WO2024031780A1 - 路径规划方法、车辆及存储介质 - Google Patents

路径规划方法、车辆及存储介质 Download PDF

Info

Publication number
WO2024031780A1
WO2024031780A1 PCT/CN2022/119271 CN2022119271W WO2024031780A1 WO 2024031780 A1 WO2024031780 A1 WO 2024031780A1 CN 2022119271 W CN2022119271 W CN 2022119271W WO 2024031780 A1 WO2024031780 A1 WO 2024031780A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
current vehicle
current
obstacles
path
Prior art date
Application number
PCT/CN2022/119271
Other languages
English (en)
French (fr)
Inventor
康代轲
李力耘
邱杰
肖智冲
李杨
Original Assignee
广州小鹏自动驾驶科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州小鹏自动驾驶科技有限公司 filed Critical 广州小鹏自动驾驶科技有限公司
Publication of WO2024031780A1 publication Critical patent/WO2024031780A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes

Definitions

  • This application relates to the field of autonomous driving technology, and in particular to a path planning method, vehicle and storage medium.
  • smart cars With the continuous development of smart car technology, smart cars generally have automatic driving functions.
  • the path planning method of the related art has shortcomings in planning the path of the left-turn intersection.
  • this application provides a path planning method, vehicle and storage medium, which can plan and generate a safer left-turn path in a left-turn intersection scenario and improve driving safety.
  • the first aspect of this application provides a path planning method, including:
  • a preset algorithm is used to generate a planned left turn path for the current vehicle.
  • several reverse-driving vehicles are identified from the obstacles according to preset rules, including:
  • the obstructed vehicle is identified from the obstacle, and based on the traveling direction of the obstructed vehicle being opposite to the direction of the current vehicle's traveling path, the obstructed vehicle is identified as a vehicle traveling in the opposite direction.
  • obtaining the current vehicle current pose and the current vehicle target pose includes:
  • the target pose of the current vehicle is obtained based on the high-precision map information and navigation information of the current vehicle, and the current pose of the current vehicle is obtained based on the positioning information of the current vehicle.
  • constructing a virtual static obstacle using the identified several reverse-driving vehicles includes:
  • using a preset algorithm to generate a planned left turn path for the current vehicle with reference to the current vehicle's current posture, the current vehicle target posture, and the virtual static obstacle includes:
  • the obtaining of identified obstacles includes:
  • a second aspect of this application provides a vehicle, including:
  • the pose acquisition module is used to obtain the current pose of the current vehicle and the target pose of the vehicle;
  • Perception module used to obtain identified obstacles
  • a virtual static obstacle construction module used to identify a number of reverse-driving vehicles from the obstacles according to preset rules, and use the identified several reverse-driving vehicles to construct virtual static obstacles;
  • a path planning module configured to refer to the current vehicle's current posture, the current vehicle's target posture, and the virtual static obstacle, and use a preset algorithm to generate a planned left turn path for the current vehicle's driving.
  • the virtual static obstacle building module includes:
  • a reverse vehicle identification module is used to identify an obstructed vehicle from the obstacle, and recognize that the obstructed vehicle is a reverse-traveling vehicle based on the traveling direction of the obstructed vehicle being opposite to the direction of the current vehicle's traveling path.
  • the virtual static obstacle building module includes:
  • a static graph construction module for traversing all identified reverse-driving vehicles, and based on the geometric boundaries of the reverse-driving vehicles, constructing virtual static obstacles extending a set distance to the left of the driving direction of the reverse-driving vehicles. , construct a static obstacle map based on the virtual static obstacles.
  • the path planning module uses the current vehicle pose as the starting point of the planned path, the current vehicle target pose as the end point of the planned path, and all the objects in the static obstacle map.
  • the virtual static obstacles are obstacles in the planned path.
  • the hybrid A* algorithm is used to search the planned path, and the left-turn planned path of the current vehicle that satisfies kinematic constraints is obtained.
  • the pose acquisition module acquires the target pose of the current vehicle based on the high-precision map information and navigation information of the current vehicle, and acquires the current pose of the current vehicle based on the positioning information of the current vehicle.
  • the sensing module collects images or videos in front or to the side of the current vehicle, and identifies obstacles from the images or videos.
  • a third aspect of the present application provides a computer-readable storage medium on which executable code is stored.
  • the processor is caused to execute the method as described above.
  • This application identifies several reverse-driving vehicles from obstacles according to preset rules, and uses the identified several reverse-driving vehicles to construct virtual static obstacles; then the current vehicle's current pose, the current vehicle target pose, and The virtual static obstacle uses a preset algorithm to generate a planned left turn path for the current vehicle driving. Since the solution of this application is to make the dynamic problem static and construct the dynamic reverse traffic flow as a static obstacle, a preset algorithm that can handle static obstacles, such as the hybrid A* algorithm, can be used to generate a collision-free solution that satisfies the kinematic constraints.
  • the driving path is used as the planned left turn path of the current vehicle, so that given the current vehicle, that is, the starting position and target position of the own vehicle, the reverse traffic flow can be avoided and the vehicle can pass safely without protection. Turn left at the intersection.
  • Figure 1 is a schematic diagram showing a conflict between a left-turn path of a vehicle and a forward path of reverse traffic shown in the related art
  • Figure 2 is a first flow diagram of the path planning method shown in this application.
  • Figure 3 is a second flow diagram of the path planning method shown in this application.
  • Figure 4 is a schematic diagram of the application framework of the path planning method shown in this application.
  • Figure 5 is a schematic diagram of identifying vehicles traveling in the opposite direction in the path planning method shown in this application;
  • Figure 6 is a schematic diagram comparing the current vehicle left turn path generated by this application and the current vehicle left turn path generated by related technologies;
  • FIG. 7 is a schematic structural diagram of the vehicle shown in this application.
  • FIG 8 is another structural schematic diagram of the vehicle shown in this application.
  • first information may also be called second information, and similarly, the second information may also be called first information. Therefore, features defined as “first” and “second” may explicitly or implicitly include one or more of these features.
  • “plurality” means two or more than two, unless otherwise explicitly and specifically limited.
  • the path planning method of the related art has shortcomings in planning the path of the left-turn intersection. As shown in Figure 1, in the scenario of passing through an unprotected left-turn intersection, when the current vehicle 10 turns left at the left-turn intersection, the planned path conflicts with the forward path of the reverse traffic flow 20, which will cause risks.
  • This application provides a path planning method that can plan and generate a safer left-turn path in left-turn intersection scenarios and improve driving safety.
  • Figure 2 is a first flow diagram of the path planning method shown in this application. This method can be applied to vehicles.
  • the method includes:
  • the target pose of the current vehicle can be obtained based on the high-precision map information and navigation information of the current vehicle, and the current pose of the current vehicle can be obtained based on the positioning information of the current vehicle.
  • This application can use recognition technology in related technologies to identify obstacles from images or videos collected by the perception module.
  • the obstructed vehicle can be identified from the obstacle, and based on the traveling direction of the obstructed vehicle being opposite to the direction of the current vehicle's traveling path, the obstructed vehicle can be identified as a vehicle traveling in the opposite direction.
  • a virtual static obstacle can be constructed extending a set distance to the left of the driving direction of the reverse-driving vehicle
  • a static obstacle can be constructed based on the virtual static obstacles. Obstacle map. This application constructs the dynamic reverse traffic flow as a static obstacle, which can realize the staticization of dynamic problems.
  • the current vehicle pose is used as the starting point of the planned path
  • the current vehicle target pose is used as the end point of the planned path
  • the virtual static obstacles in the static obstacle map are used as obstacles in the planned path
  • the hybrid A* algorithm is used Perform planned path search to obtain the planned left-turn path for the current vehicle that satisfies kinematic constraints.
  • the hybrid A* algorithm is an algorithm that considers the actual motion constraints of the object based on the A* algorithm.
  • the hybrid A* algorithm performs heuristic search in a continuous coordinate system and can ensure that the generated trajectory satisfies the kinematic constraints of the vehicle.
  • the difference between the hybrid A* algorithm and the ordinary A* algorithm is that the path planned by the hybrid A* algorithm takes into account the kinematic constraints of the vehicle, that is, it satisfies the maximum curvature constraint of the vehicle.
  • This application identifies several reverse-driving vehicles from obstacles based on preset rules, and uses the identified several reverse-driving vehicles to construct virtual static obstacles; then you can refer to the current vehicle's current pose, the current vehicle target pose, and the virtual static obstacle Obstacles, use a preset algorithm to generate a planned left turn path for the current vehicle. Since the solution of this application is to make the dynamic problem static and construct the dynamic reverse traffic flow as a static obstacle, a preset algorithm that can handle static obstacles, such as the hybrid A* algorithm, can be used to generate a collision-free solution that satisfies the kinematic constraints.
  • the driving path is used as the planned left turn path of the current vehicle, so that given the current vehicle, that is, the starting position and target position of the own vehicle, the reverse traffic flow can be avoided and the vehicle can pass safely without protection. Turn left at the intersection.
  • Figure 3 is a second schematic flowchart of the path planning method shown in this application.
  • Figure 4 is a schematic diagram of the application framework of the path planning method shown in this application.
  • This application provides an obstacle avoidance path planning method that obtains the current vehicle target pose based on high-precision map information and navigation information, obtains the current vehicle's current pose based on positioning information, and obtains all obstacle vehicle information from the perception module.
  • the opposite vehicle can be determined based on the position and attitude of the obstructed vehicle.
  • the dynamic problem is made static, and a static obstacle map is established that takes into account reverse traffic flow.
  • a hybrid A* algorithm that can handle static obstacles is used to search for a collision-free left turn planning path that satisfies kinematic constraints.
  • Hybrid A* algorithm (Hybrid A* algorithm) is a graph search algorithm that is improved on the A* algorithm. Its difference from the ordinary A* algorithm is that the path planned by the hybrid A* algorithm takes into account the kinematic constraints of the vehicle, that is, it satisfies The maximum curvature constraint of the vehicle is determined.
  • Motion constraints are a type of constraints in dynamic systems.
  • the constraint equations contain not only the coordinates of each particle, but also the velocity of each particle. Since the velocity of a particle is mathematically expressed as the differential of the particle coordinates with respect to time, it is also called "differential constraint".
  • the kinematic constraints of the vehicle generally refer to the fact that when the vehicle is driving normally on the road, its lateral (y-axis) and normal (z-axis) velocities are zero unless sideslip or jumping occurs. Vehicle movement is subject to kinematic constraints, so the vehicle cannot achieve instantaneous lateral movement.
  • Front-wheel drive vehicles must rely on the steering of the front wheels to achieve lane changes, steering, etc., and cannot move too fast on curves.
  • the hybrid A* algorithm is an improvement of the A* algorithm.
  • the hybrid A* algorithm satisfies the kinematic constraints of the vehicle.
  • the Reed-Shepp curve or Dubins curve can be used to connect the target, and the body outline can be added to determine whether it collides with obstacles. If there is no collision with the obstacle, the curve is retained and the path is generated; if it collides with the obstacle, the curve is discarded, and the node is searched again from the open list and expanded again.
  • the Reeds-Shepp curve is composed of several arcs with fixed radius and a straight line segment, and the radius of the arc is the minimum turning radius of the vehicle.
  • the Dubins curve is similar to the Reeds-Shepp curve, except that there is an additional constraint: the vehicle can only drive forward, not backward (cannot engage reverse gear).
  • the method includes:
  • the target pose of the current vehicle is obtained based on the high-precision map information and navigation information of the current vehicle and recorded as X_t
  • the current pose of the current vehicle is obtained based on the positioning information of the current vehicle and recorded as X_e.
  • This application can collect images or videos of the front or side of the current vehicle through the perception module of the current vehicle, and use recognition technology in related technologies to identify obstacles from the images or videos collected by the perception module.
  • the obstacle detection may be image-based obstacle detection, lidar-based obstacle detection, or obstacle detection based on the fusion of vision and lidar, etc. This application is not limited to this.
  • the obstacle vehicle is identified from the obstacle, and all the obstacle vehicles recognized from the perception module are traversed. According to the direction of the obstacle vehicle's driving direction being opposite to the direction of the current vehicle's driving path, the obstacle vehicle is identified as a vehicle traveling in the opposite direction.
  • the obstructed vehicle is a vehicle traveling in the opposite direction (also called a reverse obstructed vehicle).
  • the current vehicle is 501 and the obstacle vehicle is 502.
  • the curve is the planned driving path 503 of the current vehicle 501.
  • the obstacle vehicle 502 is Vehicles traveling in the opposite direction.
  • the center point of the obstacle vehicle 502 can be projected onto the current vehicle 501 driving path 503, the projection point is found, and then the heading (heading angle) of the projection point is obtained. If the heading angle of this projection point is the same as the heading angle of the obstacle vehicle 502 In the opposite direction, it means that the obstacle vehicle 502 is a vehicle traveling in the opposite direction.
  • the virtual static obstacles in the static obstacle map are used as the planned path
  • a set algorithm such as the hybrid A* algorithm is used to search for the planned path. Since the hybrid A* algorithm is an algorithm that satisfies vehicle kinematics, the hybrid A* algorithm can ultimately be used to generate a drivable path that satisfies kinematic constraints and can avoid reverse traffic flow.
  • the current vehicle turns left in the left-turn intersection scenario according to the generated drivable path, it can avoid the reverse traffic flow, thereby improving driving safety.
  • FIG. 6 is a schematic diagram comparing the current vehicle left turn path generated by the present application and the current vehicle left turn path generated by related technologies.
  • the current vehicle's current pose X_e and the current vehicle's target pose X_t are shown in Figure 6. If the reverse traffic flow is not considered, the hybrid A* algorithm is directly used for path search according to relevant technical methods, and the path searched is the blue path 101 in Figure 6. But obviously this is unreasonable, because the blue path 101 rushed into the reverse traffic flow and intersected with the driving path of the obstructed vehicle, which caused a conflict.
  • the black box with an arrow in Figure 6 represents the reverse-driving vehicles 602 in reverse traffic flow that are filtered out using geometric relationships based on the information provided by the sensing module.
  • This application plan makes the dynamic problem static, constructs the dynamic reverse traffic flow as a static obstacle, and can quickly generate a collision-free path from one specified pose to another specified pose in the free space as the planned path, that is, generate the current
  • the left-turn collision-free path from the pose to the target pose can ensure safety while ensuring the comfort of the path, and improve the traffic efficiency of the autonomous driving system through unprotected left-turn intersections.
  • this application also provides a vehicle.
  • FIG. 7 is a schematic structural diagram of the vehicle shown in this application.
  • the vehicle 70 provided by this application includes: a pose acquisition module 71, a perception module 72, a virtual static obstacle construction module 73, and a path planning module 74.
  • the pose acquisition module 71 is used to acquire the current vehicle pose and the vehicle target pose.
  • the pose acquisition module 71 can acquire the target pose of the current vehicle based on the high-precision map information and navigation information of the current vehicle, and acquire the current pose of the current vehicle based on the positioning information of the current vehicle.
  • Perception module 72 is used to obtain identified obstacles.
  • the perception module 72 can collect images or videos in front of or to the side of the current vehicle, and use recognition technology in related technologies to identify obstacles from the images or videos collected by the perception module 72 .
  • the virtual static obstacle construction module 73 is used to identify several reverse-driving vehicles from the obstacles according to preset rules, and use the identified several reverse-driving vehicles to construct virtual static obstacles.
  • the path planning module 74 is used to generate a planned left turn path for the current vehicle by using a preset algorithm with reference to the current vehicle's current posture, the current vehicle's target posture, and virtual static obstacles.
  • the path planning module 74 uses the current vehicle's current posture as the starting point of the planned path, uses the current vehicle target posture as the end point of the planned path, uses the virtual static obstacles in the static obstacle map as obstacles in the planned path, and uses hybrid A *The algorithm performs planned path search and obtains the planned left-turn path for the current vehicle that satisfies kinematic constraints.
  • the virtual static obstacle construction module 73 may include: a reverse vehicle recognition module 731 and a static image construction module 732.
  • the reverse vehicle identification module 731 is used to identify the obstructed vehicle from the obstacle and identify the obstructed vehicle as the reverse vehicle according to the direction of travel of the obstructed vehicle being opposite to the direction of the current vehicle's traveling path.
  • the static graph construction module 732 is used to traverse all identified reverse-driving vehicles, and construct virtual static obstacles based on the geometric boundaries of the reverse-driving vehicles by extending a set distance to the left of the driving direction of the reverse-driving vehicles. Static Obstacles Construct a static obstacle graph.
  • the vehicle provided by this application identifies several reverse-driving vehicles from obstacles according to preset rules, and uses the identified several reverse-driving vehicles to construct virtual static obstacles; then it can refer to the current vehicle's current posture and current vehicle target position. pose and virtual static obstacles, and use a preset algorithm to generate a planned left-turn path for the current vehicle. Since the solution of this application is to make the dynamic problem static and construct the dynamic reverse traffic flow as a static obstacle, a preset algorithm that can handle static obstacles, such as the hybrid A* algorithm, can be used to generate a collision-free solution that satisfies the kinematic constraints.
  • the driving path is used as the planned left turn path of the current vehicle, so that given the current vehicle, that is, the starting position and target position of the own vehicle, the reverse traffic flow can be avoided and the vehicle can pass safely without protection. Turn left at the intersection.
  • FIG 8 is another structural schematic diagram of the vehicle shown in this application.
  • vehicle 1000 includes memory 1010 and processor 1020 .
  • the processor 1020 can be a central processing unit (Central Processing Unit, CPU), or other general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or an on-site processor.
  • Programmable gate array Field-Programmable Gate Array, FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • Memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and persistent storage. Among them, ROM can store static data or instructions required by the processor 1020 or other modules of the computer. Persistent storage may be readable and writable storage. Persistent storage may be a non-volatile storage device that does not lose stored instructions and data even when the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (eg, magnetic or optical disk, flash memory) as the permanent storage device. In other embodiments, the permanent storage device may be a removable storage device (eg, floppy disk, optical drive).
  • System memory can be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory.
  • System memory can store some or all of the instructions and data the processor needs to run.
  • memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (eg, DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks, and/or optical disks may also be used.
  • memory 1010 may include a readable and/or writable removable storage device, such as a compact disc (CD), a read-only digital versatile disc (eg, DVD-ROM, dual-layer DVD-ROM), Read-only Blu-ray discs, ultra-density discs, flash memory cards (such as SD cards, min SD cards, Micro-SD cards, etc.), magnetic floppy disks, etc.
  • a readable and/or writable removable storage device such as a compact disc (CD), a read-only digital versatile disc (eg, DVD-ROM, dual-layer DVD-ROM), Read-only Blu-ray discs, ultra-density discs, flash memory cards (such as SD cards, min SD cards, Micro-SD cards, etc.), magnetic floppy disks, etc.
  • Computer-readable storage media do not contain carrier waves and transient electronic signals that are transmitted wirelessly or wired.
  • the memory 1010 stores executable code.
  • the processor 1020 can be caused to execute part or all of the above-mentioned methods.
  • the method according to the present application can also be implemented as a computer program or computer program product, which computer program or computer program product includes computer program code instructions for executing part or all of the steps in the above method of the present application.
  • the application may also be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) with executable code (or computer program or computer instruction code) stored thereon,
  • executable code or computer program or computer instruction code
  • the processor of the electronic device or server, etc.
  • the processor is caused to execute part or all of the respective steps of the above method according to the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请提供一种路径规划方法、车辆及存储介质。该路径规划方法，包括：获取当前车辆当前位姿和当前车辆目标位姿；获取识别的障碍物；根据预设规则从所述障碍物中识别出若干反向行驶车辆，利用识别出的所述若干反向行驶车辆构建虚拟静态障碍物；参考所述当前车辆当前位姿、所述当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。本申请提供的方案，能够在左转路口场景时规划生成更安全的左转路径，提高驾驶安全性。

Description

路径规划方法、车辆及存储介质
本申请要求于2022年8月12日提交国家知识产权局、申请号为2022109673336、申请名称为“路径规划方法、车辆及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及自动驾驶技术领域，尤其涉及一种路径规划方法、车辆及存储介质。
背景技术
随着智能汽车技术的不断发展，智能汽车一般都具有自动驾驶功能。
在城市道路的自动驾驶应用场景中，通过无保护左转路口是一个十分常见的场景。在此过程中，反向的动态车流经常存在，如果车辆自动驾驶的路径规划不当，可能会使车辆驶入反向车流中，从而导致危险。参见图1所示，当前车辆10在左转路口左转时，所规划的路径与反向车流20前进的路径冲突，将会产生风险。相关技术中，一般应用自由空间的图搜索算法例如A*算法(也称为A星算法)、混合A*算法(Hybrid A*算法，也称为混合A星算法)来生成避让障碍物的路径。但是，这些方法只能处理静态障碍物，对于类似反向车流这样的动态障碍物无法处理。
因此，相关技术的路径规划方法在规划左转路口的路径时存在不足。
发明内容
为解决或部分解决相关技术中存在的问题，本申请提供一种路径规划方法、车辆及存储介质，能够在左转路口场景时规划生成更安全的左转路径，提高驾驶安全性。
本申请第一方面提供一种路径规划方法，包括：
获取当前车辆当前位姿和当前车辆目标位姿；
获取识别的障碍物；
根据预设规则从所述障碍物中识别出若干反向行驶车辆，利用识别出 的所述若干反向行驶车辆构建虚拟静态障碍物；
参考所述当前车辆当前位姿、所述当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。
在一实施方式中，所述根据预设规则从所述障碍物中识别出若干反向行驶车辆，包括：
从所述障碍物识别出障碍车辆，根据所述障碍车辆的行驶方向与所述当前车辆的行驶路径方向相反，识别出所述障碍车辆为反向行驶车辆。
在一实施方式中，所述获取当前车辆当前位姿和当前车辆目标位姿，包括：
根据当前车辆的高精度地图信息和导航信息获取当前车辆目标位姿，根据当前车辆的定位信息获取当前车辆当前位姿。
在一实施方式中，所述利用识别出的所述若干反向行驶车辆构建虚拟静态障碍物，包括：
遍历所有识别出的反向行驶车辆，基于所述反向行驶车辆的几何边界，在所述反向行驶车辆的行驶方向的左侧延伸设定距离构建虚拟静态障碍物，根据所述虚拟静态障碍物构建静态障碍物图。
在一实施方式中，所述参考所述当前车辆当前位姿、所述当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径，包括：
以所述当前车辆当前位姿为规划路径的起点，以所述当前车辆目标位姿为规划路径的终点，以所述静态障碍物图中的所述虚拟静态障碍物为规划路径中的障碍物，利用混合A*算法进行规划路径搜索得到满足运动学约束的当前车辆行驶的左转规划路径。
在一实施方式中，所述获取识别的障碍物，包括：
采集当前车辆前方或侧方的图像或视频，从所述图像或视频中识别出障碍物。
本申请第二方面提供一种车辆，包括：
位姿获取模块，用于获取当前车辆当前位姿和车辆目标位姿；
感知模块，用于获取识别的障碍物；
虚拟静态障碍物构建模块，用于根据预设规则从所述障碍物中识别出 若干反向行驶车辆，利用识别出的所述若干反向行驶车辆构建虚拟静态障碍物；
路径规划模块，用于参考所述当前车辆当前位姿、所述当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。
在一实施方式中，所述虚拟静态障碍物构建模块包括：
反向车辆识别模块，用于从所述障碍物识别出障碍车辆，根据所述障碍车辆的行驶方向与所述当前车辆的行驶路径方向相反，识别出所述障碍车辆为反向行驶车辆。
在一实施方式中，所述虚拟静态障碍物构建模块包括：
静态图构建模块，用于遍历所有识别出的反向行驶车辆，基于所述反向行驶车辆的几何边界，在所述反向行驶车辆的行驶方向的左侧延伸设定距离构建虚拟静态障碍物，根据所述虚拟静态障碍物构建静态障碍物图。
在一实施方式中，所述路径规划模块，以所述当前车辆当前位姿为规划路径的起点，以所述当前车辆目标位姿为规划路径的终点，以所述静态障碍物图中的所述虚拟静态障碍物为规划路径中的障碍物，利用混合A*算法进行规划路径搜索，得到满足运动学约束的当前车辆行驶的左转规划路径。
在一实施方式中，所述位姿获取模块根据当前车辆的高精度地图信息和导航信息获取当前车辆目标位姿，根据当前车辆的定位信息获取当前车辆当前位姿。
在一实施方式中，所述感知模块采集当前车辆前方或侧方的图像或视频，从所述图像或视频中识别出障碍物。
本申请第三方面提供一种计算机可读存储介质，其上存储有可执行代码，当所述可执行代码被电子设备的处理器执行时，使所述处理器执行如上所述的方法。
本申请提供的技术方案具有以下有益效果：
本申请根据预设规则从障碍物中识别出若干反向行驶车辆，利用识别出的所述若干反向行驶车辆构建虚拟静态障碍物；然后可以参考当前车辆当前位姿、当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成 当前车辆行驶的左转规划路径。由于本申请方案是将动态问题静态化，将动态的反向车流构建为静态障碍物，这样可以利用能处理静态障碍物的预设算法例如混合A*算法等生成无碰撞的满足运动学约束的行驶路径，将该行驶路径作为当前车辆行驶的左转规划路径，从而能在给定当前车辆也即自车的起始位置和目标位置的情况下，可以避开反向车流，安全通过无保护左转路口。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本申请。
附图说明
通过结合附图对本申请示例性实施方式进行更详细的描述，本申请的上述以及其它目的、特征和优势将变得更加明显，其中，在本申请示例性实施方式中，相同的参考标号通常代表相同部件。
图1是相关技术中示出的车辆左转路径与反向车流前进的路径冲突的示意图；
图2是本申请示出的路径规划方法的第一流程示意图；
图3是本申请示出的路径规划方法的第二流程示意图；
图4是本申请示出的路径规划方法的应用框架示意图；
图5是本申请示出的路径规划方法中识别反向行驶车辆的示意图；
图6是本申请生成的当前车辆左转路径与相关技术生成的当前车辆左转路径的对比示意图；
图7是本申请示出的车辆的一结构示意图；
图8是本申请示出的车辆的另一结构示意图。
具体实施方式
下面将参照附图更详细地描述本申请的实施方式。虽然附图中显示了本申请的实施方式，然而应该理解，可以以各种形式实现本申请而不应被这里阐述的实施方式所限制。相反，提供这些实施方式是为了使本申请更加透彻和完整，并且能够将本申请的范围完整地传达给本领域的技术人员。
在本申请使用的术语是仅仅出于描述特定实施例的目的，而非旨在限 制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。应当理解，尽管在本申请可能采用术语“第一”、“第二”、“第三”等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本申请范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本申请的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。
相关技术的路径规划方法在规划左转路口的路径时存在不足。如图1所示，在通过无保护左转路口的场景下，当前车辆10在左转路口左转时，所规划的路径与反向车流20前进的路径冲突，将会产生风险。本申请提供一种路径规划方法，能够在左转路口场景时规划生成更安全的左转路径，提高驾驶安全性。
以下结合附图详细描述本申请的技术方案。
图2是本申请示出的路径规划方法的第一流程示意图。该方法可以应用于车辆。
参见图2，该方法包括：
S201、获取当前车辆当前位姿和当前车辆目标位姿。
其中，可以根据当前车辆的高精度地图信息和导航信息获取当前车辆目标位姿，根据当前车辆的定位信息获取当前车辆当前位姿。
S202、获取识别的障碍物。
本申请可以利用相关技术中的识别技术，从感知模块采集的图像或视频中识别出障碍物。
S203、根据预设规则从障碍物中识别出若干反向行驶车辆，利用识别出的若干反向行驶车辆构建虚拟静态障碍物。
其中，可以从障碍物识别出障碍车辆，根据障碍车辆的行驶方向与当前车辆的行驶路径方向相反，识别出障碍车辆为反向行驶车辆。
其中，可以遍历所有识别出的反向行驶车辆，基于反向行驶车辆的几 何边界，在反向行驶车辆的行驶方向的左侧延伸设定距离构建虚拟静态障碍物，根据虚拟静态障碍物构建静态障碍物图。本申请将动态的反向车流构建为静态障碍物，可以实现动态问题静态化。
S204、参考当前车辆当前位姿、当前车辆目标位姿和虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。
其中，以当前车辆当前位姿为规划路径的起点，以当前车辆目标位姿为规划路径的终点，以静态障碍物图中的虚拟静态障碍物为规划路径中的障碍物，利用混合A*算法进行规划路径搜索，得到满足运动学约束的当前车辆行驶的左转规划路径。
混合A*算法是在A*算法的基础上考虑物体实际运动约束的一种算法。混合A*算法是在连续坐标系下进行启发式搜索，并且能够保证生成的轨迹满足车辆的运动学约束。混合A*算法与普通的A*算法区别在于，混合A*算法规划的路径考虑了车辆的运动学约束，即满足了车辆的最大曲率约束。
本申请根据预设规则从障碍物中识别出若干反向行驶车辆，利用识别出的若干反向行驶车辆构建虚拟静态障碍物；然后可以参考当前车辆当前位姿、当前车辆目标位姿和虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。由于本申请方案是将动态问题静态化，将动态的反向车流构建为静态障碍物，这样可以利用能处理静态障碍物的预设算法例如混合A*算法等生成无碰撞的满足运动学约束的行驶路径，将该行驶路径作为当前车辆行驶的左转规划路径，从而能在给定当前车辆也即自车的起始位置和目标位置的情况下，可以避开反向车流，安全通过无保护左转路口。
图3是本申请示出的路径规划方法的第二流程示意图。图4是本申请示出的路径规划方法的应用框架示意图。
本申请提供一种避障路径规划方法，基于高精度地图信息和导航信息获取当前车辆目标位姿，基于定位信息获取当前车辆当前位姿，并从感知模块获取所有障碍车辆信息。在此基础上，根据障碍车辆的位置及姿态可以判断出反向车车辆。以此为基础，将动态问题静态化，建立一个考虑反向车流的静态障碍物图，最终使用能处理静态障碍物的混合A*算法，搜 索得到无碰撞的满足运动学约束的左转规划路径。混合A*算法(Hybrid A*算法)是一种图搜索算法，改进于A*算法，其与普通的A*算法区别在于，混合A*算法规划的路径考虑了车辆的运动学约束，即满足了车辆的最大曲率约束。
运动约束，是动力学系统的一类约束，其约束方程中不仅含有各质点坐标，而且含有各质点的速度。由于在数学上质点的速度表示为质点坐标对时间的微分，因此也称“微分约束”。车辆的运动学约束，一般是指车辆在道路上正常行驶时，除非发生侧滑和跳跃，其侧向(y轴向)和法向(z轴向)速度为零。车辆运动受到运动学约束，因此车辆不能实现瞬时侧向移动，前驱的车辆必须依赖前轮的转向才能实现变道、转向等操作，在弯道上不能速度过快等。
混合A*算法是A*算法的一种改进，混合A*算法满足车辆的运动学约束。混合A*算法中可以用Reed-Shepp曲线或Dubins曲线与目标相连接，并加入车身轮廓判断是否与障碍物碰撞。如果和障碍物无碰撞，则保留曲线并生成路径；如果与障碍物发生碰撞则放弃曲线，并从开启列表中重新寻找节点，重新进行扩展。Reeds-Shepp曲线由几段半径固定的圆弧和一段直线段拼接组成，而且圆弧的半径就是车辆的最小转向半径。Dubins曲线与Reeds-Shepp曲线差不多，只不过多了一个约束条件：车辆只能朝前开，不能后退(不能挂倒挡)。
参见图3和图4，该方法包括：
S301、根据高精度地图信息、导航信息及定位信息，获取当前车辆当前位姿和当前车辆目标位姿。
例如，根据当前车辆的高精度地图信息和导航信息获取当前车辆目标位姿并记为X_t，根据当前车辆的定位信息获取当前车辆当前位姿并记为X_e。
S302、通过感知模块获取识别的障碍物。
本申请可以通过当前车辆的感知模块采集当前车辆前方或侧方的图像或视频，利用相关技术中的识别技术，从感知模块采集的图像或视频中识别出障碍物。其中障碍物检测可以是基于图像的障碍物检测、基于激光雷达的障碍物检测或基于视觉和激光雷达融合的障碍物检测等，本申请对 此并不加以限定。
S303、从障碍物识别出反向行驶车辆。
从障碍物识别出障碍车辆，遍历所有从感知模块识别到的障碍车辆，根据障碍车辆的行驶方向与当前车辆的行驶路径方向相反，识别出障碍车辆为反向行驶车辆。
例如，根据当前车辆当前位姿X_e、当前车辆目标位姿X_t及识别出的障碍车辆，根据几何关系和朝向夹角，判断障碍车辆是不是反向行驶车辆(也称为反向障碍车辆)。
参见图5，假设当前车辆为501，障碍车辆为502，曲线是规划的当前车辆501的行驶路径503，根据障碍车辆502的行驶方向与当前车辆501的行驶路径方向相反，可识别障碍车辆502是反向行驶车辆。
例如，可以将障碍车辆502中心点，往当前车辆为501行驶路径503上投影，找到投影点，然后获取投影点的heading(航向角)，如果这个投影点的航向角与障碍车辆502的航向角反向，就说明障碍车辆502是反向行驶车辆。
S304、利用反向行驶车辆构建构建虚拟静态障碍物。
遍历所有在上一步中识别到的反向行驶车辆，基于其几何边界，向其行驶方向的左侧延长一段设定长的距离，构建静态的虚拟静态障碍物，所有这些虚拟静态障碍物，组成了一张静态障碍物图。本申请将动态的反向车流构建为静态障碍物，可以实现动态问题静态化。
S305、参考当前车辆当前位姿、当前车辆目标位姿和虚拟静态障碍物，利用混合A*算法生成当前车辆行驶的左转规划路径。
以当前车辆当前位姿X_e为规划路径的起点，以当前车辆目标位姿X_t为规划路径的终点，根据上一步建立的静态障碍物图，以静态障碍物图中的虚拟静态障碍物为规划路径中的障碍物，考虑运动学约束和舒适性，使用设定算法例如混合A*算法进行规划路径的搜索。由于混合A*算法是满足车辆运动学的算法，因此最终使用混合A*算法可以生成得到满足运动学约束的可以避让反向车流的可行驶路径。
当前车辆按照生成的可行驶路径在左转路口场景下左转行驶，就可以避让反向车流，从而提高行驶安全。
例如，参见图6，是本申请生成的当前车辆左转路径与相关技术生成的当前车辆左转路径的对比示意图。
当前车辆当前位姿X_e以及当前车辆目标位姿X_t如图6所示。如果不考虑反向车流，按相关技术方法直接使用混合A*算法进行路径搜索，搜索出来的路径是图6中蓝色路径101。但显然这是不合理的，因为蓝色路径101冲进了反向车流中，与障碍车辆的行驶路径相交也即产生冲突。图6中带箭头黑色框表示的是基于感知模块提供的信息，使用几何关系筛选出的反向车流的反向行驶车辆602。基于这些反向行驶车辆602，沿着其前进方向的左侧，拉伸一段设定长的距离，建立一个长方形的虚拟静态障碍物，如图6中灰色填充的长方体603所示，所有这些长方体603，组成了一张静态障碍物图。最后，再以当前车辆当前位姿为规划路径的起点，以当前车辆目标位姿为规划路径的终点，以静态障碍物图中的虚拟静态障碍物为规划路径中的障碍物，使用混合A*算法进行规划路径搜索，最终生成得到当前车辆601的满足运动学约束的可以避让反向车流的左转规划路径604。
本申请方案，将动态问题静态化，将动态的反向车流构建为静态障碍物，可以快速生成自由空间内一指定位姿到另一指定位姿的无碰撞路径作为规划路径，也即生成当前位姿到目标位姿的左转无碰撞路径，在保证路径舒适性的同时可保证安全性，提高自动驾驶系统过无保护左转路口的通行效率。
与前述应用功能实现方法相对应，本申请还提供了一种车辆。
图7是本申请示出的车辆的结构示意图。
参见图7，本申请提供的车辆70，包括：位姿获取模块71、感知模块72、虚拟静态障碍物构建模块73、路径规划模块74。
位姿获取模块71，用于获取当前车辆当前位姿和车辆目标位姿。位姿获取模块71可以根据当前车辆的高精度地图信息和导航信息获取当前车辆目标位姿，根据当前车辆的定位信息获取当前车辆当前位姿。
感知模块72，用于获取识别的障碍物。感知模块72可以采集当前车辆前方或侧方的图像或视频，利用相关技术中的识别技术，从感知模块72采集的图像或视频中识别出障碍物。
虚拟静态障碍物构建模块73，用于根据预设规则从障碍物中识别出若干反向行驶车辆，利用识别出的若干反向行驶车辆构建虚拟静态障碍物。
路径规划模块74，用于参考当前车辆当前位姿、当前车辆目标位姿和虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。路径规划模块74以当前车辆当前位姿为规划路径的起点，以当前车辆目标位姿为规划路径的终点，以静态障碍物图中的虚拟静态障碍物为规划路径中的障碍物，利用混合A*算法进行规划路径搜索，得到满足运动学约束的当前车辆行驶的左转规划路径。
其中，虚拟静态障碍物构建模块73可以包括：反向车辆识别模块731、静态图构建模块732。
反向车辆识别模块731，用于从障碍物识别出障碍车辆，根据障碍车辆的行驶方向与当前车辆的行驶路径方向相反，识别出障碍车辆为反向行驶车辆。
静态图构建模块732，用于遍历所有识别出的反向行驶车辆，基于反向行驶车辆的几何边界，在反向行驶车辆的行驶方向的左侧延伸设定距离构建虚拟静态障碍物，根据虚拟静态障碍物构建静态障碍物图。
本申请提供的车辆，根据预设规则从障碍物中识别出若干反向行驶车辆，利用识别出的若干反向行驶车辆构建虚拟静态障碍物；然后可以参考当前车辆当前位姿、当前车辆目标位姿和虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。由于本申请方案是将动态问题静态化，将动态的反向车流构建为静态障碍物，这样可以利用能处理静态障碍物的预设算法例如混合A*算法等生成无碰撞的满足运动学约束的行驶路径，将该行驶路径作为当前车辆行驶的左转规划路径，从而能在给定当前车辆也即自车的起始位置和目标位置的情况下，可以避开反向车流，安全通过无保护左转路口。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不再做详细阐述说明。
图8是本申请示出的车辆的另一结构示意图。
参见图8，车辆1000包括存储器1010和处理器1020。
处理器1020可以是中央处理单元(Central Processing Unit，CPU)， 还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
存储器1010可以包括各种类型的存储单元，例如系统内存、只读存储器(ROM)和永久存储装置。其中，ROM可以存储处理器1020或者计算机的其他模块需要的静态数据或者指令。永久存储装置可以是可读写的存储装置。永久存储装置可以是即使计算机断电后也不会失去存储的指令和数据的非易失性存储设备。在一些实施方式中，永久性存储装置采用大容量存储装置(例如磁或光盘、闪存)作为永久存储装置。另外一些实施方式中，永久性存储装置可以是可移除的存储设备(例如软盘、光驱)。系统内存可以是可读写存储设备或者易失性可读写存储设备，例如动态随机访问内存。系统内存可以存储一些或者所有处理器在运行时需要的指令和数据。此外，存储器1010可以包括任意计算机可读存储媒介的组合，包括各种类型的半导体存储芯片(例如DRAM，SRAM，SDRAM，闪存，可编程只读存储器)，磁盘和/或光盘也可以采用。在一些实施方式中，存储器1010可以包括可读和/或写的可移除的存储设备，例如激光唱片(CD)、只读数字多功能光盘(例如DVD-ROM，双层DVD-ROM)、只读蓝光光盘、超密度光盘、闪存卡(例如SD卡、min SD卡、Micro-SD卡等)、磁性软盘等。计算机可读存储媒介不包含载波和通过无线或有线传输的瞬间电子信号。
存储器1010上存储有可执行代码，当可执行代码被处理器1020处理时，可以使处理器1020执行上文述及的方法中的部分或全部。
本领域技术人员还将明白的是，结合这里的申请所描述的各种示例性逻辑块、模块、电路和算法步骤可以被实现为电子硬件、计算机软件或两者的组合。
此外，根据本申请的方法还可以实现为一种计算机程序或计算机程序产品，该计算机程序或计算机程序产品包括用于执行本申请的上述方法中部分或全部步骤的计算机程序代码指令。
或者，本申请还可以实施为一种计算机可读存储介质(或非暂时性机器可读存储介质或机器可读存储介质)，其上存储有可执行代码(或计算机程序或计算机指令代码)，当可执行代码(或计算机程序或计算机指令代码)被电子设备(或服务器等)的处理器执行时，使处理器执行根据本申请的上述方法的各个步骤的部分或全部。
以上已经描述了本申请的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其他普通技术人员能理解本文披露的各实施例。

Claims (13)

  1. 一种路径规划方法，其特征在于，包括：
    获取当前车辆当前位姿和当前车辆目标位姿；
    获取识别的障碍物；
    根据预设规则从所述障碍物中识别出若干反向行驶车辆，利用识别出的所述若干反向行驶车辆构建虚拟静态障碍物；
    参考所述当前车辆当前位姿、所述当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。
  2. 根据权利要求1所述的方法，其特征在于，所述根据预设规则从所述障碍物中识别出若干反向行驶车辆，包括：
    从所述障碍物识别出障碍车辆，根据所述障碍车辆的行驶方向与所述当前车辆的行驶路径方向相反，识别出所述障碍车辆为反向行驶车辆。
  3. 根据权利要求1所述的方法，其特征在于，所述获取当前车辆当前位姿和当前车辆目标位姿，包括：
    根据当前车辆的高精度地图信息和导航信息获取当前车辆目标位姿，根据当前车辆的定位信息获取当前车辆当前位姿。
  4. 根据权利要求1所述的方法，其特征在于，所述利用识别出的所述若干反向行驶车辆构建虚拟静态障碍物，包括：
    遍历所有识别出的反向行驶车辆，基于所述反向行驶车辆的几何边界，在所述反向行驶车辆的行驶方向的左侧延伸设定距离构建虚拟静态障碍物，根据所述虚拟静态障碍物构建静态障碍物图。
  5. 根据权利要求4所述的方法，其特征在于，所述参考所述当前车辆当前位姿、所述当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径，包括：
    以所述当前车辆当前位姿为规划路径的起点，以所述当前车辆目标位姿为规划路径的终点，以所述静态障碍物图中的所述虚拟静态障碍物为规划路径中的障碍物，利用混合A*算法进行规划路径搜索得到满足运动学约束的当前车辆行驶的左转规划路径。
  6. 根据权利要求1所述的方法，其特征在于，所述获取识别的障碍物，包括：
    采集当前车辆前方或侧方的图像或视频，从所述图像或视频中识别出障碍物。
  7. 一种车辆，其特征在于，包括：
    位姿获取模块，用于获取当前车辆当前位姿和当前车辆目标位姿；
    感知模块，用于获取识别的障碍物；
    虚拟静态障碍物构建模块，用于根据预设规则从所述障碍物中识别出若干反向行驶车辆，利用识别出的所述若干反向行驶车辆构建虚拟静态障碍物；
    路径规划模块，用于参考所述当前车辆当前位姿、所述当前车辆目标位姿和所述虚拟静态障碍物，利用预设算法生成当前车辆行驶的左转规划路径。
  8. 根据权利要求7所述的车辆，其特征在于，所述虚拟静态障碍物构建模块包括：
    反向车辆识别模块，用于从所述障碍物识别出障碍车辆，根据所述障碍车辆的行驶方向与所述当前车辆的行驶路径方向相反，识别出所述障碍车辆为反向行驶车辆。
  9. 根据权利要求7所述的车辆，其特征在于，所述虚拟静态障碍物构建模块包括：
    静态图构建模块，用于遍历所有识别出的反向行驶车辆，基于所述反向行驶车辆的几何边界，在所述反向行驶当前车辆的行驶方向的左侧延伸设定距离构建虚拟静态障碍物，根据所述虚拟静态障碍物构建静态障碍物图。
  10. 根据权利要求9所述的车辆，其特征在于：
    所述路径规划模块，以所述当前车辆当前位姿为规划路径的起点，以所述当前车辆目标位姿为规划路径的终点，以所述静态障碍物图中的所述虚拟静态障碍物为规划路径中的障碍物，利用混合A*算法进行规划路径搜索，得到满足运动学约束的当前车辆行驶的左转规划路径。
  11. 根据权利要求7所述的车辆，其特征在于：
    所述位姿获取模块根据当前车辆的高精度地图信息和导航信息获取当前车辆目标位姿，根据当前车辆的定位信息获取当前车辆当前位姿。
  12. 根据权利要求7所述的车辆，其特征在于：
    所述感知模块采集当前车辆前方或侧方的图像或视频，从所述图像或视频中识别出障碍物。
  13. 一种计算机可读存储介质，其上存储有可执行代码，当所述可执行代码被电子设备的处理器执行时，使所述处理器执行如权利要求1-6中任一项所述的方法。
PCT/CN2022/119271 2022-08-12 2022-09-16 路径规划方法、车辆及存储介质 WO2024031780A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210967333.6A CN115235499A (zh) 2022-08-12 2022-08-12 路径规划方法、车辆及存储介质
CN202210967333.6 2022-08-12

Publications (1)

Publication Number Publication Date
WO2024031780A1 true WO2024031780A1 (zh) 2024-02-15

Family

ID=83679703

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/119271 WO2024031780A1 (zh) 2022-08-12 2022-09-16 路径规划方法、车辆及存储介质

Country Status (2)

Country Link
CN (1) CN115235499A (zh)
WO (1) WO2024031780A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118443049A (zh) * 2024-07-04 2024-08-06 新石器慧通（北京）科技有限公司 无人车的备用路径规划方法、存储介质及无人车

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001021377A (ja) * 1999-07-12 2001-01-26 Clarion Co Ltd ナビゲーション装置及びナビゲーション用記録媒体
CN113587951A (zh) * 2021-09-30 2021-11-02 国汽智控(北京)科技有限公司 路径规划方法、装置、系统、服务器、存储介质及产品
CN113819917A (zh) * 2021-09-16 2021-12-21 广西综合交通大数据研究院 自动驾驶路径规划方法、装置、设备及存储介质
CN113885525A (zh) * 2021-10-30 2022-01-04 重庆长安汽车股份有限公司 一种自动驾驶车辆脱困的路径规划方法、系统、车辆及存储介质
CN114355950A (zh) * 2022-01-25 2022-04-15 苏州挚途科技有限公司 掉头轨迹的规划方法及装置
CN114750782A (zh) * 2022-04-19 2022-07-15 重庆兰德适普信息科技有限公司 路径规划方法、装置、设备及车辆控制方法、装置、设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001021377A (ja) * 1999-07-12 2001-01-26 Clarion Co Ltd ナビゲーション装置及びナビゲーション用記録媒体
CN113819917A (zh) * 2021-09-16 2021-12-21 广西综合交通大数据研究院 自动驾驶路径规划方法、装置、设备及存储介质
CN113587951A (zh) * 2021-09-30 2021-11-02 国汽智控(北京)科技有限公司 路径规划方法、装置、系统、服务器、存储介质及产品
CN113885525A (zh) * 2021-10-30 2022-01-04 重庆长安汽车股份有限公司 一种自动驾驶车辆脱困的路径规划方法、系统、车辆及存储介质
CN114355950A (zh) * 2022-01-25 2022-04-15 苏州挚途科技有限公司 掉头轨迹的规划方法及装置
CN114750782A (zh) * 2022-04-19 2022-07-15 重庆兰德适普信息科技有限公司 路径规划方法、装置、设备及车辆控制方法、装置、设备

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118443049A (zh) * 2024-07-04 2024-08-06 新石器慧通（北京）科技有限公司 无人车的备用路径规划方法、存储介质及无人车

Also Published As

Publication number Publication date
CN115235499A (zh) 2022-10-25

Similar Documents

Publication Publication Date Title
CN110647142B (zh) 使用优化方法规划自动驾驶车辆的停车轨迹生成
CN107767658B (zh) 组队自主车辆导航传感器互换
EP3342666B1 (en) Method and system for operating autonomous driving vehicles using graph-based lane change guide
JP7346499B2 (ja) 情報処理装置、情報処理方法、およびプログラム
JP7398196B2 (ja) 駐車支援装置及び駐車支援方法
JP2015518600A5 (zh)
CN114258366A (zh) 对于自主车辆的折线轮廓表示
WO2024031780A1 (zh) 路径规划方法、车辆及存储介质
JP7152521B2 (ja) 運転者支援システム
JP7414410B2 (ja) 車両の動的視野に基づく視認距離決定
WO2024056064A1 (zh) 转弯路径规划方法、设备、车辆及存储介质
JP2020087191A (ja) 車線境界設定装置、車線境界設定方法
JP2021084556A (ja) 車両制御システム及び車両制御方法
JP2023065279A (ja) 自律システムのための譲るシナリオのエンコード
CN117885764B (zh) 车辆的轨迹规划方法、装置、车辆及存储介质
JP2022542082A (ja) ポーズ特定方法、ポーズ特定装置、コンピュータ可読記憶媒体、コンピュータ機器及びコンピュータプログラム
Kim et al. Trajectory planning and control of autonomous vehicles for static vehicle avoidance in dynamic traffic environments
CN113442908B (zh) 自动泊车路径规划方法及系统、泊车控制设备
JP6658968B2 (ja) 運転支援方法及び運転支援装置
JP4843880B2 (ja) 走行路環境検出装置
WO2022216641A1 (en) Counter-steering penalization during vehicle turns
CN115230731A (zh) 行驶路径确定方法、装置、终端及介质
CN116476840A (zh) 变道行驶方法、装置、设备及存储介质
CN116161018A (zh) 平行泊车路径规划方法及系统
CN115871709A (zh) 自动驾驶车辆进站轨迹规划方法、装置、设备、介质和车辆

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22954726

Country of ref document: EP

Kind code of ref document: A1