Vehicle control device and vehicle control method

Abstract

This will improve the efficiency and convenience of automated vehicle driving and parking when passing other vehicles and parking. [Solution] The vehicle control device 1 includes a candidate evacuation position generation unit 601 that generates candidate evacuation positions, which are candidates for positions where the vehicle will evacuate, based on the predicted results of the position of the vehicle and the routes of other vehicles; a candidate parking position generation unit 602 that generates candidate parking positions, which are candidates for parking positions where the vehicle will park; a candidate evacuation position determination unit 603 that determines a candidate evacuation position for the vehicle based on the candidate evacuation positions and the candidate parking positions; a candidate route generation unit 604 that generates candidate routes that are candidates for routes from the position of the vehicle to the candidate parking positions via the candidate evacuation positions; an acceptance judgment unit 605 that judges whether or not to accept the selection of a parking position from the occupant of the vehicle at the evacuation position; and an occupant cooperative trajectory planning unit 606 that plans the trajectory of the vehicle based on the judgment result by the acceptance judgment unit.

Description

[Technical Field]

[0001] The present invention relates to a vehicle control device and a vehicle control method. [Background technology]

[0002] In recent years, the development of autonomous driving technology for automobiles and other vehicles has progressed. Autonomous driving requires an appropriate road width. However, roads on which vehicles travel are not always of an appropriate width. For example, on narrow roads where it is difficult for the host vehicle to pass oncoming vehicles, a different control method than normal driving is required to move the host vehicle to a location where passing is possible. Furthermore, in parking lots exceeding a certain size, cooperative driving control is required to efficiently manage the movement of surrounding vehicles and the use of parking spaces. In addition to situations where an oncoming vehicle must pass on a narrow road, other situations are also possible, such as when the host vehicle waits for an oncoming vehicle to enter a parking space, or when a parked vehicle must park or wait for the parked vehicle to exit a parking space. In these situations, vehicles must communicate appropriately with each other to efficiently and safely pass each other and enter and exit parking spaces. For example, Patent Document 1 discloses a technology for planning the actions of a vehicle, such as starting, stopping, and direction of travel, in order to control the vehicle to return to the entrance of a road where passing is possible on a road where there is no evacuation space between the vehicle and an oncoming vehicle.

[0003] Patent Document 1 describes an information processing device that "includes a map generation unit that generates map data around the vehicle and updates the map data as the vehicle moves, and an evacuation space detection unit that detects evacuation spaces where the vehicle can escape based on the map data and generates evacuation space information, which is information about the detected evacuation spaces and is used to set an evacuation route for the vehicle to escape in order to pass an oncoming vehicle." [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-151177 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in conventional methods, when automated driving to pass other vehicles on narrow roads in urban areas or automated parking assistance in parking lots, the driving route changes during the passing process due to a change in the intention of the oncoming vehicle or a prediction error in the behavior of the oncoming vehicle predicted by the vehicle itself. The change in driving route reduces the efficiency of the automated driving or automatic parking and stopping, and causes problems such as a decrease in convenience.

[0006] The present invention has been made to solve the above problems, and an object of the present invention is to improve the efficiency and convenience of automatic vehicle driving and automatic parking and stopping when passing each other, parking, stopping, etc. [Means for solving the problem]

[0007] The vehicle control device of the present invention includes an evacuation position candidate generation unit that generates evacuation position candidate locations, which are candidate locations for the vehicle to evacuate, based on the predicted results of the position of the vehicle and the routes of other vehicles; a parking position candidate generation unit that generates parking position candidate locations, which are candidate parking positions for the vehicle to park or stop; an evacuation position determination unit that determines an evacuation position for the vehicle based on the evacuation position candidate locations and the parking position candidate locations; a route candidate generation unit that generates route candidate locations, which are candidate routes from the position of the vehicle to the parking position candidate locations via the evacuation positions; an acceptance determination unit that determines whether or not to accept the selection of a parking position from an occupant of the vehicle at the evacuation position; and an occupant cooperative trajectory planning unit that plans the trajectory of the vehicle based on the determination result by the acceptance determination unit. The above vehicle control device is one aspect of the present invention, and a vehicle control method reflecting one aspect of the present invention is configured in the same manner as the above vehicle control device. [Effects of the Invention]

[0008] According to the present invention having the above configuration, it is possible to improve the efficiency and convenience of automatic vehicle driving and automatic parking and stopping when passing each other, parking, stopping, etc. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram showing an example of the configuration of a driving system and sensors of a vehicle equipped with a vehicle control device according to a first embodiment of the present invention. [Figure 2] 1 is a block diagram showing an example of a functional configuration of a vehicle control device according to a first embodiment of the present invention. [Figure 3] 1 is a block diagram showing an example of the hardware configuration of a vehicle control device according to a first embodiment of the present invention. [Figure 4] 2 is a block diagram showing an example of the functional configuration of a risk map generating unit of the vehicle control device according to the first embodiment of the present invention. FIG. [Figure 5] 5 is a flowchart showing the procedure of a delay risk map generation process in the vehicle control device according to the first embodiment of the present invention. [Figure 6] 3A and 3B are diagrams showing an example of a cooperative action plan and a congestion risk map in the vehicle control device according to the first embodiment of the present invention. [Figure 7] 2 is a block diagram showing an example of the functional configuration of an automatic driving planning unit of the vehicle control device according to the first embodiment of the present invention. FIG. [Figure 8] 2 is a block diagram showing an example of the functional configuration of a driving mode management unit of the vehicle control device according to the first embodiment of the present invention. FIG. [Figure 9] 2 is a block diagram showing an example of the functional configuration of an occupant collaborative trajectory generation unit of the vehicle control device according to the first embodiment of the present invention. FIG. [Figure 10] 5 is a flowchart showing the procedure of a process for generating candidate escape positions in the vehicle control device according to the first embodiment of the present invention. [Figure 11] 3 is a diagram for explaining the process of generating candidate escape positions in the vehicle control device according to the first embodiment of the present invention. FIG. [Figure 12] 4 is a flowchart showing the procedure of a parking / stopping position candidate generation process in the vehicle control device according to the first embodiment of the present invention. [Figure 13] 3 is a diagram for explaining a method for generating parking / stopping position candidates in the vehicle control device according to the first embodiment of the present invention. FIG. [Figure 14] 5 is a flowchart showing the procedure of a process for determining a retreat position in the vehicle control device according to the first embodiment of the present invention. [Figure 15] 4 is a flowchart showing the procedure of a route candidate generation process in the vehicle control device according to the first embodiment of the present invention. [Figure 16] FIG. 2 is a diagram for explaining a method for generating route candidates in the vehicle control device according to the first embodiment of the present invention. [Figure 17] 5 is a flowchart showing the procedure of a process for determining whether or not a parking position selection is accepted in the vehicle control device according to the first embodiment of the present invention. [Figure 18] 5 is a flowchart showing the procedure of an occupant collaborative trajectory planning process in the vehicle control device according to the first embodiment of the present invention. [Figure 19] 3 is a diagram showing an example of a display of an HMI when a parking / stopping position is selected in the vehicle control device according to the first embodiment of the present invention. FIG. [Figure 20] FIG. 10 is a diagram showing an example of a cooperative behavior trajectory of the vehicle and a vehicle that requires cooperative behavior when the vehicle does not accept or determine the selection of a parking position from the occupant. [Figure 21] FIG. 10 is a diagram showing an example of a traveling speed at which a passenger in the vehicle feels uneasy or uncomfortable; [Figure 22] 3 is a diagram showing an example of a cooperative action route of the vehicle when the vehicle control device according to the first embodiment of the present invention performs acceptance determination of a parking / stopping position selection. FIG. [Figure 23] 3 is a diagram showing an example of the traveling speed of the host vehicle at which the vehicle control device according to the first embodiment of the present invention can reduce discomfort felt by the occupants of the host vehicle. FIG. [Figure 24] FIG. 10 is a block diagram showing an example of the configuration of an occupant collaborative trajectory generation unit of a vehicle control device according to a second embodiment of the present invention. [Figure 25] 10 is a flowchart showing the procedure of a certainty factor calculation process in a vehicle control device according to a second embodiment of the present invention. [Figure 26] 10 is a flowchart showing the procedure of a process for determining whether or not a parking position selection is accepted in a vehicle control device according to a second embodiment of the present invention. [Figure 27] 10 is a diagram showing an example of traveling of the host vehicle when a vehicle control device according to a second embodiment of the present invention performs acceptance determination of a parking / stopping position selection. FIG. [Figure 28] FIG. 10 is a diagram for explaining adjustment of a traveling speed based on a confidence factor in a vehicle control device according to a second embodiment of the present invention. [Figure 29] FIG. 10 is a diagram showing a scene in which cooperation with surrounding vehicles is performed according to an application example of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functions or configurations are designated by the same reference numerals, and redundant description will be omitted. The present invention is applicable to, for example, a computing device for vehicle control capable of communicating with an on-board ECU (Electronic Control Unit) for an Advanced Driver Assistance System (ADAS) or Autonomous Driving (AD).

[0011] First Embodiment First, the configuration of the driving system and sensors of a vehicle equipped with a vehicle control device according to a first embodiment of the present invention will be described. Fig. 1 is a diagram showing an example of the configuration of the driving system and sensors of a vehicle 100 equipped with a vehicle control device 1 according to this embodiment.

[0012] The vehicle 100 can perform autonomous driving under the control of the vehicle control device 1. As shown in FIG. 1 , the vehicle 100 has a left front wheel 101FL, a right front wheel 101FR, a left rear wheel 101RL, and a right rear wheel 101RR. Hereinafter, when the left front wheel 101FL, the right front wheel 101FR, the left rear wheel 101RL, and the right rear wheel 101RR are not distinguished from one another, they will be collectively referred to as "each wheel." The vehicle 100 is also equipped with a forward recognition sensor 2, a left side recognition sensor 3, a right side recognition sensor 4, and a rear recognition sensor 5 as sensors for recognizing the external world. Hereinafter, when the forward recognition sensor 2, the left side recognition sensor 3, the right side recognition sensor 4, and the rear recognition sensor 5 are not distinguished from one another, they will be collectively referred to as "each sensor." Each sensor detects various types of external information, such as the relative distance and relative speed between the vehicle and surrounding vehicles. Each sensor supplies the detected external information to the vehicle control device 1 as a detection signal. For example, a camera can be used as each sensor for recognizing the external world. Note that the sensor configuration shown in Fig. 1 is an example and is not limited to the example shown in Fig. 1. The type of sensor may also be various sensors such as an ultrasonic sensor, a stereo camera, an infrared camera, a radar, or a LiDAR, or a combination of these sensors.

[0013] The vehicle control device 1 calculates command values ​​for the steering control mechanism 10, the brake control mechanism 13, and the throttle control mechanism 20 to control the traveling direction of the vehicle 100 based on external information detected by each sensor. The vehicle 100 also includes a steering control device 8 that controls the steering control mechanism 10 based on the command value from the vehicle control device 1. The vehicle 100 also includes a braking control device 15 that controls the brake control mechanism 13 to adjust the braking force distribution to each wheel based on the command value from the vehicle control device 1. The vehicle 100 also includes an acceleration control device 19 that controls the throttle control mechanism 20 to adjust the torque output of the engine based on the command value from the vehicle control device 1, and a display device 24 that displays the driving plan of the vehicle 100 and predicted behavior of nearby moving objects. The vehicle 100 also includes a communication device 23 that performs road-to-vehicle or vehicle-to-vehicle communication.

[0014] Next, a configuration for operating the brakes of the vehicle 100 will be described. As shown in FIG. 3 (described later), the vehicle control device 1 is configured with an arithmetic processing device 210 (an example of a computer) equipped with a CPU (Central Processing Unit), memory, etc. A program for performing vehicle driving control processing is stored in the vehicle control device 1, and the vehicle control device 1 generates a driving plan by executing the program. The vehicle control device 1 calculates command values ​​for each control mechanism for controlling vehicle driving in accordance with the generated driving plan, namely, a steering control mechanism 10, a brake control mechanism 13, and a throttle control mechanism 20. Hereinafter, when the control mechanisms are not distinguished from one another, they will be referred to as "actuators." The respective control devices for each actuator, namely, a steering control device 8, a braking control device 15, and an acceleration control device 19, receive command values ​​from the vehicle control device 1 and control the actuators based on the received command values.

[0015] When a driver is driving the vehicle 100, the force generated by depressing the brake pedal 12 is boosted by a brake booster (not shown), and a corresponding hydraulic pressure is generated by a master cylinder (not shown). The generated hydraulic pressure is supplied to wheel cylinders 16FL, 16FR, 16RL, and 16RR arranged on each wheel via a brake control mechanism 13.

[0016] Wheel cylinders 16FL-16RR are composed of cylinders, pistons, pads, etc. The pistons are propelled by hydraulic fluid supplied from master cylinder 9, and pads connected to the pistons are pressed against disc rotors. The disc rotors rotate together with the wheels that make up each wheel. Therefore, the braking torque acting on the disc rotors becomes a braking force acting between the wheels and the road surface. With the above configuration, braking force can be generated on each wheel in response to the driver's brake pedal operation.

[0017] The braking control device 15, like the vehicle control device 1, is configured as an arithmetic processing device 210 shown in Fig. 3 of the drawings. The braking control device 15 receives sensor signals from a combined sensor 14 capable of detecting longitudinal acceleration, lateral acceleration, and yaw rate, and from wheel speed sensors 11FL to 11RR installed on each wheel. The braking control device 15 also receives a brake command from the vehicle control device 1 and a sensor signal from a steering wheel angle detection device 21 via a steering control device 8, which will be described later. The braking control device 15 is also connected to a brake control mechanism 13 having a pump and a control valve, and can generate any braking force on each wheel independently of the driver's brake pedal operation.

[0018] The braking control device 15 estimates vehicle spin, drift-out, and wheel lock based on the various input sensor signals, and generates braking forces on the wheels in question to suppress these, thereby improving the driving stability of the occupants. Furthermore, the vehicle control device 1 can generate any braking force in the vehicle 100 by sending a brake command to the braking control device 15, and plays a role in automatically braking the vehicle in autonomous driving where no operation by the occupants is required. However, the braking configuration is not limited to this configuration, and other actuators such as a brake-by-wire may also be used.

[0019] Next, a configuration for performing a steering operation of the vehicle 100 will be described. While the occupant is driving the vehicle 100, the steering torque detection device 7 detects the steering torque input by the occupant via the steering wheel 6, and the steering wheel angle detection device 21 detects the steering wheel angle. The steering control device 8 controls the motor to generate an assist torque based on the detected steering torque and steering wheel angle. Similarly to the vehicle control device 1, the steering control device 8 is configured with an arithmetic processing device 210 shown in FIG. 3, which will be described later.

[0020] The resultant force of the steering torque of the occupant and the assist torque of the motor operates the steering control mechanism 10 to change the direction of the front wheels (turn the front wheels). Meanwhile, depending on the turning angle of the front wheels, a reaction force from the road surface is transmitted to the steering control mechanism 10, which then transmits the road reaction force to the occupant.

[0021] The steering control device 8 generates torque using a motor and controls the steering control mechanism 10, independent of the steering operation by the occupant. Therefore, the vehicle control device 1 can control the front wheels to any turning angle by sending a steering force command to the steering control device 8, and therefore plays a role in automatically steering the vehicle in autonomous driving where no operation by the occupant is required. Note that the present invention is not limited to the steering control device 8 shown in Fig. 1, and a configuration in which steering operation is performed using another actuator such as a steer-by-wire may also be used.

[0022] Next, the configuration of the accelerator of the vehicle 100 will be described. The amount of depression of the accelerator pedal 17 by the driver is detected by a stroke sensor 18 and input to an acceleration control device 19. Similar to the vehicle control device 1, the acceleration control device 19 is configured as an arithmetic processing device 210 shown in FIG. 3, which will be described later.

[0023] The acceleration control device 19 adjusts the throttle opening according to the depression amount of the accelerator pedal 17 and controls the engine. As a result, the acceleration control device 19 can accelerate the vehicle 100 according to the accelerator pedal operation by the occupant. Furthermore, the acceleration control device 19 can control the throttle opening independently of the accelerator operation by the occupant. Therefore, the vehicle control device 1 can generate any acceleration in the vehicle 100 by transmitting an acceleration command to the acceleration control device 19, and plays a role in automatically accelerating the vehicle in autonomous driving where no operation by the occupant is required.

[0024] [Example of vehicle control device configuration] Next, the functional configuration of the vehicle control device 1 implemented in the vehicle 100 according to this embodiment will be described. FIG. 2 is a block diagram showing an example of the functional configuration of the vehicle control device 1 according to this embodiment. As shown in FIG. 2, the vehicle control device 1 includes an automatic driving planning unit 201, a vehicle driving control unit 203, an actuator control unit 204, and a risk map generation unit 205. Each component is connected via a vehicle network 206 so as to be able to send and receive information data to and from each other. The vehicle network 206 may be a wired connection or a wireless connection.

[0025] The automatic driving planning unit 201 creates a driving plan including the operation of the vehicle at each position on the driving route in order to automatically drive the vehicle 100 to the destination. The driving route is generated in advance based on map information, the current position, and the position of the destination. The vehicle driving control unit 203 generates command values ​​for controlling the operation of the vehicle 100 during autonomous driving in accordance with the driving plan created by the autonomous driving planner 201. The actuator control unit 204 controls each actuator such as the engine, brake, steering, etc., based on the command value input from the vehicle driving control unit 203. The risk map generating unit 205 generates a risk map of vehicles and three-dimensional objects such as obstacles that exist around the host vehicle, including oncoming vehicles.

[0026] Next, the arithmetic processing device 210 constituting the vehicle control device 1 will be described. Fig. 3 is a block diagram showing an example of the hardware configuration of the arithmetic processing device 210 according to this embodiment. As shown in Fig. 2, the arithmetic processing device 210 includes a CPU 211, a memory 212, an input / output unit 213, and a communication interface (I / F) 214. The CPU 211, the memory 212, the input / output unit 213, and the communication I / F 214 are connected via a bus B so as to be able to send and receive information data to and from each other.

[0027] The CPU 211 reads out from the memory 212 and executes program code of software that realizes various functions of the vehicle control device 1. Note that a GPU (Graphics Processing Unit) may be used instead of the CPU 211, or the CPU 211 and a GPU may be used together.

[0028] The memory 212 is, for example, a memory such as a ROM (Read Only Memory) or a RAM (Random Access Memory). The memory 212 may be a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The memory 212 stores programs for realizing the functions of the vehicle control device 1, parameters (including thresholds), map information, road information, various risk maps, driving conditions, history information, and the like.

[0029] The input / output unit 213 performs input processing of various kinds of external information detected by the sensors shown in FIG. 1, and also performs output processing of command values ​​for each actuator, etc. The communication I / F 214 performs information transmission processing with other information processing devices in the vehicle 100, such as the braking control device 15, and also performs transmission and reception processing with the outside via the communication device 23 shown in FIG.

[0030] It should be noted that all of the components of the vehicle control device 1 are not necessarily implemented in one arithmetic processing device. For example, the actuator control unit 204 may be implemented in an engine control controller (arithmetic processing device) or a brake control controller (arithmetic processing device) of the vehicle 100. Furthermore, the automatic driving planning unit 201, vehicle driving control unit 203, actuator control unit 204, and risk map generation unit 205 of the vehicle control device 1 may each be implemented in a different arithmetic processing device (controller).

[0031] [Example of functional configuration of the risk map generation unit] Next, a description will be given of an example of the functional configuration of the risk map generation unit 205 of the vehicle control device 1. Fig. 4 is a block diagram showing an example of the functional configuration of the risk map generation unit 205 of the vehicle control device 1 according to this embodiment. As shown in Fig. 4, the risk map generation unit 205 inputs various types of external environment information from sensors that recognize the external environment, such as a radar 301, a stereo camera 302, a vehicle sensor 303, and a lidar 304.

[0032] The radar 301 measures the distance and direction to the target by emitting radio waves toward the target and measuring the reflected waves. Information (point cloud data) such as the distance and direction to the target detected by the radar 301 is supplied to the risk map generation unit 205.

[0033] The stereo camera 302 simultaneously captures images of an object from multiple different directions to detect depth information of the object. The depth information detected by the stereo camera 302 is supplied to the risk map generation unit 205.

[0034] Vehicle sensor 303 is a collective term for multiple sensors mounted on vehicle 100. Vehicle sensor 303 detects information related to the vehicle's speed, tire rotation speed, etc., and information calculated based on the average position of the autonomously driven vehicle using GNSS (Global Navigation Satellite System). Vehicle sensor 303 also detects destination information input by a passenger in the autonomously driven vehicle using a navigation system as an interface, and destination information specified by an operator or the like in a remote location using wireless communication such as a telephone line. The various pieces of information detected by vehicle sensor 303 are supplied to risk map generation unit 205.

[0035] The lidar 304 measures scattered light from an object in response to pulsed laser irradiation, and detects the distance to the object at a long distance. Information (point cloud data) on the distance to the object at a long distance detected by the lidar 304 is supplied to the risk map generation unit 205. Note that the lidar 304 is not necessarily required.

[0036] 4, the risk map generation unit 205 includes a sensor information processing unit 305, a map information processing unit 306, a solid object behavior prediction unit 307, a memory unit 308, a stay risk map generation unit 309A, and a self-localization processing unit 310. The risk map generation unit 205 also includes a fixed obstacle risk map generation unit 309B and a moving obstacle risk map generation unit 309C. The sensor information processing unit 305, the map information processing unit 306, and the self-localization processing unit 310 are connected to the solid object behavior prediction unit 307. The solid object behavior prediction unit 307 is further connected to the stay risk map generation unit 309A. The sensor information processing unit 305, the map information processing unit 306, and the self-localization processing unit 310 are also connected to the stay risk map generation unit 309A. The sensor information processing unit 305, the map information processing unit 306, the solid object behavior prediction unit 307, and the self-location estimation processing unit 310 are also connected to the fixed obstacle risk map generation unit 309B and the moving obstacle risk map generation unit 309C. In the figure, the arrows between these processing units and the fixed obstacle risk map generation unit 309B and the moving obstacle risk map generation unit 309C are omitted.

[0037] The sensor information processing unit 305 receives input of various types of external environment information from the radar 301, the stereo camera 302, the vehicle sensor 303, and the lidar 304. The sensor information processing unit 305 also functions as a recognition unit that performs recognition processing to recognize the surrounding situation of the vehicle 100 based on the received various types of external environment information. The sensor information processing unit 305 also outputs the received various types of external environment information and the recognized surrounding situation of the vehicle to the three-dimensional object behavior prediction unit 307.

[0038] Here, the surrounding situation includes, for example, object information of moving objects present around the vehicle. The object information includes attribute information of moving objects such as pedestrians, bicycles, and vehicles, as well as the current positions and current velocity vectors of the moving objects. Here, moving objects also include parked vehicles and the like that may move in the future even if the velocity obtained at the current time is zero.

[0039] The storage unit 308 stores route information from the point where the vehicle 100 starts autonomous driving to the destination point, road information on the route and its surroundings, traffic signal information, and a traffic rule database (DB) for the section of the route traveled. The storage unit 308 also stores various types of external information (for example, point cloud information, etc.) from the stereo camera 302, the vehicle sensor 303, and the lidar 304.

[0040] The map information processing unit 306 acquires road lane centerline information, traffic light information, and other information necessary for autonomous driving from the information stored in the memory unit 308. The map information processing unit 306 also organizes information such as the lighting status of traffic lights along which the autonomous vehicle is scheduled to pass, and converts this lane centerline information, traffic light information, and other information into information in a usable format. The map information processing unit 306 also outputs the converted lane centerline information, traffic light information, and other information to the three-dimensional object behavior prediction unit 307.

[0041] The self-position estimation processing unit 310 estimates the current position of the vehicle based on external environment information around the vehicle detected by each sensor, point cloud information, the steering angle of the vehicle, the vehicle speed, information obtained by GNSS, etc. The self-position estimation processing unit 310 also outputs the estimated position of the vehicle to the three-dimensional object behavior prediction unit 307.

[0042] The three-dimensional object behavior prediction unit 307 calculates the position and speed of a three-dimensional object present around the vehicle in the future (the next time or a certain time later) based on various information input from the sensor information processing unit 305, the map information processing unit 306, and the self-position estimation processing unit 310, and outputs the calculated position and speed as object prediction information. In order to predict the movement of a three-dimensional object, which is a moving object, the three-dimensional object behavior prediction unit 307 performs object prediction, which predicts the position R(X(T), Y(T)) of the three-dimensional object at a future time T based on the type of the three-dimensional object (car, bicycle, pedestrian, etc.). As a specific method of object prediction, for example, the following formula (1) can be used for calculation.

[0043]

number

[0044] In equation (1), T represents future time, R(X(T), Y(T)) represents the position of the three-dimensional object at future time T, and Vn (Vxn, Vyn) represents the current velocity of the three-dimensional object. Calculations using equation (1) are performed under the assumption that the three-dimensional object moves at a constant velocity in a straight line, maintaining its current velocity in the future. This makes it possible to predict many objects in a short period of time.

[0045] Note that object prediction is not limited to the above-described method. For example, a method of predicting future positions and speed information of other vehicles using a trained neural network model that uses position and speed information of other vehicles detected by a sensor and image information obtained by a camera may be applied. A calculation method that uses a neural network model also makes it possible to calculate the reliability of the output object prediction information.

[0046] The stagnation risk map generation unit 309A generates a stagnation risk map indicating the stagnation risk around the vehicle based on the processing results of the sensor information processing unit 305, the map information processing unit 306, the self-position estimation processing unit 310, and the three-dimensional object behavior prediction unit 307. When there are three-dimensional objects such as other vehicles, pedestrians, or bicycles around the vehicle, a collision or deadlock may occur if the vehicle does not take cooperative action with the three-dimensional objects. For such driving scenes, the stagnation risk map generation unit 309A predicts the target behavior of the three-dimensional objects that are taking cooperative action, and generates a stagnation risk map (see FIG. 6) based on the predicted target behavior of the three-dimensional objects.

[0047] The fixed obstacle risk map generation unit 309B generates a fixed obstacle risk map that indicates the fixed obstacle risk around the vehicle based on the processing results of the sensor information processing unit 305, the map information processing unit 306, the self-position estimation processing unit 310, and the three-dimensional object behavior prediction unit 307.

[0048] Similar to fixed obstacle risk map generation unit 309B, moving obstacle risk map generation unit 309C generates a moving obstacle risk map indicating the moving obstacle risk around the host vehicle based on the processing results of each processing unit.

[0049] [Stagnation risk map generation process] Next, a description will be given of the stagnation risk map generation process in the risk map generation unit 205. Fig. 5 is a flowchart showing the procedure of the stagnation risk map generation process in the vehicle control device 1 according to this embodiment.

[0050] First, the sensor information processing unit 305 of the risk map generating unit 205 acquires various information including external environment information around the vehicle from each sensor (step S401).

[0051] Next, the three-dimensional object behavior prediction unit 307 predicts the target behavior of the three-dimensional object based on the various acquired information, such as the current position and speed information of the three-dimensional object around the vehicle, and road environment information on which the vehicle and the three-dimensional object are traveling (step S402). The road environment information includes information on the road shape and the three-dimensional object existing in the vicinity, surrounding map information, congestion information, etc.

[0052] Next, the stay risk map generation unit 309A determines whether or not there is an object for cooperative behavior (step S403). In this process, if the stay risk map generation unit 309A determines, based on the predicted target behavior of a three-dimensional object around the vehicle, that there is a possibility of a collision, deadlock, or the like occurring unless cooperative behavior with the three-dimensional object is performed, it determines that there is an object for cooperative behavior, and step S403 is a YES determination. On the other hand, if the stay risk map generation unit 309A determines, based on the predicted target behavior of a three-dimensional object around the vehicle, that there is no need to perform cooperative behavior with the three-dimensional object, it determines that there is no object for cooperative behavior, and step S403 is a NO determination.

[0053] In the process of step S403, if the stagnation risk map generation unit 309A determines that there is an object of cooperative behavior (YES in step S403), it performs the process of step S404. In the process of step S404, the stagnation risk map generation unit 309A generates and outputs a cooperative behavior plan and a stagnation risk map based on the target behavior of the object of cooperative behavior (step S404).

[0054] On the other hand, in the process of step S403, if the stay risk map generating unit 309A determines that there is no object of cooperative behavior (NO in step S403), or after the process of step S404, the stay risk map generating process ends.

[0055] Next, a description will be given of the cooperative action plan and the stagnation risk map generated by the stagnation risk map generating unit 309A. Fig. 6 is a diagram showing an example of the cooperative action plan and the stagnation risk map in the vehicle control device 1 according to this embodiment.

[0056] The host vehicle M1 shown in FIG. 6 is located at the entrance / exit of a relatively large parking lot. The parked vehicle M2 is about to leave the parking lot and is an object that requires cooperative behavior with the host vehicle M1. In the case of the scene shown in FIG. 5, the risk map generation unit 205 predicts that the vehicle M2 will reach the target point 2203 in the future (a predetermined time until the cooperative behavior is completed) based on various input information. The risk map generation unit 205 then predicts the route of the vehicle M2 to the predicted target point 2203 and calculates the area where the vehicle M2 passes along that route as the stay risk map 701 (see the hatched area). The risk map generation unit 205 also recognizes the surrounding vacant areas of the stay risk map 701 as candidate evacuation areas.

[0057] Furthermore, the risk map generation unit 205 calculates an evacuation position 2202 where the host vehicle M1 will evacuate, based on the target point 2203 of the vehicle M2 and the stay risk map 701. Then, the risk map generation unit 205 considers a sequence for executing each evacuation action in series or in parallel so that the actions of the host vehicle M1 and the vehicle M2 are both completed, and sets the sequence that can realize this as the cooperative action plan.

[0058] As a cooperative action plan, the risk map generation unit 205 first formulates an action plan from the position of the host vehicle M1 to the evacuation position 2202. Next, the risk map generation unit 205 formulates an action plan for when the vehicle M2 passes beside the host vehicle M1. Finally, the risk map generation unit 205 formulates an action plan for the host vehicle M1 from the evacuation position 2202 to a target parking position (for example, parking position 2201a). Note that if a sequence for completing such cooperative action cannot be found, the risk map generation unit 205 revisits the target point of the vehicle M2, the retention risk map, and the host vehicle evacuation position, and recursively searches for a sequence.

[0059] [Example of the configuration of the Autonomous Driving Planning Department] Next, a description will be given of an example of the functional configuration of the automatic driving planning unit 201 of the vehicle control device 1. Fig. 7 is a block diagram showing an example of the configuration of the automatic driving planning unit 201 of the vehicle control device 1 according to this embodiment.

[0060] 7, the autonomous driving planning unit 201 includes a driving planner 501, a trajectory planner 507, and a driving mode manager 509. The driving planner 501 is connected to the trajectory planner 507, which is connected to the driving mode manager 509, which is further connected to the driving planner 501. The autonomous driving planning unit 201 is supplied with object prediction information, a risk map, and a cooperative action plan generated by the risk map generator 205, lane information, map information, external environment information, and route information stored in the memory unit 308, UI information acquired from an in-vehicle UI (User Interface), and the like.

[0061] The driving planner 501 calculates candidate target behavior weights for the vehicle based on route information, external environment information, detection information from the vehicle sensor 303, occupant status information, and the like. The candidate target behavior weights include a LK (Lane Keep) weight for maintaining the current lane of the vehicle and a LC (Lane Change) weight for changing lanes from the current lane to an adjacent lane. The candidate target behavior weights also include an OA (Object Avoidance) weight for avoiding obstacles ahead, a CO (Cooperative Operation) weight for cooperative operation with other vehicles, and a CC (Crew Cooperative) weight for generating a trajectory for cooperating with the occupants. For example, when the vehicle 100 is traveling on a straight road, if there are no vehicles or objects ahead that need to be avoided or if the route information suggests that there is no need to change lanes to an adjacent lane, the driving planner 501 calculates LK weight = 1, LC weight = 0, OA weight = 0, CO weight = 0, and CC weight = 0. The driving planner 501 outputs the calculated candidate target behavior weights to the trajectory planner 507.

[0062] The trajectory planning unit 507 performs a traveling trajectory generation process to generate a traveling trajectory from the current position of the vehicle to a target position. As shown in Fig. 7, the trajectory planning unit 507 includes a lane keeping trajectory generation unit (LK) 502, a lane change trajectory generation unit (LC) 503, and an obstacle avoidance trajectory generation unit (OA) 504. The trajectory planning unit 507 also includes a cooperative behavior trajectory generation unit (CO) 505, an occupant cooperative trajectory generation unit (CC) 508, and a trajectory arbitration unit 506.

[0063] The lane keeping trajectory generating unit (LK) 502 generates a trajectory for keeping the host vehicle traveling in the center of the lane in which it is currently traveling. The lane change trajectory generating unit (LC) 503 generates a trajectory for changing lanes to an adjacent lane of the lane on which the host vehicle is currently traveling. The obstacle avoidance trajectory generation unit (OA) 504 generates a trajectory for avoiding an object that is present in the lane in which the host vehicle is currently traveling and that may become an obstacle to traveling. The cooperative behavior trajectory generation unit (CO) 505 generates a cooperative behavior trajectory for cooperative behavior with a surrounding object such as an oncoming vehicle. For example, as the cooperative behavior trajectory, a trajectory for moving the host vehicle to a retreat position when the host vehicle and a moving object (e.g., an oncoming vehicle) pass each other and a speed profile that defines the speed on the trajectory are generated. The crew cooperative trajectory generator (CC) 508 generates a crew cooperative trajectory based on the candidate evacuation locations in the cooperative action plan, the speed profile to the candidate evacuation locations, and the travel route to the candidate evacuation locations. The crew cooperative trajectory generator (CC) 508 will be described in detail later with reference to FIG. 9.

[0064] The trajectory arbitration unit 506 evaluates the generated lane keeping trajectory, lane change trajectory, obstacle avoidance trajectory, cooperative behavior trajectory, and occupant cooperative trajectory based on the type of three-dimensional object around the vehicle, the safety level of the trajectory, the weight of the candidate target behavior, etc., and selects the trajectory with the best evaluation as the target trajectory. The trajectory arbitration unit 506 also outputs the selected target trajectory and the evaluation value of the trajectory to the driving mode management unit 509.

[0065] [Configuration example of driving mode management unit] Next, the functional configuration of the driving mode management unit 509 will be described. The driving mode management unit 509 calculates previous selection information for calculating target behavior candidate weights at the next sampling time using a driving mode corresponding to the trajectory selected by the trajectory arbitration unit 506 and an evaluation value of the selected trajectory. For example, assume that at the current sampling time, LK weight = 60, LC weight = 40, OA weight = 0, CO weight = 0, and CC weight = 0, and a lane-keeping trajectory (LK) is selected. In this case, at the next sampling time, the driving mode management unit 509 generates the driving mode (driving information) of the previously selected lane-keeping trajectory (LK) as the current driving mode (current driving information) so that LK is more likely to be selected for the sake of behavior continuity.

[0066] FIG. 8 is a block diagram showing an example of the functional configuration of the driving mode management unit 509 of the vehicle control device according to this embodiment. Various information such as a target driving mode, a manual driving request, and system information is supplied to the driving mode management unit 509. The target driving mode is a driving mode corresponding to the target trajectory selected by the trajectory planning unit 507, i.e., LK, LC, OA, CO, and CC driving modes. The manual driving request is received from the vehicle driving control unit 203 when it is determined that the autonomous driving system needs to take over driving (give up). The system information is, for example, ON / OFF information of the power switch of the vehicle 100 and ON / OFF information of the autonomous driving switch of the autonomous driving system.

[0067] 8, the driving mode management unit 509 manages a manual driving mode 2901, an automatic driving system off mode 2902, and an automatic driving mode 2903. The driving mode management unit 509 outputs the current mode state as the current driving mode.

[0068] When the power switch or the like of the vehicle 100 is turned on (an example of UI information in FIG. 7), the driving mode management unit 509 transitions the current driving mode from the automatic driving system off mode 2902 to the manual driving mode 2901. In addition, when the automatic driving switch is turned on by the driver or the like (an example of UI information in FIG. 7), the driving mode management unit 509 transitions the current driving mode from the manual driving mode 2901 to the automatic driving mode 2903.

[0069] The autonomous driving mode 2903 includes lane keeping (LK) mode, lane change (LC) mode, obstacle avoidance (OA) mode, cooperative action (CO) mode, and occupant cooperation (CC) mode. There are intermediate transition states between each mode. Depending on the road environment, a deadlock or an event requiring a change of driving to the driver may occur in the CO mode, and the autonomous driving system may determine that it is necessary to take over (give up). In such a case, a manual driving request is issued from the vehicle driving control unit 203, and the current driving mode transitions from the autonomous driving mode 2903 to the manual driving mode 2901.

[0070] [Configuration example of crew collaborative trajectory generation unit] Next, a description will be given of an example of the functional configuration of the occupant collaborative trajectory generation unit 508. Fig. 9 is a block diagram showing an example of the functional configuration of the occupant collaborative trajectory generation unit 508 of the vehicle control device 1 according to this embodiment. The occupant collaborative trajectory generation unit 508 is supplied with the risk map and collaborative action plan generated by the risk map generation unit 205, external environment information, lane information stored in the memory unit 308, map information, and occupant input information input by the occupant of the vehicle 100.

[0071] 9 , the occupant cooperative trajectory generation unit 508 includes an occupant cooperative position generation unit 601, a parking / stopping position generation unit 602, an occupant cooperative position determination unit 603, a route candidate generation unit 604, an acceptance / determination unit 605, and an occupant cooperative trajectory planning unit 606. The occupant cooperative position generation unit 601 and the parking / stopping position candidate generation unit 602 are connected to the occupant cooperative position determination unit 603. The occupant cooperative position determination unit 603 is connected to the route candidate generation unit 604 and the acceptance / determination unit 605. The route candidate generation unit 604 and the acceptance / determination unit 605 are further connected to the occupant cooperative trajectory planning unit 606. The occupant cooperative trajectory planning unit 606 includes an occupant cooperative path generation unit 607 and an occupant cooperative speed generation unit 608.

[0072] The escape position candidate generating unit (escape position candidate generating unit 601) generates escape position candidates, which are candidates for the location where the host vehicle will escape, based on the results of prediction of the position of the host vehicle and the routes of other vehicles. The parking / stopping position candidate generating unit (parking / stopping position candidate generating unit 602) generates parking / stopping position candidates that are candidates for parking / stopping positions where the host vehicle is to park or stop. The evacuation position determination unit (evacuation position determination unit 603) determines an evacuation position for the host vehicle based on the evacuation position candidates and parking / stopping position candidates. The evacuation position determination unit (evacuation position determination unit 603) evaluates the evacuation position candidates with respect to predetermined evaluation items, and determines the evacuation position based on the evaluation results. Here, the predetermined evaluation items include at least one of safety, efficiency, and convenience. The route candidate generation unit (route candidate generation unit 604) generates route candidates that are candidates for routes from the position of the vehicle to candidate parking / stopping positions via evacuation positions. The acceptance determination unit (acceptance determination unit 605) determines whether or not to accept the selection of a parking or stopping position from the occupant of the vehicle as a withdrawal position.

[0073] The occupant cooperative trajectory planning unit (occupant cooperative trajectory planning unit 606) plans a trajectory for the vehicle based on the result of the determination by the reception and determination unit. The occupant cooperative route generation unit 607 of the occupant cooperative trajectory planning unit 606 selects an optimal route candidate from the route candidates generated by the route candidate generation unit 604 based on the result of the determination by the reception and determination unit 605, and generates the optimal route candidate as a trajectory for the vehicle. The occupant cooperative speed generation unit 608 of the occupant cooperative trajectory planning unit 606 generates a speed profile that specifies the speed at which the vehicle will travel while following the generated trajectory.

[0074] [Evacuation position candidate generation process] Next, the process of generating escape position candidates in the escape position candidate generating unit 601 will be described. Each flowchart in this specification shows a part of a vehicle control method executed by a computer constituting the vehicle control device 1 according to this embodiment. Fig. 10 is a flowchart showing the procedure of the process of generating escape position candidates in the vehicle control device 1 according to this embodiment.

[0075] First, the evacuation position candidate generating unit 601 acquires various information such as a stay risk map, a cooperative action plan, external information, lane information, and map information (step S801).

[0076] Next, the escape position candidate generation unit 601 generates escape position candidates including the target escape position and the headway angle (posture) at which the vehicle will stop at the target escape position based on the various information acquired in step S801 (step S802). After the processing of step S802, the escape position candidate generation processing ends.

[0077] Here, the process of generating candidate evacuation positions in step S802 of Fig. 10 will be described with reference to Fig. 11. Fig. 11 is a diagram for explaining the process of generating candidate evacuation positions in the vehicle control device 1 according to this embodiment. Fig. 11 shows a scene in which vehicle M2, parked in parking position 2201a, is about to leave the parking lot in front of host vehicle M1, which is located at the entrance / exit of the parking lot 741 and about to enter. In this scene, vehicle M2 is an object that requires cooperative action by host vehicle M1. In addition, there is an area 2200 in which evacuation is possible (see the area surrounded by a dashed line frame) on the left side in front of host vehicle M1.

[0078] FIG. 11 shows the stagnation risk map 701 generated by the stagnation risk map generation unit 309A (see FIG. 4). In order to realize cooperative behavior with vehicle M2, host vehicle M1 needs to move to and evacuate to a location in the evacuability area 2200 where the stagnation risk map 701 does not exist. As shown in the figure, the evacuation position candidate generation unit 601 generates position coordinates N1 to N5 as locations in the evacuability area 2200 where the stagnation risk map 701 does not exist. The evacuation position candidate generation unit 601 also generates headway angles θ1 to θ5 (attitudes) when stopping at each of the position coordinates N1 to N5. Here, (N1, θ1) to (N5, θ5) are information on the evacuation position candidates. Note that the evacuation position candidate generation unit 601 can generate any number of evacuation position and attitude candidates, but selects a location close to the stagnation risk map 701 within a range that takes into consideration the size of the host vehicle M1.

[0079] [Parking location candidate generation process] Next, a description will be given of the parking / stopping position candidate generation process in the parking / stopping position candidate generation unit 602. Fig. 12 is a flowchart showing the procedure of the parking / stopping position candidate generation process.

[0080] First, the parking / stopping position candidate generating unit 602 acquires various information such as a retention risk map, a cooperative action plan, external information, lane information, and map information (step S1501).

[0081] Next, the parking / stopping position candidate generating unit 602 generates potential parking positions as parking / stopping position candidates based on the acquired various information (step S1502).

[0082] Next, the parking / stopping position candidate generating unit 602 stores information on the generated parking / stopping position candidates in the storage unit 308 (see FIG. 4) (step S1503). After the process of step S1503, the parking / stopping position candidate generating process ends.

[0083] Next, a method for generating parking / stopping position candidates in step S1502 of the parking / stopping position candidate generating process will be described. Fig. 13 is a diagram for explaining a method for generating parking / stopping position candidates in the vehicle control device 1 according to this embodiment.

[0084] The parking / stopping position candidate is a candidate location where the host vehicle can be parked based on the current surrounding environment of the host vehicle. The parking status of the parking lot 741, the position of the host vehicle M1, and the exit start status of the vehicle M2 shown in FIG. 13 are the same as those shown in FIG. 12 , so repeated explanations will be omitted. The exit start status of the vehicle M2 is determined, for example, from whether the engine is started, whether the turn signal for exiting to the right is flashing, and whether the occupants of the vehicle M2 have just boarded the vehicle M2. In the situation shown in FIG. 13 , the parking / stopping position candidate generation unit 602 determines the parking position candidate, parking position 2201a, which will soon become vacant, and parking position 2201b, which is vacant, as parking / stopping position candidates based on the surrounding environmental conditions of the host vehicle M1. Alternatively, the parking / stopping position candidate generation unit 602 may acquire the parking status of the parking lot from a control system that manages the parking lot in advance and generate parking / stopping position candidates based on the acquired parking status of the parking lot. The parking / stopping position candidate generating unit 602 may also generate parking / stopping position candidates based on instructions from a parking lot attendant.

[0085] In the above description, the process of generating parking / stopping position candidates has been described using parking in a parking lot as an example, but the present invention is not limited to this. The process of generating parking / stopping position candidates described above can also be applied to parking / stopping when passing other vehicles on narrow roads.

[0086] [Evacuation position determination process] Next, there will be explained the process of determining the evacuation position in the evacuation position determination unit 603. Fig. 14 is a flowchart showing the procedure of the process of determining the evacuation position in the vehicle control device 1 according to this embodiment.

[0087] First, the evacuation position determination unit 603 acquires various information such as a stay risk map, a cooperative action plan, external information, lane information, and map information (step S1601).

[0088] Next, the fallback position determination unit 603 evaluates the fallback position based on the acquired various information, the fallback position candidates, and the parking / stopping position candidates (step S1602). Possible methods for evaluating fallback position candidates include methods that take safety, efficiency, convenience, etc. into consideration. Possible methods for evaluating the safety of fallback position candidates include methods that evaluate based on the distance to surrounding objects and collision risk, etc. Possible methods for evaluating the collision risk of fallback position candidates include evaluating the collision risk with other vehicles, pedestrians, etc., and selecting the fallback position candidate with the lowest risk. The collision risk can be dynamically evaluated by monitoring the surrounding situation in real time using sensors.

[0089] Another possible method for evaluating the efficiency of the candidate evacuation locations is to evaluate the waiting time at the candidate evacuation locations. Specifically, the waiting time at the candidate evacuation locations is predicted based on the state of the candidate parking locations and the state of oncoming vehicles (speed, direction, etc.), and the candidate evacuation location with the shortest predicted waiting time is selected.

[0090] Another possible method for evaluating the convenience of candidate evacuation locations is to measure the distance from the candidate evacuation location to the candidate parking location, and to prioritize and select the candidate evacuation location with the shortest distance. The distance from the candidate evacuation location to the candidate parking location can be calculated using information about the surrounding environment recognized by sensors such as LiDAR or a camera. Another possible method for evaluating the convenience of candidate evacuation locations is to optimize traffic flow. Specifically, the traffic flow of the vehicle and oncoming vehicles is taken into consideration to select a candidate evacuation location that does not obstruct traffic and ensures smooth overall traffic flow. Evaluation from the above perspectives can be performed using mathematical formulas, score-based evaluation, or the like, and a linear sum of these evaluations can be used to evaluate the evacuation locations.

[0091] Next, the escape location determination unit 603 determines an escape location based on the evaluation results of the escape location candidates (step S1603).

[0092] Next, the evacuation position determination unit 603 stores information about the determined evacuation position in the storage unit 308 (step S1604). After the processing of step S1604, the evacuation position determination processing ends.

[0093] [Route candidate generation process] Next, a description will be given of the route candidate generation process performed by the route candidate generation unit 604. Fig. 15 is a flowchart showing the procedure of the route candidate generation process performed by the vehicle control device 1 according to this embodiment.

[0094] First, the route candidate generating unit 604 acquires various information such as a delay risk map, a cooperative action plan, external information, lane information, and map information (step S1701).

[0095] Next, the route candidate generation unit 604 generates route candidates that lead to the parking position candidate via the evacuation position based on the various acquired information (step S1702). In this process, the route candidate generation unit 604 uses the stay risk map generated by the stay risk map generation unit 309A and the evacuation position determined by the evacuation position determination unit 603 to generate route candidates (see FIG. 16) for the evacuation position and the parking position candidate by, for example, a method of generating arcs, straight lines, and clothoid curves.

[0096] Next, the route candidate generating unit 604 stores the generated route candidates in the storage unit 308 (step S1703). After the process of step S1703, the route candidate generating process ends.

[0097] Next, the route candidates generated by the route candidate generation unit 604 will be described. FIG. 16 is a diagram for explaining a method for generating route candidates in the vehicle control device 1 according to this embodiment. The parking lot 741 and the position of the host vehicle M1 shown in FIG. 16 are the same as those in FIG. 6, and therefore a repeated description will be omitted. Note that in FIG. 16, it is assumed that the vehicle M2 has already left the parking lot, and therefore the parking position 2201a is vacant. As shown in the figure, the route candidate generation unit 604 generates a target route for the host vehicle M1 to travel from its current position to the evacuation position (N3, θ3) using straight lines and arc curves. Specifically, the route candidate generation unit 604 first generates the route for the host vehicle M1 to travel from its current position to the evacuation position as a straight line that is approximately parallel to the center line 1101 that is along the current direction of the host vehicle M1. Then, the route candidate generation unit 604 generates a curved route using an arc curve at a point where the host vehicle M1 approaches the evacuation position (N3, θ3) that is off the center line. Then, the route candidate generating unit 604 generates routes leading to each of the parking positions 2201a and 2201b, which are parking / stopping position candidates.

[0098] [Parking location selection acceptance determination process] Next, a description will be given of the acceptance determination process in the acceptance determination unit 605. Fig. 17 is a flowchart showing the procedure of the acceptance determination process for parking position selection in the vehicle control device 1 according to this embodiment.

[0099] First, the reception determination unit 605 acquires various information such as a delay risk map, a cooperative action plan, outside world information, lane information, and map information (step S1801).

[0100] Next, the reception / determination unit 605 determines whether the current position of the vehicle is a withdrawal position (step S1802).

[0101] In the process of step S1802, if it is determined that the current position of the vehicle is not a withdrawal position (NO determination in step S1802), the acceptance determination unit 605 determines not to accept the selection of a parking position from the occupant (step S1803).

[0102] On the other hand, in the process of step S1802, if the acceptance determination unit 605 determines that the current position of the host vehicle is a fall-off position (YES determination in step S1802), it performs acceptance determination of the parking position selection (step S1804). In this process, the acceptance determination unit 605 performs acceptance determination of the parking position selection based on the acquired various information, the fall-off position, and the occupant status. Possible occupant statuses include the occupant's line of sight, wakefulness state, riding position, field of view range, etc. The acceptance determination of the parking position selection is a determination of whether or not to accept the selection of a parking position from the driver or occupant of the host vehicle at the fall-off position. For example, if it is inferred that the occupant is awake and recognizes nearby parking spaces, the acceptance determination unit 605 determines that the parking position selection can be accepted. In this embodiment, it is assumed that the acceptance determination unit 605 performs acceptance determination of the parking position selection with the parking position candidates already determined each time the host vehicle arrives at a fall-off position. A state in which parking and stopping position candidates are determined means a state in which the parking and stopping position candidates do not change due to, for example, the parking and stopping position candidates being taken by other vehicles or new parking and stopping position candidates being created when other vehicles leave the parking lot.

[0103] For example, if it is presumed that a nearby vehicle parked in the parking lot is about to leave and a new parking position is predicted to be created, i.e., if the parking position candidate is changeable, the acceptance determination unit 605 determines that the parking position selection cannot be accepted. In this case, the parking position candidate generation process described in Fig. 12 and the route candidate generation process described in Fig. 15 are executed again, and then the acceptance determination for the parking position selection is also performed again. By performing this type of acceptance determination for the parking position selection, it is possible to avoid the hassle of changing the parking position candidate and to avoid leaving open the possibility of parking at a better parking position.

[0104] After the processing of step S1803 or step S1804, the acceptance determination unit 605 stores the acceptance determination result of the parking position selection in the storage unit 308 (step S1805). The acceptance determination result of the parking position selection is information that links the evacuation position at the time of execution of the acceptance determination with the result of acceptance / non-acceptance.

[0105] [Crew collaborative trajectory planning processing] Next, a description will be given of the crew collaborative trajectory planning process in the crew collaborative trajectory planning unit 606. Fig. 18 is a flowchart showing the procedure of the crew collaborative trajectory planning process in the vehicle control device 1 according to this embodiment.

[0106] First, the occupant collaborative trajectory planning unit 606 acquires various information such as a delay risk map, a collaborative action plan, external information, lane information, and map information (step S1001).

[0107] Next, the crew cooperative trajectory planning unit 606 (crew cooperative route generation unit 607) determines the acceptance determination result of the parking position selection by the acceptance determination unit 605 (step S1002). In this process, if the acceptance determination result of the parking position selection is acceptable, the determination in step S1002 is YES. On the other hand, if the acceptance determination result of the parking position selection is unacceptable, the determination in step S1002 is NO.

[0108] In step S1002, if the result of the acceptance determination of the parking position selection is not acceptable (NO determination in step S1002), the occupant cooperative route generation unit 607 performs the process of step S1004 described below.

[0109] On the other hand, in step S1002, if the result of the acceptance determination for the parking position selection is acceptable (YES determination in step S1002), the occupant cooperative route generation unit 607 displays an HMI (Human Machine Interface), which is a means for accepting the selection of a parking position from the occupant of the vehicle, on the display device 24 (step S1003). Note that the display of the HMI is not limited to the in-vehicle display device 24, and a mobile terminal of the occupant that is communicably connected to the vehicle may be used.

[0110] Here, an example of an HMI display that accepts a parking position selection from an occupant will be described with reference to FIG. 19. FIG. 19 is a diagram showing an example of an HMI display when a parking position is selected in the vehicle control device 1 according to this embodiment. On the left side of the HMI screen shown in FIG. 19, a message is displayed saying, "Please select a parking position from the parking position candidates (1 and 2)." On the right side of the HMI screen, an image of the parking lot where the host vehicle M1 is located is displayed. On the image of the parking lot, the parking position candidates are displayed surrounded by dashed frames. The occupant of the host vehicle M1 can select a parking position by checking the parking position candidates (1 and 2) displayed on the image of the parking lot and performing a selection operation on the position where the vehicle is desired to park.

[0111] The HMI screen shown in FIG. 19 does not display information unnecessary for selecting a parking position candidate, such as information about nearby pedestrians. By not displaying unnecessary information at the parking position candidate, it becomes easier for the occupant to select a parking position from among the parking positions. Furthermore, if it is unclear whether the vehicle can reach a parking position from its current position due to an obstacle or the like outside the detection area of ​​the vehicle sensor 303 (see FIG. 4), the occupant may be notified of this via the HMI and asked to make a decision. The configuration of the HMI screen is not limited to that shown in FIG. 19, and any screen configuration may be used as long as it allows the display and selection of parking position candidates.

[0112] 18 shows a process in which the HMI is displayed only when a parking location selection is accepted, but the present invention is not limited to this. The means for accepting a parking location selection from an occupant of the vehicle may output different notification information depending on whether or not the selection of a parking location is accepted. For example, if the means for accepting a parking location selection from an occupant of the vehicle does not accept the selection of a parking location, notification information indicating that the selection cannot be accepted and the reason for the acceptance is displayed via the HMI. Furthermore, the means for accepting a parking location selection from an occupant is not limited to an HMI, but may be an in-vehicle audio device, or a combination of an HMI and an audio device.

[0113] Returning to FIG. 18, the processing after step S1003 will now be described. If the determination in step S1002 is NO, or after the processing of step S1003, the occupant cooperative route generation unit 607 selects an optimal occupant cooperative route based on the acceptance determination result of the parking position selection and the evaluation result of the generated route candidates (step S1004). In this processing, the occupant cooperative trajectory planning unit (occupant cooperative trajectory planning unit 606) plans a trajectory of the host vehicle from the position of the host vehicle to a withdrawal position determined by the acceptance determination unit (acceptance determination unit 605) to accept the selection of a parking position, and a trajectory of the host vehicle from the withdrawal position to a parking position accepted by the occupant from among the parking position candidates.

[0114] On the other hand, when the reception determination unit (reception determination unit 605) determines that the selection of a parking position from the occupant at the evacuation position is not accepted, the occupant cooperative trajectory planning unit (occupant cooperative trajectory planning unit 606) plans a trajectory of the host vehicle from the position of the host vehicle to at least one candidate parking position. Specifically, the occupant cooperative trajectory planning unit (occupant cooperative trajectory planning unit 606) calculates individual evaluation values ​​that evaluate predetermined evaluation targets for route candidates from the position of the host vehicle to the candidate parking position via the evacuation position, calculates a comprehensive evaluation value of the route candidates based on the individual evaluation values, and selects a route candidate based on the comprehensive evaluation value to plan the trajectory of the host vehicle. The method of evaluating the route candidates will be described later.

[0115] Next, the crew-cooperative trajectory planning unit 606 stores information on the generated optimal crew-cooperative route, i.e., information on the planned trajectory of the host vehicle, in the storage unit 308 (step S1005). After processing in step S1005, the crew-cooperative trajectory planning process ends.

[0116] [Route candidate evaluation method] Here, a description will be given of a method for evaluating route candidates in step S1004 shown in Fig. 19. One possible method for evaluating route candidates is to calculate a comprehensive evaluation value for each route candidate using the following formula (2), for example.

[0117]

number

[0118] Equation (2) calculates the total product of the individual evaluation value (i) and the weighting coefficient (i) set for the individual evaluation value (i) as the overall evaluation value. Here, the individual evaluation values ​​include a safety evaluation value, a convenience evaluation value, a ride comfort evaluation value, a discomfort evaluation value, and an evaluation value of a feeling of oppression from oncoming vehicles. i is a number from 1 to 5. The weighting coefficient for each individual evaluation value is a value determined in advance depending on the driving scene. Note that the individual evaluation values ​​are not limited to including all of the above five individual evaluation values. The individual evaluation values ​​may include at least one of the safety evaluation value, the convenience evaluation value, the ride comfort evaluation value, the discomfort evaluation value, and the evaluation value of a feeling of oppression from oncoming vehicles. Furthermore, the individual evaluation values ​​may include evaluation values ​​other than the above five individual evaluation values.

[0119] Specifically, the safety evaluation value is a value that evaluates safety using the distance to surrounding objects and the risk value of contact with fixed obstacles (not shown). The safety evaluation value is indicated, for example, by the inverse of the minimum distance between a road boundary and a route candidate, or by the value (probability) of a collision risk map (not shown). In this embodiment, the route information is assumed to be planar coordinate information, and the trajectory is route information to which time information has been added. Regarding the weighting coefficient of the safety evaluation value, for example, in a scene where the vehicle is traveling on a passing route, it is necessary to ensure a sufficient distance to avoid contact with or approaching surrounding objects. For this reason, the weighting coefficient of the safety evaluation value is set large for such a traveling scene.

[0120] The convenience evaluation value is a value that evaluates convenience using the length from the position of the vehicle to the evacuation position, assuming that the speed of the vehicle is constant regardless of the length of the route. For example, the convenience evaluation value can be the length of the route from the position of the vehicle to the evacuation position. Regarding the weighting coefficient of the convenience evaluation value, for example, in a scene where it takes time to coordinate with an oncoming vehicle, if the oncoming vehicle waits for a long time, other vehicles and the occupants of the vehicle may feel distrustful. Therefore, the weighting coefficient of the convenience evaluation value is set large for such driving scenes.

[0121] The ride comfort evaluation value is calculated based on whether the acceleration and jerk (time derivative of acceleration) occurring in the vehicle when the vehicle is following the route candidate increase. The ride comfort evaluation value is expressed, for example, as the value of (the inverse of the turning radius) x (the total turning angle). The turning radius is the radius of the circle formed by the center of gravity of the vehicle when turning. The total turning angle is the sum of the steering angles occurring when following the occupant-cooperative route candidate. The ride comfort of the route is considered to be poor in situations where large lateral acceleration occurs or where lateral acceleration occurs for a long time. Furthermore, when the turning radius of the route is small, the larger the total turning angle, the less comfortable the route is considered to be. For such situations, the weighting coefficient of the ride comfort evaluation value is set based on the physical condition of the occupants. For example, if the occupants include young children or people in poor health, the weighting coefficient of the ride comfort evaluation value is set to a large value.

[0122] The discomfort evaluation value is calculated based on the number of turns required to pass other vehicles, based on the idea that cooperative behavior that requires turning can cause discomfort. The discomfort evaluation value is indicated, for example, by the number of turns required to travel along a candidate occupant cooperative route. The weighting coefficient for the discomfort evaluation value is set based on the physical condition of the occupants. For example, if the occupants include a small child or someone who is in poor health, the weighting coefficient for the discomfort evaluation is set to a large value.

[0123] The evaluation value of the sense of oppression from oncoming vehicles is a value that evaluates the possibility that a route in which the vehicle approaches too closely to an oncoming vehicle will cause occupants of the vehicle and other vehicles to feel distrustful or scared, and is calculated based on the distance between the candidate route and the oncoming vehicle. The evaluation value of the sense of oppression from oncoming vehicles is indicated, for example, by the reciprocal of the smallest distance between the candidate route and the center position coordinates of the other vehicle. The weighting coefficient of the evaluation value of the sense of oppression from oncoming vehicles is set, for example, large for scenes in which the vehicle is traveling on a narrow road, and small for scenes in which the vehicle is traveling on a wide road.

[0124] The smaller the overall evaluation value of the crew-cooperative route candidate, the more preferable the trajectory candidate is. Therefore, the crew-cooperative route generation unit 607 of the crew-cooperative trajectory planning unit 606 selects the route candidate with the smallest overall evaluation value as the optimal crew-cooperative route to plan the trajectory of the vehicle.

[0125] Next, we will explain how the crew-cooperative speed generator 608 of the crew-cooperative trajectory planner 606 calculates the target speed profile. When calculating the target speed profile for traveling along the target route, one method is to select routes that satisfy the variational equation of the following formula (3) as candidates.

[0126]

number

[0127] In the above equation (3), w1, w2, and w3 are weighting coefficients corresponding to longitudinal acceleration, lateral acceleration, and (speed limit - host vehicle speed), respectively, and are registered in advance in the storage unit 308. Furthermore, w1, w2, and w3 are changeable, and multiple speed profiles can be generated by changing w1, w2, and w3 or by changing the items to be evaluated (vehicle longitudinal acceleration, lateral acceleration, etc.). Note that the behavior of the vehicle when traveling along a target route, such as the vehicle longitudinal acceleration and lateral acceleration in equation (3), can be obtained from a plant model. Examples of plant models include a bicycle model and a four-wheel model.

[0128] Next, a cooperative behavior trajectory of the host vehicle and a vehicle that needs to be coordinated with the host vehicle when the selection of a parking position from the occupant is not accepted and determined will be described. Figure 20 is a diagram showing an example of a cooperative behavior trajectory of the host vehicle and a vehicle that needs to be coordinated with the host vehicle when the selection of a parking position from the occupant is not accepted and determined.

[0129] The parking state of the parking lot 741, the position of the host vehicle M1, and the departure start state of the vehicle M2 shown in FIG. 20 are the same as those shown in FIG. 13, so a duplicated explanation will be omitted. As shown in the figure, the vehicle control device of the host vehicle M1 generates an evacuation behavior trajectory (see the curved arrow from the host vehicle position to the evacuation position 2202) to temporarily stop the host vehicle M1 at the evacuation position 2202 to avoid the departure of the vehicle M2. After the vehicle M2 passes beside the host vehicle, the host vehicle M1 stops again at the parking position selection position 1301 to select a parking position. Therefore, the vehicle control device of the host vehicle M1 plans a behavior trajectory from the evacuation position 2202 to the parking position selection position 1301 (see the curved arrow from the evacuation position 2202 to the parking position selection position 1301). At this time, the occupant selects a parking position from the parking position 2201a or the parking position 2201b. Then, the vehicle control device of the host vehicle M1 plans a parking trajectory (see the curved arrow from the selected parking position 1301 to the parking position 2201a) toward the parking position selected by the occupant, for example, the parking position 2201a. As described above, if the acceptance determination of the parking position selection is not performed, the host vehicle M1 will stop twice, once to move the vehicle M2 away and once to select a parking position. As the number of stops increases, a problem occurs in which the occupant of the host vehicle M1 feels uneasy or uncomfortable. Figure 21 is a diagram showing an example of a traveling speed at which the occupant of the host vehicle feels uneasy or uncomfortable.

[0130] FIG. 21 shows the time change characteristics of the traveling speed of the host vehicle M1 from the traveling start position shown in FIG. 20. The horizontal axis in FIG. 21 represents time, and the vertical axis represents the traveling speed of the host vehicle M1. As shown in FIG. 21, the host vehicle M1 stops temporarily (speed = 0) when cooperatively withdrawing with the vehicle M2, and stops again (speed is almost 0) when selecting a parking position. Such repeated multiple stops cause anxiety and discomfort to traffic participants such as the occupants of the host vehicle M1, pedestrians (not shown), and following vehicles. Furthermore, such repeated multiple stops may disrupt traffic flow, causing congestion in the parking lot and adversely affecting surrounding traffic.

[0131] Therefore, the vehicle control device 1 according to this embodiment plans an optimal cooperative behavior route by accepting and determining a parking position selection request, with the aim of parking and stopping at a parking position desired by the occupants without interfering with the travel of vehicle M2. Figure 22 is a diagram showing an example of a cooperative behavior route of the host vehicles when a parking position selection request is accepted and determined by the vehicle control device 1 according to this embodiment. The parking state of the parking lot 741, the position of host vehicle M1, the evacuation position 2202, and the departure start state of vehicle M2 shown in Figure 22 are the same as those shown in Figure 20, so repeated explanations will be omitted.

[0132] When the acceptance determination unit 605 of the vehicle control device 1 (see FIG. 9) determines that the current position of the host vehicle is the retreat position 2202, it performs the acceptance determination process for the parking position selection described in FIG. 17. As shown in FIG. 22, at the retreat position 2202, the acceptance determination unit 605 determines that the parking position selection is acceptable. Therefore, when the host vehicle M1 stops at the retreat position 2202, the occupant selects, for example, the parking position 2201a as the parking position. Then, the vehicle control device 1 plans a parking trajectory 1401 that leads from the retreat position 2202 to the parking position 2201a. The cooperative behavior path (see the curved arrow) planned by the vehicle control device 1 shown in FIG. 22 allows the occupant's selection of the parking position to be accepted with only one stop. Reducing the number of stops can reduce the occupant's anxiety and discomfort, the occurrence of congestion in the parking lot, and adverse effects on surrounding traffic.

[0133] FIG. 23 is a diagram showing an example of the traveling speed of the host vehicle at which the vehicle control device 1 according to this embodiment can reduce the discomfort felt by the occupants of the host vehicle. The horizontal and vertical axes shown in FIG. 23 are the same as those shown in FIG. 21, and therefore a duplicated explanation will be omitted. As shown in FIG. 23, the host vehicle M1 temporarily stops (speed = 0) during a cooperative evacuation with the vehicle M2, and a parking position is also selected at that time. As can be seen by comparing with the diagram shown in FIG. 21, the execution of the parking position selection acceptance determination process in the vehicle control device 1 can prevent the vehicle from stopping multiple times. Therefore, it is possible to reduce the possibility of causing anxiety or discomfort to traffic participants such as the occupants of the host vehicle M1, pedestrians (not shown), and following vehicles, as well as congestion in the parking lot and adverse effects on surrounding traffic.

[0134] [effect] As described above, the vehicle control device 1 according to this embodiment generates candidate evacuation positions and candidate parking positions for the vehicle when there is another vehicle that requires cooperative action in a driving scene such as passing each other or parking, and selects an evacuation position from the candidate evacuation positions so as not to interfere with the predicted target behavior of the other vehicle. Furthermore, when parking in a parking lot or the like, the vehicle control device 1 accepts and determines whether to accept a parking position selection from the occupant when stopping at the selected evacuation position to avoid the other vehicle that requires cooperative action. Accepting and determining the selection of a parking position from the occupant at the evacuation position prevents the vehicle from repeatedly stopping when selecting a parking position, thereby reducing the possibility of causing anxiety or discomfort to traffic participants such as the occupant, pedestrians, and following vehicles, as well as congestion in the parking lot and adverse effects on surrounding traffic. Therefore, the vehicle control device 1 according to this embodiment can improve the efficiency and convenience of the vehicle's autonomous driving and automatic parking / stopping during passing each other, parking, and other situations.

[0135] Second Embodiment Next, a vehicle control device 1a according to a second embodiment of the present invention will be described. The vehicle control device 1a according to this embodiment aims to reduce discomfort felt by the occupants of the host vehicle and improve parking success rates when the host vehicle M1 and surrounding vehicles cooperate with each other. To this end, the occupant cooperative trajectory generation unit 508a of the vehicle control device 1a includes a confidence factor calculation unit (confidence factor calculation unit 609) that calculates a confidence factor for evaluating the probability of the predicted path of the other vehicle. The acceptance determination unit (acceptance determination unit 605) of the occupant cooperative trajectory generation unit 508a determines whether to accept the selection of a parking position at the evacuation position based on the confidence factor. Note that the components of the vehicle control device 1a other than the occupant cooperative trajectory generation unit 508a are the same as those of the vehicle control device 1 according to the first embodiment, and therefore redundant description will be omitted.

[0136] 24 is a diagram showing an example of the functional configuration of the occupant-cooperative trajectory generation unit 508a of the vehicle control device 1a according to this embodiment. As can be seen by comparing FIG. 24 with FIG. 9, the components of the occupant-cooperative trajectory generation unit 508a other than the confidence factor calculation unit 609 are the same as the components of the occupant-cooperative trajectory generation unit 508 (see FIG. 9), and therefore, redundant explanations of the similar components will be omitted here. The confidence factor calculation unit 609 is connected to the input side of the reception / determination unit 605, performs confidence factor calculation processing, and outputs the calculated confidence factor to the reception / determination unit 605.

[0137] [Certainty calculation processing] Next, a description will be given of the confidence factor calculation process in the confidence factor calculation unit 609. Fig. 25 is a flowchart showing the procedure of the confidence factor calculation process in the vehicle control device 1a according to this embodiment.

[0138] First, the certainty factor calculation unit 609 acquires various information such as a delay risk map, an occupant collaboration plan, external information, lane information, map information, etc. (step S2401).

[0139] Next, the confidence factor calculation unit 609 calculates the confidence factor of the predicted result of the other vehicle's path based on the acquired various information and the occupant status (step S2402). In this process, the confidence factor calculation unit (confidence factor calculation unit 609) calculates the confidence factor based on at least one of the behavior of the occupant of the other vehicle and the status of the lighting equipment mounted on the other vehicle. Specifically, when calculating the confidence factor based on the behavior of the occupant of the other vehicle, for example, a method using the line of sight of the occupant of the other vehicle can be considered. In this method, the line of sight (direction of gaze) of the occupant of the other vehicle is tracked by a monitoring camera mounted on the vehicle, and the line of sight of the occupant of the other vehicle is reflected in the prediction of the behavior (path) of the other vehicle. For example, if the direction of travel of the other vehicle estimated based on the line of sight of the occupant of the other vehicle checking left and right matches the direction of travel of the other vehicle predicted by the three-dimensional object behavior prediction unit 307 (see FIG. 4), the confidence factor calculation unit 609 increases the confidence factor of the predicted result of the other vehicle's path.

[0140] Furthermore, when calculating the confidence level based on the status of the lights mounted on the other vehicle, a method using, for example, the status of the turn signals (an example of a light) of the other vehicle can be considered. In this method, for example, when the direction of travel of the other vehicle estimated based on the turn signals of the other vehicle coincides with the direction of travel of the other vehicle predicted by the three-dimensional object behavior prediction unit 307 (see FIG. 4 ), the confidence level calculation unit 609 increases the confidence level of the predicted result of the path of the other vehicle. Furthermore, for example, when the turn signals of the other vehicle predicted in real time are not lit, the confidence level calculation unit 609 decreases the confidence level of the predicted result of the path of the other vehicle. Furthermore, the confidence level calculation unit 609 may calculate the confidence level of the predicted direction of travel of the other vehicle (the path of the other vehicle) based on the frequency and timing of blinking of the turn signals. Similarly, the confidence level may be calculated using the status of the brake lights (an example of a light). For example, the confidence level calculation unit 609 increases the confidence level of the predicted action of the other vehicle, such as deceleration or stopping, when the brake lights are lit. Furthermore, the certainty factor calculation unit 609 increases the certainty factor of the other vehicle's predicted acceleration or continued movement when the brake lights are not illuminated. Furthermore, the certainty factor calculation unit 609 may calculate the certainty factor of the other vehicle's predicted direction of travel based on the illumination duration or blinking pattern of the brake lights, etc.

[0141] Furthermore, in the process of step S2402, the certainty factor calculation unit (certainty factor calculation unit 609) may calculate the certainty factor of the predicted result of the other vehicle's route based on the field of view information of the occupants of the host vehicle. Specifically, for example, the vehicle control device 1a of the host vehicle can detect the positions of dynamic and static objects present around the host vehicle and analyze factors that obstruct the field of view from the host vehicle to the target position. The certainty factor calculation unit 609 increases the certainty factor of the other vehicle's route predicted based on information detected from a direction analyzed as not having factors that obstruct the field of view from the host vehicle to the target position. Furthermore, the certainty factor calculation unit 609 increases the certainty factor of the other vehicle's route predicted based on information detected by a sensor from a direction with fewer obstacles and dark areas, taking into account, for example, the arrangement and brightness of objects present within the field of view.

[0142] Furthermore, the method of calculating the certainty factor is based on the reliability of the sensor detection information. Specifically, for example, the certainty factor calculation unit 609 evaluates the reliability and accuracy of each sensor (radar, LiDAR, camera, etc.) mounted on the host vehicle, and calculates the certainty factor of the predicted result of the route of another vehicle around the host vehicle based on the evaluation result. For example, if multiple sensors show the same result, the certainty factor calculation unit 609 increases the certainty factor of the predicted result of the route of another vehicle.

[0143] Alternatively, the confidence level may be calculated based on past prediction data, patterns, etc. For example, the confidence level calculation unit 609 analyzes past movement data of the vehicle to be predicted stored in the storage unit 308 to extract movement patterns in similar situations. Then, the confidence level calculation unit 609 predicts the behavior of other vehicles in the current situation based on the extracted patterns, and calculates the confidence level of the prediction result based on the success rate of similar cases in the past, etc.

[0144] Furthermore, machine learning, deep learning, or the like may be used as a method for calculating the confidence level. For example, the behavior of other vehicles is predicted by using a machine learning or deep learning model based on past sensor detection information or real-time sensor detection information. When this method is applied, the confidence level calculation unit 609 can calculate the confidence level of the predicted result of the path of other vehicles based on the reliability and uncertainty of the model used.

[0145] Another possible method for calculating the confidence level is the uncertainty propagation method. For example, the uncertainty of the sensor detection information and the model is estimated using a method such as the Monte Carlo method or a Kalman filter, and the estimation result is reflected in the confidence level of the predicted result of the other vehicle's path. For example, the higher the estimated uncertainty, the lower the confidence level of the predicted result of the other vehicle's path.

[0146] After the process of step S2402 in Fig. 25, the certainty factor calculation unit 609 stores the calculated certainty factor in the storage unit 308 (see Fig. 2) (step S2403). After the process of step S2403, the certainty factor calculation process ends.

[0147] Next, a description will be given of the parking position selection acceptance determination process by the acceptance determination unit 605 (see FIG. 24) based on the certainty factor calculated by the certainty factor calculation unit 609. FIG. 26 is a flowchart showing the procedure of the parking position selection acceptance determination process in the vehicle control device 1a according to this embodiment. As can be seen from comparing FIG. 26 with FIG. 17, the processing of each step other than step S2501 of the parking position selection acceptance determination process according to this embodiment is the same as the processing of each step shown in FIG. 17, so duplicated explanations will be omitted.

[0148] 26, the process of step S2501 is performed when it is determined that the current position of the vehicle is a withdrawal position (YES determination in step S1802). In the process of step S2501, the reception determination unit 605 (see FIG. 24) determines whether the certainty factor calculated by the certainty factor calculation unit 609 is equal to or greater than a predetermined value.

[0149] If the acceptance determination unit 605 determines that the certainty factor calculated by the certainty factor calculation unit 609 is equal to or greater than a predetermined value (YES determination in step S2501), it performs the process of step S1804, i.e., the process of making an acceptance determination for the parking position selection. On the other hand, if the acceptance determination unit 605 determines that the certainty factor calculated by the certainty factor calculation unit 609 is less than the predetermined value (NO determination in step S2501), it performs the process of step S1803, i.e., the process of not making an acceptance determination for the parking position selection.

[0150] Here, the predetermined value for determining the degree of certainty is a threshold value of the degree of certainty registered in advance. If the degree of certainty is equal to or greater than the predetermined value, the reliability of the predicted route (movement) of the other vehicle is determined to be high, and if the degree of certainty is less than the predetermined value, the reliability of the predicted route (movement) of the other vehicle is determined to be low. In other words, in this embodiment, if the reliability of the predicted route (movement) of the other vehicle is low, the selection of the parking position is not accepted.

[0151] Next, an example of the traveling of the host vehicle when the vehicle control device 1a performs a decision to accept the selection of a parking position will be described. Fig. 27 is a diagram showing an example of the traveling of the host vehicle when the vehicle control device 1a according to this embodiment performs a decision to accept the selection of a parking position.

[0152] In the parking lot shown in FIG. 27, the host vehicle M1 is located at the entrance / exit A. Parking position 2201b is vacant. Vehicle M2 parked in parking position 2201a is estimated to be about to leave. It is unclear whether vehicle M3 at the back of the parking lot is searching for a parking space or about to leave. In this situation, the leave positions determined by the leave position determination unit 603 are leave position_1 to leave position_3 shown in the figure. When the host vehicle M1 stops at leave position_1, it is impossible to predict whether vehicle M2 is leaving or not, and the parking position candidates may change, so the reception determination unit 605 determines that the acceptance of the parking position selection is not permitted. Next, when the host vehicle M1 stops at leave position_2, the situation is almost the same as at leave position_1, so the reception determination unit 605 determines that the acceptance of the parking position selection is not permitted. Next, when the host vehicle M1 stops at the evacuation position_1, the host vehicle position is close to both the parking position 2201a and the parking position 2201b. At this time, if the vehicle M3 is not moving, it is predicted that the vehicle is likely to stop temporarily. If the left turn signal of the vehicle M3 is flashing, it is predicted that the vehicle will attempt to park at the parking position 2201b. If the right turn signal of the vehicle M3 is flashing, it is predicted that the vehicle will attempt to park at the parking position 2201a. If the vehicle M3 is traveling straight, it is predicted that the vehicle will attempt to leave the parking lot. In either of the above cases, the certainty of the prediction result is high. Therefore, if the left turn signal of the vehicle M3 is not flashing, the acceptance determination unit 605 determines that the parking position selection is acceptable. Also, at this time, if the vehicle M2 is in the process of leaving the parking lot, the vehicle M3 can also be parked at the parking position 2201a even if it is predicted that the vehicle will attempt to park at the parking position 2201b.

[0153] The confidence level calculated by the confidence level calculation unit 609 may be used not only in the acceptance determination process for parking position selection, but also in generating a speed profile in the cooperative behavior trajectory generation unit 505 or the occupant cooperative speed generation unit 608 of the occupant cooperative trajectory planning unit 606.

[0154] For example, the occupant cooperative trajectory planning unit (occupant cooperative trajectory planning unit 606) adjusts the speed at which the host vehicle travels while tracking the trajectory based on the confidence level. Specifically, when the confidence level of the predicted other vehicle's behavior is low (below a predetermined value), the occupant cooperative trajectory planning unit 606 reduces the host vehicle's speed so that the host vehicle travels at a low speed (for example, 5 km / h or less) until the other vehicle's behavior can be confirmed. Furthermore, when the confidence level of the predicted other vehicle's behavior is below a predetermined value but the difference from the predetermined value is within a certain range (when the confidence level is medium), the occupant cooperative trajectory planning unit 606 generates a speed profile that causes the host vehicle to travel at a medium speed (for example, about 10 km / h) while continuously monitoring the surrounding environment. At this time, the selection of parking positions is not limited, and guidance to the selected parking position continues, but the host vehicle is controlled to travel carefully.

[0155] Furthermore, the calculation of the confidence factor by the confidence factor calculation unit 609 is not limited to being performed only on the predicted result of the path (movement) of the other vehicle. For example, the confidence factor may be calculated based on the surrounding environment information of the host vehicle detected by a sensor. In this case, for example, if the confidence factor of the information detected by the sensor is high that the surrounding environment of the host vehicle is bright and there are no obstacles, the occupant cooperative trajectory planning unit 606 may cause the host vehicle to travel at a normal speed (e.g., approximately 20 km / h) and guide the host vehicle to a parking position. FIG. 28 shows an example of adjusting the traveling speed in this case. FIG. 28 is a diagram for explaining an example of adjusting the traveling speed based on the confidence factor in the vehicle control device 1a according to this embodiment. As shown in FIG. 28, when the confidence factor of the surrounding environment information of the host vehicle is high, the occupant cooperative trajectory planning unit 606 sets the target upper limit speed high, and when the confidence factor of the surrounding environment information of the host vehicle is low, the target upper limit speed is set low.

[0156] [effect] As described above, the vehicle control device 1a according to this embodiment calculates the confidence level of the predicted result of the route (movement) of another vehicle, and determines whether to accept the selection of a parking position at the evacuation position based on the calculated confidence level. If the confidence level of the predicted result of the movement of the other vehicle is low, the vehicle control device 1a does not accept the selection of a parking position. This operation control prevents the occupant from being unable to park in the desired parking position or from having to reverse due to being unable to drive cooperatively with other vehicles, thereby enabling a smooth evacuation action. Therefore, the vehicle control device 1a according to this embodiment has the same effects as the vehicle control device 1 according to the first embodiment, and can also reduce opportunities for traffic participants to disrupt traffic flow and factors that cause congestion. Furthermore, the vehicle control device 1a calculates the confidence level of the surrounding environment information of the host vehicle detected by the sensor, and adjusts the traveling speed of the host vehicle according to the calculated confidence level, thereby avoiding sudden braking and sudden acceleration, preventing the occupant from feeling anxious or uncomfortable, and improving driving safety.

[0157] <Application example> In the above embodiments, examples have been described in which the present invention is applied to a parking scene in a parking lot, but the present invention is not limited to this. The present invention can also be applied to a scene in which the vehicle cooperates with surrounding vehicles on a narrow road (see scene (a) in FIG. 29 ) or a scene in which the vehicle cooperates with oncoming vehicles to avoid an obstacle in the path of the vehicle (see scene (b) in FIG. 29 ).

[0158] FIG. 29 illustrates a scene in which the vehicle cooperates with nearby vehicles according to an application example of the present invention. Scene (a) in FIG. 29 illustrates a scene in which the vehicle cooperates with nearby vehicles on a narrow road. Black dots in scene (a) in FIG. 29 represent obstacles. On the narrow road illustrated in scene (a) in FIG. 29, the obstacle, an oncoming vehicle M2 of the host vehicle M1, and a vehicle M3 approaching from behind are simultaneously present. Scene (b) in FIG. 29 illustrates a scene in which the vehicle cooperates with oncoming vehicles to avoid the obstacle in the path of the host vehicle. On the road illustrated in scene (b) in FIG. 29, there is an obstacle P3 in the path of the host vehicle M1, and there is a high possibility that the host vehicle M1 will obstruct the oncoming vehicle M2 when avoiding the obstacle P3. In cases such as scenes (a) and (b) in FIG. 29, the vehicle control device 1 (or vehicle control device 1a) of the host vehicle M1 during autonomous driving cannot determine a retreat position and therefore issues a cooperation request to the occupant via the HMI. When the occupant specifies a retreat location via the HMI, the vehicle control device 1 (or vehicle control device 1a) performs the processes described in each of the above embodiments, plans the optimal route to the retreat location, and performs automatic retreat operation.

[0159] It should be noted that the present invention is not limited to the above-described embodiments, and various other applications and modifications are possible without departing from the gist of the present invention as set forth in the claims. For example, the above-described embodiments have described the configuration of a vehicle control device in detail and specifically in order to clearly explain the present invention, and are not necessarily limited to having all of the described configurations. Furthermore, it is possible to replace part of the configuration of the embodiments described here with the configuration of other embodiments, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is also possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0160] In addition, the passing operation described in Figure 6 etc. is an example of passing by pulling the vehicle to the left side of the road in areas where vehicles drive on the left side of the road, and in areas where vehicles drive on the right side of the road, the left and right directions when passing are reversed.

[0161] In each of the above-described embodiments, a driving trajectory (occupant cooperative trajectory) is generated (calculated) and the vehicle is driven automatically along the driving trajectory. Generally, a driving trajectory includes information on a coordinate position on a road and the time when the vehicle passes through the coordinate position. In the present invention, the driving is controlled based on the information on the coordinate position and the time. In contrast to this, the travel trajectory may be information on a so-called travel route that has only information on coordinate positions on the road, without information on the time when the vehicle passes each coordinate position. When passing other vehicles, it is preferable to determine to which position the vehicle will move at each time while predicting the position of the oncoming vehicle at each time, but in a situation where the oncoming vehicle is stopped, for example, a travel route that has only information on coordinate positions may be generated instead of a travel trajectory. By generating a travel route in this manner, it is not necessary to handle time information, and the travel trajectory (travel route) can be generated more easily.

[0162] Furthermore, in the configuration shown in FIG. 3, the vehicle control device 1 configured as a computer is configured as a device that performs the processing of each of the above-mentioned embodiments, but a program implemented in an existing vehicle control device 1 may be modified to perform similar processing. In this case, the program may be prepared in the memory of the computer shown in FIG. 3, or may be stored in an external memory, an IC card, an SD card, an optical disk, or other recording medium and transferred. Furthermore, a part or all of the vehicle control device 1 may be realized by dedicated hardware such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0163] In addition, in each of the above-described embodiments, the control lines and information lines of the vehicle control device and each processing function unit are shown as those considered necessary for explanation, and not all control lines and information lines in the product are necessarily shown. In reality, it may be considered that almost all components are interconnected. Furthermore, with regard to each flowchart showing the procedure of each process described in each of the above-described embodiments, the order of the processes may be changed or multiple processes may be executed simultaneously as long as the process results are the same.

[0164] Furthermore, although the term "parallel" is used in this specification, this term does not mean only "parallel" in the strict sense, but also includes the meaning of "parallel" in the strict sense and also includes the meaning of "approximately parallel" within a range in which the function can be exerted. [Explanation of symbols]

[0165] 1, 1a... vehicle control device, 201... automatic driving planning unit, 203... vehicle driving control unit, 204... actuator control unit, 205... risk map generation unit, 206... vehicle network, 305... sensor information processing unit, 306... map information processing unit, 307... three-dimensional object behavior prediction unit, 308... memory unit, 309A... retention risk map generation unit, 309B... fixed obstacle risk map generation unit, 309C... moving obstacle risk map generation unit, 310... self-position estimation processing unit, 501... driving planning unit, 502... lane keeping track Path generation unit 503... lane change trajectory generation unit, 504... obstacle avoidance trajectory generation unit, 505... cooperative behavior trajectory generation unit, 506... trajectory arbitration unit, 507... trajectory planning unit, 508, 508a... occupant cooperative trajectory generation unit, 509... driving mode management unit, 601... evacuation position candidate generation unit, 602... parking / stopping position candidate generation unit, 603... evacuation position determination unit, 604... route candidate generation unit, 605... acceptance determination unit, 606... occupant cooperative trajectory planning unit, 607... occupant cooperative path generation unit, 608... occupant cooperative speed generation unit, 609... confidence factor calculation unit

Claims

1. a candidate evacuation position generating unit that generates candidate evacuation positions, which are candidates for positions where the host vehicle will evacuate, based on a predicted result of the position of the host vehicle and the route of another vehicle; a parking / stopping position candidate generating unit that generates parking / stopping position candidates that are candidates for parking / stopping positions where the host vehicle is to be parked; an evacuation position determination unit that determines an evacuation position for the host vehicle based on the evacuation position candidate and the parking / stopping position candidate; a route candidate generation unit that generates route candidates that are candidates for a route from the position of the vehicle to the parking / stopping position candidate via the evacuation position; an acceptance / determination unit that determines whether or not a selection of a parking / stopping position from an occupant of the vehicle is accepted at the evacuation position; an occupant collaborative trajectory planning unit that plans a trajectory of the vehicle based on the determination result by the reception determination unit. Vehicle control device.

2. The occupant cooperative trajectory planning unit plans a trajectory of the host vehicle from the position of the host vehicle to the evacuation position determined by the reception / determination unit to accept the selection of the parking / stopping position, and a trajectory of the host vehicle from the evacuation position to a parking position received from the occupant from among the parking / stopping position candidates. The vehicle control device according to claim 1 .

3. The occupant cooperative trajectory planning unit plans a trajectory of the host vehicle from the position of the host vehicle to at least one of the candidate parking / stopping positions when the reception / determination unit determines that the selection of the parking / stopping position from the occupant at the evacuation position is not accepted. The vehicle control device according to claim 1 .

4. The crew collaborative trajectory planning unit calculating an individual evaluation value for evaluating a predetermined evaluation target for the route candidate from the position of the vehicle to the parking / stopping position candidate via the evacuation position; calculating a comprehensive evaluation value of the route candidate based on the individual evaluation values; The route candidates are selected based on the overall evaluation value, and a trajectory of the vehicle is planned. The vehicle control device according to claim 3.

5. The individual evaluation values ​​include at least one of a safety evaluation value, a convenience evaluation value, a ride comfort evaluation value, a discomfort evaluation value, and an evaluation value of a feeling of oppression from an oncoming vehicle. The vehicle control device according to claim 4.

6. a certainty factor calculation unit that calculates a certainty factor that evaluates the probability of the predicted route of the other vehicle; The acceptance / determination unit determines whether to accept the selection of the parking / stopping position at the evacuation position based on the certainty factor. The vehicle control device according to claim 1 .

7. The certainty factor calculation unit calculates the certainty factor based on at least one of an action of an occupant of the other vehicle and a state of a lighting device mounted on the other vehicle. The vehicle control device according to claim 6.

8. The certainty factor calculation unit calculates the certainty factor based on visual field information of an occupant of the host vehicle. The vehicle control device according to claim 6.

9. The occupant collaborative trajectory planning unit adjusts the speed at which the vehicle travels while following the trajectory of the host vehicle based on the degree of certainty. The vehicle control device according to claim 6.

10. The means for accepting the selection of the parking / stopping position from the occupant of the vehicle outputs different notification information depending on whether the selection of the parking / stopping position is accepted or not accepted. The vehicle control device according to claim 1 .

11. The evacuation location determination unit evaluates the evacuation location candidates with respect to predetermined evaluation items and determines the evacuation location based on the evaluation results. The vehicle control device according to claim 1 .

12. The predetermined evaluation items include at least one of safety, efficiency, and convenience. The vehicle control device according to claim 11.

13. A vehicle control method executed by a computer, comprising: a candidate evacuation position generating step of generating candidate evacuation positions, which are candidates for positions where the host vehicle will evacuate, based on the predicted position of the host vehicle and the routes of other vehicles; a parking / stopping position candidate generating step of generating parking / stopping position candidates that are candidates for parking / stopping positions where the host vehicle is to be parked; an evacuation position determination step of determining an evacuation position for the host vehicle based on the evacuation position candidate and the parking / stopping position candidate; a route candidate generating step of generating route candidates that are candidates for a route from the position of the vehicle to the parking / stopping position candidate via the evacuation position; an acceptance / determination step of determining whether or not a selection of a parking / stopping position from an occupant of the vehicle is accepted at the evacuation position; and a step of planning a trajectory of the vehicle based on the determination result of the reception determination step. Vehicle control method.

Images