Mobile body control device, mobile body control method, and storage medium

Abstract

Provided is a mobile body control device, a mobile body control method, and a storage medium that can suppress an increase in a calculation load and appropriately evaluate a target track to control a mobile body. The mobile body control device includes: an object target recognition unit that recognizes an object target present in the vicinity of a mobile body; and a movement plan generation unit that generates a movement plan for the mobile body, the movement plan including generating a target track in which a plurality of track points are connected, the movement plan generation unit generating the target track in such a manner that a line segment in which track points adjacent to each other in the traveling direction of the mobile body are connected to each other does not enter a risk region that includes the recognized object target.

Description

TECHNICAL FIELD

[0001] The present application relates to a mobile body control device, a mobile body control method, and a storage medium. BACKGROUND

[0002] Research and practicalization of making a mobile body, such as a vehicle, automatically travel (hereinafter, referred to as automatic driving) are progressing. In automatic driving, it is required to automatically generate a target trajectory in accordance with a situation of a travel direction.

[0003] In connection therewith, an invention of a vehicle control device is disclosed, which has a first setting section that sets a first potential based on a road region for a plurality of divided regions obtained by dividing the road region, a second setting section that sets a second potential for the divided regions based on a surrounding object detected by the detection section, an evaluation section that derives an index value obtained by evaluating a potential of a focus divided region focused on among the plurality of divided regions based on the first potential and the second potential set for the focus divided region and foresight information generated for a surrounding divided region selected from a surrounding of the focus divided region, and a selection section that selects one or more divided regions along a travel direction of the vehicle from the plurality of divided regions based on the index value derived by the evaluation section (see Patent Literature 1).

[0004] PRIOR ART DOCUMENTS

[0005] PATENT LITERATURE

[0006] Patent Literature 1: Japanese Patent Application Publication No. 2019-34627 SUMMARY

[0007] PROBLEMS TO BE SOLVED BY THE INVENTION

[0008] Since it is difficult to generate a target trajectory of automatic driving as a continuous curve, it is assumed to be generated by a polygonal line in which points (trajectory points) are connected. Since there is not a small interval in the trajectory points, in the conventional technology, sometimes a risk region related to an object target of which a risk size is small falls between the trajectory points, although it is judged that a target trajectory passing through the risk region is outside the risk region, and a risk of the target trajectory cannot be properly evaluated.

[0009] The present application is completed in consideration of such a situation, and one of the objects is to provide a mobile body control device, a mobile body control method, and a storage medium capable of suppressing an increase in a calculation load and properly evaluating a target trajectory to control a mobile body.

[0010] MEANS FOR SOLVING THE PROBLEMS

[0011] The mobile body control device, the mobile body control method, and the storage medium of the present application adopt the following structure.

[0012] (1) The mobile body control device of one aspect of the present application includes: an object target recognition section that recognizes an object target existing in the vicinity of a mobile body; and a movement plan generation section that generates a movement plan of the mobile body, the movement plan including generating a target track that connects a plurality of track points through which the mobile body should travel, the movement plan generation section generating the target track in such a manner that a line segment connecting the track points adjacent to each other in the traveling direction of the mobile body to each other does not enter a risk region that contains the recognized object target.

[0013] (2) In the aspect of the above (1), the movement plan generation section sets the risk region in the shape of an ellipse.

[0014] (3) In the aspect of the above (2), the movement plan generation section, with respect to the risk region set in the shape of an ellipse, performs a deformation process including reducing the risk region and the line segment in the major axis direction of the ellipse or enlarging the risk region and the line segment in the minor axis direction of the ellipse in such a manner that the ellipse is converted into a circle, evaluates the degree of approach of the target track with respect to the object target based on the result of the deformation process, and generates the target track based on the result of the evaluation.

[0015] (4) In the aspect of the above (3), the movement plan generation section, before performing the deformation process, performs a rotation process that rotates the risk region and the line segment around the center of the ellipse so that the major axis direction and the minor axis direction of the ellipse coincide with axes on an imaginary plane.

[0016] (5) The mobile body control method of another aspect of the present application causes a computer mounted on a mobile body to perform the following processes: recognizing an object target existing in the vicinity of the mobile body; and generating a movement plan of the mobile body, the movement plan including generating a target track that connects a plurality of track points through which the mobile body should travel, the movement plan generation section generating the target track in such a manner that a line segment connecting the track points adjacent to each other in the traveling direction of the mobile body to each other does not enter a risk region that contains the recognized object target.

[0017] (6) Another aspect of the present application is a storage medium storing a program that causes a computer mounted on a mobile body to execute processing of: recognizing an object target existing in the vicinity of the mobile body; and generating a movement plan of the mobile body, the movement plan including generating a target track to be traveled by the mobile body, the target track being formed by connecting a plurality of track points, and in generating the movement plan, the target track is generated in such a manner that a line segment formed by connecting to each other track points adjacent to each other in the traveling direction of the mobile body does not enter a risk area including the recognized object target.

[0018] Effects of Invention

[0019] According to the aspects (1) to (6) described above, it is possible to suppress an increase in the computational load, and to appropriately evaluate the target track to control the mobile body. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a configuration diagram of a vehicle system of a vehicle control device using the embodiment.

[0021] Figure 2 is a functional configuration diagram of the first control section and the second control section.

[0022] Figure 3 is a diagram for explaining a candidate point, a first index, and a second index.

[0023] Figure 4 is a diagram illustrating a distribution P(R) of the first index R, a distribution P(B) of the second index B at the 4-4 line of Figure 3

[0024] Figure 5 is a diagram for explaining a reason for calculating the first index R with respect to the candidate line segment cLK.

[0025] Figure 6 is a diagram for explaining a principle of calculating the first index R with respect to the candidate line segment cLK.

[0026] Figure 7 is a diagram showing an example of the contents of the rotation processing and the deformation processing.

[0027] Figure 8 is a diagram for explaining a condition for determining the flag value Flag(i).

[0028] Figure 9 is a diagram for explaining an example of a calculation method of the second index B.

[0029] Figure 10 is a diagram for explaining a third index (1) thereof.

[0030] Figure 11 ​is a graph for explaining the third index (its 2).

[0031] Figure 12 is a graph illustrating a target trajectory generated with respect to a plurality of object targets.

[0032] Figure 13 is a flowchart showing an example of a flow of processing performed by the first control section 120.

[0033] Figure 14 is a flowchart showing an example of a flow of processing performed by the first control section 120 of the second embodiment.

[0034] Figure 15 is a graph for explaining the processing of the target trajectory generation section 145 of the third embodiment.

[0035] Figure 16 is a flowchart showing an example of a flow of processing performed by the first control section 120 of the third embodiment.

[0036] Figure 17 is a graph showing an example of a hardware structure of the automated driving control device 100 of the embodiment.

[0037] BRIEF DESCRIPTION OF DRAWINGS

[0038] 100 automated driving control device

[0039] 120 first control section

[0040] 130 recognition section

[0041] 132 object target recognition section

[0042] 134 travel lane recognition section

[0043] 140 action plan generation section

[0044] 141 candidate point setting section

[0045] 142 first index derivation section

[0046] 142A rotation and deformation processing section

[0047] 142B index calculation section

[0048] 143 second index derivation section

[0049] 144 third index derivation section

[0050] 145 target trajectory generation section

[0051] 160 second control section DETAILED DESCRIPTION

[0052] Hereinafter, the embodiments of the mobile body control device, the mobile body control method, and the storage medium of the present application will be described with reference to the accompanying drawings. In the following description, a vehicle is exemplified as a representative example of the mobile body, but the mobile body is not limited to the vehicle, and can be applied to all mobile bodies that autonomously move such as micro-movement, robots (including robots having wheels, multi-legged walking robots, and the like), and the like.

[0053] <First Embodiment>

[0054] [Overall Structure]

[0055] Figure 1 is a configuration diagram of a vehicle system of a vehicle control device using the embodiment. The vehicle on which the vehicle system 1 is mounted is, for example, a vehicle of two wheels, three wheels, four wheels, or the like, and a drive source thereof is an internal combustion engine such as a diesel engine, a gasoline engine, an electric motor, or a combination thereof. The electric motor operates using power generated by a generator coupled to the internal combustion engine or power discharged from a secondary battery or a fuel cell.

[0056] The vehicle system 1 is provided with, for example, a camera 10, a radar device 12, a probe 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 operation member 80, an autonomous driving control device 100, a travel drive force output device 200, a brake device 210, and a steering device 220. These devices and apparatuses are connected to each other through a multiplex communication line such as a CAN (Controller Area Network) communication line, a serial communication line, a wireless communication network, or the like. Note that, Figure 1 The configuration shown is merely an example, and a part of the configuration can be omitted, and further another configuration can be added.

[0057] 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 mounted to an arbitrary portion of a vehicle (hereinafter, referred to as the host vehicle M) on which the vehicle system 1 is mounted. In the case of photographing the front, the camera 10 is mounted to the upper portion of the front windshield glass, the back surface of the interior rearview mirror, or the like. The camera 10 repeatedly photographs the periphery of the host vehicle M, for example, periodically. The camera 10 can also be a stereo camera.

[0058] The radar device 12 radiates electric waves such as millimeter waves to the periphery of the host vehicle M, and detects electric waves (reflected waves) reflected by objects to detect at least the positions (distances and directions) of the objects. The radar device 12 is installed at an arbitrary position of the host vehicle M. The radar device 12 can also detect the positions and speeds of objects by an FM-CW (Frequency Modulated Continuous Wave) method.

[0059] The detector 14 is a LIDAR (Light Detection and Ranging). The detector 14 radiates light to the periphery of the host vehicle M, and measures scattered light. The detector 14 detects distances to objects based on times from light emission to light reception. The radiated light is, for example, pulsed laser light. The detector 14 is installed at an arbitrary position of the host vehicle M.

[0060] The object recognition device 16 performs sensor fusion processing on detection results detected by some or all of the camera 10, the radar device 12, and the detector 14 to recognize positions, types, speeds, and the like of objects. The object recognition device 16 outputs the recognition results to the automatic driving control device 100. The object recognition device 16 can output the detection results of the camera 10, the radar device 12, and the detector 14 directly to the automatic driving control device 100. The object recognition device 16 can also be omitted from the vehicle system 1.

[0061] The communication device 20 communicates with other vehicles existing in the periphery of the host vehicle M, or communicates with various server devices via a wireless base station, for example, using a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), or the like.

[0062] The HMI 30 prompts various information to an occupant of the host 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.

[0063] The vehicle sensors 40 include 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 about the vertical axis, a direction sensor that detects the orientation of the host vehicle M, and the like.

[0064] The navigation device 50 includes, for example, a GNSS (Global Navigation Satellite System) receiver 51, a navigation HMI 52, and a route decision section 53. The navigation device 50 holds first map information 54 in a storage device such as a HDD (Hard Disk Drive), a flash memory, or the like. The GNSS receiver 51 determines the position of the host vehicle M based on a signal received from a GNSS satellite. The position of the host vehicle M can also be determined or supplemented by an INS (Inertial Navigation System) that uses the output of the vehicle sensor 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, a button, or the like. The navigation HMI 52 can also be partially or wholly shared with the aforementioned HMI 30. The route decision section 53 determines, for example, a route (hereinafter referred to as an on-map route) from the position of the host vehicle M determined by the GNSS receiver 51 (or an arbitrary position input) to a destination input by an occupant using the navigation HMI 52, with reference to the first map information 54. The first map information 54 is, for example, information that represents the shape of a road by a line that represents the course of the road and nodes connected by the line. The first map information 54 can also include the curvature of the road, POI (Point Of Interest) information, or the like. The on-map route is output to the MPU 60. The navigation device 50 can also perform route guidance using the navigation HMI 52 based on the on-map route. The navigation device 50 can also be implemented by the function of a terminal device such as a smartphone, a tablet terminal, or the like held by an occupant. The navigation device 50 can also transmit the current position and the destination to a navigation server via the communication device 20 and acquire a route equivalent to the on-map route from the navigation server.

[0065] The MPU 60 includes, for example, a recommended lane decision section 61 that holds second map information 62 in a storage device such as a HDD, a flash memory, or the like. The recommended lane decision section 61 divides the on-map route provided from the navigation device 50 into a plurality of blocks (for example, every 100 [m] in the vehicle travel direction) and determines a recommended lane for each block with reference to the second map information 62. The recommended lane decision section 61 makes a determination as to which lane to travel on, for example, the first lane from the left. The recommended lane decision section 61 determines the recommended lane in such a manner that the host vehicle M can travel on a reasonable route for traveling to a branched destination in the case where there is a branch site in the on-map route.

[0066] The second map information 62 is map information of higher precision than the first map information 54. The second map information 62 includes, for example, information of the center of a lane or information of the boundary of a lane, and the like. In addition, road information, traffic restriction information, dwelling information (dwelling, postal code), facility information, telephone number information, and the like can be included in the second map information 62. The second map information 62 can be updated at any time by the communication device 20 communicating with other devices.

[0067] The driving operation member 80 includes, for example, an accelerator pedal, a brake pedal, a shift lever, a steering wheel, a special-shaped steering wheel, a joystick, and other operation members. Sensors that detect an operation amount or the presence or absence of an operation are installed in the driving operation member 80, and the detection results are output to some or all of the automatic driving control device 100, or the travel driving force output device 200, the brake device 210, and the steering device 220.

[0068] 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 section 120 and a second control section 160. The first control section 120 and the second control section 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 can 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), a GPU (Graphics Processing Unit), and the like, and can also be realized by a combination of software and hardware. The program can be stored in advance in a storage device (a storage device including a non-transitory storage medium) such as an HDD, a flash memory, or the like of the automatic driving control device 100, or can be stored in a removable storage medium such as a DVD, a CD-ROM, or the like, and installed in the HDD, the flash memory, or the like of the automatic driving control device 100 by mounting the storage medium (non-transitory storage medium) to a drive device.

[0069] Figure 2Fig. 1 is a functional configuration diagram of the first control unit and the second control unit. The first control unit 120 includes, for example, an identification unit 130 and a travel plan generation unit 140. The first control unit 120 implements, for example, an AI (Artificial Intelligence)-based function and a function based on a pre-provided model in parallel. For example, the function of "identifying an intersection" can be implemented by "performing identification of an intersection based on deep learning or the like and identification based on a pre-provided condition (presence of a signal capable of pattern matching, road marking, or the like), and comprehensively evaluating both by scoring them". Thus, the reliability of automated driving is ensured.

[0070] The identification unit 130 includes, for example, an object target identification unit 132 and a travel lane identification unit 134. The object target identification unit 132 identifies the position and the speed, acceleration, or the like of an object target in the periphery of the host vehicle M based on information input from the camera 10, the radar device 12, and the probe 14 via the object identification device 16. The object target includes both a stationary object and a moving object. The position of the object target is identified, for example, as a position on an absolute coordinate with a representative point (center of gravity, center of the drive shaft, or the like) of the host vehicle M as the origin, and is used in control. The position of the object can be represented by a representative point such as the center of gravity, a corner, or the like of the object, or can be represented by a region that is expressed. The "state" of the object can also include the acceleration, jerk, or "behavior state" (for example, whether or not a lane change is being performed or is to be performed) of the object.

[0071] The travel lane identification unit 134 identifies, for example, the relative position of the lane (travel lane) in which the host vehicle M is traveling with respect to the host vehicle M. For example, the travel lane identification unit 134 identifies the travel lane by comparing the pattern of the road division line (for example, the arrangement of solid lines and broken lines) obtained from the second map information 62 with the pattern of the road division line in the periphery of the host vehicle M identified from the image captured by the camera 10. Note that the identification unit 130 can identify the travel lane by identifying the road division line, the travel road boundary (road boundary) including the shoulder, curb, median, guardrail, or the like, not limited to the road division line. In this identification, the position of the host vehicle M obtained from the navigation device 50 and the processing result of the INS processing can also be added.

[0072] The travel lane recognition unit 134, when recognizing the travel lane, recognizes the position and posture of the host vehicle M with respect to the travel lane. The travel lane recognition unit 134, for example, can recognize the deviation of the reference point of the host vehicle M from the center of the lane and the angle of the advancing direction of the host vehicle M with respect to the line connecting the center of the lane as the relative position and posture of the host vehicle M with respect to the travel lane. Instead, the travel lane recognition unit 134 can recognize the position of the reference point of the host vehicle M with respect to the arbitrary side end portion (road division line or road boundary) of the travel lane as the relative position of the host vehicle M with respect to the travel lane.

[0073] The action plan generation unit 140, for example, has 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 generation 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 can be included in the recognition unit 130.

[0074] The action plan generation unit 140 generates a target trajectory in which the host vehicle M automatically (independently of the operation of the driver) travels in the future in such a manner that the host vehicle M travels on the recommended lane decided by the recommended lane decision unit 61 in principle and can cope with the surrounding situation of the host vehicle M. The target trajectory generation unit 145 generates a 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. Details thereof will be described later.

[0075] The target trajectory, for example, is expressed as a trajectory in which the places (trajectory points) where the representative point (for example, the center of the front end portion, the center of gravity, the center of the rear wheel shaft, or the like) of the host vehicle M should arrive are arranged (connected) in order at regular intervals (for example, every several [m]) in the road length direction. The target velocity and the target acceleration at regular sampling times (for example, every several [sec]) are given to the target trajectory. The trajectory point can also be the position where the host vehicle M should arrive at the sampling time at regular sampling times. In this case, the information of the target velocity and the target acceleration is expressed by the interval of the trajectory points.

[0076] The second control unit 160 controls the travel driving force output device 200, the brake device 210, and the steering device 220 so that the host vehicle M passes through the target trajectory generated by the action plan generation unit 140 at a predetermined time.

[0077] The second control section 160 includes, for example, a retrieval section 162, a speed control section 164, and a steering control section 166. The retrieval section 162 retrieves information of the target trajectory (trajectory point) generated by the travel plan generation section 140 and stores the information in a memory (not shown). The speed control section 164 controls the travel drive force output device 200 or the brake device 210 based on a speed component attached to the target trajectory stored in the memory. The steering control section 166 controls the steering device 220 according to the bending condition of the target trajectory stored in the memory. The processing of the speed control section 164 and the steering control section 166 is realized, for example, by a combination of feedforward control and feedback control. As an example, the steering control section 166 performs a combination of feedforward control corresponding to the curvature of the road ahead of the host vehicle M and feedback control based on the deviation from the target trajectory.

[0078] The travel drive force output device 200 outputs a travel drive force (torque) for vehicle travel to the drive wheels. The travel drive force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, and the like, and an ECU (Electronic Control Unit) that controls them. The ECU controls the above-described structure in accordance with information input from the second control section 160 or information input from the driving operation member 80.

[0079] The brake device 210 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the hydraulic cylinder, and a brake ECU. The brake ECU controls the electric motor in accordance with information input from the second control section 160 or information input from the driving operation member 80 so that a brake torque corresponding to a brake operation is output to each wheel. The brake device 210 can include a mechanism that transmits hydraulic pressure generated by operation of a brake pedal included in the driving operation member 80 to the hydraulic cylinder via a master hydraulic cylinder as a backup. Note that the brake device 210 can also be an electronically controlled hydraulic brake device that controls an actuator in accordance with information input from the second control section 160 to transmit hydraulic pressure of the master hydraulic cylinder to the hydraulic cylinder.

[0080] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor, for example, applies a force to a rack-and-pinion mechanism to change the orientation of the steered wheels. The steering ECU drives the electric motor in accordance with information input from the second control section 160 or information input from the driving operation member 80 to change the orientation of the steered wheels.

[0081] [Generation of Target Trajectory]

[0082] The method of generating the target trajectory will be described in more detail below.

[0083] The first index deriving section 142 derives, for each of a plurality of line segments (hereinafter, referred to as candidate line segments) that connect the candidate points (locations) on the travel direction side of the host vehicle M, a first index R (risk) that becomes a value of negativity as the candidate line segment approaches the object target recognized by the object target recognition section 132, and establishes a correspondence between the first index R and each of the plurality of candidate points. The "establishing a correspondence" means, for example, saving to a storage as information corresponding to each other. In the present embodiment, the value is "negativity" when it is positive, and "positivity" when it is close to zero, and the score described later is set to a value (a preferable value) that becomes more positive as the value is closer to zero, but the relationship can be reversed. Thus, the first index deriving section 142 derives, for each of a plurality of candidate line segments on the travel direction side of the host vehicle M, a first index R that becomes a value that is smaller as the candidate line segment approaches the object target recognized by the object target recognition section 132. The first index deriving section 142 includes a rotation and deformation processing section 142A and an index calculation section 142B. The functions of these auxiliary function sections will be described later.

[0084] The second index deriving section 143 derives, for each of a plurality of candidate points on the travel direction side of the host vehicle M, a second index B (benefit) that becomes a value that is smaller (more positive) as the candidate point approaches a recommended track set in a predetermined rule, and establishes a correspondence between the second index B and each of the plurality of candidate points.

[0085] Figure 3 is a view for explaining the candidate points, the first index, and the second index. In the view, rT is a recommended path. The second index deriving section 143 sets, for example, a center line of a recommended lane (L1 in Figure 3 ) decided by the recommended lane decision section 61 as the recommended path rT. This is not limited thereto, and the second index deriving section 143 can set a line that is biased to either side within the recommended lane as the recommended path rT. In a curve, the recommended path becomes a curved shape. In addition, in a case where the action plan generation section 140 causes the host vehicle M to perform a lane change, a path from a certain lane to an adjacent other lane can be set as the recommended path rT.

[0086] In the view, cK is a candidate point. The candidate point setting section 141 sets a plurality of candidate points cK on a road on the travel direction side of the host vehicle M in a manner that has an extension in each of a road length direction (X direction) and a road width direction (Y direction). A line segment that connects the candidate points cK adjacent to each other in the X direction to each other is a candidate line segment cLK. Hereinafter, the road length direction is referred to as the longitudinal direction, and the road width direction is referred to as the lateral direction. In principle, the candidate point setting section 141 sets a plurality of candidate points cK on the recommended path rT at a predetermined distance from a representative point rM of the host vehicle M (Path x (i), Path y(i) (i = 1, 2,... N), the lateral position of each candidate point cK is changed by a prescribed width scale without omission to set the candidate point cK. The argument i is a value set, for example, in order from near to far from the representative point of the host vehicle M. The candidate point cK (Path x (i), Path y (i) ) and the candidate point cK (Path x (i+1), Path y (i+1) ) is defined as a candidate line segment cLK(i). An orbit obtained by connecting the candidate points cK in the longitudinal direction becomes a candidate (temporary orbit) of the target orbit, and the candidate point cK constituting the determined temporary orbit, that is, the target orbit, becomes an orbit point. The candidate point cK on the recommended path rT is sometimes referred to as a base path. As described later, the setting method of the candidate point cK is not limited to searching in the lateral direction with the base path as a reference, but can be a method of searching with the previous target orbit as a reference.

[0087] In the figure, OB is an object target recognized by the object target recognition section 132, and P(R) indicates the distribution of the first index R. In the figure, a darker portion indicates a larger value. The first index derivation section 142, for example, assumes an ellipse with the representative point rOB of the object target OB as a center, derives the first index R for each candidate line segment cLK(i) (i = 1 ~ n) in such a manner that the place of the closest representative point rOB of the candidate line segment cLK(i) is closer to the center of the ellipse as larger, and farther from the center as smaller. Hereinafter, the coordinates of the representative point rOB are denoted as (Obstacle x , Obstacle y ). The distribution P(R) of the first index R assumes an isohypse of the derived value, and is derived in such a manner that the ellipse with the desired direction as a major axis. The ratio of the major axis to the minor axis of the ellipse is changed, for example, according to the length of the longitudinal direction of the object target OB, the kind of the object target OB, and the like. The outer edge line of the ellipse where the first index R is zero is denoted as eOB. The desired direction is, for example, the assumed moving direction of the object target OB (if it is a vehicle or a bicycle, the direction of the body axis direction or the orientation of the wheel), and if the object target OB is a stationary object, the road extending direction or the advancing direction of the host vehicle M. These "directions" are recognized by the object target recognition section 132, for example. It is not limited thereto, but the desired direction can be determined by an arbitrary method. Note that the distribution P(R) of the first index R can be set to a circular shape of the isohypse of the value, or to another shape, according to the kind of the object target OB.

[0088] In the figure, P(B) represents the distribution of the second index B. In the figure, the darker the color, the larger the value. The second index derivation unit 143 derives, for each candidate point cK, the second index B that becomes more affirmative the closer to the recommended path rT (or the base path).

[0089] Figure 4 is a graph that illustrates the distribution P(R) of the first index R and the distribution P(B) of the second index B at the 4-4 line of Figure 3 . The distribution P(R) of the first index R represents a distribution that has a peak at the position of the center rOB of the object target OB in the lateral direction, becomes smaller the farther from the peak, and becomes zero if sufficiently far. The distribution P(B) of the second index B represents a distribution that becomes zero at the position in the lateral direction of the recommended path rT, becomes larger the farther from the recommended path rT, and becomes a fixed value in the region of the lane L2 adjacent to the recommended lane L1 (may not be so but also becomes larger the farther from the recommended path rT in the region of the lane L2). In addition, the distribution P(B) of the second index B can also be set in such a way as to decrease near the center line of the lane L2.

[0090] Here, the reason why the first index R is not calculated for the candidate point cK but for the candidate line segment cLK is explained. Figure 5 is a graph for explaining the reason why the first index R is calculated for the candidate line segment cLK. In the figure, the i-th candidate point cK(Path x (i), Path x (i)) and the i+1-th candidate point cK(Path x (i+1), Path x (i+1)) are located outside the outer edge line eOB of the ellipse where the first index R is zero, and if it is assumed that the first index R is calculated for the candidate point cK, no penalty of the first index R is given to the candidate of the target trajectory illustrated. However, when the host vehicle M actually travels along the candidate of the target trajectory, it is sometimes the case that the representative point of the host vehicle M enters the inside of the outer edge line eOB of the ellipse from the candidate line segment cLK(i), and an undesirable state occurs. If the interval of the candidate point cK and the trajectory point K is set to be sufficiently narrow, the frequency of occurrence of this problem can be reduced. However, the shorter the interval, the more the load of the computer processing increases, and as a result, the vehicle control can also be delayed. Therefore, development is being promoted on the premise that the interval of the candidate point cK and the trajectory point K is set to be somewhat wide. In the automatic driving control device 100 (vehicle control device) of the embodiment, the above problem is solved by calculating the first index R for the candidate line segment cLK.

[0091] In the case where the first index R is calculated for the candidate line segment cLK, the rule is shown, for example, as follows. Figure 6is a diagram for explaining the principle of calculating the first index R for the candidate line segment cLK. In principle, the first index derivation section 142 sets the value corresponding to the point (closest point) on the candidate line segment cLK that intersects with the innermost contour line when an infinite number of contour lines of an elliptical shape 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 to be closer to 1 as it is closer to the center of the ellipse, and is zero on and outside the outer edge line eOB of the ellipse. This value can be directly calculated by some calculation method, but the geometric calculation becomes cumbersome.

[0092] Therefore, in the embodiment, the rotation and deformation processing section 142A and the index calculation section 142B perform the following processing described below, thereby reducing the calculation load of the first index R. Figure 7 is a diagram showing an example of the contents of the rotation and deformation processing. The rotation and deformation processing section 142A first rotates the ellipse and the candidate line segment cLK around the center (= center of the object target) rOB of the ellipse in such a manner that the major axis and the minor axis of the ellipse set for the object target OB coincide with the two axes in the virtual plane used for the calculation (in the drawing, the same as the XY axes that are the road coordinate axes, but not limited thereto) when calculating the first index R for the object target OB. Next, the rotation and deformation processing section 142A reduces the ellipse and the candidate line segment cLK in the major axis direction (or enlarges the ellipse and the candidate line segment cLK in the minor axis direction) so that the length of the major axis of the ellipse coincides with the length of the minor axis. Thereby, the outer edge line eOB of the ellipse becomes a circular shape. The rotation and deformation processing section 142A also performs processing of enlarging or reducing the outer edge line eOB and the candidate line segment cLK so that the radius of the outer edge line eOB having a circular shape becomes 1. The outer edge line after the rotation, enlargement, or reduction is denoted as eOB*.

[0093] After the above processing, the index calculation section 142B decides the flag value Flag(i) for each candidate line segment cLK(i). Figure 8 is a diagram for explaining the conditions for deciding the flag value Flag(i). Here, the end points of a certain candidate line segment cLK(i) are denoted as A and B, and the center rOB of the object target is denoted as the center point C. The index calculation section 142B sets the flag value Flag(i) to 1 in the case where at least one of the following conditions 1 and 2 is satisfied, and condition 3 is satisfied, and sets the flag value Flag(i) to 0 in the case where condition 3 is not satisfied.

[0094] (Condition 1) The angle φ(V AB (V AC (V AB / V AC), the vector V from the end point B toward the center point C BA BC The angle φ(V BA / V BC ) is an acute angle.

[0095] (Condition 2) At least one of the distance D AC between the end point A and the center point C and the distance D BC between the end point B and the center point C is 1 or less.

[0096] (Condition 3) The distance D CL between the straight line including the candidate line segment cLK(i) and the center point C is 1 or less. The index calculation section 142B calculates the distance D CL based on Equation (1). Hereinafter, the distance D CL related to the candidate line segment cLK(i) is referred to as the distance D CL (i).

[0097] The index calculation section 142B calculates the distance based on Equation (1) and calculates the first index R Path related to the temporary track based on Equation (2). Equations (1), (2) are directed to one object target OB, and the index calculation section 142B calculates the first index R Path_ob1 , R Path_ob2 ,... directed to each object target OB based on Equations (1), (2) in a case where a plurality of object targets OB exist in the vicinity of the temporary track, and adds them to calculate the first index R Path . Note that although the distance D CL (i) is 1 or less, in consideration of the state where the entire candidate line segment cLK(i) is located outside eOB*, if this state, neither Condition 1 nor 2 is satisfied, and thus the term {Flag(i) x D Path (i)} in R CL is zero.

[0098] D CL (i) = {Path x (i) x Path y (i+1) - Path x (i+1) x Path y (i)} / sqrt[{Path x (i+1) - Path x (i)} 2 + {Path y (i+1) - Path y (i)} 2 ]... (1)

[0099] R​Path =∑ i＝1 N {Flag(i)xD CL (i)}…(2)

[0100] Figure 9 is a graph for explaining an example of a calculation method of the second index B. The second index derivation section 143, for example, calculates the square of the distance D rTi between the candidate point cK and the candidate point on the base path corresponding to the position in the longitudinal direction as the second index B with respect to each candidate point cK. The distance D rTi is calculated by formula (3). In the formula, Base x (i) is the X coordinate of the i-th candidate point on the base path, and Base y (i) is the Y coordinate of the i-th candidate point on the base path. Note that, in the case where the candidate point cK is searched in the lateral direction with the candidate point cK on the base path as a reference, Path x (i) - Base x (i) becomes zero. If a certain temporary track is set and the candidate points constituting the temporary track are set as cK(i) (i = 1, 2,..., N), the second index B path related to the temporary track is represented by formula (4).

[0101] D rTi =√{(Path x (i) - Base x (i)) 2 + (Path y (i) - Base y (i)) 2}…(3)

[0102] B Path =∑ i＝1 N {D rTi}…(4)

[0103] Note that, as the calculation procedure including the derivation of the first index R and the second index B, for example, the following two calculation procedures can be considered, but either of the calculation procedures can be adopted. The processing of the first index R Figure 13 described later is based on the idea of Procedure 2.

[0104] (Procedure 1)

[0105] All candidate points are set without omission → the first index R is derived with respect to the line segment connecting all the candidate points in advance, the second index B is derived with respect to all the candidate points, and saved to the memory → a temporary track is set → the first index R and the second index B of the candidate points on the temporary track are read out from the memory.

[0106] (Step 2)

[0107] The candidate point is set → a temporary track is set → a first index R is derived for a line segment connecting the candidate points on the temporary track, and a second index B is derived for the candidate points on the temporary track.

[0108] The third index derivation section 144 derives a third index that evaluates the shape of a temporary track obtained by connecting a plurality of candidate points cK in the longitudinal direction. Also, the target track generation section 145 generates a target track based on the first index R, the second index B, and the third index, to suppress the vehicle M from making an unnecessary sharp turn.

[0109] The third index derivation section derives a third index that evaluates the smoothness of the temporary track, based on some or all of three elements (1) to (3) shown below. In the following description, it is assumed that the third index derivation section derives the third index based on all of the three elements, and the three elements are referred to as third indexes Cl, C2, and C3. Also, the independent variable t that appears means the processing that belongs to the tth control cycle in the process in which each part of the first control section 120 periodically repeats the processing. Hereinafter, the description is made focusing on the processing in which the control cycle is the tth.

[0110] Figure 10 is a diagram for explaining the third index (1).

[0111] (1) The third index derivation section derives a third index Cl that is the sum of squares of distances ΔY1(i-1,i,t) in the lateral direction between the candidate points cK(i,t) and the candidate points cK(i-1,t) in the tth control cycle (this control cycle) for i = 1 to N (Formula (5)). Note that cK(0,t) is set to the representative point rM of the vehicle M, for example. By reducing the third index Cl, it is possible to make the shape of the target track a simple shape in which the change in the lateral direction is small, and to suppress the vehicle M from making a sharp turn.

[0112] C1 =∑ i＝1 N {ΔY1(i-1,i,t) 2}…(5)

[0113] Figure 11 is a diagram for explaining the third index (2).

[0114] (2) The third index derivation section derives, as a third index C2, a square sum of lateral distances ΔY2(i, t-C, t) between positions cK#(i, t-C) on the target track TJ(t-C) at which the longitudinal positions coincide with the candidate point cK(i, t) and the candidate point cK(i, t) for i = 1 ~ N, by comparing the candidate point cK(i, t) in the tth control cycle (this control cycle) with the target track TJ(t-C) generated in the t-Cth control cycle (the control cycle before last time) (Formula (6)). Note that the target track TJ(t-C) is strictly a set of track points K, and thus, in this case, a polygonal line obtained by connecting the track points K that are continuous in the longitudinal direction is referred to as the target track TJ(t-C). C is a natural number of 1 or more. By reducing the third index C2, it is possible to suppress the temporal change of the target track that is repeatedly generated over time, and to suppress the sharp turn of the host vehicle M. Figure 11 In the example of Formula (6), C = 1. By reducing the third index C2, it is possible to suppress the temporal change of the target track that is repeatedly generated over time, and to suppress the sharp turn of the host vehicle M.

[0115] C2 = Σ i＝1 N {ΔY2(i-1, i-C, t) 2}…(6)

[0116] The above will be described again with reference to Figure 10

[0117] (3) The third index derivation section derives, as a third index C3, a square of an angle θ(V → MK(p，t) , V → MK(p，t-E) ) formed by a vector V → MK(p，t-E) from the representative point rM of the host vehicle M toward the pth candidate point cK(p, t) in the tth control cycle (this control cycle) and a vector V → MK(p，t) from the representative point rM of the host vehicle M toward the pth candidate point cK(p, t-E) in the t-Eth control cycle (the control cycle before last time) (Formula (7)). Note that, although the vectors can be expressed as "straight lines", in this case, the vectors are expressed as vectors. E is a natural number of 1 or more. By reducing the third index C3, it is possible to suppress the temporal change of the future position in the target track that particularly affects the behavior of the host vehicle M, and to suppress the sharp turn of the host vehicle M.

[0118] C3 = θ 2 …(7)

[0119] ​The target trajectory generation section 145 generates a target trajectory based on the first index R, the second index B, and the third index. For example, the target trajectory generation section 145 derives a score by inputting the first index R, the second index B, and the third index to a function, and sets a plurality of candidate points cK of which a combination of values that become the score is the smallest to a plurality of trajectory points K that constitute the target trajectory. The score is derived by calculating a weighted sum with respect to the first index R, the second index B, and the third index C1, C2, C3, for example, as represented by Expression (8). Instead of this, a part or all of the first index R, the second index B, and the third index can be multiplied by each other or the like, and the score can be derived in an arbitrary method as long as the gist of the application is not changed. "As long as the gist of the application is not changed" means that as long as the tendency that the smaller the first index R is, the smaller the score is, the smaller the second index B is, the smaller the score is, and the smaller the third index is, the smaller the score is is maintained. w1, w2, w3, w4, and w5 are each an arbitrary positive value.

[0120] Score (t) = w1 x R Path + w2 x B path + w3 x C1 + w4 x C2 + w5 x C3... (8)

[0121] By this processing, compared to a case where the target trajectory is generated based on only the first index R and the second index B, it is possible to reduce the probability that the host vehicle M makes a sharp turn. In addition, since the processing of generating the target trajectory based on only the first index R and the second index B is not separated from the processing of evaluating the shape of the trajectory, it is possible to flexibly generate the target trajectory in a variety of scenes.

[0122] Here, the object target is not necessarily stationary, and an object such as a bicycle or a pedestrian that moves at a low speed compared to the speed of the host vehicle M also belongs to the object target. In this case, the first index derivation section 142 can derive the first index R taking the passage of time into consideration.

[0123] Figure 12 is a graph that illustrates a target trajectory generated with respect to a plurality of object targets. In the graph, OB2 is a second object target (bicycle), P(R) OB1 is a distribution of the first index R corresponding to the first object target OB1, P(R) OB2 is a distribution of the second index R corresponding to the second object target OB2. P(R) OB1 takes the shape of an ellipse centered on the representative point rOB1 of the object target OB1, and with respect to this, P(R) OB2The distribution of the first index R is generated as described above, and the distribution of the first index R is adjusted in accordance with the movement of the representative point rOB2 of the object target OB2. The distribution of the first index R is adjusted in accordance with the movement of the representative point rOB2 of the object target OB2, and the size of the distribution itself is also different, but the first index deriving section 142 adjusts the size of the distribution, for example, on the basis of the size of the object target OB and the like. The first index deriving section 142 estimates the movement path of the representative point rOB2 as, for example, a movement path along the outer edge of the distribution of the first index R related to the first object target OB1, and estimates the position of the representative point rOB2 in the future on the basis of the speed of the object target OB2 at present. Also, the distribution P(R) of the first index R is set for each position of the representative point rOB2 in the future. OB2，1 OB2，2 OB2，3 OB2，4 OB2，j OB2，j The argument j of P(R) is a concept of time having the same period as j of the control cycle. That is, the argument j indicates the position of the object target OB2 at the time point after how many cycles the control cycle is.

[0124] The first index deriving section 142 can generate the distribution P(R) of the first index R as described above, and adjust the distribution of the first index R in accordance with the movement of the representative point rOB2 of the object target OB2. The first index deriving section 142 estimates the movement path of the representative point rOB2 as, for example, a movement path along the outer edge of the distribution of the first index R related to the first object target OB1, and estimates the position of the representative point rOB2 in the future on the basis of the speed of the object target OB2 at present. Also, the distribution P(R) of the first index R is set for each position of the representative point rOB2 in the future. OB2，1 OB2，2 OB2，3 OB2，4 OB2，j The distribution of the first index R is generated as described above, and the distribution of the first index R is adjusted in accordance with the movement of the representative point rOB2 of the object target OB2. The distribution of the first index R is adjusted in accordance with the movement of the representative point rOB2 of the object target OB2, and the size of the distribution itself is also different, but the first index deriving section 142 adjusts the size of the distribution, for example, on the basis of the size of the object target OB and the like. The first index deriving section 142 estimates the movement path of the representative point rOB2 as, for example, a movement path along the outer edge of the distribution of the first index R related to the first object target OB1, and estimates the position of the representative point rOB2 in the future on the basis of the speed of the object target OB2 at present. Also, the distribution P(R) of the first index R is set for each position of the representative point rOB2 in the future. OB2，j The distribution of the first index R is generated as described above, and the distribution of the first index R is adjusted in accordance with the movement of the representative point rOB2 of the object target OB2. The distribution of the first index R is adjusted in accordance with the movement of the representative point rOB2 of the object target OB2, and the size of the distribution itself is also different, but the first index deriving section 142 adjusts the size of the distribution, for example, on the basis of the size of the object target OB and the like. The first index deriving section 142 estimates the movement path of the representative point rOB2 as, for example, a movement path along the outer edge of the distribution of the first index R related to the first object target OB1, and estimates the position of the representative point rOB2 in the future on the basis of the speed of the object target OB2 at present. Also, the distribution P(R) of the first index R is set for each position of the representative point rOB2 in the future.

[0125] Figure 13 is a flowchart showing an example of the flow of the processing performed by the first control section 120. The processing of this flowchart is repeatedly performed for each of the control cycles described above.

[0126] First, the object target recognition section 132 recognizes the object target on the advancing direction side of the host vehicle M (step S100), and the travel lane recognition section 134 recognizes the relative position of the travel lane with respect to the host vehicle M (step S102).

[0127] Next, the candidate point setting section 141 sets the candidate points (step S104), and sets a plurality of temporary tracks obtained by connecting the candidate points in the longitudinal direction (step S106).​​​​​​​​​

[0128] Next, the first index deriving section 142, the second index deriving section 143, and the third index deriving section 144 derive the first index R Path、 the second index B Path the third index C1 to C3 (step S108)

[0129] Next, the target track generating section 145 calculates the score for each of the temporary tracks (step S110), and sets the temporary track with the smallest score as the target track (step S112).

[0130] Instead of selecting the temporary track to calculate the score as described above, the autonomous driving control device 100 can also generate the target track by simultaneous perturbation optimization (SPSA: Simultaneous Perturbation Stochastic Approximation). Simultaneous perturbation optimization is a kind of probabilistic gradient method using random variables. In this case, the autonomous driving control device 100 can generate the target track more quickly than by selecting the temporary track without omission by applying the method of calculating the score described above to simultaneous perturbation optimization.

[0131] In addition, in the above description, the first index, the second index, and the third index are calculated and the target track is generated by integrating them, but as long as the first index is calculated by the above-described method, the processing equivalent to the second index and the third index can be omitted, changed, or the like as appropriate.

[0132] The autonomous driving control device 100 according to the first embodiment described above includes an object target recognition section 132 that recognizes an object target existing in the periphery of the host vehicle M, and an action plan generating section 140 that generates an action plan of the host vehicle M, the action plan including generating a target track in which a plurality of track points are connected, the action plan generating section 140 generating the target track so that a line segment in which track points adjacent to each other in the traveling direction of the host vehicle M are connected to each other does not enter a risk area including the recognized object target, and thus it is possible to suppress an increase in the calculation load and to appropriately evaluate the target track to control the vehicle.

[0133] <Second Embodiment>

[0134] Hereinafter, the second embodiment will be described. In the first embodiment, no particular limitation is placed on the setting of the temporary track, but in the second embodiment, the distance ΔY1 (see FIG. 6) in the lateral direction between the candidate points cK adjacent to each other in the longitudinal direction is set to be equal to or greater than a predetermined value (for example, 1 m) and less than or equal to a predetermined value (for example, 10 m). Figure 10) set an upper limit, and even if there is one case where ΔY1 exceeds the upper limit, the temporary track is excluded from the candidates of the target track. Here, the distance is set as an element that does not have a direction. That is, as a pre-process, a process of excluding from the calculation object of the score the temporary track in which there is a portion where ΔY1 exceeds the threshold ThY is performed. Thereby, it is possible to further reduce the probability that the host vehicle M makes a sharp turn.

[0135] Figure 14 is a flowchart showing an example of a flow of processing performed by the first control section 120 of the second embodiment. The processing of this flowchart is repeatedly performed for each control cycle as described above. Note that the processing of steps S100 to S106 and the processing of steps S108 to S112 are the same as the processing described in the first embodiment, and thus the description is omitted. Figure 13

[0136] After the processing of step S106, the candidate point setting section 141 excludes from the temporary track in which the candidate points are connected in the longitudinal direction the temporary track in which there is a portion where ΔY1 exceeds the threshold ThY (step S107).

[0137] Note that, instead of first setting the temporary track without omission and excluding the temporary track in which at least one ΔY1 exceeds the threshold ThY, it is also possible to limit the search range (search angle) in such a way that ΔY1 does not exceed the threshold ThY when searching for the temporary track sequentially from the end portion in the longitudinal direction.

[0138] According to the second embodiment described above, in addition to the same effects as the first embodiment, it is possible to further reduce the probability that the host vehicle M makes a sharp turn. In addition, since the processing of calculating the score is performed after the temporary tracks are screened, it is possible to reduce the processing load.

[0139] <Third Embodiment>

[0140] Hereinafter, the third embodiment will be described. In the third embodiment, the target track generation section 145, with respect to the target track selected based on the score, confirms whether there is a portion where ΔY1 exceeds the threshold ThY, and in the case where there is a portion where ΔY1 exceeds the threshold ThY, corrects the target track in such a way that ΔY1 becomes equal to or less than the threshold ThY.

[0141] Figure 15 is a diagram for describing the processing of the target track generation section 145 of the third embodiment. In the diagram, the qth track point K(q, t) has a relationship in which the distance ΔY1 in the lateral direction exceeds the threshold ThY with respect to the (q-1)th track point K(q-1, t). Note that since the target track has already been generated, it is referred to as a "track point K" rather than a "candidate point cK". ΔY1 in the third embodiment is the distance when the candidate point is referred to as a track point.​

[0142] In this case, the target trajectory generation section 145, for example, selects the object target closest to the track point K to correct the position of the qth track point K(q, t) or the (q-1)th track point K(q-1, t) in the lateral direction in such a way that it departs from the representative point of the object target. In Figure 15 In the example, the representative point rOB of the object target OB is observed from the track point K(q) to be on the left side, and therefore the target trajectory generation section 145 moves the position of the (q-1)th track point K(q-1, t) to the right side, which is the side that departs from the representative point rOB of the object target OB. The target trajectory generation section 145, for example, sets the amount of movement to be the minimum amount of movement that does not exceed the threshold value ThY. In the case where the result of this processing is that the distance in the lateral direction between the (q-1)th track point K(q-1, t) and the (q-2)th track point K(q-2, t) becomes to exceed the threshold value ThY, the (q-2)th track point K(q-2, t) is moved to the right side. The target trajectory generation section 145 of the third embodiment performs such processing in a wave-like manner until all of ΔY1 becomes to be equal to or less than the threshold value ThY.

[0143] In this processing, it is necessary to determine the track point K at which ΔY1 is initially confirmed. This is because, if the track point K is not determined, it is possible that the processing spreads from both sides and does not converge. For example, the target trajectory generation section 145 of the third embodiment sets the track point K (the uth track point K(u, t) in Figure 15 ) having the largest amount of displacement in the lateral direction from the base path as the search start point, and confirms whether or not ΔY1 exceeds the threshold value ThY from the search start point toward both the preceding side (the side close to the host vehicle M) and the distal side (the side away from the host vehicle M).

[0144] Figure 16 is an example of a flowchart showing the flow of processing performed by the first control section 120 of the third embodiment. The processing of this flowchart is repeatedly performed for each of the aforementioned control cycles. Note that the processing of steps S100 to S112 is the same as the processing explained in Figure 13 , and therefore the explanation is omitted.

[0145] When the target trajectory is generated, the target trajectory generation section 145 sets the trajectory point farthest from the representative point rM of the host vehicle M in the lateral direction as the search start point (step S118). Then, it is sequentially determined whether there is a portion where ΔYl exceeds the threshold value ThY toward the front side and the rear side of the search start point, respectively (step S120). In the case where it is determined that there is a portion where ΔYl exceeds the threshold value ThY, the target trajectory generation section 145 corrects the target trajectory by moving either trajectory point of the portion to the opposite side of the closest object target (step S122). Then, the corrected trajectory point is set as the search start point (step S124), and the process of step S120 is performed again (step S120). However, the search to the opposite side is not performed with respect to the front side and the rear side. If there is no longer a portion where ΔYl exceeds the threshold value ThY, the process of one cycle of the present flowchart ends.

[0146] According to the third embodiment described above, in addition to the same effects as the first embodiment, the probability of the host vehicle M making a sharp turn can be further reduced.

[0147] [Hardware structure]

[0148] Figure 17 is a diagram showing an example of a hardware structure of the automatic driving control device 100 of the embodiment. As shown in the figure, the automatic driving control device 100 is a structure in which a communication controller 100-1, a CPU 100-2, a RAM (Random Access Memory) 100-3 used as a work memory, a ROM (Read Only Memory) 100-4 that stores a boot program and the like, a storage device 100-5 such as a flash memory or a HDD (Hard Disk Drive), a drive device 100-6, and the like are connected to each other through an internal bus or a dedicated communication line. The communication controller 100-1 performs communication with constituent elements other than the automatic driving control device 100. A program 100-5a executed by the CPU 100-2 is stored in the storage device 100-5. The program is expanded to the RAM 100-3 by a DMA (Direct Memory Access) controller (not shown) or the like, and is executed by the CPU 100-2. Thereby, a part or all of the first control section 120 and the second control section 160 are realized.

[0149] The embodiment described above can be expressed as follows.

[0150] The vehicle control device is configured to have:

[0151] a storage device that stores a program; and

[0152] a hardware processor,

[0153] The following processing is performed by executing a program stored in the storage device by the hardware processor:

[0154] identifying an object target existing in the periphery of the vehicle; and

[0155] generating a movement plan of the vehicle, the movement plan including generating a target track connecting a plurality of track points to be traveled by the vehicle,

[0156] in generating the movement plan, the target track is generated in such a manner that a line segment connecting track points adjacent to each other in the traveling direction of the vehicle to each other does not enter a risk area including the identified object target.

[0157] The above describes specific embodiments of the present application using the embodiments, but the present application is not limited at all by such embodiments, and various modifications and substitutions can be applied within the scope of the gist of the present application.

Claims

1. A mobile body control device, wherein, The moving body control device includes: An object target recognition unit that identifies object targets existing around a moving object; and An action plan generation unit generates an action plan for the mobile entity, the action plan including generating a target track formed by connecting multiple track points that the mobile entity should travel on. The action plan generation unit performs a risk assessment based on the distance between the center of the risk area containing the identified target object and the line segment connecting adjacent track points along the direction of travel of the moving body, and generates the target track. The action plan generation unit defines the risk area in an elliptical shape. The action plan generation unit deforms the risk area, which is defined in the shape of an ellipse, by converting the ellipse into a circle. This deformation includes either reducing the risk area and line segments along the major axis of the ellipse or enlarging them along the minor axis. Based on the result of this deformation, the unit evaluates the proximity of the target trajectory to the target object and generates the target trajectory based on the evaluation result. Before performing the deformation process, the action plan generation unit performs a rotation process that rotates the risk area and the line segment around the center of the ellipse so that the major and minor axes of the ellipse are aligned with the axes on the imaginary plane. The action plan generation unit assesses a risk on the line segment if at least one of conditions 1 and 2 is met, and condition 3 is also met. This achieves a risk assessment between the ellipse and the line segment through a risk assessment between the circle and the line segment. Condition 1 is that the angles formed by the vector from one endpoint of the line segment toward the other endpoint and the vector from the one endpoint toward the center point of the risk area, and the angles formed by the vector from the other endpoint toward the one endpoint and the vector from the other endpoint toward the center point, are both acute angles. Condition 2 is that at least one of the distances between one endpoint and the center point and the distances between the other endpoint and the center point is below a specified value. Condition 3 is that the distance between the straight line containing the line segment and the center point is below a specified value.

2. A method for controlling a moving body, wherein, The mobile body control method causes a computer mounted on the mobile body to perform the following processing: Identify object targets existing in the vicinity of the moving body; and Generate a movement plan for the mobile entity, the movement plan including generating a target track that the mobile entity should travel on, consisting of connecting multiple track points. When generating the action plan, for the line segment formed by connecting adjacent track points in the direction of travel of the moving body, a risk assessment is performed based on the distance between the center of the risk area containing the identified object target and the line segment, and the target track is generated. The risk area is defined in the shape of an ellipse. For the risk area defined in the shape of an ellipse, a deformation process is performed to convert the ellipse into a circle. This deformation process includes either reducing the risk area and the line segments along the major axis of the ellipse or enlarging the risk area and the line segments along the minor axis of the ellipse. Based on the result of this deformation process, the proximity of the target trajectory to the object target is evaluated, and the target trajectory is generated based on the evaluation result. Before performing the deformation process, a rotation process is performed to rotate the risk area and the line segment around the center of the ellipse so that the major and minor axes of the ellipse are aligned with the axes on the imaginary plane. If at least one of conditions 1 and 2 is met, and condition 3 is also met, the line segment is assessed as having a risk. Thus, the risk assessment between the circle and the line segment is achieved through the risk assessment between the circle and the line segment. Condition 1 is that the angles formed by the vector from one endpoint of the line segment toward the other endpoint and the vector from the one endpoint toward the center point of the risk area, and the angles formed by the vector from the other endpoint toward the one endpoint and the vector from the other endpoint toward the center point, are both acute angles. Condition 2 is that at least one of the distances between one endpoint and the center point and the distances between the other endpoint and the center point is below a specified value. Condition 3 is that the distance between the straight line containing the line segment and the center point is below a specified value.

3. A storage medium, wherein, The storage medium stores a program that causes a computer mounted on the mobile device to perform the following processing: Identify object targets existing in the vicinity of the moving body; and Generate a movement plan for the mobile entity, the movement plan including generating a target track that the mobile entity should travel on, consisting of connecting multiple track points. When generating the action plan, for the line segment formed by connecting adjacent track points in the direction of travel of the moving body, a risk assessment is performed based on the distance between the center of the risk area containing the identified object target and the line segment, and the target track is generated. The risk area is defined in the shape of an ellipse. For the risk area defined in the shape of an ellipse, a deformation process is performed to convert the ellipse into a circle. This deformation process includes either reducing the risk area and the line segments along the major axis of the ellipse or enlarging the risk area and the line segments along the minor axis of the ellipse. Based on the result of this deformation process, the proximity of the target trajectory to the object target is evaluated, and the target trajectory is generated based on the evaluation result. Before performing the deformation process, a rotation process is performed to rotate the risk area and the line segment around the center of the ellipse so that the major and minor axes of the ellipse are aligned with the axes on the imaginary plane. If at least one of conditions 1 and 2 is met, and condition 3 is also met, the line segment is assessed as having a risk. Thus, the risk assessment between the circle and the line segment is achieved through the risk assessment between the circle and the line segment. Condition 1 is that the angles formed by the vector from one endpoint of the line segment toward the other endpoint and the vector from the one endpoint toward the center point of the risk area, and the angles formed by the vector from the other endpoint toward the one endpoint and the vector from the other endpoint toward the center point, are both acute angles. Condition 2 is that at least one of the distances between one endpoint and the center point and the distances between the other endpoint and the center point is below a specified value. Condition 3 is that the distance between the straight line containing the line segment and the center point is below a specified value.

Images