION: An action plan device generates an action plan to stop a mobile body in front of a crosswalk conflict area when a traffic participant exists in the crosswalk conflict area and when it is determined that the traffic participant exists in a crosswalk standby area and also intends to pass the crosswalk based on obstacle information acquired from mobile body sensors and a roadside sensor, mobile body position information, road information, and area information including the crosswalk conflict area and the crosswalk standby area which are output from a crosswalk detection section.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to a behavior planning device and a mobile object control system. [Background technology]

[0002] When a mobile vehicle is autonomously driving along a predetermined route, it may need to cross a crosswalk before reaching its destination. If there are pedestrians or other traffic participants near the crosswalk, the mobile vehicle must slow down or stop appropriately. Furthermore, when passing through a crosswalk without a traffic light, not only when there are traffic participants on the crosswalk, but also when the mobile vehicle is about to cross the crosswalk near the entrance to the crosswalk, the mobile vehicle must give priority to the passage of traffic participants and stop and wait before the stop line.

[0003] In response to this, for example, in Patent Document 1, the approach to a pedestrian crossing is judged and the vehicle is decelerated in accordance with the recognition result of a pedestrian crossing the pedestrian crossing. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-89516 Summary of the Invention [Problem to be solved by the invention]

[0005] In Patent Document 1, the object situation around the vehicle is recognized through an object recognition device using a camera, radar device, and viewfinder mounted on the vehicle, so there is a concern that if a traffic participant attempting to cross the crosswalk near the entrance to the crosswalk is in the vehicle's blind spot, the vehicle may not be able to slow down appropriately.

[0006] The present disclosure discloses technology for solving the above-mentioned problems, and aims to provide a behavior planning device and a mobile object control system that can generate a behavior plan that allows a mobile object to appropriately slow down or stop by combining information obtained from a mobile object sensor installed on the mobile object and a roadside sensor installed on the roadside to detect traffic participants around a crosswalk. [Means for solving the problem]

[0007] The behavior planning device of the present disclosure comprises: an obstacle information acquisition unit that acquires information about obstacles around the mobile object from a mobile object sensor installed on the mobile object and a roadside sensor installed on a roadside; a mobile object position acquisition unit that acquires the position of the mobile object; a road information acquisition unit that acquires road information around the mobile object; a crosswalk detection unit that detects crosswalks around the moving object from the position of the moving object acquired by the moving object position acquisition unit and the road information acquired by the road information acquisition unit, and outputs area information that includes a crosswalk conflict area that includes the crosswalk and a crosswalk waiting area that is adjacent to the crosswalk conflict area and extends outside the travel route on which the moving object travels; a behavior planning unit that generates a behavior plan for the moving object, including deceleration and stopping, based on the area information output from the crosswalk detection unit and the obstacle information acquired by the obstacle information acquisition unit, The action planning unit the obstacle is in the crosswalk conflict area; and If it is determined that the obstacle is present in the crosswalk waiting area and that the vehicle will pass through the crosswalk, generating an action plan to stop the moving object before the pedestrian crossing conflict area; It is something. [Effects of the Invention]

[0008] According to the present disclosure, by combining information obtained from a mobile body sensor installed on a mobile body and a roadside sensor installed on the roadside to detect traffic participants around a crosswalk, it is possible to generate an action plan that allows the mobile body to appropriately slow down or stop. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a functional block diagram showing a configuration of a behavior planning apparatus according to a first embodiment. [Figure 2] 1 is a diagram showing an example of a detection range of an obstacle by a mobile sensor mounted on a vehicle, which is a mobile body; [Figure 3] 3 is a diagram for explaining each area output by the pedestrian crossing detection unit according to the first embodiment. FIG. [Figure 4] 4 is a flowchart showing the operation of the behavior planning device according to the first embodiment. [Figure 5] FIG. 10 is a diagram for explaining the velocity vector components of a traffic participant used to determine whether the traffic participant will pass through a crosswalk. [Figure 6] 10A and 10B are diagrams for explaining velocity vector components of obstacle information detected by a moving body sensor and a roadside sensor; [Figure 7] FIG. 10 is a functional block diagram showing the configuration of a mobile object control system according to a second embodiment. [Figure 8] FIG. 1 is a diagram illustrating a hardware configuration of an action planning device and a mobile object control system. [Figure 9] FIG. 10 is a diagram illustrating another hardware configuration of the behavior planning device and the mobile object control system. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the behavior planning device and mobile object control system disclosed in this specification will be described with reference to the drawings. Note that in each drawing, the same reference numerals indicate the same or corresponding parts. Therefore, detailed descriptions thereof may be omitted to avoid duplication.

[0011] The drawings are schematic, and for the sake of convenience, components may be omitted or simplified as appropriate. Furthermore, the relative sizes and positions of components shown in different drawings are not necessarily accurately depicted and may be changed as appropriate. Furthermore, hatching may be used in drawings such as plan views that are not cross-sectional views to facilitate understanding of the embodiments. Furthermore, even if ordinal numbers such as "first" or "second" are used, these terms are used for convenience to facilitate understanding of the contents of the embodiments, and are not limited to the ordering that may result from these ordinal numbers.

[0012] Embodiment 1 The behavior planning apparatus according to the first embodiment will be described below with reference to the drawings. An example of generating a behavior plan for a vehicle will be described below, taking an automobile as an example of a moving body to which the behavior planning device is applied. <Device configuration> Fig. 1 is a functional block diagram showing the configuration of a behavior planning apparatus according to Embodiment 1. In Fig. 1, behavior planning apparatus 100 includes an obstacle information acquisition unit 10 that acquires obstacle information around the host vehicle, a road information acquisition unit 20 that acquires information about the area around the host vehicle and the road on which the host vehicle is traveling, a mobile object position acquisition unit 30 that acquires position information about the host vehicle, a mobile object state acquisition unit 40 that acquires information about the state of the host vehicle from sensors mounted on the vehicle, a crosswalk detection unit 50 that detects crosswalks around the host vehicle and outputs a preset area, and a behavior planning unit 60 that plans the behavior of the host vehicle.

[0013] The obstacle information acquisition unit 10 acquires information about obstacles present around the vehicle from a mobile sensor 1 mounted on the mobile and a roadside sensor 2 installed on the roadside. Obstacles are, for example, other vehicles, pedestrians, bicycles, motorbikes, and other traffic participants present around the vehicle.

[0014] The mobile sensor 1 is, for example, at least one of a camera, a radar, a LiDAR (Light Detection And Ranging), and a sonar sensor (ultrasonic sensor) provided on the vehicle. The mobile sensor 1 may output to the obstacle information acquisition unit 10 obstacle information associated with a type of obstacle classified as another vehicle, a pedestrian, a bicycle, a motorcycle, or the like, that exists around the vehicle.

[0015] The camera is installed in a position where it can capture images of the front, sides, and rear of the vehicle, and from the captured images, it obtains information about the environment in which the vehicle is located, such as information about the lane and obstacles in front of the vehicle.

[0016] The radar emits radar light ahead of the vehicle and detects the reflected waves to measure the relative distance and relative speed of an obstacle present ahead of the vehicle, and outputs the measurement results.

[0017] LiDAR detects the position of an object by shining a laser around the vehicle and detecting the time difference between the time it takes for the laser to reflect off an object and return.

[0018] A sonar sensor detects the position and distance of an object by emitting ultrasonic waves to the area around the vehicle and detecting the time difference between the time it takes for the waves to reflect off an object and return.

[0019] FIG. 2 shows an example in which multiple mobile body sensors 1 described above are combined and arranged on a vehicle, illustrating the detection range of each mobile body sensor 1. In FIG. 2, seven mobile body sensors 1, 1a to 1g, are mounted on the host vehicle MO, with two mobile body sensors 1a and 1b at the front, three mobile body sensors 1c, 1f, and 1g at the sides, and two mobile body sensors 1d and 1e at the rear. The detection ranges of each mobile body sensor 1 are indicated by fan-shaped dashed lines, and the host vehicle MO can detect obstacles within detection ranges SN1, SN2, and SN7 at the front, SN3 and SN6 at the sides, and SN4 and SN5 at the rear. While the number of mobile body sensors 1 is not limited to seven, it is desirable to be able to set the obstacle detection range to encompass the entire periphery of the host vehicle MO.

[0020] The roadside sensor 2 is provided, for example, on the roadside, and includes at least one of a radar, a LiDAR, and a sonar sensor. The obstacle information acquisition unit 10 acquires information about the roadside surroundings detected by the roadside sensor 2 as obstacle information via wireless communication. The roadside sensor 2 may be provided not only on the roadside, but also on the road such as the carriageway, road shoulder, or sidewalk, or may be provided on a building or utility pole near the road. Information about the roadside surroundings may also be acquired from a remote control system or the like.

[0021] The road information acquisition unit 20 acquires information about roads around the vehicle. The road information acquisition unit 20 includes a map information acquisition unit 22 that has previously acquired map data of the planned driving route of the vehicle, and acquires road information around the vehicle based on vehicle position information acquired by a mobile object position acquisition unit 30 (described later). Note that the road information acquisition unit 20 may also include a road information detection unit (not shown) other than the map information acquisition unit 22.

[0022] Here, the map data includes road information such as the center line of the lane in which the vehicle is traveling, lane width information, stop line information at intersections, crosswalk information, information on the number of branches at intersections such as T-junctions and crossroads, and information on the start position of diverging roads. In addition, the road information included in the map data may be obtained from the surrounding structure detection results obtained from at least one of the mobile sensor 1 equipped on the vehicle, which is a camera, radar, LiDAR, and sonar sensor.

[0023] The mobile object position acquisition unit 30 is equipped with a GNSS (Global Navigation Satellite System) sensor to identify the position of the vehicle. A GNSS antenna is connected to the GNSS sensor, which receives positioning signals from positioning satellites orbiting in satellite orbits, analyzes the received positioning signals, and outputs information about the phase center of the GNSS antenna (latitude, longitude, altitude, direction, etc.). In this way, the mobile object position acquisition unit 30 acquires position information about the vehicle.

[0024] In addition to using a GNSS sensor, the position of a moving object may also be obtained using SLAM (Simulataneous Localization and Mapping: simultaneous self-position estimation and environmental map creation) technology that uses the detection results of surrounding structures obtained from at least one of a camera, radar, LiDAR, and sonar sensor.

[0025] The moving body state acquisition unit 40 detects and acquires the motion state of the vehicle from various sensors mounted on the vehicle, such as a vehicle speed sensor, a gyro sensor, a steering angle sensor, and an acceleration sensor.

[0026] The crosswalk detection unit 50 detects information about crosswalks around the vehicle from the road information acquisition unit 20 and the mobile object position acquisition unit 30, and outputs area information including the crosswalk conflict area CNF and the crosswalk waiting area WA described below. Fig. 3 is a diagram showing a situation where a crosswalk CR is present ahead of a travel path R on which a vehicle MO is traveling. In Fig. 3, a crosswalk detection unit 50 outputs a crosswalk conflict area CNF and a crosswalk waiting area WA based on information about the detected crosswalk CR. The crosswalk conflict area CNF is an area where vehicles are prohibited from entering when conditions prevent the vehicle MO from passing through the crosswalk CR. The crosswalk waiting area WA is an area adjacent to the crosswalk conflict area CNF and excluding the travel path R, and traffic participants in this crosswalk waiting area WA are subject to a determination as to whether or not to pass through the crosswalk CR.

[0027] As shown in the figure, the crosswalk CR is the area indicated by the dashed line, and the crosswalk conflict area CNF is the area indicated by the dotted line that includes the crosswalk CR, and is the area within the stop line SL where a traveling vehicle MO must stop before the crosswalk. The crosswalk waiting area WA is the area indicated by the dashed line, and is the area that extends from the crosswalk conflict area CNF to the outside of the roadway. 3, one roadside sensor 2 is provided, but the number is not limited to one. It is desirable to provide multiple roadside sensors 2 so that the crosswalk conflict area CNF and the crosswalk waiting area WA can be detected together with the mobile sensor 1 without any blind spots.

[0028] The behavior planning unit 60 determines whether to decelerate or stop the vehicle MO using the obstacle information acquired by the obstacle information acquisition unit 10, the position information of the vehicle itself (i.e., the moving object position) acquired by the moving object position acquisition unit 30, the motion state of the moving object acquired by the moving object state acquisition unit 40, and information on the crosswalk conflict area CNF and the crosswalk waiting area WA acquired by the crosswalk area acquisition unit. In other words, when the vehicle MO travels toward the crosswalk CR ahead on the travel path R, it determines whether to decelerate or stop, and generates a behavior plan for the vehicle. Based on the behavior plan generated by the behavior planning unit 60, the vehicle MO controls each actuator (not shown) that drives the vehicle, such as the brakes and steering.

[0029] In this embodiment, the behavior planning apparatus 100 is mounted on a vehicle MO, which is a moving object, that is, all of the components of the behavior planning apparatus 100 are mounted on the moving object. As a modified example, in remote control of a moving object by a control tower, all of the components of the behavior planning apparatus 100 may be installed in the control tower.

[0030] In addition, the obstacle information acquisition unit 10, road information acquisition unit 20, crosswalk detection unit 50 and behavior planning unit 60 may be provided on the control side, and the output of the behavior planning unit 60 on the control side may be transmitted to the mobile body. Without being limited to this, the components consisting of the obstacle information acquisition unit 10, the road information acquisition unit 20, the crosswalk detection unit 50, and the behavior planning unit 60 may be provided separately. Specifically, the obstacle information acquisition unit 10 and the behavior planning unit 60 may be provided inside the moving body, and the road information acquisition unit 20 and the crosswalk detection unit 50 may be provided on the control side.

[0031] Furthermore, when the roadside sensor 2 is mounted together with a computing device in an obstacle information detector (hereinafter referred to as a roadside unit RSU), the roadside unit RSU may be provided with an obstacle information acquisition unit 10, a road information acquisition unit 20, and a crosswalk detection unit 50, and the mobile body may be provided with a behavior planning unit 60. In this case, information from the obstacle information acquisition unit 10, the road information acquisition unit 20, and the crosswalk detection unit 50 mounted in the roadside unit RSU may be transmitted to the behavior planning unit 60 of the mobile body via communication.

[0032] As described above, the obstacle information acquisition unit 10, the road information acquisition unit 20, the crosswalk detection unit 50, and the behavior planning unit 60 do not necessarily have to be mounted on the moving body, and may be provided in the control and roadside units.

[0033] <Operation of the behavior planning device 100> Next, the operation of the behavior planning apparatus 100 according to the first embodiment will be described with reference to the flowchart in Fig. 4. The processing of the flowchart in Fig. 4 is repeatedly executed while the host vehicle is traveling. Each step in Fig. 4 will be described in association with each functional unit shown in the functional block diagram in Fig. 1.

[0034] First, in step S101, the obstacle information acquisition unit 10 acquires information on obstacles present around the vehicle output from the mobile sensor 1 and the roadside sensor 2. In this way, the mobile sensor 1 and the roadside sensor 2 can cover the blind spots of each other's sensors by using information from either of the obstacle information detection means (sensors) that are installed in different locations and have different detection ranges.

[0035] In step S102, the moving body position acquisition unit 30 acquires the position of the vehicle itself. In step S103, the road information acquisition unit 20 acquires road information from the map information acquisition unit 22, or acquires road information output from a road information detection unit (not shown). In step S104, the crosswalk detection unit 50 detects crosswalks CR around the vehicle from the position of the vehicle acquired in step S102 and the road information acquired in step S103, and outputs the crosswalk conflict area CNF and the crosswalk waiting area WA to the behavior planning unit 60.

[0036] In step S105, the behavior planning unit 60 determines whether or not an obstacle exists in the crosswalk conflict area CNF based on the obstacle information output from the obstacle information acquisition unit 10 and the crosswalk conflict area CNF output from the crosswalk area acquisition unit. If an obstacle exists (Yes in step S105), the process proceeds to step S108, and if an obstacle does not exist (No in step S105), the process proceeds to step S106.

[0037] When the process proceeds to step S106, the behavior planning unit 60 determines whether or not an obstacle exists in the crosswalk waiting area WA based on the obstacle information output from the obstacle information acquisition unit 10 and the crosswalk waiting area WA output from the crosswalk area acquisition unit. If an obstacle exists (Yes in step S106), the process proceeds to step S107, and if an obstacle does not exist (No in step S106), the process proceeds to step S110.

[0038] If the process proceeds to step S107, the behavior planning unit 60 predicts whether an obstacle in the crosswalk waiting area WA will pass through the crosswalk, based on the obstacle information output from the obstacle information acquisition unit 10 and the crosswalk waiting area WA output from the crosswalk area acquisition unit. If it is predicted that the obstacle will pass through the crosswalk (Yes in step S107), the process proceeds to step S108, and if it is predicted that the obstacle will not pass through the crosswalk (No in step S107), the process proceeds to step S109.

[0039] When the process proceeds to step S108, the behavior planning unit 60 plans an action for the vehicle MO to stop just before the pedestrian crossing conflict area CNF. When the process proceeds to step S109, the behavior planning unit 60 plans an action in which the vehicle will enter and pass through the pedestrian crossing conflict area CNF at a slow speed. When the process proceeds to step S110, the behavior planning unit 60 plans an action for the vehicle to enter and pass through the pedestrian crossing conflict area CNF.

[0040] That is, the behavior planning device 100 according to this embodiment detects a crosswalk CR around a traveling vehicle, and if an obstacle is present in the crosswalk conflict area CNF, generates a behavior plan in which the vehicle stops before the crosswalk conflict area CNF so as not to obstruct the passage of the obstacle. Also, if there is no obstacle in the crosswalk conflict area CNF and an obstacle in the crosswalk waiting area WA is predicted to pass through the crosswalk, the behavior planning device 100 generates a behavior plan in which the vehicle stops before the crosswalk conflict area CNF. Also, if there is no obstacle in the crosswalk conflict area CNF and even if an obstacle is present in the crosswalk waiting area WA, the behavior planning device 100 predicts that the vehicle will not pass through the crosswalk, the behavior planning device 100 generates a behavior plan in which the vehicle enters and passes through the crosswalk conflict area CNF at a slow speed. If there are no obstacles in either the crosswalk conflict area CNF or the crosswalk waiting area WA, the behavior planning device 100 generates a behavior plan in which the vehicle passes through the crosswalk conflict area CNF.

[0041] Furthermore, if no pedestrian crossing CR can be detected around the vehicle in step S104, the pedestrian crossing conflict area CNF and pedestrian crossing waiting area WA cannot be acquired either, and the process can be returned to step S101.

[0042] <Predicting the behavior of obstacles in the crosswalk waiting area WA> Here, a method for predicting whether or not a traffic participant, who is an obstacle in the crosswalk waiting area WA, will enter and pass through the crosswalk CR in step S107 will be described with reference to the drawings.

[0043] The prediction of whether a traffic participant will enter and pass through the crosswalk CR is determined based on one or a combination of the following conditions. If the conditions for determining that the traffic participant will pass through the crosswalk and the conditions for determining that the traffic participant will not pass through the crosswalk overlap, the conditions for determining that the traffic participant will pass through the crosswalk take priority. FIG. 5 is a diagram for explaining a method for determining whether traffic participants Ob1 and Ob2 in the crosswalk waiting area WA will pass through the crosswalk CR, and is a diagram for explaining the velocity vector components of traffic participants Ob1 and Ob2.

[0044] (1) Condition 1 If the speed of a traffic participant detected by the obstacle information acquisition unit 10 within the crosswalk waiting area WA in the direction approaching the crosswalk conflict area CNF is greater than a preset value, it is determined that the traffic participant will pass through the crosswalk. Here, the speed in the direction approaching the pedestrian crossing conflict area CNF corresponds to the magnitude of the speed vector Vin1 of the traffic participant Ob1 and the magnitude of the speed vector Vin2 of the traffic participant Ob2 in FIG.

[0045] In this way, by using the direction and speed of movement of traffic participants as the judgment conditions, it is possible to improve the judgment accuracy so that traffic participants waiting on the sidewalk are given priority to crossing the road.

[0046] (2) Condition 2 The obstacle information acquisition unit 10 determines that a traffic participant detected in the crosswalk waiting area WA will cross the crosswalk if the time from when the traffic participant began to exist in the crosswalk waiting area WA is within a preset time. For example, if the waiting time at a crosswalk with a traffic light is about the same as the waiting time for the light, it is predicted that the person will cross the crosswalk when the light changes. However, if the waiting time for the light is more than twice as long, the traffic participant is predicted not to cross the crosswalk because they did not cross the crosswalk even when it was possible to cross.

[0047] Furthermore, since it is determined that the vehicle will pass through the crosswalk for a preset time after detecting an obstacle in the crosswalk waiting area WA, it is possible to prevent erroneous determinations such as erroneously determining that the vehicle will not pass through the crosswalk even if the obstacle detected in the crosswalk waiting area has disappeared due to detection variability. In other words, once an obstacle is detected, it is determined that the vehicle will pass through the crosswalk for a preset time until the obstacle is removed, so it is possible to reduce the probability of generating an action plan for a moving object that may erroneously determine that the vehicle will not pass through due to a short period of detection loss or detection error, and that may obstruct the passage of traffic participants.

[0048] (3) Condition 3 When a traffic participant detected by the obstacle information acquisition unit 10 within the crosswalk waiting area WA is detected to be moving at a speed in a direction other than the direction approaching the crosswalk conflict area CNF for a predetermined period of time or longer, it is determined that the traffic participant will not cross the crosswalk. Here, the speed in the direction approaching the pedestrian crossing conflict area CNF corresponds to the magnitude of the speed vector Vin1 of traffic participant Ob1 and the magnitude of the speed vector Vin2 of traffic participant Ob2 in Figure 5, as described above. Therefore, the speed in a direction other than the direction approaching the pedestrian crossing conflict area CNF corresponds to the case where the traffic participant Ob1 has the magnitude of any of the components of the speed vectors Vout1, Vout2, and Vout3, and the traffic participant Ob2 has the magnitude of any of the components of the speed vectors Vout4, Vout5, and Vout6 in Figure 5. In other words, this is a state where the traffic participant Ob1 does not have the component of the speed vector Vin1, and the traffic participant Ob2 does not have the component of the speed vector Vin2.

[0049] For example, if a traffic participant continues to move within the crosswalk waiting area WA without approaching the crosswalk conflict area CNF, is moving parallel to the direction of travel on the road, or is moving away from the crosswalk, it is determined that the participant will not pass. In this way, by determining that an obstacle moving from the crosswalk waiting area WA in a direction other than the crosswalk conflict area CNF will not pass through the crosswalk, it is possible to prevent a stalemate, such as a moving object stopping unnecessarily.

[0050] (4) Condition 4 Only when the difference between the values ​​of the detected position and moving speed of a traffic participant detected by the mobile sensor 1 and the roadside sensor 2 within the crosswalk waiting area WA is equal to or less than a preset value, is it determined that the traffic participant will not cross the crosswalk. An example of the obstacle information detected by the mobile sensor 1 and the roadside sensor 2 used in this determination is shown in FIG. 6. In FIG. 6, the position P veh and velocity V veh , X-direction velocity vector component Vx veh , Y-direction velocity vector component Vy veh The mobile sensor 1 also detects the type of obstacle. Similarly, the roadside sensor 2 detects the position P rsu , velocity V rsu, X-direction velocity vector component Vx rsu , Y-direction velocity vector component Vy rsu , and detects the obstacle type.

[0051] This allows the system to determine whether the same obstacle has been detected based on the position, speed, and obstacle type information of each obstacle detected by the mobile sensor 1 and the roadside sensor 2, and if it is the same obstacle, the system determines whether or not to cross the crosswalk by comparing the position, speed, and speed vector components between the sensors. Here, the method of comparing the information may be a method of finding the difference between values ​​and making a judgment based on a threshold, or a method of finding correlation and making a judgment based on a correlation coefficient.

[0052] As described above, if it is determined that the vehicle will not cross the crosswalk (No in step S107), the behavior planning unit 60 plans an action for the vehicle to slow down and enter and pass through the crosswalk conflict area CNF (step S108). Therefore, if the vehicle makes an incorrect determination that the vehicle will not cross the crosswalk, it may obstruct the passage of traffic participants who are obstacles. For this reason, the same target (obstacle) is detected multiple times by the mobile sensor 1 and the roadside sensor 2, which are installed in different conditions such as different locations, and a determination is made based on the differences in position and speed between the sensors, so that each sensor monitors the other. With this configuration, the probability of an incorrect determination that the vehicle will not cross the crosswalk, which may obstruct the passage of traffic participants, can be reduced by mutual monitoring. Therefore, even if the detection results of mobile sensor 1 determine that the obstacle will not pass through the crosswalk and roadside sensor 2 determine that the obstacle will not pass through the crosswalk, if the differences in the position and speed of the obstacle between the sensors are not equal to or less than the respective preset values, it will not be determined that the obstacle will not pass through the crosswalk.

[0053] As described above, the behavior planning device according to the first embodiment includes an obstacle information acquisition unit that acquires information about obstacles around the mobile object from mobile object sensors installed on the mobile object and roadside sensors installed on the roadside, a mobile object position acquisition unit that acquires the position of the mobile object, a road information acquisition unit that acquires road information about the area around the mobile object, a crosswalk detection unit that detects crosswalks around the mobile object from the position of the mobile object acquired by the mobile object position acquisition unit and the road information acquired by the road information acquisition unit and outputs area information that includes a crosswalk conflict area including the crosswalk and a crosswalk waiting area that is adjacent to the crosswalk conflict area and extends outside the travel path along which the mobile object travels, and a behavior planning unit that generates a behavior plan for the mobile object, including deceleration and stopping, based on the area information output by the crosswalk detection unit and the obstacle information acquired by the obstacle information acquisition unit. The behavior planning unit is configured to generate a behavior plan for stopping the mobile object just before the crosswalk conflict area when an obstacle is present in the crosswalk conflict area or when an obstacle is present in the crosswalk waiting area and it is determined that the mobile object will pass through the crosswalk. By combining information from mobile sensors installed on mobile objects with information obtained from roadside sensors installed on the roadside to detect traffic participants attempting to cross the crosswalk, it is possible to cover sensor blind spots by combining information from detection means installed in different locations and with different detection ranges.In addition, by configuring detection in a multiplexed system, it is possible to improve detection and judgment accuracy, and to appropriately decelerate, stop, and restart the mobile object, thereby achieving the effect of efficiently controlling the movement of the mobile object.

[0054] Furthermore, when the vehicle approaches a crosswalk, priority can be given to pedestrians, cyclists, wheelchair users, and other traffic participants who are crossing or waiting to cross the crosswalk. Furthermore, based on information from a mobile body sensor installed on the mobile body and information obtained from a roadside sensor installed on the roadside, it is determined whether a traffic participant will attempt to cross the crosswalk, and if at least one of the determination results in the traffic participant crossing the crosswalk, the mobile body is stopped just before the crosswalk conflict area, thereby covering the blind spot of one sensor and ensuring that the traffic participant passes through the crosswalk.In other words, by not adopting a determination that the traffic participant will not pass through when at least one of the determination results in the traffic participant crossing the crosswalk, the probability of a determination error that could impede the passage of traffic participants is reduced, and it is possible to create an action plan for the mobile body that is less likely to impede the passage of traffic participants.

[0055] Embodiment 2 The mobile object control system according to the second embodiment will be described below with reference to the drawings. Fig. 7 is a functional block diagram showing the configuration of a mobile object control system according to embodiment 2. In Fig. 7, a mobile object control system 1000 includes the behavior planning device 100 described in embodiment 1 and a drive train control unit 200 that drives a mobile object. Based on the behavior plan generated by the behavior planning device 100, each actuator 300 is controlled by the drive train control unit 200 to perform operations such as stopping and decelerating the mobile object. The actuators are, for example, an engine, a brake, a steering unit (handle), and the like.

[0056] In this way, in the mobile object control system 1000 according to the second embodiment, the drive train control unit 200 controls the actuator 300 based on the behavior plan generated by the behavior planning device 100, and therefore, the same effect as in the first embodiment is achieved. That is, the effect is achieved in that a behavior planning device and a mobile object control system can be obtained that can cause a mobile object to perform efficient autonomous driving without impeding the progress of traffic participants crossing the crosswalk.

[0057] FIG. 8 shows an example of the hardware configuration of the behavior planning device 100 in the first and second embodiments described above, and includes an arithmetic processing circuit 1100 and a storage device 1200. Although the storage device is not shown, it may include auxiliary storage devices such as a ROM (Read Only Memory) that stores programs for executing the functions of each functional unit and a RAM (Random Access Memory) that stores data for the execution results of each functional unit, which are the results of calculations performed by the programs. An auxiliary storage device such as a hard disk may also be included. The arithmetic processing circuit 1100 executes the program input from the storage device 1200. In this case, the program is input to the arithmetic processing circuit 1100 from the auxiliary storage device via a volatile storage device. The arithmetic processing circuit 1100 may output data such as calculation results to a volatile storage device of the storage device 1200, or may store the data in the auxiliary storage device via the volatile storage device.

[0058] The behavior planning apparatus 100 further includes an input / output circuit 1300. The input / output circuit 1300 receives output results relating to obstacle information from the mobile sensor 1 and the roadside sensor 2, and outputs a behavior plan generated by the behavior planning unit 60 to the drivetrain control unit 200. The hardware configuration of the moving body control system 1000 shown in the second embodiment is also the same as that shown in Fig. 8. In this case, the input / output circuit 1300 outputs the calculation result of the drive system control unit 200 to the actuator 300.

[0059] A processor such as a CPU (Central Processing Unit) or a DSP (Digital Signal Processor) is applied to the arithmetic processing circuit 1100. Dedicated hardware may also be applied to the arithmetic processing circuit 1100. When the arithmetic processing circuit 1100 is dedicated hardware, the arithmetic processing circuit 1100 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination of these.

[0060] Furthermore, the functional units of the behavior planning apparatus 100 and the mobile object control system 1000 may be realized by individual arithmetic processing circuits, or may be realized together by a single arithmetic processing circuit. Furthermore, the functional units of the behavior planning device 100 and the mobile object control system 1000 can realize the above-mentioned functions by hardware, software, or a combination of these, with some functions being realized by dedicated hardware processing circuits and other functions being realized by software.

[0061] 9 shows another example of the hardware configuration of the mobile object control system 1000. A communication circuit 1400 is further provided in addition to the configuration of FIG. The communication circuit 1400 includes a wide-area communication unit and a short-range communication unit as a communication module. The wide-area communication unit uses a communication standard that complies with a predetermined wide-area wireless communication standard, such as LTE (Long Term Evolution), 4G (4th Generation; fourth generation mobile communication system), or 5G (5th Generation; fifth generation mobile communication system). The short-range communication unit uses, for example, DSRC (Dedicated Short Range Communications), and although not described in the above embodiment, by using this for communication with other vehicles, information about other vehicles around the vehicle can be obtained. A certain communication speed is guaranteed for these communications.

[0062] <Other embodiments> In the above description, the behavior planning apparatus 100 and the mobile object control system 1000 are described using an automobile as an example of a mobile object to which the apparatus is applied. However, the application is not limited to automobiles and can be applied to various other mobile objects. The behavior planning apparatus 100 can be used as an apparatus for planning the behavior of a mobile object, such as an in-building mobile robot that inspects the interior of a building, a line inspection robot, or a personal mobility vehicle. When the mobile object is not an automobile, the road information acquisition unit can acquire road information that indicates the drivable area of ​​the route along which the mobile object travels. The obstacle information acquired by the roadside sensor can be, for example, information from an obstacle information detection unit installed within a building, a line, or within the range in which the personal mobility object moves. Furthermore, the crosswalk can be set as, for example, a crosswalk installed within a building, a line, or within the range in which the personal mobility object moves, or an area where traffic participants cross.

[0063] In the above embodiments, the dimensions, shapes, relative positional relationships, and implementation conditions of each component may be described, but these are merely examples in all aspects and are not limited to those described in this specification. They may be applied to the embodiments alone or in various combinations. Therefore, countless modifications and equivalents not shown as examples are contemplated within the scope of the technology disclosed in this specification, including, for example, modifying, adding, or omitting at least one component, and further, extracting at least one component in at least one embodiment and combining it with a component in another embodiment.

[0064] Furthermore, unless a contradiction arises, any component described in the above embodiments as being provided with "one" component may be provided with "one or more." Furthermore, each component in the above-described embodiments is a conceptual unit, and within the scope of the technology disclosed in this specification, one component may be composed of multiple structures. In some cases, a single component corresponds to a part of a structure, and in other cases, multiple components This includes cases where the elements are provided in one structure.

[0065] Furthermore, each of the components in the embodiments described above includes structures having other structures or shapes as long as they perform the same function. Furthermore, the descriptions in this specification are incorporated by reference for all purposes relating to the present technology, and none of them is admitted to be prior art.

[0066] Furthermore, each of the components described in the above embodiments can be implemented as software. It may also be considered as firmware or its corresponding hardware, and both In this concept, each component is referred to as a "unit" or a "processing circuit".

[0067] Various aspects of the present disclosure are summarized below as appendices.

[0068] (Appendix 1) an obstacle information acquisition unit that acquires information about obstacles around the mobile object from a mobile object sensor installed on the mobile object and a roadside sensor installed on a roadside; a mobile object position acquisition unit that acquires the position of the mobile object; a road information acquisition unit that acquires road information around the mobile object; a crosswalk detection unit that detects crosswalks around the moving object from the position of the moving object acquired by the moving object position acquisition unit and the road information acquired by the road information acquisition unit, and outputs area information that includes a crosswalk conflict area that includes the crosswalk and a crosswalk waiting area that is adjacent to the crosswalk conflict area and extends outside the travel route on which the moving object travels; a behavior planning unit that generates a behavior plan for the moving object, including deceleration and stopping, based on the area information output from the crosswalk detection unit and the obstacle information acquired by the obstacle information acquisition unit, The action planning unit the obstacle is in the crosswalk conflict area; and If it is determined that the obstacle is present in the crosswalk waiting area and that the vehicle will pass through the crosswalk, A behavior planning device that generates a behavior plan for stopping the moving object before the pedestrian crossing conflict area. (Appendix 2) The action planning unit If the obstacle is present in the crosswalk waiting area, 2. The behavior planning device according to claim 1, wherein the device determines whether the obstacle will pass through the crosswalk based on the information about the obstacle acquired from the mobile object sensor and the information about the obstacle acquired from the roadside sensor, and generates a behavior plan to stop the mobile object just before the crosswalk conflict area if the determination result based on the information about the obstacle acquired from at least one of the mobile object sensor and the roadside sensor is that the obstacle will pass through the crosswalk. (Appendix 3) The action planning unit If the obstacle is present in the crosswalk waiting area, 3. The behavior planning device according to claim 1, wherein the device determines that the obstacle present in the crosswalk waiting area will pass through the crosswalk if the speed of the obstacle in a direction approaching the crosswalk conflict area is greater than a preset value. (Appendix 4) The action planning unit If the obstacle is present in the crosswalk waiting area, 4. The behavior planning device according to claim 1, wherein the device determines that the obstacle present in the crosswalk waiting area will pass through the crosswalk if a time period from when the obstacle began to be present in the crosswalk waiting area is within a preset time period. (Appendix 5) The action planning unit If the obstacle is present in the crosswalk waiting area, 5. The behavior planning device according to any one of appendix 1 to 4, wherein, when a speed of the obstacle present in the crosswalk waiting area in a direction other than a direction approaching the crosswalk conflict area is detected for a predetermined time or longer, it is determined that the obstacle will not cross the crosswalk. (Appendix 6) The action planning unit If the obstacle is present in the crosswalk waiting area, 6. The behavior planning device according to any one of appendix 1 to 5, wherein the device determines that the obstacle will not cross the crosswalk only if a difference between the values ​​of the position and speed of the obstacle acquired from the mobile sensor and the roadside sensor is equal to or less than a preset value. (Appendix 7) A mobile object control system including the behavior planning device according to any one of Supplementary Note 1 to 6 and a drive train control unit that drives the mobile object, The drive train control unit controls the moving body based on the behavior plan generated by the behavior planning device. [Explanation of symbols]

[0069] 1, 1a, 1b, 1c, 1d, 1e, 1f, 1g: mobile object sensor, 2: roadside sensor, 10: obstacle information acquisition unit, 20: road information acquisition unit, 22: map information acquisition unit, 30: mobile object position acquisition unit, 40: mobile object state acquisition unit, 50: crosswalk detection unit, 60: action planning unit, 100: action planning device, 200: drive system control unit, 300: actuator, 1000: mobile object control system, 1100: arithmetic processing circuit, 1200: storage device, 1300: input / output circuit, 1400: communication circuit, MO: host vehicle, RSU: roadside unit, R: travel path, CR: crosswalk, CNF: crosswalk conflict area, WA: crosswalk waiting area, Ob1, Ob2: traffic participants, SN1,SN2,SN3,SN4,SN5,SN6,SN7: Detection range, SL: Stop line.

Claims

1. an obstacle information acquisition unit that acquires information about obstacles around the mobile object from a mobile object sensor installed on the mobile object and a roadside sensor installed on a roadside; a mobile object position acquisition unit that acquires the position of the mobile object; a road information acquisition unit that acquires road information around the mobile object; a crosswalk detection unit that detects crosswalks around the moving object from the position of the moving object acquired by the moving object position acquisition unit and the road information acquired by the road information acquisition unit, and outputs area information that includes a crosswalk conflict area that includes the crosswalk and a crosswalk waiting area that is adjacent to the crosswalk conflict area and extends outside the travel route on which the moving object travels; a behavior planning unit that generates a behavior plan for the moving object, including deceleration and stopping, based on the area information output from the crosswalk detection unit and the obstacle information acquired by the obstacle information acquisition unit, The action planning unit the obstacle is in the crosswalk conflict area; and If it is determined that the obstacle is present in the crosswalk waiting area and that the vehicle will pass through the crosswalk, A behavior planning device that generates a behavior plan for stopping the moving object before the pedestrian crossing conflict area.

2. The action planning unit If the obstacle is present in the crosswalk waiting area, 2. The behavior planning device according to claim 1, wherein the device determines whether the obstacle will pass through the crosswalk based on the information about the obstacle acquired from the mobile object sensor and the information about the obstacle acquired from the roadside sensor, and generates a behavior plan for stopping the mobile object just before the crosswalk conflict area if the determination result based on the information about the obstacle acquired from at least one of the mobile object sensor and the roadside sensor is that the obstacle will pass through the crosswalk.

3. The action planning unit If the obstacle is present in the crosswalk waiting area, 3. The behavior planning device according to claim 1, wherein the device determines that the obstacle present in the crosswalk waiting area will pass through the crosswalk if the speed of the obstacle in a direction approaching the crosswalk conflict area is greater than a preset value.

4. The action planning unit If the obstacle is present in the crosswalk waiting area, 3. The behavior planning device according to claim 1, wherein the device determines that the obstacle present in the crosswalk waiting area will pass through the crosswalk if a time period from when the obstacle begins to be present in the crosswalk waiting area is within a preset time period.

5. The action planning unit If the obstacle is present in the crosswalk waiting area, 3. The behavior planning device according to claim 1, wherein, when a speed of the obstacle present in the crosswalk waiting area in a direction other than a direction approaching the crosswalk conflict area is detected for a predetermined time or longer, it is determined that the obstacle will not cross the crosswalk.

6. The action planning unit If the obstacle is present in the crosswalk waiting area, 3. The behavior planning device according to claim 1, wherein the device determines that the obstacle will not pass through the crosswalk only if a difference between the values ​​of the position and speed of the obstacle acquired from the mobile sensor and the roadside sensor is equal to or less than a preset value.

7. 3. A mobile object control system including the behavior planning device according to claim 1 or 2 and a drive train control unit that drives the mobile object, The drive train control unit controls the moving body based on the behavior plan generated by the behavior planning device.

Images