MOBILE BODY CONTROL DEVICE, MOBILE BODY CONTROL METHOD, AND PROGRAM

The mobile object control device generates target trajectories by recognizing targets and converting risk areas into circles for evaluation, addressing the challenge of risk assessment in autonomous driving and reducing calculation load.

JP7584313B2Active Publication Date: 2024-11-15HONDA MOTOR CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2021009983
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-01-26
Publication Date
2024-11-15
Estimated Expiration
2041-01-26

AI Technical Summary

Technical Problem

Existing technologies face challenges in generating a continuous target trajectory for autonomous driving, leading to risk areas being overlooked between trajectory points, and difficulty in accurately assessing the risk of target trajectories.

Method used

A mobile object control device and method that recognizes targets and generates a target trajectory by connecting adjacent trajectory points, using risk areas shaped as ellipses, converting them into circles for evaluation, and aligning directions to assess the risk of target objects without increasing calculation load.

Benefits of technology

The solution allows for appropriate evaluation and control of the target trajectory while minimizing calculation load, reducing the risk of sharp turns and improving risk assessment accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007584313000001
    Figure 0007584313000001
  • Figure 0007584313000002
    Figure 0007584313000002
  • Figure 0007584313000003
    Figure 0007584313000003
Patent Text Reader

Abstract

To provide a mobile body control device, mobile body control method, and program capable of appropriately evaluating a target track so as to control a mobile body while suppressing an increase of a calculation load.SOLUTION: A mobile body control device comprises: a target recognition section for recognizing a target existing in the periphery of a mobile body; and a behavior plan generation section for generating a behavior plan of the mobile body, which includes generation of a target track on which the mobile body has to travel and for which a plurality of track points are connected. The behavior plan generation section generates the target track not to allow a line segment connecting the mutually adjacent track points with respect to an advance direction of the mobile body to enter a risk area including the recognized target.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a mobile object control device, a mobile object control method, and a program. [Background technology]

[0002] Research and practical application of autonomous driving, which is a technology that allows moving objects such as vehicles to travel autonomously, is currently underway. In autonomous driving, it is necessary to automatically generate a target trajectory according to the situation in the direction of travel.

[0003] In relation to this, an invention has been disclosed for a vehicle control device that includes a first setting unit that sets a first potential for a plurality of divided areas obtained by dividing a road area based on the road area; a second setting unit that sets a second potential for the divided areas based on surrounding objects detected by the detection unit; an evaluation unit that derives an index value that evaluates the potential of a target divided area based on the first potential and second potential set for a target divided area of ​​the plurality of divided areas and prediction information generated for surrounding divided areas selected from around the target divided area; and a selection unit that selects one or more divided areas from the plurality of divided areas along the traveling direction of the vehicle based on the index value derived by the evaluation unit (see Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-34627 A Summary of the Invention [Problem to be solved by the invention]

[0005] Since it is difficult to generate a target trajectory for autonomous driving as a continuous curve, it is assumed that it will be generated as a broken line consisting of a series of points (trajectory points). Since there are some intervals between trajectory points, with conventional technology, risk areas for targets with small risk sizes fall between trajectory points, and even though the target trajectory passes through the risk area, it is determined that the target trajectory passes outside the risk area, and there are cases where the risk of the target trajectory cannot be appropriately evaluated.

[0006] The present invention has been made in consideration of the above circumstances, and one of its objectives is to provide a mobile body control device, a mobile body control method, and a program that can appropriately evaluate a target trajectory and control a mobile body while suppressing an increase in the calculation load. [Means for solving the problem]

[0007] A mobile object control device, a mobile object control method, and a program according to the present invention employ the following configuration. (1): A mobile body control device according to one embodiment of the present invention includes a target recognition unit that recognizes targets present around a mobile body, and a behavior plan generation unit that generates a behavior plan for the mobile body, the target trajectory along which the mobile body should travel, the target trajectory including a series of trajectory points. The behavior plan generation unit generates the target trajectory such that a line segment connecting adjacent trajectory points in the direction of travel of the mobile body does not enter a risk area including the recognized target.

[0008] (2) In the above aspect (1), the action plan generating unit sets the risk area in the shape of an ellipse.

[0009] (3): In the above aspect (2), the action plan generation unit performs a deformation process on the risk area set in the shape of an ellipse, including shrinking the risk area and the line segment in the major axis direction of the ellipse or expanding the risk area and the line segment in the minor axis direction of the ellipse, so as to convert the ellipse into a circle, evaluates the degree of approach of the target trajectory to the target based on the result of the deformation process, and generates the target trajectory based on the result of the evaluation.

[0010] (4): In the above aspect (3), before performing the transformation process, the action plan generation unit performs a rotation process in which the risk area and the line segment are rotated around the center of the ellipse to align the major and minor axis directions of the ellipse with the axes on a virtual plane.

[0011] (5): A mobile body control method according to another aspect of the present invention includes a computer mounted on the mobile body recognizing targets present around the mobile body and generating a target trajectory along which the mobile body should travel, the target trajectory being a series of multiple trajectory points, to generate an action plan for the mobile body, and in generating the action plan, the target trajectory is generated such that a line segment connecting adjacent trajectory points in the direction of travel of the mobile body does not enter a risk area including the recognized targets.

[0012] (6): A program according to another aspect of the present invention causes a computer mounted on a moving body to recognize targets present in the vicinity of the moving body, and generates an action plan for the moving body, the action plan including generating a target trajectory along which the moving body should travel, the target trajectory being a series of multiple trajectory points, and when generating the action plan, generates the target trajectory such that a line segment connecting adjacent trajectory points in the direction of travel of the moving body does not enter a risk area including the recognized target. Effect of the Invention

[0013] According to the above aspects (1) to (6), it is possible to appropriately evaluate the target trajectory and control the moving object while suppressing an increase in the calculation load. [Brief description of the drawings]

[0014] [Figure 1] 1 is a configuration diagram of a vehicle system using a vehicle control device according to an embodiment. [Diagram 2] FIG. 2 is a functional configuration diagram of a first control unit and a second control unit. [Diagram 3] 11 is a diagram for explaining candidate points, a first index, and a second index. FIG. [Figure 4] 4 is a diagram illustrating a distribution P(R) of the first index R and a distribution P(B) of the second index B on line 4-4 in FIG. 3. [Diagram 5] 13 is a diagram for explaining the reason for determining the first index R for the candidate line segment cLK. FIG. [Figure 6] 13 is a diagram for explaining the principle of determining a first index R for a candidate line segment cLK. FIG. [Figure 7] 11A and 11B are diagrams illustrating an example of the contents of rotation processing and transformation processing. [Figure 8] FIG. 13 is a diagram for explaining conditions for determining a flag value Flag(i). [Figure 9] 13 is a diagram for explaining an example of a calculation method of a second index B. FIG. [Figure 10] FIG. 13 is a diagram (part 1) for explaining the third index. [Figure 11] FIG. 2 is a second diagram for explaining the third index. [Figure 12] FIG. 10 is a diagram illustrating an example of target trajectories generated for a plurality of targets. [Figure 13] 11 is a flowchart showing an example of the flow of processing executed by a first control unit 120. [Figure 14] 10 is a flowchart showing an example of a flow of processes executed by a first control unit 120 in the second embodiment. [Figure 15] FIG. 13 is a diagram for explaining the processing of a target trajectory generating unit 145 in the third embodiment. [Figure 16]13 is a flowchart showing an example of a flow of processes executed by a first control unit 120 in the third embodiment. [Figure 17] 1 is a diagram illustrating an example of a hardware configuration of an automatic driving control device 100 according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, an embodiment of a mobile object control device, a mobile object control method, and a program of the present invention will be described with reference to the drawings. In the following description, a vehicle is used as a representative example of a mobile object, but the mobile object is not limited to a vehicle and can be applied to any mobile object that moves autonomously, such as micromobility and robots (including those with wheels and those that walk on multiple legs).

[0016] First Embodiment [Overall configuration] 1 is a configuration diagram of a vehicle system using a vehicle control device according to an embodiment. The vehicle on which the vehicle system 1 is mounted is, for example, a two-wheeled, three-wheeled, or four-wheeled vehicle, and its drive source is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination of these. The electric motor operates using power generated by a generator connected to the internal combustion engine, or discharged power from a secondary battery or a fuel cell.

[0017] The vehicle system 1 includes, for example, a camera 10, a radar device 12, a finder 14, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, a vehicle sensor 40, a navigation device 50, an MPU (Map Positioning Unit) 60, a driving operator 80, an automatic driving control device 100, a driving force output device 200, a brake device 210, and a steering device 220. These devices and equipment are connected to each other by multiple communication lines such as a CAN (Controller Area Network) communication line, a serial communication line, a wireless communication network, etc. Note that the configuration shown in FIG. 1 is merely an example, and some of the configuration may be omitted, or other configuration may be added.

[0018] The camera 10 is, for example, a digital camera using a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is attached to an arbitrary location of a vehicle (hereinafter, the vehicle M) in which the vehicle system 1 is mounted. When capturing an image of the front, the camera 10 is attached to the top of the front windshield, the back of the rearview mirror, or the like. The camera 10, for example, periodically and repeatedly captures images of the surroundings of the vehicle M. The camera 10 may be a stereo camera.

[0019] The radar device 12 emits radio waves such as millimeter waves around the vehicle M and detects radio waves reflected by an object (reflected waves) to detect at least the position (distance and direction) of the object. The radar device 12 is attached to an arbitrary location of the vehicle M. The radar device 12 may detect the position and speed of an object by an FM-CW (Frequency Modulated Continuous Wave) method.

[0020] The finder 14 is a LIDAR (Light Detection and Ranging). The finder 14 irradiates light around the vehicle M and measures the scattered light. The finder 14 detects the distance to the target based on the time from light emission to light reception. The irradiated light is, for example, a pulsed laser light. The finder 14 is attached to an arbitrary position of the vehicle M.

[0021] The object recognition device 16 performs sensor fusion processing on some or all of the detection results from the camera 10, the radar device 12, and the finder 14 to recognize the position, type, speed, etc. of the object. The object recognition device 16 outputs the recognition result to the autonomous driving control device 100. The object recognition device 16 may output the detection results from the camera 10, the radar device 12, and the finder 14 directly to the autonomous driving control device 100. The object recognition device 16 may be omitted from the vehicle system 1.

[0022] The communication device 20 communicates with other vehicles in the vicinity of the vehicle M, for example, using a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), etc., or communicates with various server devices via a wireless base station.

[0023] The HMI 30 presents various information to an occupant of the vehicle M and accepts input operations by the occupant. The HMI 30 includes various display devices, a speaker, a buzzer, a touch panel, switches, keys, and the like.

[0024] The vehicle sensor 40 includes a vehicle speed sensor that detects the speed of the host vehicle M, an acceleration sensor that detects acceleration, a yaw rate sensor that detects the angular velocity around a vertical axis, a direction sensor that detects the direction of the host vehicle M, and the like.

[0025] The navigation device 50 includes, for example, a GNSS (Global Navigation Satellite System) receiver 51, a navigation HMI 52, and a route determination unit 53. The navigation device 50 holds first map information 54 in a storage device such as a HDD (Hard Disk Drive) or a flash memory. The GNSS receiver 51 identifies the position of the vehicle M based on a signal received from a GNSS satellite. The position of the vehicle M may be identified or complemented by an INS (Inertial Navigation System) using the output of the vehicle sensor 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, keys, and the like. The navigation HMI 52 may be partially or entirely shared with the above-mentioned HMI 30. The route determination unit 53, for example, determines a route (hereinafter, a route on a map) from the position of the vehicle M identified by the GNSS receiver 51 (or an arbitrary position input) to a destination input by a driver using the navigation HMI 52, with reference to the first map information 54. The first map information 54 is, for example, information in which road shapes are expressed by links indicating roads and nodes connected by the links. The first map information 54 may include road curvature and POI (Point Of Interest) information. The route on the map is output to the MPU 60. The navigation device 50 may perform route guidance using the navigation HMI 52 based on the route on the map. The navigation device 50 may be realized by, for example, a function of a terminal device such as a smartphone or tablet terminal owned by a passenger. The navigation device 50 may transmit a current position and a destination to a navigation server via the communication device 20, and obtain a route equivalent to the route on the map from the navigation server.

[0026] The MPU 60 includes, for example, a recommended lane determination unit 61, and holds second map information 62 in a storage device such as an HDD or a flash memory. The recommended lane determination unit 61 divides the route on the map provided by the navigation device 50 into a plurality of blocks (for example, by dividing it into 100 m intervals in the vehicle travel direction), and determines a recommended lane for each block by referring to the second map information 62. The recommended lane determination unit 61 determines which lane from the left the vehicle should travel in. When a branch point is present on the route on the map, the recommended lane determination unit 61 determines a recommended lane so that the host vehicle M can travel along a reasonable route to proceed to the branch point.

[0027] The second map information 62 is map information with higher accuracy than the first map information 54. The second map information 62 includes, for example, information on the center of lanes or information on boundaries of lanes. The second map information 62 may also include road information, traffic regulation information, address information (address and zip code), facility information, telephone number information, and the like. The second map information 62 may be updated as needed by the communication device 20 communicating with another device.

[0028] The driving operators 80 include, for example, an accelerator pedal, a brake pedal, a shift lever, a steering wheel, a special steering wheel, a joystick, and other operators. The driving operators 80 are fitted with sensors that detect the amount of operation or the presence or absence of operation, and the detection results are output to the automatic driving control device 100, or some or all of the driving force output device 200, the brake device 210, and the steering device 220.

[0029] The automatic driving control device 100 is an example of a vehicle control device. The automatic driving control device 100 includes, for example, a first control unit 120 and a second control unit 160. The first control unit 120 and the second control unit 160 are each realized by, for example, a hardware processor such as a CPU (Central Processing Unit) executing a program (software). In addition, some or all of these components may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (storage device having a non-transient storage medium) such as an HDD or flash memory of the automatic driving control device 100, or may be stored in a removable storage medium such as a DVD or CD-ROM, and the storage medium (non-transient storage medium) may be installed in the HDD or flash memory of the automatic driving control device 100 by mounting the storage medium to a drive device.

[0030] FIG. 2 is a functional configuration diagram of the first control unit and the second control unit. The first control unit 120 includes, for example, a recognition unit 130 and an action plan generation unit 140. The first control unit 120 realizes, for example, a function based on AI (Artificial Intelligence) and a function based on a pre-given model in parallel. For example, the function of "recognizing an intersection" may be realized by executing in parallel the recognition of an intersection by deep learning or the like and the recognition based on pre-given conditions (such as traffic lights and road markings that can be pattern matched), and by scoring both and evaluating them comprehensively. This ensures the reliability of the autonomous driving.

[0031] The recognition unit 130 includes, for example, a target recognition unit 132 and a driving lane recognition unit 134. The target recognition unit 132 recognizes the position of a target around the vehicle M, and its state such as speed and acceleration based on information input from the camera 10, the radar device 12, and the finder 14 via the object recognition device 16. The target includes both a stationary object and a moving object. The position of the target is recognized as a position on an absolute coordinate system with a representative point of the vehicle M (such as the center of gravity or the center of the drive shaft) as the origin, and is used for control. The position of an object may be represented by a representative point such as the center of gravity or a corner of the object, or may be represented by a represented area. The "state" of an object may include the acceleration or jerk of the object, or the "action state" (for example, whether or not the object is changing lanes or is about to change lanes).

[0032] The driving lane recognition unit 134 recognizes, for example, the relative position of the lane in which the host vehicle M is traveling (driving lane) with respect to the host vehicle M. For example, the driving lane recognition unit 134 recognizes the driving lane by comparing a pattern of road dividing lines (for example, an arrangement of solid lines and dashed lines) obtained from the second map information 62 with a pattern of road dividing lines around the host vehicle M recognized from an image captured by the camera 10. Note that the recognition unit 130 may recognize the driving lane by recognizing road boundaries (road boundaries) including not only road dividing lines but also road dividing lines, shoulders, curbs, medians, guard rails, etc. In this recognition, the position of the host vehicle M obtained from the navigation device 50 and the processing results by the INS may be taken into consideration.

[0033] When recognizing the driving lane, the driving lane recognition unit 134 recognizes the position and attitude of the host vehicle M with respect to the driving lane. For example, the driving lane recognition unit 134 may recognize the deviation of the reference point of the host vehicle M from the center of the lane and the angle with respect to a line connecting the centers of the lanes in the traveling direction of the host vehicle M as the relative position and attitude of the host vehicle M with respect to the driving lane. Alternatively, the driving lane recognition unit 134 may recognize the position of the reference point of the host vehicle M with respect to either side end of the driving lane (a road dividing line or a road boundary) as the relative position of the host vehicle M with respect to the driving lane.

[0034] The action plan generating unit 140 includes, for example, a candidate point setting unit 141, a first index derivation unit 142, a second index derivation unit 143, a third index derivation unit 144, and a target trajectory generating unit 145. Some or all of the candidate point setting unit 141, the first index derivation unit 142, the second index derivation unit 143, and the third index derivation unit 144 may be included in the recognition unit 130.

[0035] The action plan generating unit 140 generates a target trajectory along which the host vehicle M will automatically (without relying on the driver's operation) travel in the future so that the host vehicle M will travel in the recommended lane determined by the recommended lane determining unit 61 in principle and can respond to the surrounding conditions of the host vehicle M. The target trajectory generating unit 145 generates the target trajectory based on the first index derived by the first index derivation unit 142, the second index derived by the second index derivation unit 143, and the third index derived by the third index derivation unit 144. The details of this will be described later.

[0036] The target trajectory is expressed, for example, as a sequence of points (trajectory points) that the representative points of the vehicle M (e.g., the center of the front end, the center of gravity, the center of the rear wheel axle, etc.) should reach along the longitudinal direction of the road, arranged in order at predetermined distances (e.g., every few meters). The target trajectory is assigned a target speed and target acceleration for each predetermined sampling time (e.g., about a few tenths of a second). The trajectory points may be positions that the vehicle M should reach at each predetermined sampling time. In this case, the information on the target speed and target acceleration is expressed as the intervals between the trajectory points.

[0037] The second control unit 160 controls the traveling driving force output device 200, the braking device 210, and the steering device 220 so that the host vehicle M passes the target trajectory generated by the action plan generating unit 140 at the scheduled time.

[0038] The second control unit 160 includes, for example, an acquisition unit 162, a speed control unit 164, and a steering control unit 166. The acquisition unit 162 acquires information on the target trajectory (trajectory points) generated by the action plan generation unit 140, and stores it in a memory (not shown). The speed control unit 164 controls the traveling drive force output device 200 or the brake device 210 based on a speed element associated with the target trajectory stored in the memory. The steering control unit 166 controls the steering device 220 according to the curvature of the target trajectory stored in the memory. The processing of the speed control unit 164 and the steering control unit 166 is realized, for example, by a combination of feedforward control and feedback control. As an example, the steering control unit 166 executes a combination of feedforward control according to the curvature of the road ahead of the host vehicle M and feedback control based on the deviation from the target trajectory.

[0039] The driving force output device 200 outputs a driving force (torque) for the vehicle to travel to the driving wheels. The driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, and an ECU (Electronic Control Unit) that controls these. The ECU controls the above components according to information input from the second control unit 160 or information input from the driving operation device 80.

[0040] The braking device 210 includes, for example, a brake caliper, a cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the cylinder, and a brake ECU. The brake ECU controls the electric motor according to information input from the second control unit 160 or information input from the driving operation element 80, so that a brake torque corresponding to a braking operation is output to each wheel. The braking device 210 may include a backup mechanism that transmits hydraulic pressure generated by operation of a brake pedal included in the driving operation element 80 to the cylinder via a master cylinder. The braking device 210 may be an electronically controlled hydraulic brake device that controls an actuator according to information input from the second control unit 160 to transmit hydraulic pressure in the master cylinder to the cylinder.

[0041] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor changes the direction of the steered wheels by applying a force to, for example, a rack and pinion mechanism. The steering ECU drives the electric motor in accordance with information input from the second control unit 160 or information input from the driving operator 80 to change the direction of the steered wheels.

[0042] [Generation of target trajectory] The method for generating the target trajectory will be described in more detail below.

[0043] The first index derivation unit 142 derives a first index R (risk), which becomes a negative value as it approaches the target recognized by the target recognition unit 132, for each line segment (hereinafter referred to as a candidate line segment) connecting multiple candidate points (points) on the traveling direction side of the vehicle M, and associates it with each of the multiple candidate points. "Associating" means, for example, storing in a memory as information corresponding to each other. In this embodiment, a positive value is "negative" and a value closer to zero is "positive", and the score described later is a more positive value (preferable value) as the value approaches zero, but this relationship may be reversed. Therefore, the first index derivation unit 142 derives a first index R, which becomes a smaller value as it approaches the target recognized by the target recognition unit 132, for each of the multiple candidate line segments on the traveling direction side of the vehicle M. The first index derivation unit 142 includes a rotation / transformation processing unit 142A and an index calculation unit 142B. The functions of these sub-functional units will be described later.

[0044] The second index derivation unit 143 derives a second index B (benefit), which becomes smaller (more positive) the closer the recommended trajectory set by a predetermined rule is, for each of multiple candidate points in the traveling direction of the vehicle M, and corresponds it to each of the multiple candidate points.

[0045] FIG. 3 is a diagram for explaining the candidate points, the first index, and the second index. In the figure, rT is a recommended route. For example, the second index derivation unit 143 sets the center line of the recommended lane (L1 in FIG. 3) determined by the recommended lane determination unit 61 as the recommended route rT. Not limited to this, the second index derivation unit 143 may set a line biased to the left or right within the recommended lane as the recommended route rT. On a curved road, the recommended route has a curved shape. In addition, when the action plan generation unit 140 causes the vehicle M to change lanes, a route from one lane to another adjacent lane may be set as the recommended route rT.

[0046] In the figure, cK is a candidate point. The candidate point setting unit 141 sets multiple candidate points cK on the road in the traveling direction of the host vehicle M so as to have a spread in both the road longitudinal direction (X direction) and the road width direction (Y direction). A line segment connecting candidate points cK adjacent to each other in the X direction is a candidate line segment cLK. Hereinafter, the road longitudinal direction is referred to as the vertical direction, and the road width direction is referred to as the horizontal direction. In principle, the candidate point setting unit 141 sets multiple candidate points cK (Path r) on the recommended route rT at predetermined distances from the representative point rM of the host vehicle M. x (i),Path y (i)) is set (i=1, 2, ... N), and the lateral position of each candidate point cK is changed in increments of a predetermined width to comprehensively set the candidate points cK. The argument i is a value that is set in order of proximity to the representative point of the host vehicle M, for example. x (i),Path y (i)) and candidate point cK (Path x (i+1),Path y A candidate line segment connecting the first and second line segments (i+1) and (i+2) is defined as a candidate line segment cLK(i). A vertical connection of the candidate points cK becomes a candidate (temporary trajectory) for the target trajectory, and the candidate points cK constituting the determined temporary trajectory, i.e., the target trajectory, become trajectory points. The candidate points cK on the recommended route rT may be referred to as a base path. As will be described later, the method of setting the candidate points cK is not limited to a method of searching horizontally based on the base path, but may also be a method of searching based on the previous target trajectory.

[0047] In the figure, OB is a target recognized by the target recognition unit 132, and P(R) indicates the distribution of the first index R. In the figure, darker colors indicate larger values. The first index derivation unit 142 assumes an ellipse with the representative point rOB of the target OB at its center, for example, and derives the first index R for each candidate line segment cLK(i) (i=1 to n) such that the closer the location of the candidate line segment cLK(i) closest to the representative point rOB is to the center of the ellipse, the larger the first index R is, and the farther it is from the center, the smaller the first index R is. Hereinafter, the coordinates of the representative point rOB are referred to as (Obstacle x ,Obstacle y ) The distribution P(R) of the first index R is derived so that if the contour lines of the values ​​are calculated, the distribution P(R) of the first index R is derived so that it has an elliptical shape with the desired direction as the major axis. The ratio of the major axis to the minor axis of the ellipse is changed, for example, depending on the vertical length of the target OB and the type of the target OB. The outer edge of the ellipse where the first index R is zero is expressed as eOB. The desired direction is, for example, the expected moving direction of the target OB (the axial direction of the vehicle body or the direction of the wheels in the case of a vehicle or bicycle), or the road extension direction or the traveling direction of the host vehicle M if the target OB is a stationary object. These "directions" are recognized, for example, by the target recognition unit 132. The desired direction may be determined by any method without being limited to this. Depending on the type of the target OB, the distribution P(R) of the first index R may be set so that the contour lines of the values ​​have a circular shape, or may be set to another shape.

[0048] In the figure, P(B) indicates the distribution of the second index B. In the figure, a darker color indicates a larger value. The second index derivation unit 143 derives the second index B for each candidate point cK, the more positive the value becomes as the point gets closer to the recommended route rT (or the base path).

[0049] FIG. 4 is a diagram illustrating the distribution P(R) of the first index R and the distribution P(B) of the second index B on the line 4-4 in FIG. 3. The distribution P(R) of the first index R is a distribution that has a peak at the lateral position of the center rOB of the target OB, and becomes smaller as it moves away from the peak, and becomes zero when it is sufficiently far away. The distribution P(B) of the second index B is a distribution that becomes zero at the lateral position of the recommended route rT, becomes larger as it moves away from the recommended route rT, and becomes a constant value in the area of ​​the lane L2 adjacent to the recommended lane L1 (alternatively, it may be set so that the value becomes larger as it moves away from the recommended route rT in the area of ​​the lane L2). The distribution P(B) of the second index B may be set so that it becomes smaller near the center line of the lane L2.

[0050] Here, the reason why the first index R is obtained for the candidate line segment cLK instead of the candidate point cK will be described. FIG. 5 is a diagram for explaining the reason why the first index R is obtained for the candidate line segment cLK. In the figure, x (i),Path x (i)) and the i+1th candidate point cK(Path x (i+1),Path x (i+1)) are both outside the outer edge line eOB of the ellipse where the first index R is zero, and if the first index R is obtained for the candidate point cK, the target trajectory candidate shown in the figure will not be penalized by the first index R. However, when the vehicle M actually travels along this target trajectory candidate, as can be seen from the fact that the candidate line segment cLK(i) enters inside the outer edge line eOB of the ellipse, the representative point of the vehicle M may enter inside the outer edge line eOB of the ellipse, resulting in an undesirable state. If the interval between the candidate point cK and the trajectory point K is set sufficiently narrow, the occurrence frequency of such a problem can be reduced. However, the shorter the interval, the greater the load on the computer processing, and there is a concern that the delayed results will delay vehicle control. Therefore, development is being carried out on the premise that the interval between the candidate point cK and the trajectory point K will be set to a certain extent. In the automatic driving control device 100 (vehicle control device) of the embodiment, the first index R is obtained for the candidate line segment cLK, thereby solving such a problem.

[0051] When the first index R is obtained for the candidate line segment cLK, the rule is, for example, as follows. FIG. 6 is a diagram for explaining the principle of obtaining the first index R for the candidate line segment cLK. In principle, the first index derivation unit 142 determines, among the points on the candidate line segment cLK, a value corresponding to a point (closest point) that intersects with the innermost contour line when an infinite number of elliptical contour lines are drawn from the center of the ellipse toward the outer edge line eOB, as the first index R for the candidate line segment cLK. The first index R corresponding to the closest point is calculated so that it approaches 1 the closer it is to the center of the ellipse, and is zero on the outer edge line eOB of the ellipse and outside it. This value may be obtained directly by some calculation method, but the geometric calculation becomes complicated.

[0052] Therefore, in the embodiment, the rotation / transformation processing unit 142A and the index calculation unit 142B perform the processes described below to reduce the calculation load of the first index R. FIG. 7 is a diagram showing an example of the contents of the rotation process and the transformation process. First, when calculating the first index R for a certain target OB, the rotation / transformation processing unit 142A rotates the ellipse and the candidate line segment cLK around the center of the ellipse (=the center of the target) rOB so that the major axis and minor axis of the ellipse, which is the risk area set for the target OB, match two axes (which are the same as the XY axes, which are the road coordinate axes in the figure, but are not limited to this) in a virtual plane for calculation. Next, the rotation / transformation processing unit 142A reduces the ellipse and the candidate line segment cLK in the major axis direction (or expands the ellipse and the candidate line segment cLK in the minor axis direction) so that the length of the major axis of the ellipse matches the length of the minor axis. As a result, the outer edge line eOB of the ellipse becomes a circle. The rotation / transformation processing unit 142A further performs processing to enlarge or reduce the outer edge line eOB and the candidate line segment cLK so that the radius of the outer edge line eOB, which has become a circle, becomes 1. The outer edge line after this rotation / enlargement / reduction is represented as eOB*.

[0053] After the above process, the index calculation unit 142B determines a flag value Flag(i) for each candidate line segment cLK(i). FIG. 8 is a diagram for explaining conditions for determining the flag value Flag(i). Here, the explanation will be given by denoting the end points of a candidate line segment cLK(i) of interest as A and B, and the center rOB of the target as center point C. The index calculation unit 142B sets the flag value Flag(i) to 1 when at least one of the following conditions 1 and 2 is satisfied and also condition 3 is satisfied, and sets the flag value Flag(i) to 0 otherwise.

[0054] (Condition 1) Vector V going from endpoint A to B AB and vector V going from end point A to center point C AC The angle φ(V AB / V AC ) and vector V from end point B to A BA and vector V going from end point B to center point C BC The angle φ(V BA / V BC ) are both acute angles. (Condition 2) Distance D between end point A and center point C AC and the distance D between the end point B and the center point C BC At least one of these is less than or equal to 1. (Condition 3) Distance D between the line including the candidate line segment cLK(i) and the center point C CL is equal to or smaller than 1. The index calculation unit 142B calculates the distance D based on the formula (1). CL In the following, the distance D CL , the distance D CL This is written as (i).

[0055] The index calculation unit 142B calculates the distance based on the formula (1) and calculates a first index R for a certain tentative orbit based on the formula (2). Path The formulas (1) and (2) focus on one target OB, and when multiple targets OB are present in the vicinity of the tentative trajectory, the index calculation unit 142B calculates the first index R Path_ob1、 R Path_ob2、 ... are calculated based on formulas (1) and (2), and the first index R is calculated by adding them together.Path Calculate the distance D CL It is possible that (i) is 1 or less, but the entire candidate line segment cLK(i) is outside eOB*. In this case, conditions 1 and 2 are both satisfied, so R Path The term {Flag(i)×D CL (i)} will be zero.

[0056] D CL (i)={Path x (i)×Path y (i+1)-Path x (i+1)×Path y (i)} / √[{Path x (i+1)-Path x (i) 2 +{Path y (i+1)-Path y (i) 2 ] …(1) R Path =Σ i=1 N {Flag(i)×D CL (i)} …(2)

[0057] 9 is a diagram for explaining an example of a method for calculating the second index B. For example, the second index derivation unit 143 calculates the distance D between the candidate point cK and the candidate point on the base path that corresponds to the vertical position. rTi The square of the distance D is calculated as the second index B for each candidate point cK. rTi is calculated by the formula (3). x (i) is the X coordinate of the i-th candidate point on the base path, y (i) is the Y coordinate of the i-th candidate point on the base path. When searching for a candidate point cK in the horizontal direction based on the candidate point cK on the base path, x (i)-Base x (i) is zero. When a tentative orbit is set and the candidate points constituting the tentative orbit are cK(i) (i = 1, 2, ..., N), the second index B Path is expressed by equation (4).

[0058] D rTi =√{(Path x (i)-Base x (i) 2 +(Path y (i)-Base y (i) 2} …(3) B Path =Σ i=1 N {D rTi} …(4)

[0059] As a calculation procedure including derivation of the first index R and the second index B, for example, the following two calculation procedures are possible, but either calculation procedure may be adopted. The process of FIG. 13 described later is based on the idea of ​​procedure 2. (Step 1) Comprehensively set candidate points → Derive the first index R for the line segments connecting all candidate points, and the second index B for all candidate points, and store them in memory → Set tentative trajectory → Read out the first index R and second index B of the candidate points on the tentative trajectory from memory. (Step 2) Set candidate points → set tentative trajectory → derive a first index R for the line segment connecting the candidate points on the tentative trajectory, and a second index B for the candidate points on the tentative trajectory.

[0060] The third index derivation unit 144 derives a third index by evaluating the shape of a tentative trajectory that connects multiple candidate points cK in the vertical direction. The target trajectory generation unit 145 generates a target trajectory based on the first index R, the second index B, and the third index, thereby suppressing unnecessary sharp turns of the host vehicle M.

[0061] The third index derivation unit derives a third index that evaluates the smoothness of the provisional trajectory based on some or all of the following three elements (1) to (3). In the following description, it is assumed that the third index derivation unit derives the third index based on all of the three elements, and the three elements are referred to as third indexes C1, C2, and C3. In addition, the argument t that appears indicates that the control cycle corresponds to the t-th process among the processes that are periodically repeated by each unit of the first control unit 120. The following description focuses on the process that is the t-th control cycle.

[0062] FIG. 10 is a diagram (part 1) for explaining the third index. (1) The third index derivation unit obtains the lateral distance ΔY1(i-1, i, t) between candidate point cK(i, t) in the t-th control cycle (the current control cycle) and candidate point cK(i-1, t) for i = 1 to N, and derives the sum of squares as the third index C1 (Equation (5)). Note that cK(0, t) is, for example, the representative point rM of the host vehicle M. By making the third index C1 small, the shape of the target trajectory can be made simple with small lateral changes, and sharp turns of the host vehicle M can be suppressed.

[0063] C1=Σ i=1 N {ΔY1(i-1,i,t) 2} …(5)

[0064] FIG. 11 is a diagram (part 2) for explaining the third index. (2) The third index derivation unit compares each of the candidate points cK(i,t) in the t-th control cycle (the current control cycle) with the target trajectory TJ(tC) generated in the tC-th control cycle (the control cycle before the previous one), calculates the horizontal distance ΔY2(i,tC,t) between the position cK#(i,tC) on the target trajectory TJ(tC) whose vertical position coincides with the candidate point cK(i,t) and the candidate point cK(i,C) for i=1=N, and derives the sum of squares as the third index C2 (Equation (6)). Note that the target trajectory TJ(tC) is strictly a set of trajectory points K, so here, a broken line connecting successive trajectory points K in the vertical direction is called the target trajectory TJ(tC). C is a natural number equal to or greater than 1. In the example of FIG. 11, C=1. By making the third index C2 small, the change over time of the target trajectory that is repeatedly generated over time can be suppressed, and sharp turns of the host vehicle M can be suppressed.

[0065] C2=Σ i=1 N {ΔY2(i-1,iC,t) 2} …(6)

[0066] Description will be given again with reference to FIG. (3) The third index derivation unit calculates a vector V from the representative point r of the host vehicle M to the p-th candidate point c(p,t) in the t-th control cycle (the current control cycle). → MK(p,t) and a vector V from the representative point rM of the host vehicle M to the p-th candidate point cK(p,tE) in the tE-th control cycle (the control cycle before the previous one). → MK(p,t-E) The angle θ(V → MK(p,t-E) ,V → MK(p,t) ) is derived as the third index C3 (equation (7)). Note that the vector may be expressed as a "straight line", but is expressed as a vector here. E is a natural number equal to or greater than 1. By making the third index C3 small, it is possible to suppress temporal changes in future points in the target trajectory that particularly affect the behavior of the host vehicle M, and to suppress sharp turns of the host vehicle M.

[0067] C3 = θ 2 …(7)

[0068] The target trajectory generating unit 145 generates a target trajectory based on the first index R, the second index B, and the third index. For example, the target trajectory generating unit 145 derives a score by inputting the first index R, the second index B, and the third index into a function, and sets a plurality of candidate points cK that are a combination with the smallest score value as a plurality of trajectory points K that constitute the target trajectory. The score is derived by calculating a weighted sum of the first index R, the second index B, and the third indexes C1, C2, and C3, for example, as represented by formula (8). Alternatively, the score may be derived by any method as long as the gist of the invention is not changed, such as multiplying a part or all of the first index R, the second index B, and the third index by each other. "As long as the gist of the invention is not changed" means as long as the tendency that the smaller the first index R, the smaller the score, the smaller the second index B, and the smaller the third index, the smaller the score, is maintained. Each of w1, w2, w3, w4, and w5 is any positive value.

[0069] Score(t)=w1×R Path +w2×B Path +w3×C1+w4×C2+w5×C3 …(8)

[0070] This process can reduce the probability of the host vehicle M making a sharp turn, compared to a case where a target trajectory is generated based only on the first index R and the second index B. In addition, since the process of generating a target trajectory based only on the first index R and the second index B and the process of evaluating the shape of the trajectory are not separated, a target trajectory can be flexibly generated in a variety of situations.

[0071] Here, the target is not necessarily stationary, and may be an object, such as a bicycle or a pedestrian, that moves at a slower speed than the speed of the host vehicle M. In this case, the first index derivation unit 142 may derive the first index R taking into account the passage of time.

[0072] FIG. 12 is a diagram illustrating an example of a target trajectory generated for a plurality of targets. In the figure, OB2 is a second target (bicycle), and P(R) OB1 is the distribution of the first index R corresponding to the first target OB1, P(R) OB2 is the distribution of the second index R corresponding to the second target OB2. P(R) OB1 has an elliptical shape centered on the representative point rOB1 of the target OB1, while P(R) OB2 As the representative point rOB2 of the target OB2 moves, the distribution P(R) of the first index R is circular, with the center at each destination position. The size of the distribution also differs, but the first index derivation unit 142 adjusts the size of the distribution based on, for example, the size of the target OB. The first index derivation unit 142 estimates that the movement path of the representative point rOB2 follows, for example, the outer edge of the distribution of the first index R related to the first target OB1, and estimates the position of the future representative point rOB2 according to the current speed of the target OB2. Then, for each position of the future representative point rOB2, the distribution P(R) of the first index R is calculated. OB2,1 , P(R) OB2,2 , P(R) OB2,3 , P(R) OB2,4 , …, P(R) OB2,j Set P(R) OB2,j The argument j is a concept of time having the same period as the control cycle j. That is, the argument j indicates how many control cycles later the position of the target OB2 is.

[0073] The first index derivation unit 142 calculates the distribution P(R) of the first index R generated as described above. OB2,1 , P(R) OB2,2 , P(R) OB2,3 , P(R) OB2,4 , …, P(R) OB2,jmay be simply superimposed and treated as the distribution of the first index R of the second target OB2 without considering time, or, taking into consideration the movement of the second target OB2, for example, for candidate points cK(k) with a large k, that is, candidate points cK(k) far from the host vehicle M, the distribution of the first index R with a small argument j corresponding to the time required to reach the candidate point may not be considered. For example, depending on the speed of the host vehicle M, for candidate points cK(k) with k≧Th1, P(R) with j≧Th2 may be used. OB2,j The first index R may be assigned by taking only the above into consideration.

[0074] 13 is a flowchart showing an example of the flow of processing executed by the first control unit 120. The processing of this flowchart is repeatedly executed for each of the above-mentioned control cycles.

[0075] First, the target recognition unit 132 recognizes a target in the traveling direction of the host vehicle M (step S100), and the driving lane recognition unit 134 recognizes the relative position of the driving lane with respect to the host vehicle M (step S102).

[0076] Next, the candidate point setting unit 141 sets candidate points (step S104), and sets a plurality of tentative trajectories by connecting the candidate points in the vertical direction (step S106).

[0077] Next, the first index derivation unit 142, the second index derivation unit 143, and the third index derivation unit 144 each derive a first index R Path , second indicator B Path Then, third indices C1 to C3 are derived (step S108).

[0078] Next, the target trajectory generating unit 145 calculates a score for each tentative trajectory (step S110), and sets the tentative trajectory with the smallest score as the target trajectory (step S112).

[0079] Instead of comprehensively selecting tentative trajectories and calculating the score as described above, the autonomous driving control device 100 may generate a target trajectory by simultaneous perturbation optimization (SPSA: Simultaneous Perturbation Stochastic Approximation). Simultaneous perturbation optimization is a type of stochastic gradient method using random variables. In this case, the autonomous driving control device 100 can generate a target trajectory more quickly than by comprehensively selecting tentative trajectories by applying the score calculation method described above to simultaneous perturbation optimization.

[0080] In addition, in the above explanation, the first index, second index, and third index are calculated and then combined to generate the target trajectory, but as long as at least the first index is calculated by the above method, the processing corresponding to the second index and the third index may be omitted, modified, etc. as appropriate.

[0081] According to the first embodiment of the autonomous driving control device 100 described above, the autonomous driving control device 100 includes a target recognition unit 132 that recognizes targets present in the vicinity of the host vehicle M, and a behavior plan generation unit 140 that generates a behavior plan for the host vehicle M, the behavior plan generation unit 140 including generating a target trajectory along which the host vehicle M should travel, the target trajectory being a series of multiple trajectory points. The behavior plan generation unit 140 generates the target trajectory so that a line segment connecting adjacent trajectory points in the traveling direction of the host vehicle M does not enter a risk area including the recognized target, and therefore the target trajectory can be appropriately evaluated and the vehicle can be controlled while suppressing an increase in the calculation load.

[0082] <Second embodiment> The second embodiment will be described below. In the first embodiment, no particular restrictions are imposed when setting a tentative trajectory. However, in the second embodiment, an upper limit is imposed on the horizontal distance ΔY1 (see FIG. 10) between candidates cK adjacent in the vertical direction, and if there is even one ΔY1 that exceeds the upper limit, that tentative trajectory is excluded from the candidates for the target trajectory. Here, the distance does not have a directional element. That is, as a pre-processing, a process is performed to exclude in advance from the score calculation targets any tentative trajectory having a portion where ΔY1 exceeds a threshold value ThY. This can further reduce the probability of the host vehicle M making a sharp turn.

[0083] Fig. 14 is a flowchart showing an example of the flow of processing executed by the first control unit 120 of the second embodiment. The processing of this flowchart is repeatedly executed for each control cycle described above. Note that the processing of steps S100 to S106 and the processing of steps S108 to S112 are similar to those described in Fig. 13, and therefore description thereof will be omitted.

[0084] Following the process of step S106, the candidate point setting unit 141 removes, from the tentative trajectory formed by vertically connecting the candidate points, any tentative trajectory in which ΔY1 exceeds a threshold value ThY (step S107).

[0085] In addition, instead of first comprehensively setting tentative trajectories and excluding any tentative trajectories in which ΔY1 exceeds the threshold value ThY, when searching the tentative trajectories in order from the vertical end, the search range (search angle) may be limited so that ΔY1 does not exceed the threshold value ThY.

[0086] According to the second embodiment described above, in addition to achieving the same effects as the first embodiment, it is possible to further reduce the probability of the vehicle M making a sharp turn. In addition, since the process of calculating the score is performed after narrowing down the tentative trajectories, it is possible to reduce the processing load.

[0087] <Third embodiment> The third embodiment will be described below. In the third embodiment, the target trajectory generation unit 145 checks whether or not there is a portion where ΔY1 exceeds a threshold value ThY for a target trajectory selected based on the score, and if there is a portion where ΔY1 exceeds the threshold value ThY, corrects the target trajectory so that ΔY1 is equal to or smaller than the threshold value ThY.

[0088] 15 is a diagram for explaining the processing of the target trajectory generating unit 145 of the third embodiment. In the figure, the q-th trajectory point K(q,t) is in a relationship with the q-1-th trajectory point K(q-1,t) in which the lateral distance ΔY1 exceeds the threshold value ThY. Note that since the target trajectory has already been generated, it is referred to as "trajectory point K" rather than "candidate point cK". ΔY1 in the third embodiment is obtained by replacing the candidate point with the trajectory point.

[0089] In such a case, the target trajectory generating unit 145, for example, selects the target closest to the trajectory point K, and laterally corrects the position of the q-th trajectory point K(q,t) or the q-1-th trajectory point K(q-1,t) so as to move away from the representative point of the target. In the example of FIG. 15, since the representative point rOB of the target OB is on the left side as viewed from the trajectory point K(q), the target trajectory generating unit 145 moves the position of the q-1-th trajectory point K(q-1,t) to the side away from the representative point rOB of the target OB, that is, to the right. For example, the target trajectory generating unit 145 sets the amount of movement to the minimum amount of movement that does not cause ΔY1 to exceed the threshold value ThY. If the lateral distance between the q-1-th trajectory point K(q-1,t) and the q-2-th trajectory point K(q-2,t) exceeds the threshold value ThY as a result of this process, the q-2-th trajectory point K(q-2,t) is moved to the right. The target trajectory generating unit 145 of the third embodiment repeats such processing until all of ΔY1 becomes equal to or smaller than the threshold value ThY.

[0090] In this process, it is necessary to determine the trajectory point K at which ΔY1 is checked first. If this is not determined, the process may spread from both sides and not converge. For example, the target trajectory generation unit 145 of the third embodiment sets the trajectory point K (the u-th trajectory point K(u,t) in FIG. 15) at which the amount of lateral displacement from the base path is the largest as the search start point, and checks whether ΔY1 exceeds the threshold value ThY in two directions from the search start point, the near side (the side approaching the vehicle M) and the far side (the side moving away from the vehicle M).

[0091] Fig. 16 is a flowchart showing an example of the flow of processing executed by the first control unit 120 of the third embodiment. The processing of this flowchart is repeatedly executed for each control cycle described above. Note that the processing of steps S100 to S112 is similar to that described in Fig. 13, and therefore description thereof will be omitted.

[0092] When the target trajectory is generated, the target trajectory generating unit 145 sets the trajectory point farthest in the lateral direction from the representative point rM of the vehicle M as the search start point (step S118). Then, it is determined whether there is a point where ΔY1 exceeds the threshold value ThY in sequence toward the front side and the back side of the search start point (step S120). If it is determined that there is a point where ΔY1 exceeds the threshold value ThY, the target trajectory generating unit 145 moves any of the trajectory points at that point to the opposite side of the nearest target to correct the target trajectory (step S122). Then, it sets the corrected trajectory point as the search start point (step S124), and performs the process of step S120 again (step S120). However, the search is not performed toward the opposite side with respect to the front side and the back side. When there is no point where ΔY1 exceeds the threshold value ThY, one cycle of the process of this flowchart ends.

[0093] According to the third embodiment described above, in addition to achieving the same effects as the first embodiment, the probability of the host vehicle M making a sharp turn can be further reduced.

[0094] [Hardware configuration] FIG. 17 is a diagram showing an example of a hardware configuration of an automatic driving control device 100 according to an embodiment. As shown in the figure, the automatic driving control device 100 includes a communication controller 100-1, a CPU 100-2, a random access memory (RAM) 100-3 used as a working memory, a read only memory (ROM) 100-4 for storing a boot program, a storage device 100-5 such as a flash memory or a hard disk drive (HDD), a drive device 100-6, and the like, all of which are connected to each other via an internal bus or a dedicated communication line. The communication controller 100-1 communicates with components other than the automatic driving control device 100. The storage device 100-5 stores a program 100-5a to be executed by the CPU 100-2. This program is expanded in the RAM 100-3 by a direct memory access (DMA) controller (not shown) or the like, and executed by the CPU 100-2. As a result, a part or all of the first control unit 120 and the second control unit 160 are realized.

[0095] The above-described embodiment can be expressed as follows. A storage device storing a program; a hardware processor; The hardware processor executes the program stored in the storage device, Recognizes targets around the vehicle, generating a motion plan for the vehicle, the motion plan including generating a target trajectory along which the vehicle should travel, the target trajectory being a series of a plurality of trajectory points; When generating the action plan, the target trajectory is generated so that a line segment connecting the trajectory points adjacent to each other in a traveling direction of the vehicle does not enter a risk area including the recognized target. The vehicle control device is configured as follows.

[0096] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0097] 100 Automatic driving control device 120 First Control Section 130 Recognition part 132 Target recognition unit 134 Lane Recognition Unit 140 Action Plan Generation Unit 141 Candidate point setting unit 142 First index derivation part 142A Rotation / Transformation Processing Unit 142B Indicator calculation section 143 Second index derivation part 144 Third indicator derivation part 145 Target trajectory generation unit 160 Second Control Section

Claims

1. A target recognition unit that recognizes targets present around the moving object; a behavior plan generating unit that generates a behavior plan for the moving object, the behavior plan including generating a target trajectory along which the moving object should travel, the target trajectory being a series of a plurality of trajectory points; the action plan generation unit generates the target trajectory such that a line segment connecting the trajectory points adjacent to each other in a traveling direction of the moving body does not enter a risk area including the recognized target; The action plan generation unit The risk area is set in an elliptical shape; performing a transformation process for the risk area set in an ellipse shape, the transformation process including shrinking the risk area and the line segment in a major axis direction of the ellipse or expanding the risk area and the line segment in a minor axis direction of the ellipse so as to convert the ellipse into a circle; evaluating a degree of approach of the target trajectory to the target based on a result of the transformation process; and generating the target trajectory based on a result of the evaluation. Mobile control device.

2. the action plan generating unit performs a rotation process, before performing the transformation process, by rotating the risk area and the line segment around a center of the ellipse to align the major axis direction and the minor axis direction of the ellipse with axes on a virtual plane; The mobile object control device according to claim 1.

3. A computer installed in a vehicle Recognizing targets present around the moving object; generating a behavior plan for the moving object, the behavior plan including generating a target trajectory along which the moving object should travel, the target trajectory being a series of a plurality of trajectory points; When generating the action plan, the target trajectory is generated so that a line segment connecting the trajectory points adjacent to each other in a traveling direction of the moving body does not enter a risk area including the recognized target; The risk area is set in an elliptical shape; With respect to the risk area set in the shape of an ellipse, a transformation process is performed including shrinking the risk area and the line segment in a major axis direction of the ellipse or expanding the risk area and the line segment in a minor axis direction of the ellipse so as to convert the ellipse into a circle; evaluating a degree of approach of the target trajectory to the target based on a result of the transformation process; generating the target trajectory based on a result of the evaluation; A method for controlling a moving object.

4. A computer installed in a moving vehicle Recognizing targets present around the moving body; generating a behavior plan for the moving object, the behavior plan including generating a target trajectory along which the moving object should travel, the target trajectory being a series of a plurality of trajectory points; When generating the action plan, the target trajectory is generated so that a line segment connecting the trajectory points adjacent to each other in a traveling direction of the moving body does not enter a risk area including the recognized target; The risk area is set in the shape of an ellipse; performing a transformation process for the risk area set in the shape of an ellipse, the transformation process including shrinking the risk area and the line segment in a major axis direction of the ellipse or expanding the risk area and the line segment in a minor axis direction of the ellipse, so as to convert the ellipse into a circle; evaluating a degree of approach of the target trajectory to the target based on a result of the transformation process; generating the target trajectory based on a result of the evaluation; program.

Citation Information

Patent Citations

  • Vehicle control device, vehicle control method, and program

    JP2019034627A

  • Electronic control device

    JP2020045024A

  • Image presentation device, image presentation method, and non-transitory computer-readable medium having program stored thereon

    WO2020213105A1