WO2021197177A1 - 在无信号灯路口实现车路协同的方法和装置 - Google Patents

在无信号灯路口实现车路协同的方法和装置 Download PDF

Info

Publication number
WO2021197177A1
WO2021197177A1 PCT/CN2021/082858 CN2021082858W WO2021197177A1 WO 2021197177 A1 WO2021197177 A1 WO 2021197177A1 CN 2021082858 W CN2021082858 W CN 2021082858W WO 2021197177 A1 WO2021197177 A1 WO 2021197177A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
coordinates
coordinate system
information
plane coordinate
Prior art date
Application number
PCT/CN2021/082858
Other languages
English (en)
French (fr)
Inventor
李柏
边学鹏
Original Assignee
北京京东乾石科技有限公司
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 北京京东乾石科技有限公司 filed Critical 北京京东乾石科技有限公司
Priority to KR1020227038183A priority Critical patent/KR20220163426A/ko
Priority to EP21780862.5A priority patent/EP4131210A4/en
Priority to JP2022557948A priority patent/JP7477636B2/ja
Priority to US17/916,383 priority patent/US20230154330A1/en
Publication of WO2021197177A1 publication Critical patent/WO2021197177A1/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
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3658—Lane guidance
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/164—Centralised systems, e.g. external to vehicles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
    • 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
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
    • G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096733—Systems involving transmission of highway information, e.g. weather, speed limits where a selection of the information might take place
    • G08G1/096741—Systems involving transmission of highway information, e.g. weather, speed limits where a selection of the information might take place where the source of the transmitted information selects which information to transmit to each vehicle
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096775—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096877—Systems involving transmission of navigation instructions to the vehicle where the input to the navigation device is provided by a suitable I/O arrangement
    • G08G1/096888—Systems involving transmission of navigation instructions to the vehicle where the input to the navigation device is provided by a suitable I/O arrangement where input information is obtained using learning systems, e.g. history databases
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes

Definitions

  • the embodiments of the present disclosure relate to the technical field of intelligent traffic management, in particular to the technical field of vehicle-road collaborative management, and in particular to a method and device for implementing vehicle-road collaboration at intersections without traffic lights.
  • Vehicle-road collaboration using wireless communication and new-generation Internet technologies to implement dynamic real-time information interaction between vehicles, vehicles and roads in an all-round way, and implement active vehicle safety control and road collaborative management on the basis of full-time and spatial dynamic traffic information collection and integration.
  • Fully realize the effective coordination of people, vehicles and roads ensure traffic safety, improve traffic efficiency, and form a safe, efficient and environmentally friendly road traffic system.
  • the embodiments of the present disclosure propose a method and device for realizing vehicle-road coordination at intersections without traffic lights.
  • the embodiments of the present disclosure provide a method for implementing vehicle-road coordination at intersections without traffic lights.
  • the method includes: obtaining road area width information, obstacle coordinates, and coordinates of each vehicle in a plane coordinate system, and obtaining Each vehicle movement category, and the acquisition of various vehicle motion state parameters; input the road area width information in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle, each vehicle movement category and each vehicle motion state parameter input for planning
  • the model of the vehicle trajectory obtains trajectory planning information; among them, the model used to plan the vehicle trajectory is based on the road area width information in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle, and the type of traffic movement to determine the constraints of avoiding collisions Condition, and determine the loss function based on each vehicle motion state parameter and each vehicle coordinate; Based on the trajectory planning information, drive each vehicle to travel.
  • the traffic movement category of each vehicle includes: one of a left turning movement, a forward movement, or a right turning movement required for each vehicle to travel to any target lane.
  • obtaining the coordinates of the obstacle in the plane coordinate system includes: mapping the obstacle in the form of a square to the plane coordinate system based on the size information of the obstacle and the position information of the obstacle on the road. Replace the squares with multiple inscribed circles of, where each inscribed circle is tangent to two adjacent sides of the square that are close to the inner corners of the origin of the plane coordinate system.
  • obtaining the coordinates of each vehicle in the plane coordinate system includes: mapping each vehicle in the form of a rectangle to the plane coordinate system based on the size information of each vehicle, and replacing the rectangle with a symmetrical double circumscribed circle of the rectangle, Obtain the coordinates and radius of the center of the symmetric double circumscribed circle of the rectangle in the plane coordinate system, where the symmetric double circumscribed circle is the smallest symmetric double circumscribed circle that can contain the rectangle.
  • replacing the square with multiple inscribed circles of a square to obtain the centers and radii of the multiple inscribed circles in the plane coordinate system includes: taking the side length of the square as the diameter and the center of the square as the center
  • the circle is regarded as the largest inscribed circle of a square; the multiple circles that are tangent to the inner corners of the square near the origin of the plane coordinate system are regarded as the multiple small inscribed circles of the square, and the radii of the multiple small inscribed circles are the same as the largest inscribed circle
  • the radius of the circle is proportional to the series of attenuation.
  • the constraint conditions for avoiding collisions are determined, including: based on the width information of the road area, the coordinates of the obstacle, and The coordinates of each vehicle determine the first avoidance collision constraint condition that each vehicle does not collide with an obstacle at any time t under any traffic action category; determine each vehicle based on the first avoidance collision constraint condition and road area width information In the passable area of any passable action category; based on the coordinates of the vehicle, determine the first in the passable area where any two vehicles under the same passable action category do not collide and any two vehicles under different passable action categories do not collide. Second, avoid collision constraints.
  • determining the passable area of each vehicle in any passable action category includes: based on the first avoidance collision constraint condition and road area width information, responding to The passing action category of the vehicle is a left-turning action. It is determined that the passable area of the vehicle in the left-turning action includes the opposing road area; and/or based on the first collision avoidance constraint condition and the road area width information, the road area in the plane coordinate system The intersection area as a passable area for each vehicle to travel freely and flexibly.
  • determining the loss function based on each vehicle motion state parameter and each vehicle coordinate includes: determining the first equation about the change of the vehicle motion state parameter based on the parameters of each vehicle motion state; The second equation of the distance between any two vehicles; based on the coordinates of each vehicle, determine the third-party distance about the distance between each vehicle and the X-axis and Y-axis of the plane coordinate system; based on the first equation, the second equation and the third-party distance, Determine the loss function about the state of the vehicle.
  • the method for implementing vehicle-road collaboration at intersections without traffic lights is applied to a vehicle-road collaborative management system, and the vehicle-road collaborative management system is configured to: use a sensing device and a communication device to obtain each intelligent network connection within a preset distance from the intersection. Vehicle coordinates, traffic action category and motion state parameters; based on the acquired coordinates, traffic action category and motion state parameters of each intelligent networked vehicle, execute any of the above methods to achieve vehicle-road coordination at intersections without traffic lights until the The vehicle leaves the intersection for a predetermined distance.
  • the embodiments of the present disclosure provide a method for realizing vehicle-road coordination at intersections without traffic lights, including: obtaining information for trajectory planning, including: obtaining road area width information and obstacle information in a plane coordinate system The coordinates and the coordinates of each vehicle are used to obtain the movement category of each vehicle and the parameters of the movement state of each vehicle.
  • obtaining the coordinates of the obstacle in the plane coordinate system includes: taking the center point of the intersection in the plane coordinate system as the coordinate origin, Obtain the coordinates of four blocks adjacent to the crossroad; each block includes: a largest circle, a plurality of small circles that are inscribed with two sides adjacent to the origin of the circumscribed square of the largest circle, and The sides of the circumscribed square of the largest circle are parallel to the coordinate axis of the plane coordinate system, and the radii of the plurality of small circles are attenuated in proportion to the radius of the largest circle; the information used for trajectory planning is input for Plan the model of the vehicle trajectory to obtain the planned trajectory information; wherein the model for planning the vehicle trajectory is determined based on the width information of the road area in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle, and the type of traffic movement Avoid collision constraints, and determine the loss function based on each vehicle motion state parameter and each vehicle coordinate; drive each vehicle to travel based on the planned trajectory information.
  • the embodiments of the present disclosure provide a device for realizing vehicle-road coordination at intersections without traffic lights.
  • the device includes: an acquiring unit configured to acquire road area width information, obstacle coordinates, and various information in a plane coordinate system.
  • the planning unit is configured to configure the road area width information in the plane coordinate system, the coordinates of the obstacles, the coordinates of each vehicle, and the movement of each vehicle Type and each vehicle motion state parameter input is used to plan the vehicle trajectory model to obtain trajectory planning information; among them, the model used to plan the vehicle trajectory is based on the road area width information in the plane coordinate system, the coordinates of obstacles, and the coordinates of each vehicle.
  • Coordinates and traffic action categories determine the constraint conditions for avoiding collisions, and determine the loss function based on each vehicle motion state parameter and each vehicle coordinate;
  • the drive unit is configured to drive each vehicle based on the trajectory planning information.
  • the traffic action category of each vehicle in the acquisition unit and the planning unit includes: one of a left turning action, a forward action, or a right turning action required for each vehicle to travel to any target lane.
  • acquiring the coordinates of the obstacle in the plane coordinate system in the acquiring unit includes: based on the size information of the obstacle, mapping the obstacle in the form of a square to the plane coordinate system, and inscribed in a plurality of squares.
  • a circle replaces a square, wherein each inscribed circle is tangent to two adjacent sides of the square near the origin of the plane coordinate system.
  • acquiring the coordinates of each vehicle in the plane coordinate system in the acquiring unit includes: mapping each vehicle in the form of a rectangle to the plane coordinate system based on the size information of each vehicle, and circumscribes each vehicle in the form of a rectangle.
  • the circle replaces the rectangle to obtain the coordinates and radius of the center of the symmetric double circumscribed circle of the rectangle in the plane coordinate system, where the symmetric double circumscribed circle is the smallest symmetric double circumscribed circle that can contain the rectangle.
  • replacing the square in the form of multiple inscribed circles in the acquisition unit includes: taking a circle with a side length of the square as the diameter and the center of the square as the center as the largest inscribed circle of the square;
  • the multiple circles that are tangent to the two sides adjacent to the inner corners of the origin of the plane coordinate system in the square are regarded as the multiple small inscribed circles of the square, and the radii of the multiple small inscribed circles are the same as the maximum inscribed circles.
  • the radius of the circle is proportional to the series of attenuation.
  • the planning unit determines the constraint conditions for avoiding collisions based on the road area width information in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle, and the type of traffic movement, which are determined by the following subunits: First avoiding collisions
  • the constraint condition determination subunit determines the first avoidance collision constraint condition that each vehicle does not collide with the obstacle at any time t under any traffic movement category based on the road area width information, the coordinates of the obstacle and the coordinates of the vehicle;
  • the pass area determination subunit based on the first avoidance collision constraint condition and road area width information, determines the passable area of each vehicle in any passable action category;
  • the second avoidance collision constraint condition determination subunit based on the coordinates of the vehicle, determines the The second collision avoidance constraint condition in the passable area that any two vehicles under the same traffic action category do not collide and any two vehicles under different traffic action categories do not collide.
  • the passable area determination subunit determines the passable area of each vehicle in any passable action category based on the first avoidance collision constraint condition and the road area width information, including: based on the first avoidance collision constraint condition and Road area width information, in response to the vehicle’s passing action category being a left turning action, determining that the passable area of the vehicle in the left turning action includes the opposing road area; and/or based on the first avoidance collision constraint condition and road area width information,
  • the intersection area of the road area in the plane coordinate system is regarded as a passable area for each vehicle to travel freely and flexibly.
  • the determination of the loss function based on the vehicle motion state parameters and the vehicle coordinates is determined by the following sub-units: the first equation determining sub-unit, based on the parameters of each vehicle motion state, determines the change of each vehicle motion state parameter The first equation of the second equation; the second equation determination sub-unit, based on the coordinates of the vehicle, determine the second equation about the distance between any two vehicles; the third-party process determination sub-unit, based on the coordinates of the vehicle, determine the distance between the vehicle and the origin of the coordinate The third-party process; the loss function determination subunit, based on the first equation, the second equation and the third-party process, determines the loss function about the vehicle traffic state.
  • the device for realizing vehicle-road coordination at intersections without traffic lights is applied to a vehicle-road collaborative management system, and the vehicle-road collaborative management system is configured to: use sensing equipment and communication equipment to obtain each intelligent network connection within a preset distance from the intersection. Vehicle coordinates, traffic action category and motion state parameters; based on the acquired coordinates, traffic action category and motion state parameters of each intelligent networked vehicle, execute any of the above methods to achieve vehicle-road coordination at intersections without traffic lights until the The vehicle leaves the intersection for a predetermined distance.
  • the embodiments of the present disclosure provide a device for realizing vehicle-road coordination at intersections without traffic lights, including: an information unit configured to obtain information for trajectory planning, including: obtaining a road area in a plane coordinate system
  • the width information, the coordinates of obstacles and the coordinates of each vehicle, the acquisition of each vehicle movement category, and the acquisition of each vehicle motion state parameter; among them, the acquisition of the coordinates of the obstacle in the plane coordinate system includes: taking the coordinates of the intersection in the plane coordinate system
  • the center point is the origin of the coordinates, and the coordinates of the four blocks adjacent to the crossroad are obtained; each block includes: a largest circle, and the largest circle is inscribed with the two sides adjacent to the origin of the circumscribed square of the largest circle.
  • the trajectory unit is configured as The information used for trajectory planning is input into the model for planning the vehicle trajectory to obtain planned trajectory information; wherein, the model for planning the vehicle trajectory is based on the width information of the road area and the obstacles in the plane coordinate system.
  • the coordinates, the coordinates of each vehicle and the type of traffic movement are determined, the constraint conditions for avoiding collisions are determined, and the loss function is determined based on the motion state parameters of each vehicle and the coordinates of each vehicle; the action unit is configured to drive each vehicle based on the planned trajectory information Driving.
  • the embodiments of the present disclosure provide a server, including: one or more processors; a storage device on which one or more programs are stored; when one or more programs are used by one or more processors Execution enables one or more processors to implement the method of any one of the above embodiments.
  • the embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, where the program is executed by a processor to implement the method of any of the above embodiments.
  • the model used to plan the trajectory of the vehicle is based on the road area width information in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle and the type of traffic movement, and the constraint conditions for avoiding collisions are determined, and based on each vehicle
  • the motion state parameters and the coordinates of each vehicle determine the loss function; finally, based on the trajectory planning information, each vehicle is driven to travel.
  • the model for planning the trajectory of each vehicle can be used to make the planned trajectory of each vehicle output by the model more accurate.
  • the trajectory is more flexible and coordinated, thereby avoiding congestion caused by various vehicles in the intersection area, and ultimately can greatly improve the efficiency of the intersection.
  • FIG. 1 is an exemplary system architecture diagram in which some embodiments of the present disclosure can be applied;
  • Fig. 2 is a flowchart of an embodiment of a method for implementing vehicle-road coordination at intersections without signal lights according to the present disclosure
  • FIG. 3 is a schematic diagram of an application scenario of mapping road width information, obstacle information, and vehicle information to a plane coordinate system according to an embodiment of the present disclosure
  • Fig. 4 is a schematic diagram showing obstacles in the form of multiple inscribed circles according to an embodiment of the present disclosure
  • Fig. 5 is a schematic diagram of determining that the vertex of a vehicle is outside a certain convex polygonal obstacle according to an embodiment of the present disclosure
  • Fig. 6 is an application scenario diagram for determining the passable area of each vehicle according to an embodiment of the present disclosure
  • FIG. 7 is an application scene diagram of the area where each vehicle is located at the end time according to an embodiment of the present disclosure
  • FIG. 8 is a flowchart of an embodiment of determining obstacle coordinates in a method for implementing vehicle-road coordination at intersections without signal lights according to the present disclosure
  • FIG. 9 is an application scenario diagram in which obstacles are represented by multiple inscribed circles in the method for implementing vehicle-road coordination at intersections without signal lights according to the present disclosure
  • Fig. 10 is a flowchart of an embodiment of determining the coordinates of each vehicle in the method for implementing vehicle-road coordination at intersections without signal lights according to the present disclosure
  • FIG. 11 is a diagram of an application scene in which vehicles are represented in a symmetrical double-connected circular form in the method for implementing vehicle-road coordination at intersections without signal lights according to the present disclosure
  • FIG. 12 is a schematic structural diagram of an embodiment of a device for implementing vehicle-road coordination at intersections without signal lights according to the present disclosure
  • FIG. 13 is a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure.
  • FIG. 1 shows an exemplary system architecture 100 of a method or device for implementing vehicle-road coordination at intersections without traffic lights to which embodiments of the present disclosure can be applied.
  • the system architecture 100 may include various sensing devices 101, 102, and 103, a network 104, a server 105, various vehicles 106, 107, and 108, and a network 109.
  • the network 104 is used to provide a medium for communication links between the sensing devices 101, 102, 103 and the server 105.
  • the network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.
  • the network 109 is used to provide a medium for communication links between the respective vehicles 106, 107, 108 and the server 105.
  • the network 109 may also include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.
  • the sensing devices 101, 102, 103 interact with the server 105 through the network 104 to receive or send messages, etc.; each vehicle 106, 107, 108 interacts with the server 105 through the network 109 to receive or send messages, and so on.
  • the sensing devices 101, 102, 103 can be devices that can sense the size information of each vehicle, the parameter information of each vehicle motion state, the position information of the vehicle, and the traffic movement category of each vehicle, including but not limited to radar, visual sensor, and buried underground The ground induction coil and so on.
  • the sensing devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. There is no specific limitation here.
  • the server 105 may be a server that provides various services, for example, a background server that provides driving instruction signals for planning trajectories for various vehicles.
  • the background server can analyze and process the received vehicle driving data and road information data, and drive each vehicle to travel according to the processing result.
  • a device for realizing vehicle-road coordination at intersections without traffic lights can be set in the server 105. There is no specific limitation here.
  • the server can be hardware or software.
  • the server can be implemented as a distributed server cluster composed of multiple servers, or as a single server.
  • the server is software, it can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. There is no specific limitation here.
  • sensing devices networks, servers, and vehicles in FIG. 1 are merely illustrative. There can be any number of sensing devices, networks, servers, and vehicles according to implementation needs.
  • FIG. 2 there is shown a process 200 of an embodiment of a method for implementing vehicle-road coordination at intersections without traffic lights according to the present disclosure.
  • the method for realizing vehicle-road coordination at intersections without traffic lights includes the following steps:
  • Step 201 Obtaining information for trajectory planning, including: obtaining road area width information, obstacle coordinates and coordinates of each vehicle in a plane coordinate system, obtaining various vehicle movement types, and obtaining various vehicle motion state parameters.
  • the executor for example, the server shown in FIG. 1
  • the executor can obtain the information used for trajectory planning locally, and can also obtain it from other transit devices.
  • the passing action category may be a driving action for indicating the intention of passing.
  • the trajectory planning information can be used to indicate the road condition information of the intersection area (such as the crossroad area, the T-shaped intersection area, etc.), and can be used as the input of the model for planning the trajectory of the vehicle; the trajectory planning information can include the width of the road area in the plane coordinate system Information, the coordinates of obstacles and the coordinates of each vehicle, the type of movement of each vehicle, and the parameters of each vehicle motion state.
  • the width information of the road area in the plane coordinate system, the coordinates of obstacles and the coordinates of each vehicle, the type of movement of each vehicle, and the parameters of each vehicle motion state can be obtained locally.
  • the execution body may map the size information of each vehicle, the parameter information of each vehicle motion state and the position information of the vehicle obtained from the sensing device to the plane coordinate system. Among them, the mapping is used to reflect the actual road conditions of the intersection area into the plane coordinate system.
  • the execution subject can receive the size information, motion state parameter information, and vehicle position information of each vehicle from the sensing device through a wired connection or a wireless connection, and can obtain the width information and obstacles of the road in the intersection area from the map database. Object information; and then the executive body can map the road width information, obstacle information and vehicle information to the plane coordinate system to obtain the road area width information, obstacle coordinates and the coordinates of each vehicle in the plane coordinate system.
  • the traffic action category of each vehicle includes: one of a left turning action, a straight moving action, or a right turning action required for each vehicle to travel to any target lane.
  • vehicles in the intersection area, vehicles can enter the intersection area from 4 directions (the positive direction of the X axis, the negative direction of the X axis, the positive direction of the Y axis and the negative direction of the Y axis in the plane coordinate system) , Vehicles entering the intersection area from each direction can exit the intersection and drive to the target lane according to the three types of traffic action categories: left turn, straight, and right turn. Therefore, all vehicles passing through 4 intersections can be divided into 12 types.
  • Traffic action category the vehicles leaving the intersection from west to east are defined according to three traffic action categories: set A1 (the set of left-turning vehicles), set A2 (the set of straight-going vehicles), and the set A3 (the set of right-turning vehicles);
  • set A1 the set of left-turning vehicles
  • set A2 the set of straight-going vehicles
  • set A3 the set of right-turning vehicles
  • the three types of traffic actions included in the east-to-west exit intersection are defined as: set B1 (collection of left-turning vehicles), set B2 (collection of straight-going vehicles), and set B3 (collection of right-turning vehicles); leaving the intersection from south to north
  • the three types of traffic actions included are defined as: set C1 (collection of left-turning vehicles), set C2 (collection of straight-going vehicles), and set C3 (collection of right-turning vehicles); the three types of traffic actions that will be included when exiting the intersection from north to south Defined as: set D1 (left turning vehicle set), set D
  • the obstacle when obtaining the coordinates of the obstacle in the plane coordinate system, the obstacle can be mapped to the plane coordinate system based on the size information of the obstacle and the position information of the obstacle on the road to obtain the obstacle mapping The coordinates of the post shape.
  • the technology for mapping obstacles to the plane coordinate system can be implemented by using the existing technology or the technology developed in the future to map the obstacles to the plane coordinate system, which is not limited in the embodiment of the present disclosure.
  • the obstacle can be mapped into a plane coordinate system in the form of a polygon (for example, a rectangle or a square).
  • Obstacles can be multiple convex polygonal obstacles, then in the plane coordinate system, the vertex Q of the jth obstacle, that is, all the NP j vertices are respectively The coordinates of each vertex can be determined based on the size of the obstacle and the position of the obstacle.
  • Figure 3 shows an application scenario diagram that maps road width information, obstacle information, and vehicle information to a plane coordinate system, and maps the road width information of the intersection area to the plane coordinate system to obtain road area width information L road_width (abbreviated as L W in the figure); block 1 (abbreviated as Block1 in the following), block 2 (abbreviated as Block2 in the following), block 3 (abbreviated as Block3 in the following), block 4 (abbreviated as Block4 in the following)
  • L road_width abbreviated as L W in the figure
  • block 1 abbreviated as Block1 in the following
  • Block2 abbreviated as Block2
  • Block3 abbreviated as Block3
  • Block4 abbreviated as Block4 in the following
  • the information is mapped to the plane coordinate system to obtain the coordinates of the rectangular obstacle.
  • Figure 3 shows 12 traffic action categories A1, A2, A3, B1 , B2, B3, C1, C2, C3, D1, D2, D3.
  • the obstacle can be mapped in the form of a square to the plane coordinate system, and the Replace the square with multiple inscribed circles of the square, where each inscribed circle is tangent to two adjacent sides of the square near the origin of the plane coordinate system.
  • an obstacle with a square outline can be mapped to a plane coordinate system, or mathematical geometric operations can be used to determine the smallest square that can contain an obstacle with a convex polygon outline, and then the square can be determined based on the size information of the obstacle The length and width in the coordinate system to obtain the coordinates of the vertices of the square.
  • the square with multiple inscribed circles of the square, where each inscribed circle is adjacent to the inner corners of the square near the origin of the plane coordinate system Tangent the obtained multiple inscribed circles are re-reflected in the plane coordinate system as square obstacles.
  • the circle with the side length of the square as the diameter and the center of the square as the center is regarded as the largest inscribed circle of the square; Multiple circles tangent to two adjacent sides are used as multiple small inscribed circles of a square obstacle, and the radii of the multiple small inscribed circles are attenuated in proportion to the radius of the largest inscribed circle.
  • Figure 4 shows a schematic diagram showing obstacles in the form of multiple inscribed circles.
  • the common ratio of the geometric attenuation series is preset to 0.5 , Taking the side length of the square as the diameter, and the circle with the center of the square as the center as the largest inscribed circle of the square; then, the two sides of the square that are adjacent to the inner corners of the origin of the plane coordinate system are tangent, and the radius is the largest
  • a plurality of circles whose inscribed circle radii are in a proportional sequence are used as a plurality of small inscribed circles of a square obstacle.
  • the rectangular form of each vehicle when acquiring the coordinates of each vehicle, based on the size information of each vehicle and the position information of the vehicle on the road, the rectangular form of each vehicle can be mapped to the plane coordinate system to obtain the position of the i-th vehicle.
  • the vertex P of the vehicle at a certain time t that is, the abscissa A ix (t), B ix (t), C ix (t), D ix (t) of the four vertices of the rectangular contour, and the ordinate A iy (t ),B iy (t),C iy (t),D iy (t).
  • each vehicle can be mapped to the plane coordinate system in the form of a rectangle, and the symmetrical double circumscribed The circle replaces the rectangle to obtain the coordinates and radius of the center of the symmetric double circumscribed circle of the rectangle in the plane coordinate system, where the symmetric double circumscribed circle is the smallest symmetric double circumscribed circle that can contain the rectangle.
  • the two centers of the symmetrical double circumscribed circle may be set on the symmetry axis of the rectangle, and the radius that can cover the rectangle is determined based on the center of the circle to obtain the smallest symmetrical double circumscribed circle.
  • the traffic area of each vehicle can be limited, the obstacles can be represented in the form of multiple inscribed circles, and the vehicles can be represented in the form of a symmetrical double circumscribed circle, which can be used for planning
  • the collision avoidance constraint between the polygons in the vehicle trajectory model is transformed into convex constraints, which can reduce the complexity of solving the model used to plan the vehicle trajectory, and make the trajectory of each vehicle output by the model more accurate.
  • the trajectory of the intersection area is more coordinated, which can improve the efficiency of each vehicle in the intersection area.
  • Step 202 Input the information for trajectory planning into the model for planning the trajectory of the vehicle to obtain the planned trajectory information; wherein, the model for planning the trajectory of the vehicle is based on the width information of the road area and the coordinates of the obstacle in the plane coordinate system. , The coordinates of each vehicle and the type of traffic movement, determine the constraint conditions for avoiding collisions, and determine the loss function based on the parameters of each vehicle motion state and each vehicle coordinate.
  • the model used to plan the trajectory of the vehicle includes the constraint conditions for avoiding collisions, the loss function, and the vehicle motion differential equation set.
  • the vehicle motion differential equation set can be obtained based on the vehicle motion equation; based on the road in the plane coordinate system.
  • the area width information, the coordinates of obstacles, the coordinates of each vehicle, and the type of movement of each vehicle are used to determine the constraint conditions for avoiding collisions, and the loss function is determined based on the parameters of each vehicle motion state and each vehicle coordinate.
  • the loss function is used to reflect the optimization requirements for traffic efficiency, comfort performance, and safety performance.
  • the first collision avoidance constraint condition based on the first collision avoidance constraint condition and the road area width information, the passable area of each vehicle in any passable action category is determined; based on the coordinates of the vehicle, it is determined under the same passable action category in the passable area
  • the second collision avoidance constraint condition that any two vehicles do not collide and any two vehicles in different traffic action categories do not collide.
  • the constraint modeling method of "the vertex of the vehicle is outside a certain convex polygon obstacle" can be used to determine the constraint condition.
  • Figure 5 shows the determination of the vehicle. An application scene graph where the vertices are outside a convex polygonal obstacle, the vehicle vertex P and the convex polygonal obstacle every two adjacent vertices are formed into triangles, and the faces of these triangles are accumulated and added.
  • the jth obstacle can be established Collision avoidance constraints with the body rectangle A i B i C i D i:
  • Fig. 6 shows an application scenario diagram for determining the passable area of each vehicle in any passable action category.
  • each vehicle corresponds to the A1, A2, and A3 passable action categories.
  • There is a rectangular obstacle Block4 in the area so A3 vehicles additionally need to avoid the rectangular obstacle Block4 to drive.
  • the area occupied by the Block4 rectangular obstacle is removed from the semi-enclosed area enclosed by two straight lines is the passable area of the A3 vehicle.
  • the passable areas of A1, A2, and A3 vehicles can be defined as:
  • a ix (t), B ix (t), C ix (t), D ix (t) respectively refer to the abscissas of the four vertices of the rectangular contour of the i-th vehicle at time t; similarly, A iy (t), B iy (t), C iy (t), D iy (t) respectively refer to the ordinates of the four vertices of the rectangular outline of the vehicle at time t; VehicleOutOfPolygon( ⁇ , ⁇ ) is Refers to the collision avoidance constraint condition used to describe the collision avoidance between two convex polygons ⁇ and ⁇ .
  • the second collision avoidance constraint condition can be determined, and the second collision avoidance constraint condition is used to realize that when each vehicle moves in the corresponding passable area, the passable area overlaps the vehicle
  • the categories do not collide with each other, and the vehicles within each category do not collide.
  • the collision avoidance constraint condition of car i and car j at time t is recorded as VehicleOutOfVehicle(i,j,t)
  • the second collision avoidance constraint condition can be:
  • VehicleOutOfPolygon (A i (t)B i (t)C i (t)D i (t),A j (t)B j (t)C j (t)D j (t)).
  • the second collision avoidance constraint condition is:
  • determining the passable area of each vehicle in any passable action category includes: based on the first avoidance collision constraint condition and road area width information, responding to The traffic movement category of the vehicle is a left turn movement, and it is determined that the passable area of the vehicle in the left turn movement includes the opposing road area. In this way, left-turning vehicles can make fuller use of road space and improve overall traffic efficiency.
  • determining the passable area of each vehicle in any passable action category may include: based on the first avoidance collision constraint condition and road area width information, The intersection area of the road area in the plane coordinate system is regarded as a passable area for each vehicle to travel freely and flexibly. In this way, taking the intersection area as a passable area where vehicles can travel freely and flexibly, the space in the intersection area can be more fully utilized, and the overall traffic efficiency can be improved.
  • the first equation about the change of the vehicle motion state parameter may be determined based on the parameters of the motion state of each vehicle; the first equation about the distance between any two vehicles may be determined based on the coordinates of each vehicle.
  • the second equation based on the coordinates of each vehicle, determine the third-party distance about the distance from each vehicle to the X-axis and Y-axis of the plane coordinate system; based on the first equation, the second equation and the third-party distance, determine the loss function about the vehicle traffic state .
  • the first equation J Comfort can be an equation that reflects the comfort performance of each vehicle passing through the intersection area.
  • the movement state parameters for example, speed, acceleration, angular velocity, displacement angle
  • each vehicle starts to drive smoothly and at a constant speed to achieve comfortable performance. Therefore, the first equation J comfort can be an equation for the change of motion state parameters.
  • a buffer area can be set in the intersection area, and the vehicles in the buffer area change the motion state parameters.
  • each vehicle is on the current road segment.
  • the acceleration, angular velocity, and displacement angle of each vehicle can all be 0. Then there are the following equations:
  • [x i (0),y i (0),v j (0),a j (0), ⁇ j (0), ⁇ j (0)] [x i ,y i ,v common ,0, 0,0],i ⁇ 1,...,N V ⁇ ;
  • ⁇ i (0) ⁇ /2,i ⁇ B1 ⁇ B2 ⁇ B3;
  • ⁇ i (0) ⁇ ,i ⁇ C1 ⁇ C2 ⁇ C3;
  • ⁇ i (0) - ⁇ /2,i ⁇ D1 ⁇ D2 ⁇ D3.
  • Figure 7 shows an application scenario diagram of the area where each vehicle is located at the end time.
  • Each vehicle has the following equation at the end time t f:
  • ⁇ i (t f ) ⁇ i (0)+ ⁇ /2,i ⁇ A1 ⁇ B1 ⁇ C1 ⁇ D1;
  • ⁇ i (t f ) ⁇ i (0), i ⁇ A2 ⁇ B2 ⁇ C2 ⁇ D2;
  • ⁇ i (t f ) ⁇ i (0)- ⁇ /2, i ⁇ A3 ⁇ B3 ⁇ C3 ⁇ D3.
  • v common >0 is the speed value of each vehicle traveling at a steady and uniform speed
  • (x i , y i ) is the starting position coordinate of the i-th vehicle
  • ⁇ i (0) is the i-th vehicle expressed in a symmetrical double circumscribed circle
  • ⁇ i (t f ) is the ending time of the i-th vehicle in the form of a symmetrical double circumscribed circle at the intersection area
  • a second equation about the distance between any two vehicles is determined.
  • the second equation may be an equation J safety that reflects the safety performance of each vehicle in the intersection area. For example, you can set a buffer area in the intersection area, and each vehicle adjusts its own motion state parameters in the buffer area. At the beginning, each vehicle starts to drive at a steady and uniform speed, and the distance between each vehicle has reached a preset value (can be Calculate the distance between the two vehicles through the coordinates of the vehicles).
  • the third-party distance can be an equation reflecting the efficiency of traffic, and it can be all vehicles that reach the target lane at the termination time.
  • the distance between the vehicle and the X-axis and Y-axis of the plane coordinate system; the third-party journey can indicate that each vehicle has traveled as far as possible in the respective target lane at the end time t f when passing through the intersection area, that is, the following equation can be obtained:
  • ⁇ i (t f ) ⁇ i (0)+ ⁇ /2,i ⁇ A1 ⁇ B1 ⁇ C1 ⁇ D1;
  • ⁇ i (t f ) ⁇ i (0), i ⁇ A2 ⁇ B2 ⁇ C2 ⁇ D2;
  • ⁇ i (t f ) ⁇ i (0)- ⁇ /2, i ⁇ A3 ⁇ B3 ⁇ C3 ⁇ D3.
  • t f is the end time of each vehicle passing through the intersection area, and the third-party process can encourage many vehicles that should be able to reach the end time constraint early to move forward.
  • the second equation and the third-party process determine the loss function about the vehicle traffic state.
  • Step 203 Drive each vehicle to travel based on the planned trajectory information.
  • the executor can send a driving instruction signal for indicating the planned trajectory information to the communication device of each vehicle, and the processor of each vehicle is based on the driving instruction received by the communication device.
  • the signal controls the vehicle to travel.
  • the method for realizing vehicle-road coordination at intersections without signal lights provided by the embodiments of the present disclosure is based on the road area width information, the coordinates of obstacles, the coordinates of each vehicle, and the model for planning the trajectory of each vehicle.
  • the planned trajectory of each vehicle output by the model is more accurate, and the trajectory of each vehicle is more flexible and coordinated, thereby avoiding the congestion caused by each vehicle in the intersection area and greatly improving the traffic efficiency of the intersection.
  • the method for achieving vehicle-road coordination at intersections without traffic lights is applied to a vehicle-road collaborative management system, and the vehicle-road collaborative management system is configured to: use sensing devices and communication devices to obtain preset distances from intersections The coordinates, traffic action category, and motion state parameters of each intelligent networked vehicle within the distance; based on the acquired coordinates, traffic action category and motion state parameters of each intelligent networked vehicle, perform any one of the above to achieve vehicle roads at intersections without traffic lights A coordinated approach until the vehicle has left the intersection for a predetermined distance.
  • the vehicle-road collaborative management system triggers a multi-vehicle collaborative trajectory planning task, which is completed by the system's planning module, thereby realizing a vehicle-road collaboration method at intersections without traffic lights.
  • the planning module re-plans the movement behavior of all intelligent networked vehicles currently within the range of the intersection, and then sends it to each intelligent networked vehicle for execution through the communication module of the system. After an intelligent networked vehicle leaves the intersection takeover range, the vehicle can be removed from the system control list.
  • the multi-vehicle coordinated trajectory planning task that can be realized by the vehicle-road collaborative management system can improve the traffic efficiency of each intelligent networked vehicle.
  • FIG. 8 is a flowchart 800 of an embodiment of determining obstacle coordinates in the method for implementing vehicle-road coordination at intersections without traffic lights according to this embodiment.
  • the process of the method for determining obstacle coordinates includes the following steps:
  • Step 801 Based on the size information of the obstacle and the position information of the obstacle on the road, the obstacle is mapped into a plane coordinate system in the form of a square;
  • irregular obstacles can be mapped to the plane coordinate system in the form of convex polygons based on the size information of the obstacles and the position information of the obstacles on the road, to obtain the coordinates of each vertex of the convex polygon, but in order to make The established model is more simplified.
  • the obstacles in the scene of the intersection area can be set as squares, or based on the size information of the obstacles and the position information of the obstacles, the convex polygonal obstacles can be mapped to include the convex polygonal obstacles by mathematical and geometric operations. The smallest square of the polygon into the plane coordinate system.
  • Step 802 Replace the square with a plurality of inscribed circles of the square, where each inscribed circle is tangent to two adjacent sides of the square near the origin of the plane coordinate system.
  • the square when building a model for planning the trajectory of a vehicle, in order to convert the collision avoidance constraint in the model from a non-convex constraint to a convex constraint, the square can be replaced by multiple inscribed circles of the square, or Other shapes that can transform the non-convex constraints in the model used to plan the vehicle trajectory into convex constraints Replace the above square.
  • each inscribed circle is close to the plane coordinate system in the square The two adjacent sides of the inner corner of the origin are tangent.
  • a circle with the side length of the square as the diameter and the center of the square as the center of the square is taken as the largest inscribed circle of the square;
  • a plurality of circles tangent to two adjacent sides are regarded as a plurality of small inscribed circles of a square, and the radii of the plurality of small inscribed circles are attenuated in proportion to the radius of the largest inscribed circle.
  • Figure 9 shows an application scenario diagram in which obstacles are represented by multiple inscribed circles. Determine the radius of the largest inscribed circle of a square obstacle, and then use the common ratio of the proportional attenuation sequence If it is 0.5, make multiple inscribed circles of the square obstacle, and obtain the obstacle expressed in multiple inscribed circles.
  • the obstacles are finally represented in the form of multiple inscribed circles, and the collision avoidance constraints in the model used to plan the vehicle trajectory can be converted from non-convex constraints to convex constraints, thereby simplifying the complexity of the model. This reduces the difficulty of solving the model, and ultimately makes the planned trajectory of each vehicle more accurate, and improves the efficiency of each vehicle in the intersection area.
  • FIG. 10 is a flowchart 1000 of an embodiment of determining the coordinates of each vehicle in the method for implementing vehicle-road coordination at intersections without traffic lights according to this embodiment.
  • the process of the method for determining the coordinates of each vehicle includes the following steps:
  • Step 1001 Based on the size information of each vehicle and the position information of the vehicle on the road, each vehicle is mapped into a plane coordinate system in the form of a rectangle;
  • the vehicle can be mapped to the plane coordinate system in the form of a rectangle according to the size information and position information of the vehicle, or the car can be mapped to the plane in the form of a rectangle that can cover itself according to the shape and size of the future car.
  • the plane coordinate system In the plane coordinate system.
  • Step 1002 Replace the rectangle with the symmetric double circumscribed circle of the rectangle to obtain the coordinates and radius of the center of the symmetric double circumscribed circle of the rectangle in the plane coordinate system, where the symmetric double circumscribed circle is the smallest symmetric double circumscribed circle that can contain the rectangle.
  • the rectangle when building a model for planning the trajectory of a vehicle, in order to convert the collision avoidance constraint in the model from a non-convex constraint to a convex constraint, the rectangle can be replaced by a symmetric double circumscribed circle, or other
  • the non-convex constraint in the model used to plan the trajectory of the vehicle is transformed into a convex constraint shape to replace the foregoing rectangle, and the symmetric double circumscribed circle may be the smallest symmetric double circumscribed circle that can contain the rectangle.
  • Fig. 11 shows an application scene diagram that represents a vehicle in a symmetrical double-joined circular form.
  • R i is the radius of the circular cover, whereby the vehicle can be established i and j at time t of the car collision avoidance constraint that the second collision avoidance constraint may be:
  • each rectangular vehicle into the form of a symmetrical double circumscribed circle, and simplify the square obstacle into the form of multiple inscribed circles.
  • the first collision avoidance constraint condition for avoiding collisions between each vehicle and the obstacle can be simplified, here No longer.
  • the vehicle is finally represented in the form of a symmetric double circumscribed circle, and the collision avoidance constraint in the model used to plan the vehicle trajectory can be converted into a convex constraint, thereby simplifying the complexity of the model and reducing the model solution.
  • the difficulty ultimately makes the planned trajectory of each vehicle more accurate, and improves the efficiency of each vehicle in the intersection area.
  • the present disclosure also provides an embodiment of a method for implementing vehicle-road coordination at intersections without traffic lights, and the method embodiment includes:
  • obtain information for trajectory planning including: obtaining road area width information, obstacle coordinates and coordinates of each vehicle in the plane coordinate system, obtaining each vehicle movement category, and obtaining each vehicle motion state parameter.
  • obtaining the coordinates of the obstacle in the plane coordinate system includes: taking the center point of the intersection in the plane coordinate system as the origin of the coordinates, and obtaining the coordinates of the four blocks adjacent to the intersection; each block includes: a largest circle, A plurality of small circles that are inscribed to the two sides of the circumscribed square of the largest circle adjacent to the origin, and the sides of the circumscribed square of the largest circle are parallel to the coordinate axis of the plane coordinate system.
  • the radius of each small circle is proportional to the radius of the largest circle attenuating a series of numbers.
  • the information used for trajectory planning is input into the model for planning the trajectory of the vehicle, and the planned trajectory information is obtained; wherein, the model for planning the trajectory of the vehicle is based on the road area width information and obstacles in the plane coordinate system.
  • the coordinates of objects, the coordinates of each vehicle, and the type of traffic movement are determined, the constraint conditions for avoiding collisions are determined, and the loss function is determined based on the parameters of each vehicle motion state and each vehicle coordinate.
  • each vehicle is driven to travel.
  • this method embodiment corresponds to the method embodiment shown in FIG. 2 and is different from the method embodiment shown in FIG. 2 in that this method embodiment further determines a series based on future blocks A circular obstacle (similar to the inscribed circular obstacle shown in Figure 9), which makes the collision avoidance constraint in the model used to plan the vehicle trajectory a convex constraint, which can simplify the model Complexity, thereby reducing the difficulty of model solving, and ultimately make the planned trajectory of each vehicle more accurate, and improve the efficiency of each vehicle in the intersection area.
  • a circular obstacle similar to the inscribed circular obstacle shown in Figure 9
  • the present disclosure provides an embodiment of a device for implementing vehicle-road coordination at intersections without traffic lights.
  • This device embodiment is similar to the method embodiment shown in FIG. 2
  • the device can be specifically applied to various electronic devices.
  • the device 1200 for implementing vehicle-road coordination at intersections without traffic lights in this embodiment includes: an acquisition unit 1201, a planning unit 1202, and a driving unit 1203.
  • the acquiring unit 1201 is configured to acquire road area width information, obstacle coordinates, and coordinates of each vehicle in a plane coordinate system, to acquire various types of vehicle movement actions, and to acquire various vehicle motion state parameters
  • the planning unit 1202 is configured to Input the road area width information in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle, the type of movement of each vehicle, and the parameters of each vehicle motion state into the model used to plan the trajectory of the vehicle to obtain the trajectory planning information
  • the model for planning the trajectory of vehicles is based on the road area width information in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle and the type of traffic movement, and the constraint conditions for avoiding collisions are determined, and it is determined based on the parameters of each vehicle motion state and each vehicle coordinate Loss function
  • the drive unit 1203 is configured to drive each vehicle
  • the traffic movement category of each vehicle in the acquisition unit and the planning unit includes: the left turn movement, the forward movement, or the right turn movement required for each vehicle to travel to any target lane. A sort of.
  • acquiring the coordinates of the obstacle in the plane coordinate system in the acquiring unit includes: taking the obstacle in the form of a square based on the size information of the obstacle and the position information of the obstacle on the road Mapping to the plane coordinate system, and replacing the square obstacle with a plurality of square inscribed circles, where each inscribed circle is tangent to two adjacent sides of the square that are adjacent to the inner corners of the origin of the plane coordinate system.
  • acquiring the coordinates of each vehicle in the plane coordinate system in the acquiring unit includes: mapping each vehicle in the form of a rectangle to the plane coordinate system based on the size information of each vehicle, and Replace the rectangle with the symmetric double circumscribed circle of the rectangle to obtain the coordinates and radius of the center of the symmetric double circumscribed circle of the rectangle in the plane coordinate system, where the symmetric double circumscribed circle is the smallest symmetric double circumscribed circle that can contain the rectangle.
  • the acquisition unit replaces the square obstacles in the form of multiple inscribed circles to obtain the centers and radii of the multiple inscribed circles in the plane coordinate system, including: Is the diameter, and the circle with the center of the square as the center is regarded as the largest inscribed circle of the square; the multiple circles that are tangent to the two sides adjacent to the inner corners of the plane coordinate system in the square are regarded as the majority of the square. There are several small inscribed circles, and the radius of multiple small inscribed circles is proportional to the radius of the largest inscribed circle.
  • the constraint conditions for determining collision avoidance are determined by the following sub-units :
  • the first avoidance collision constraint condition determination sub-unit based on the road area width information, the coordinates of the obstacles and the coordinates of the vehicles, determines the first avoidance that each vehicle does not collide with the obstacle at any time t under any traffic action category Collision constraint conditions;
  • the passable area determination subunit based on the first avoidance collision constraint condition and road area width information, determine the passable area of each vehicle in any passable action category;
  • the second avoidance collision constraint determination subunit based on the vehicle The coordinates of, determine the second collision avoidance constraint condition that any two vehicles under the same traffic action category do not collide and any two vehicles under different traffic action categories do not collide in the passable area.
  • the passable area determination subunit determines the passable area of each vehicle in any passable action category based on the first collision avoidance constraint condition and road area width information, including: 1. Collision avoidance constraint conditions and road area width information, in response to the vehicle's passing action category being a left turn action, it is determined that the passable area of the vehicle in the left turn action includes the opposing road area; and/or based on the first avoidance collision constraint condition And road area width information, the intersection area of the road area in the plane coordinate system is used as a passable area for each vehicle to travel freely and flexibly.
  • the determination of the loss function based on the vehicle motion state parameters and the vehicle coordinates in the planning unit is determined by the following sub-units: the first equation determining sub-unit determines the vehicle motion based on the parameters of the vehicle motion state The first equation for the change of state parameters; the second equation determining sub-unit, based on the coordinates of the vehicle, determine the second equation about the distance between any two vehicles; the third-party process determining sub-unit, based on the coordinates of the vehicle, determine each vehicle to The third-party distance of the X-axis and Y-axis distances of the plane coordinate system; based on the first equation, the second equation and the third-party distance, the loss function about the vehicle traffic state is determined.
  • the device for implementing vehicle-road coordination at intersections without signal lights is applied to the vehicle-road collaborative management system, and the vehicle-road collaborative management system is configured to: use sensing equipment and communication equipment to obtain the preset distance from the intersection The coordinates, traffic action category, and motion state parameters of each intelligent networked vehicle within the distance; based on the acquired coordinates, traffic action category and motion state parameters of each intelligent networked vehicle, perform any one of the above to achieve vehicle roads at intersections without traffic lights A coordinated approach until the vehicle has left the intersection for a predetermined distance.
  • the present disclosure also provides an embodiment of a device for implementing vehicle-road coordination at intersections without traffic lights.
  • the device embodiment includes: an information unit (not shown in the figure) configured to obtain information for trajectory planning , Including: obtaining the road area width information in the plane coordinate system, the coordinates of obstacles and the coordinates of each vehicle, obtaining the types of vehicle movement, and obtaining the parameters of each vehicle motion state; among them, obtaining the obstacles in the plane coordinate system
  • the coordinates include: taking the center point of the intersection in the plane coordinate system as the origin of the coordinates, and obtaining the coordinates of the four blocks adjacent to the intersection; each block includes: a largest circle and a square adjacent to the largest circle.
  • a trajectory unit (not shown in the figure), configured to input the information used for trajectory planning into a model for planning a vehicle trajectory to obtain planned trajectory information; wherein, the used for planning
  • the vehicle trajectory model is based on the width information of the road area in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle, and the type of traffic movement, determines the constraint conditions for avoiding collisions, and determines the loss function based on the parameters of each vehicle motion state and each vehicle coordinate
  • the action unit (not shown in the figure) is configured to drive each vehicle based on the planned trajectory information.
  • FIG. 13 shows a schematic structural diagram of an electronic device (for example, the server in FIG. 1) 1300 suitable for implementing the embodiments of the present disclosure.
  • the server shown in FIG. 13 is only an example, and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
  • the electronic device 1300 may include a processing device (such as a central processing unit, a graphics processor, etc.) 1301, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 1302 or from a storage device 1308
  • the program in the memory (RAM) 1303 executes various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 1300 are also stored.
  • the processing device 1301, ROM 1302, and RAM 1303 are connected to each other through a bus 1304.
  • An input/output (I/O) interface 1305 is also connected to the bus 1304.
  • the following devices can be connected to the I/O interface 1305: including input devices 1306 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, vibration An output device 1307 such as a device; a storage device 1308 including a magnetic tape, a hard disk, etc.; and a communication device 1309.
  • the communication device 1309 may allow the electronic device 1300 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 13 shows an electronic device 1300 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may be implemented alternatively or provided with more or fewer devices. Each block shown in FIG. 13 may represent one device, or may represent multiple devices as needed.
  • the process described above with reference to the flowchart can be implemented as a computer software program.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 1309, or installed from the storage device 1308, or installed from the ROM 1302.
  • the processing device 1301 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
  • the computer-readable medium of the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable removable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned server; or it may exist separately without being installed in the server.
  • the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, the electronic device: obtains information for trajectory planning, including: obtaining a road area in a plane coordinate system Width information, the coordinates of obstacles and the coordinates of each vehicle, obtain each vehicle movement category, and obtain each vehicle motion state parameter; input the information used for trajectory planning into the model used to plan the trajectory of the vehicle to obtain the planned trajectory information ;
  • the model used to plan the trajectory of the vehicle is based on the road area width information in the plane coordinate system, the coordinates of obstacles, the coordinates of each vehicle, and the type of traffic movement to determine the constraint conditions for avoiding collisions, and based on the parameters of each vehicle motion state and The coordinates of each vehicle determine the loss function; based on the planned trajectory information, each vehicle is driven to travel.
  • the computer program code for performing the operations of the embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, the programming languages including object-oriented programming languages-such as Java, Smalltalk, C++, Also includes conventional procedural programming languages-such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user’s computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to Connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions can also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware.
  • the described units can also be provided in the processor.

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Automation & Control Theory (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Atmospheric Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

一种在无信号灯路口实现车路协同的方法和装置，包括：获取用于轨迹规划的信息，将用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；基于规划的轨迹信息，驱动各个车辆行驶，通过在路口智能地规划多辆汽车的行驶轨迹，取代了原有的信号灯的职能，大幅度提升路口通行效率。

Description

在无信号灯路口实现车路协同的方法和装置
相关申请的交叉引用
本专利申请要求于2020年4月1日提交的、申请号为202010248522.9、发明名称为“在无信号灯路口实现车路协同的方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本公开的实施例涉及智能交通管理技术领域，具体涉及车路协同管理技术领域，尤其涉及在无信号灯路口实现车路协同的方法和装置。
背景技术
车路协同，采用无线通信和新一代互联网等技术，全方位实施车车、车路动态实时信息交互，并在全时空动态交通信息采集与融合的基础上开展车辆主动安全控制和道路协同管理，充分实现人车路的有效协同，保证交通安全，提高通行效率，从而形成的安全、高效和环保的道路交通系统。
相关的在无信号灯路口实现车路协同方式通常是强行假设各车辆沿着特定路径运动或者使用特定模态运动。
发明内容
本公开的实施例提出了在无信号灯路口实现车路协同的方法和装置。
第一方面，本公开的实施例提供了一种在无信号灯路口实现车路协同的方法，该方法包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；将平面坐标系中的道路区域宽度信息、障碍物的 坐标、各个车辆的坐标、各个车辆通行动作类别以及各个车辆运动状态参数输入用于规划车辆行驶轨迹的模型，得到轨迹规划信息；其中，用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；基于轨迹规划信息，驱动各个车辆行驶。
在一些实施例中，各个车辆的通行动作类别包括：各个车辆行驶至任意目标车道上所需的左转弯动作、前行动作或右转弯动作中的一种。
在一些实施例中，获取平面坐标系中的障碍物的坐标包括：基于障碍物的尺寸信息以及障碍物在道路上的位置信息，将障碍物以正方形的形式映射至平面坐标系中，以正方形的多个内切圆替换正方形，其中每个内切圆均与所述正方形中靠近平面坐标系原点的内角所相邻的两条边相切。
在一些实施例中，获取平面坐标系中的各个车辆的坐标，包括：基于各个车辆的尺寸信息，将各个车辆以矩形的形式映射至平面坐标系中，以矩形的对称双外接圆替换矩形，得到矩形的对称双外接圆在平面坐标系中的圆心的坐标和半径，其中对称双外接圆为能够包含矩形的最小对称双外接圆。
在一些实施例中，以正方形的多个内切圆替换正方形，得到多个内切圆在平面坐标系中的圆心和半径，包括：将以正方形边长为直径，以正方形的中心为圆心的圆作为正方形的最大内切圆；将与正方形中靠近平面坐标系原点的内角相切的多个圆形作为正方形的多个小内切圆，且多个小内切圆的半径与最大内切圆的半径成等比衰减数列。
在一些实施例中，基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，包括：基于道路区域宽度信息、障碍物的坐标以及各个车辆的坐标，确 定每个车辆在任一通行动作类别下不与障碍物在任一时刻t发生碰撞的第一躲避碰撞约束条件；基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域；基于车辆的坐标，确定在可通行区域内同一通行动作类别下的任意两个车辆不发生碰撞以及不同通行动作类别下的任意两个车辆不发生碰撞的第二躲避碰撞约束条件。
在一些实施例中，基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域，包括：基于第一躲避碰撞约束条件和道路区域宽度信息，响应于车辆的通行动作类别为左转弯动作，确定该车辆在左转弯动作的可通行区域包括对向道路区域；和/或基于第一躲避碰撞约束条件和道路区域宽度信息，将平面坐标系中道路区域的路口区域作为供每个车辆自由灵活行驶的可通行区域。
在一些实施例中，基于各个车辆运动状态参数和各个车辆坐标确定损失函数，包括：基于各个车辆运动状态的参数，确定关于车辆运动状态参数变化的第一方程；基于各个车辆的坐标，确定关于任两个车辆之间距离的第二方程；基于各个车辆的坐标，确定关于各个车辆至平面坐标系X轴和Y轴距离的第三方程；基于第一方程、第二方程和第三方程，确定关于车辆通行状态的损失函数。
在一些实施例中，在无信号灯路口实现车路协同的方法应用于车路协同管理系统，车路协同管理系统被配置成：采用感知设备和通讯设备获取距路口预设距离内各个智能网联车辆的坐标、通行动作类别以及运动状态参数；基于获取的各个智能网联车辆的坐标、通行动作类别以及运动状态参数，执行如上任意一项的在无信号灯路口实现车路协同的方法，直至该车辆驶出路口预定距离为止。
第二方面，本公开的实施例提供了一种在无信号灯路口实现车路协同的方法，包括：获取用于轨迹规划的信息，包括：获取平面坐标 系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；其中，获取平面坐标系中的障碍物的坐标包括：以平面坐标系中十字路口的中心点为坐标原点，获取与十字路口相邻的四个街区的坐标；每个街区包括：一个最大圆、与所述最大圆的外切正方形邻近所述原点的两条边相内切的多个小圆，所述最大圆的外切正方形的边平行于所述平面坐标系的坐标轴，所述多个小圆的半径与最大圆的半径成等比衰减数列；将所述用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；基于所述规划的轨迹信息，驱动各个车辆行驶。
第三方面，本公开的实施例提供了一种在无信号灯路口实现车路协同的装置，装置包括：获取单元，被配置成获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；规划单元，被配置成将平面坐标系中的道路区域宽度信息、障碍物的坐标、各个车辆的坐标、各个车辆通行动作类别以及各个车辆运动状态参数输入用于规划车辆行驶轨迹的模型，得到轨迹规划信息；其中，用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；驱动单元，被配置成基于轨迹规划信息，驱动各个车辆行驶。
在一些实施例中，获取单元和规划单元中各个车辆的通行动作类别包括：各个车辆行驶至任意目标车道上所需的左转弯动作、前行动 作或右转弯动作中的一种。
在一些实施例中，获取单元中获取平面坐标系中的障碍物的坐标包括：基于障碍物的尺寸信息，将障碍物以正方形的形式映射至平面坐标系中，并以正方形的多个内切圆替换正方形，其中每个内切圆均与所述正方形中靠近平面坐标系原点的内角所相邻的两条边相切。
在一些实施例中，获取单元中获取平面坐标系中的各个车辆的坐标，包括：基于各个车辆的尺寸信息，将各个车辆以矩形的形式映射至平面坐标系中，并以矩形的对称双外接圆替换矩形，得到矩形的对称双外接圆在平面坐标系中的圆心的坐标和半径，其中对称双外接圆为能够包含矩形的最小对称双外接圆。
在一些实施例中，获取单元中以多个内切圆的形式替换正方形，包括：将以正方形边长为直径，以所述正方形的中心为圆心的圆作为所述正方形的最大内切圆；将与正方形中靠近平面坐标系原点的内角所相邻的两条边相切的多个圆形作为正方形的多个小内切圆，且所述多个小内切圆的半径与最大内切圆的半径成等比衰减数列。
在一些实施例中，规划单元中基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，由以下子单元确定：第一躲避碰撞约束条件确定子单元，基于道路区域宽度信息、障碍物的坐标以及车辆的坐标，确定每个车辆在任一通行动作类别下不与障碍物在任一时刻t发生碰撞的第一躲避碰撞约束条件；可通行区域确定子单元，基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域；第二躲避碰撞约束条件确定子单元，基于车辆的坐标，确定在可通行区域内同一通行动作类别下的任意两个车辆不发生碰撞以及不同通行动作类别下的任意两个车辆不发生碰撞的第二躲避碰撞约束条件。
在一些实施例中，可通行区域确定子单元中基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域，包括：基于第一躲避碰撞约束条件和道路区域宽度信息，响应于车辆的通行动作类别为左转弯动作，确定该车辆在左转弯动作的可通行区域包括对向道路区域；和/或基于第一躲避碰撞约束条件和道路区域宽度信息，将平面坐标系中道路区域的路口区域作为供每个车辆自由灵活行驶的可通行区域。
在一些实施例中，规划单元中，基于车辆运动状态参数和车辆坐标确定损失函数由以下子单元确定：第一方程确定子单元，基于各个车辆运动状态的参数，确定关于各个车辆运动状态参数变化的第一方程；第二方程确定子单元，基于车辆的坐标，确定关于任两个车辆之间距离的第二方程；第三方程确定子单元，基于车辆的坐标，确定关于车辆至坐标原点距离的第三方程；损失函数确定子单元，基于第一方程、第二方程和第三方程，确定关于车辆通行状态的损失函数。
在一些实施例中，在无信号灯路口实现车路协同的装置应用于车路协同管理系统，车路协同管理系统被配置成：采用感知设备和通讯设备获取距路口预设距离内各个智能网联车辆的坐标、通行动作类别以及运动状态参数；基于获取的各个智能网联车辆的坐标、通行动作类别以及运动状态参数，执行如上任意一项的在无信号灯路口实现车路协同的方法，直至该车辆驶出路口预定距离为止。
第四方面，本公开的实施例提供了一种在无信号灯路口实现车路协同的装置，包括：信息单元，被配置成获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；其中，获取平面坐标系中的障碍物的坐标包括：以平面坐标系中十字路口的中心点为坐标原点，获取与十字路口相邻的四个街区的坐标；每个街 区包括：一个最大圆、与所述最大圆的外切正方形邻近所述原点的两条边相内切的多个小圆，所述最大圆的外切正方形的边平行于所述平面坐标系的坐标轴，所述多个小圆的半径与最大圆的半径成等比衰减数列；轨迹单元，被配置成将所述用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；动作单元，被配置成基于所述规划的轨迹信息，驱动各个车辆行驶。
第五方面，本公开的实施例提供了一种服务器，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序；当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如上任一实施例的方法。
第六方面，本公开的实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现如上任一实施例的方法。
本公开的实施例提供的无信号灯路口实现车路协同的方法和装置，首先通过获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；然后将平面坐标系中的道路区域宽度信息、障碍物的坐标、各个车辆的坐标、各个车辆通行动作类别以及各个车辆运动状态参数输入用于规划车辆行驶轨迹的模型，得到轨迹规划信息；其中，用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；最后基于轨迹规划信息，驱动各个车辆行驶。基于道路区域宽度信息、障碍物的坐标、 各个车辆的坐标以及各个车辆通行动作类别建立的用于规划车辆行驶轨迹的模型，可以使模型输出的各个车辆的规划轨迹更加精确，各个车辆之间的行进轨迹更加灵活协调，从而避免了各个车辆在路口区域造成拥堵，最终能够大幅度提升路口通行效率。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本公开的其它特征、目的和优点将会变得更明显：
图1是本公开的一些实施例可以应用于其中的示例性系统架构图；
图2是根据本公开的在无信号灯路口实现车路协同的方法的一个实施例的流程图；
图3是根据本公开的实施例的将道路宽度信息、障碍物信息及车辆信息映射至平面坐标系中的一个应用场景的示意图；
图4是根据本公开的实施例的将障碍物以多个内切圆的形式表示的原理图；
图5是根据本公开的实施例的确定车辆的顶点处于某一凸多边形障碍物外部的原理图；
图6是根据本公开的实施例的确定各个车辆可通行区域的应用场景图；
图7是根据本公开的实施例的各个车辆在终止时刻所在区域的应用场景图；
图8是根据本公开的在无信号灯路口实现车路协同的方法中确定障碍物坐标的实施例流程图；
图9是根据本公开的在无信号灯路口实现车路协同的方法中将障碍物以多个内切圆形式表示的应用场景图；
图10是根据本公开的在无信号灯路口实现车路协同的方法中确定 各个车辆坐标的实施例流程图；
图11是根据本公开的在无信号灯路口实现车路协同的方法中将车辆以对称双接圆形式表示的应用场景图；
图12是根据本公开的在无信号灯路口实现车路协同的装置的一个实施例的结构示意图；
图13是适于用来实现本公开的实施例的电子设备的结构示意图。
具体实施方式
下面结合附图和实施例对本公开作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关技术，而非对本公开的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关计算相关的部分。
需要说明的是，在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本公开。
图1示出了可以应用本公开的实施例的在无信号灯路口实现车路协同的方法或装置的示例性系统架构100。
如图1所示，系统架构100可以包括各个感知设备101、102、103，网络104、服务器105、各个车辆106、107、108和网络109。网络104用以在感知设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。网络109用以在各个车辆106、107、108和服务器105之间提供通信链路的介质。网络109也可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
感知设备101、102、103通过网络104与服务器105交互，以接收或发送消息等；各个车辆106、107、108通过网络109与服务器105 交互，以接收或发送消息等。
感知设备101、102、103可以是具有感知各个车辆尺寸信息、各个车辆运动状态参数信息、车辆的位置信息以及各个车辆的通行动作类别的设备，包括但不限于雷达、视觉传感器、以及埋在地下的地感线圈等等。当感知设备101、102、103为软件时，可以安装在上述所列举的电子设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
服务器105可以是提供各种服务的服务器，例如对各个车辆提供规划轨迹的驱动指令信号的后台服务器。后台服务器可以对接收到的车辆行驶数据及道路信息数据进行分析等处理，并根据处理结果驱动各个车辆行驶。相应地，在无信号灯路口实现车路协同的装置可以设置于服务器105中。在此不做具体限定。
需要说明的是，服务器可以是硬件，也可以是软件。当服务器为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器为软件时，可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的感知设备、网络、服务器以及车辆的数目仅仅是示意性的。根据实现需要，可以具有任意数目的感知设备、网络、服务器和车辆。
继续参考图2，示出了根据本公开的在无信号灯路口实现车路协同的方法的一个实施例的流程200。该在无信号灯路口实现车路协同的方法，包括以下步骤：
步骤201，获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通 行动作类别，以及获取各个车辆运动状态参数。
在本实施例中，在无信号灯路口实现车路协同的方法的执行主体(例如图1所示的服务器)可以从本地获取用于轨迹规划的信息，还可从其他中转设备获取。通行动作类别可以是用于表明通行意图的行驶动作。轨迹规划信息可用于表明路口区域(例如十字路口区域、丁字路口区域等)的路况信息，并可作为用于规划车辆行驶轨迹的模型的输入；轨迹规划信息可包括平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，各个车辆通行动作类别，以及各个车辆运动状态参数。
作为一个示例，可从本地获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，各个车辆通行动作类别，以及各个车辆运动状态参数。执行主体在从本地获取上述信息数据之前，可将从感知设备获取的各个车辆尺寸信息、各个车辆运动状态参数信息以及车辆的位置信息映射至平面坐标系中。其中，映射用于将路口区域的实际路况反映至平面坐标系中。
具体的，执行主体可通过有线连接的方式或者无线连接方式，从感知设备接收各个车辆的尺寸信息、运动状态参数信息以及车辆的位置信息，可从地图数据库中获取路口区域道路的宽度信息和障碍物信息；进而执行主体可以将道路宽度信息、障碍物信息及车辆信息映射至平面坐标系中，得到平面坐标系中道路区域宽度信息、障碍物坐标和各个车辆的坐标。
在本实施例的一些可选的实现方式中，各个车辆的通行动作类别包括：各个车辆行驶至任意目标车道上所需的左转弯动作、直行动作或右转弯动作中的一种。
作为一个示例，在十字路口区域，车辆可从东南西北4个方向(平面坐标系中X轴的正方向，X轴的负方向，Y轴的正方向以及Y轴的负 方向)驶入路口区域，从每个方向驶入路口区域的车辆可以按照左转弯、直行、右弯转3种通行动作类别驶出路口并行驶至目标车道上，因此通过4个路口的所有车辆共可分为12种通行动作类别，将自西向东驶出路口的车辆按照3种通行动作类别定义为：集合A1(左转弯车辆集合)，集合A2(直行车辆集合),集合A3(右转弯车辆集合)；将自东向西驶出路口包含的3种通行动作类别定义为：集合B1(左转弯车辆集合)，集合B2(直行车辆集合)，集合B3(右转弯车辆集合)；将自南向北驶出路口包含的3种通行动作类别定义为：集合C1(左转弯车辆集合)，集合C2(直行车辆集合)，集合C3(右转弯车辆集合)；将自北向南驶出路口包含的3种通行动作类别定义为：集合D1(左转弯车辆集合)，集合D2(直行车辆集合)，集合D3(右转弯车辆集合)，任一车辆的通行动作类别属于且仅属于上述12个集合中的一个。
在本实施例中，在获取平面坐标系中的障碍物的坐标时，可以基于障碍物的尺寸信息以及障碍物在道路上的位置信息，将障碍物映射至平面坐标系中，得到障碍物映射后的形状的坐标。将障碍物映射至平面坐标系中的技术，可以采用现有技术或未来发展的技术中将障碍物映射至平面坐标系中的方式来实现，本公开实施例对此不作限定。例如，可以将障碍物以多边形的形式(例如矩形或正方形)映射至平面坐标系中。其中，假设XOY坐标系中存在N obs个凸多边形障碍物，其中第j个障碍物包含NP j个顶点
Figure PCTCN2021082858-appb-000001
不失一般性地，我们对车辆i与障碍物j之间的碰撞躲避约束进行建模(j＝1,...,N obs)。二维平面上的碰撞一定源于顶点处，这里的顶点可以是车身顶点或凸多边形障碍物的顶点。这意味着如果能够在每一时刻限制车身矩形顶点处于障碍物多边形外部，并且限制多边形障碍物的顶点处在车身矩形外部，则碰撞一定不会发生。由于每时每刻障碍物顶点
Figure PCTCN2021082858-appb-000002
车身顶点A i(t)～D i(t)所在位置均可解析表示， 至此我们只需一个能够描述“某点处于某一凸多边形外部”的约束建模方法。我们将这一问题抽象出来，专门考虑如何描述点P＝(x,y)在具有n个顶点的凸多边形Q 1～Q n外部。
障碍物可以是多个凸多边形障碍物，则在平面坐标系中，第j个障碍物的顶点Q，即所有的NP j个顶点分别
Figure PCTCN2021082858-appb-000003
各个顶点的坐标可基于障碍物的尺寸及障碍物的位置确定。
参考图3，图3示出了将道路宽度信息、障碍物信息及车辆信息映射至平面坐标系中应用场景图，将十字路口区域的道路宽度信息映射至平面坐标系中得到道路区域宽度信息L road_width(附图中简写为L W)；将矩形障碍物街区1(以下简写为Block1)，街区2(以下简写为Block2)，街区3(以下简写为Block3)，街区4(以下简写为Block4)的信息映射至平面坐标系中，得到矩形障碍物的坐标，例如Block1靠近坐标原点的顶点坐标为(-L W，L W)，Block3靠近X轴且远离原点的顶点坐标为(L W+L L，-L W)，L L为矩形障碍物的长度，同时为了直观的表明通过路口区域各个车辆的通行动作类别，图3中还示出了12种通行动作类别A1，A2，A3，B1，B2，B3，C1，C2，C3，D1，D2，D3。
返回图2，在本实施例的一些可选的实现方式中，可基于障碍物的尺寸信息以及障碍物在道路上的位置信息，将障碍物以正方形的形式映射至平面坐标系中，并以正方形的多个内切圆替换正方形，其中每个内切圆均与正方形中靠近平面坐标系原点的内角所相邻的两条边相切。
作为一个示例，可将轮廓为正方形的障碍物映射至平面坐标系中，也可利用数学几何运算，确定能够包含轮廓为凸多边形的障碍物的最小正方形，而后基于障碍物的尺寸信息，确定正方形在坐标系中的长度和宽度，从而得到正方形顶点坐标，以正方形的多个内切圆替换正方形，其中每个内切圆均与正方形中靠近平面坐标系原点的内角所相邻的两条边相切，得到的多个内切圆重新作为正方形障碍物在平面坐标系中反映。
在本实施例的一些可选的实现方式中，将以正方形的边长为直径，以正方形的中心为圆心的圆作为正方形最大内切圆；将与正方形中靠近平面坐标系原点的内角所相邻的两条边相切的多个圆形作为正方形障碍物的多个小内切圆，多个小内切圆的半径与最大内切圆的半径成等比衰减数列。
参考图4，图4示出了将障碍物以多个内切圆的形式表示的原理图，以Block2映射至第一象限后的正方形为例，将等比衰减数列的公比预设为0.5，以正方形的边长为直径，以正方形的中心为圆心的圆作为正方形最大内切圆；而后将与正方形中靠近平面坐标系原点的内角所相邻的两条边相切的，半径与最大内切圆半径成等比数列的多个圆形作为正方形障碍物的多个小内切圆。
在本实施例中，在获取各个车辆坐标时，可基于各个车辆的尺寸信息和车辆在道路上的位置信息，将各个车辆的以矩形的形式映射至平面坐标系中，得到第i辆车在某一时刻t时车辆的顶点P，即矩形轮廓四个顶点的横坐标A ix(t),B ix(t),C ix(t),D ix(t)，以及纵坐标A iy(t),B iy(t),C iy(t),D iy(t)。
在本实施例的一些可选的实现方式中，可以基于各个车辆的尺寸信息和车辆在道路上的位置信息，将各个车辆以矩形的形式映射至平面坐标系中，并以矩形的对称双外接圆替换矩形，得到矩形的对称双外接圆在平面坐标系中的圆心的坐标和半径，其中对称双外接圆为能够包含矩形的最小对称双外接圆。
作为一个示例，可以将对称双外接圆的两个圆心均设置于矩形的对称轴上，基于该圆心确定能够覆盖该矩形的半径，得到最小对称的双外接圆。
在上述实施例中，通过设置通行动作类别，可限定各个车辆的通行区域，将障碍物以多个内切圆的形式表示，并且将车辆以对称双外接圆形式表示，从而可将用于规划车辆行驶轨迹的模型中多边形之间的躲避 碰撞约束转化为凸约束，进而能够降低用于规划车辆行驶轨迹的模型的求解复杂度，使得模型输出的各个车辆的轨迹更加精确，各个车辆之间通过路口区域的轨迹更加协调，从而能够提高各个车辆在路口区域的通行效率。
步骤202，将用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数。
在本实施例中，用于规划车辆行驶轨迹的模型包括躲避碰撞的约束条件，损失函数和车辆运动微分方程组，其中车辆运动微分方程组可以基于车辆的运动方程得到；基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及各个车辆的通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数。损失函数用于反映对于通行效率、舒适性能、安全性能的优化诉求。
在本实施例的一些可选的实现方式中，可基于道路区域宽度信息、障碍物的坐标以及车辆的坐标，确定每个车辆在任一通行动作类别下不与障碍物在任一时刻t发生碰撞的第一躲避碰撞约束条件；基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域；基于车辆的坐标，确定在可通行区域内同一通行动作类别下的任意两个车辆不发生碰撞以及不同通行动作类别下的任意两个车辆不发生碰撞的第二躲避碰撞约束条件。
作为一个示例，在确定第一躲避碰撞约束条件时，可采用“车辆的顶点处于某一凸多边形障碍物外部”的约束建模方法，确定约束条件，参考图5，图5示出了确定车辆顶点处于某一凸多边形障碍物外部的应用场景 图，将车辆顶点P与凸多边形障碍物每两个相邻的顶点分别组成三角形，并将这些三角形的面积累加，如果面积之和大于凸多边形的面积，则点P处于凸多边形外部，否则点P处在凸多边形障碍物的某一边上或凸多边形障碍物的内部，由此可建立点P处于凸多边形障碍物外部的方程组：
Figure PCTCN2021082858-appb-000004
其中S Δ代表相应三角形面积，S □代表凸多边形面积。S Δ通过三角形顶点坐标进行求解，
以
Figure PCTCN2021082858-appb-000005
为例，若三角形顶点的坐标分别为：P＝(x,y)、Q k＝(x Qk,y Qk)、Q k+1＝(x Q(k+1),y Q(k+1))，则根据三角形顶点的坐标以及三角形面积公式可得到：
Figure PCTCN2021082858-appb-000006
对方程组求解后，得到点P处于凸多边形障碍物顶点Q 1～Q n外部的一般性约束条件，PointOutOfPolygon(P,Q 1...Q n)。
据此可建立第j个障碍物
Figure PCTCN2021082858-appb-000007
与车身矩形A iB iC iD i的碰撞躲避约束条件：
Figure PCTCN2021082858-appb-000008
由上，车辆i与所有障碍物之间的碰撞躲避约束条件可建立为：
Figure PCTCN2021082858-appb-000009
并将其简写为：
Figure PCTCN2021082858-appb-000010
继续参考图6，图6示出了确定每个车辆在任一通行动作类别的可通行区域应用场景图，当车辆自西向东驶入路口时，各个车辆对应着A1、A2、A3通行动作类别。在整个运动时域[0,t f]上，以A3类为例，该通行动作类别下的车辆，始终保持在直线y＝0的下方、直线x＝0的左侧区域内，由于若该区域存在矩形障碍物Block4，因此A3类车辆额外需要躲避矩形障 碍物Block4行驶，从两条直线围成的半封闭区域除去Block4矩形障碍物占据的区域即为A3类车辆的可通行区域。同理，属于A2类别的车辆始终保持在直线y＝0下方与直线y＝-L road_width(道路区域宽度的一半)上方的带状区域内行驶。属于A1类别车辆的可通行区域设置方式与A3类似原理相同，但是可额外将对向道路空间也作为A1类别车辆可行驶区域一部分。允许左转车辆利用对向道路可以是使左转车辆更充分地利用道路空间，提高总体通行效率。由上，A1、A2、A3类别车辆的可通行区域可分别定义为：
Figure PCTCN2021082858-appb-000011
-L road_width≤γ≤0,γ∈{A iy(t),B iy(t),C iy(t),D iy(t)},t∈[0,t f],i∈A2；
Figure PCTCN2021082858-appb-000012
其中，A ix(t),B ix(t),C ix(t),D ix(t)分别指第i辆车在t时刻时车辆的矩形轮廓四个顶点的横坐标；类似地，A iy(t),B iy(t),C iy(t),D iy(t)分别指第i辆车在t时刻时车辆的矩形轮廓四个顶点的纵坐标；VehicleOutOfPolygon(Γ,Υ)是指用于描述两个凸多边形Γ与Υ之间不发生碰撞的碰撞躲避约束条件。
作为一个示例，在确定可通行区域后，可确定第二躲避碰撞约束条件，第二躲避碰撞约束条件用于实现当各个车辆在相应可通行区域内运动的整个过程中，可通行区域重叠的车辆类别相互之间不发生碰撞，且各类别内部各车辆不发生碰撞。若将i车与j车在时刻t的躲避碰撞约束条件记为VehicleOutOfVehicle(i,j,t)，则第二躲避碰撞约束条件可为：
VehicleOutOfPolygon(A i(t)B i(t)C i(t)D i(t),A j(t)B j(t)C j(t)D j(t)).
具体地，第二躲避碰撞约束条件为：
VehicleOutOfVehicle(i,j,t),i∈A1,
j∈A2∪A3∪B1∪B2∪B3∪C1∪C2∪C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈A2,
j∈A3∪B1∪B2∪B3∪C1∪D1∪D2；
VehicleOutOfVehicle(i,j,t),i∈A3,j∈B1∪C1∪D1∪D2；
VehicleOutOfVehicle(i,j,t),i∈B1,
j∈B2∪B3∪C1∪C2∪C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈B2,j∈B3∪C1∪C2∪C3∪D1；
VehicleOutOfVehicle(i,j,t),i∈B3,j∈C1∪D1；
VehicleOutOfVehicle(i,j,t),i∈C1,j∈C2∪C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈C2,j∈C3∪D1∪D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈C3,j∈D1；
VehicleOutOfVehicle(i,j,t),i∈D1,j∈D2∪D3；
VehicleOutOfVehicle(i,j,t),i∈D2,j∈D3；
VehicleOutOfVehicle(i，j，t)，
Figure PCTCN2021082858-appb-000013
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000014
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000015
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000016
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000017
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000018
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000019
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000020
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000021
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000022
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000023
i≠j；
VehicleOutOfVehicle(i,j,t),
Figure PCTCN2021082858-appb-000024
i≠j.
在一些实施例中，基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域，包括：基于第一躲避碰撞约束条件和道路区域宽度信息，响应于车辆的通行动作类别为左转弯动作，确定该车辆在左转弯动作的可通行区域包括对向道路区域。这样可以使左转车辆更充分地利用道路空间，提高总体通行效率。
备选地或附加地，基于第一躲避碰撞约束条件和道路区域宽度信息， 确定每个车辆在任一通行动作类别的可通行区域，可以包括：基于第一躲避碰撞约束条件和道路区域宽度信息，将平面坐标系中道路区域的路口区域作为供每个车辆自由灵活行驶的可通行区域。这样，将路口区域当作车辆可以自由灵活行驶的可通行区域，可以更充分的利用路口区域的空间，提高总体通行效率。
在本实施例的一些可选的实现方式中，可基于各个车辆运动状态的参数，确定关于车辆运动状态参数变化的第一方程；基于各个车辆的坐标，确定关于任两个车辆之间距离的第二方程；基于各个车辆的坐标，确定关于各个车辆至平面坐标系X轴和Y轴距离的第三方程；基于第一方程、第二方程和第三方程，确定关于车辆通行状态的损失函数。
作为一个示例，基于车辆运动状态的参数，确定关于车辆运动状态参数变化的第一方程，第一方程J 舒适可以为反映通过路口区域各个车辆舒适性能的方程，则在车辆通过路口区域时，车辆的运动状态参数(例如速度、加速度、角速度、位移角)变化量小，且在起始时刻0时刻，各个车辆均开始平稳匀速行驶，以达到舒适性能。因此，第一方程J 舒适可以为运动状态参数变化的方程。例如，可在路口区域设置缓冲区域，在缓冲区域内车辆改变运动状态参数，最终在通过路口区域时的起始时刻0时刻至通过路口区域后的终止时刻t f时刻，各个车辆在当前所在路段的方向以相同的速率匀速行驶，在通过路口区域时，各个车辆的加速度，角速度，位移角可均为0，则有以下方程：
[x i(0),y i(0),v j(0),a j(0),φ j(0),ω j(0)]＝[x i,y i,v common,0,0,0],i∈{1,...,N V}；
θ i(0)＝0,i∈A1∪A2∪A3；
θ i(0)＝π/2,i∈B1∪B2∪B3；
θ i(0)＝π,i∈C1∪C2∪C3；
θ i(0)＝-π/2,i∈D1∪D2∪D3.
参考图7，图7示出了各个车辆在终止时刻所在区域的应用场景图，各 车辆在终止时刻t f的有以下方程：
[v i(t f),a i(t f),φ i(t f),ω i(t f)]＝[v common,0,0,0],i∈{1,...,N V}；
Figure PCTCN2021082858-appb-000025
Figure PCTCN2021082858-appb-000026
Figure PCTCN2021082858-appb-000027
Figure PCTCN2021082858-appb-000028
θ i(t f)＝θ i(0)+π/2,i∈A1∪B1∪C1∪D1；
θ i(t f)＝θ i(0),i∈A2∪B2∪C2∪D2；
θ i(t f)＝θ i(0)-π/2,i∈A3∪B3∪C3∪D3.
其中v common＞0是各个车辆平稳匀速行驶的速率值，(x i,y i)为第i辆车的起始位置坐标，θ i(0)为第i辆以对称双外接圆形式表示的车辆在通过路口区域的起始时刻，两个圆心的连线与坐标X轴的夹角，θ i(t f)为第i辆以对称双外接圆形式表示的车辆在通过路口区域的终止时刻，两个圆心的连线与坐标X轴的夹角。
作为一个示例，基于各个车辆的坐标，确定关于任两个车辆之间距离的第二方程，第二方程可以为反映车辆通过路口区域各个车辆安全性能的方程J 安全，用于表明各车辆之间的距离，例如可以在路口区域设置缓冲区域，各个车辆在缓冲区域调整自己的运动状态参数，在起始时刻各个车辆均开始平稳匀速行驶，各个车辆的之间距离也达到了预设值(可通过车辆的坐标计算两车辆的距离)。
作为一个示例，基于各个车辆的坐标，确定关于各个车辆至平面坐标系X轴和Y轴距离的第三方程；第三方程可以为反映通行效率的方程，可以是在终止时刻所有达到目标车道的车辆距离平面坐标系X轴和Y轴 的距离；第三方程可表明各个车辆在通过路口区域的终止时刻t f时刻，在各自的目标车道上已尽量行驶的远，即则可有以下方程：
Figure PCTCN2021082858-appb-000029
[v i(t f),a i(t f),φ i(t f),ω i(t f)]＝[v common,0,0,0],i∈{1,...,N V}；
Figure PCTCN2021082858-appb-000030
Figure PCTCN2021082858-appb-000031
Figure PCTCN2021082858-appb-000032
Figure PCTCN2021082858-appb-000033
θ i(t f)＝θ i(0)+π/2,i∈A1∪B1∪C1∪D1；
θ i(t f)＝θ i(0),i∈A2∪B2∪C2∪D2；
θ i(t f)＝θ i(0)-π/2,i∈A3∪B3∪C3∪D3.
其中，t f为各个车辆通过路口区域的终止时刻，第三方程能够鼓励本应能够提早达成终止时刻约束的诸多车辆继续前进。
作为一个示例，基于第一方程、第二方程和第三方程，确定关于车辆通行状态的损失函数，第三方程可以是J＝w 1·J 通行效率+w 2·J 舒适+w 3·J 安全,其中w 1,w 2,w 3＞0均为权重系数。
步骤203，基于规划的轨迹信息，驱动各个车辆行驶。
在本实施例中，执行主体基于步骤202规划的轨迹信息，可将用于表明规划的轨迹信息的驱动指令信号发送至各个车辆的通讯装置上，各个车辆的处理器根据通讯装置接收的驱动指令信号控制车辆行驶。
本公开的实施例提供的无信号灯路口实现车路协同的方法，基于道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及各个车辆通行动 作类别建立的用于规划车辆行驶轨迹的模型，可以使模型输出的各个车辆的规划轨迹更加精确，各个车辆之间的行进轨迹更加灵活协调，从而避免了各个车辆在路口区域造成的拥堵，能够大幅度提升路口通行效率。
在本实施例的一些可选实现方式中，在无信号灯路口实现车路协同的方法应用于车路协同管理系统，车路协同管理系统被配置成：采用感知设备和通讯设备获取距路口预设距离内各个智能网联车辆的坐标、通行动作类别以及运动状态参数；基于获取的各个智能网联车辆的坐标、通行动作类别以及运动状态参数，执行如上任意一项的在无信号灯路口实现车路协同的方法，直至该车辆驶出路口预定距离为止。
在本实现方式中，智能网联车辆被接管后，车路协同管理系统触发多车协同轨迹规划任务，该任务由系统的规划模块完成，从而实现在无信号灯路口实现车路协同的方法。规划模块将当前在路口范围内的所有智能网联车辆的运动行为进行重新规划，随后通过系统的通讯模块下发到各智能网联车辆予以执行。在有智能网联车辆驶离路口接管范围后，可以将该车辆从系统管控列表中清除。由此，车路协同管理系统所能实现的多车协同轨迹规划任务能够提升各智能网联车辆的通行效率。
继续参考图8，图8是根据本实施例的在无信号灯路口实现车路协同的方法中的确定障碍物坐标的一个实施例流程800。该确定障碍物坐标的方法的流程包括以下步骤：
步骤801，基于障碍物的尺寸信息以及障碍物在道路上的位置信息，将障碍物以正方形的形式映射至平面坐标系中；
在本实施例中，可基于障碍物的尺寸信息以及障碍物在道路上的位置信息将不规则障碍物以凸多边形的形式映射至平面坐标系中，得到凸多边形的各个顶点坐标，但是为了使建立的模型更加简化，可将路口区域的场景中的障碍物设置为正方形，或者根据障碍物的尺寸信息以及障 碍物的位置信息，利用数学几何运算，将凸多边形障碍物映射为能够包含该凸多边形的最小正方形至平面坐标系中。
步骤802，以正方形的多个内切圆替换正方形，其中每个内切圆均与正方形中靠近平面坐标系原点的内角所相邻的两条边相切。
在本实施例中，在建立用于规划车辆行驶轨迹的模型时，为了将模型中的碰撞躲避约束由非凸约束转化为凸约束，可以用正方形的多个内切圆替换正方形，也可以用其他可将用于规划车辆行驶轨迹的模型中的非凸约束转化为凸约束的形状替换上述正方形，在用多个内切圆替换正方形时，每个内切圆均与正方形中靠近平面坐标系原点的内角所相邻的两条边相切。
在本实施例的一些可选的实现方式中，将以正方形边长为直径，以正方形的中心为圆心的圆作为所述正方形的最大内切圆；将与正方形中靠近平面坐标系原点的内角所相邻的两条边相切的多个圆形作为正方形的多个小内切圆，并所述多个小内切圆的半径与最大内切圆的半径成等比衰减数列。
作为一个示例，参考图9，图9示出了将障碍物以多个内切圆形式表示的应用场景图，确定正方形障碍物的最大内切圆的半径，而后以等比衰减数列的公比为0.5，作出正方形障碍物的多个内切圆，得到以多个内切圆形式表示的障碍物。
在本实施例中，将障碍物最终以多个内切圆的形式表示，可以将用于规划车辆行驶轨迹的模型中的碰撞躲避约束由非凸约束转化为凸约束，从而可简化模型的复杂度，进而降低模型求解难度，最终使得到的各个车辆的规划轨迹更加精确，提高各个车辆在路口区域的通行效率。
继续参考图10，图10是根据本实施例的在无信号灯路口实现车路协同的方法中的确定各个车辆坐标的一个实施例流程1000。该确定各个车辆坐标的方法的流程包括以下步骤：
步骤1001，基于各个车辆的尺寸信息和车辆在道路上的位置信息，将各个车辆以矩形的形式映射至平面坐标系中；
在本实施例中，可以根据车辆的尺寸信息和位置信息，将车辆以矩形的形式映射至平面坐标系中，也可根据未来汽车的形状和尺寸将汽车以可覆盖其本身的矩形形式映射至平面坐标系中。
步骤1002，以矩形的对称双外接圆替换矩形，得到矩形的对称双外接圆在平面坐标系中的圆心的坐标和半径，其中对称双外接圆为能够包含矩形的最小对称双外接圆。
在本实施例中，在建立用于规划车辆行驶轨迹的模型时，为了将模型中的碰撞躲避约束由非凸约束转化为凸约束，可以用对称双外接圆替换矩形，也可以用其他可将用于规划车辆行驶轨迹的模型中的非凸约束转化为凸约束的形状替换上述矩形，对称双外接圆可以为能够包含矩形的最小对称双外接圆。
参考图11，图11示出了将车辆以对称双接圆形式表示的应用场景图，对于车辆i的轮廓A iB iC iD i，可采用以点(xr i,yr i)及(xf i,yf i)为圆心、R i为半径的圆形覆盖，由此可建立i车与j车在时刻t的躲避碰撞约束条件，即第二躲避碰撞约束条件可为：
Figure PCTCN2021082858-appb-000034
将各个矩形车辆简化为对称双外接圆的形式，将正方形障碍物简化为多个内切圆的形式，最终也可简化各个车辆和障碍物之间躲避碰撞的第一躲避碰撞约束条件，在此不再赘述。
在本实施例中，将车辆最终以对称双外接圆的形式表示，可以将用于规划车辆行驶轨迹的模型中的碰撞躲避约束转化为凸约束，从而可简 化模型的复杂度，进而降低模型求解难度，最终使得到的各个车辆的规划轨迹更加精确，提高各个车辆在路口区域的通行效率。
此外，本公开还提供了一种在无信号灯路口实现车路协同的方法的一个实施例，该方法实施例包括：
首先获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数。
其中，获取平面坐标系中的障碍物的坐标包括：以平面坐标系中十字路口的中心点为坐标原点，获取与十字路口相邻的四个街区的坐标；每个街区包括：一个最大圆、与所述最大圆的外切正方形邻近所述原点的两条边相内切的多个小圆，所述最大圆的外切正方形的边平行于所述平面坐标系的坐标轴，所述多个小圆的半径与最大圆的半径成等比衰减数列。
之后，将所述用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数。
最后，基于所述规划的轨迹信息，驱动各个车辆行驶。
本领域技术人员应当理解，该方法实施例与图2所示的方法实施例相对应，与图2所示的方法实施例不同的是，该方法实施例进一步确定了一种基于未来街区的系列圆形式的障碍物(类似于图9中所示的内切圆形式的障碍物)，这种障碍物使得用于规划车辆行驶轨迹的模型中的碰撞躲避约束为凸约束，从而可简化模型的复杂度，进而降低模型求解难度，最终使得到的各个车辆的规划轨迹更加精确，提高各个车辆在路口区域的通行效率。
进一步参考图12，作为对上述各图所示方法的实现，本公开提供了一种在无信号灯路口实现车路协同的装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图12所示，本实施例的在无信号灯路口实现车路协同的装置1200包括：获取单元1201、规划单元1202和驱动单元1203。其中，获取单元1201被配置为获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；规划单元1202被配置为将平面坐标系中的道路区域宽度信息、障碍物的坐标、各个车辆的坐标、各个车辆通行动作类别以及各个车辆运动状态参数输入用于规划车辆行驶轨迹的模型，得到轨迹规划信息；其中，用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；驱动单元1203配置用于基于轨迹规划信息，驱动各个车辆行驶。
在本实施例一些可选的实现方式中，获取单元和规划单元中各个车辆的通行动作类别包括：各个车辆行驶至任意目标车道上所需的左转弯动作、前行动作或右转弯动作中的一种。
在本实施例一些可选的实现方式中，获取单元中获取平面坐标系中的障碍物的坐标包括：基于障碍物的尺寸信息以及障碍物在道路上的位置信息，将障碍物以正方形的形式映射至平面坐标系中，并以正方形的多个内切圆替换正方形障碍物，其中每个内切圆均与所述正方形中靠近平面坐标系原点的内角所相邻的两条边相切。
在本实施例一些可选的实现方式中，获取单元中获取平面坐标系中的各个车辆的坐标，包括：基于各个车辆的尺寸信息，将各个车辆 以矩形的形式映射至平面坐标系中，并以矩形的对称双外接圆替换矩形，得到矩形的对称双外接圆在平面坐标系中的圆心的坐标和半径，其中对称双外接圆为能够包含矩形的最小对称双外接圆。
在本实施例一些可选的实现方式中，获取单元中以多个内切圆的形式替换正方形障碍物得到多个内切圆在平面坐标系中的圆心和半径，包括：将以正方形边长为直径，以正方形的中心为圆心的圆作为所述正方形的最大内切圆；将与正方形中靠近平面坐标系原点的内角所相邻的两条边相切的多个圆形作为正方形的多个小内切圆，且多个小内切圆的半径与最大内切圆的半径成等比衰减数列。
在本实施例一些可选的实现方式中，规划单元中基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件由以下子单元确定：第一躲避碰撞约束条件确定子单元，基于道路区域宽度信息、障碍物的坐标以及车辆的坐标，确定每个车辆在任一通行动作类别下不与障碍物在任一时刻t发生碰撞的第一躲避碰撞约束条件；可通行区域确定子单元，基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域；第二躲避碰撞约束条件确定子单元，基于车辆的坐标，确定在可通行区域内同一通行动作类别下的任意两个车辆不发生碰撞以及不同通行动作类别下的任意两个车辆不发生碰撞的第二躲避碰撞约束条件。
在本实施例一些可选的实现方式中，可通行区域确定子单元中基于第一躲避碰撞约束条件和道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域，包括：基于第一躲避碰撞约束条件和道路区域宽度信息，响应于车辆的通行动作类别为左转弯动作，确定该车辆在左转弯动作的可通行区域包括对向道路区域；和/或基于第一躲避碰撞约束条件和道路区域宽度信息，将平面坐标系中道路区域的路 口区域作为供每个车辆自由灵活行驶的可通行区域。
在本实施例一些可选的实现方式中，规划单元中基于车辆运动状态参数和车辆坐标确定损失函数由以下子单元确定：第一方程确定子单元，基于车辆运动状态的参数，确定关于车辆运动状态参数变化的第一方程；第二方程确定子单元，基于车辆的坐标，确定关于任两个车辆之间距离的第二方程；第三方程确定子单元，基于车辆的坐标，确定各个车辆至平面坐标系X轴和Y轴距离的第三方程；基于第一方程、第二方程和第三方程，确定关于车辆通行状态的损失函数。
在本实施例一些可选的实现方式中，在无信号灯路口实现车路协同的装置应用于车路协同管理系统，车路协同管理系统被配置成：采用感知设备和通讯设备获取距路口预设距离内各个智能网联车辆的坐标、通行动作类别以及运动状态参数；基于获取的各个智能网联车辆的坐标、通行动作类别以及运动状态参数，执行如上任意一项的在无信号灯路口实现车路协同的方法，直至该车辆驶出路口预定距离为止。
此外，本公开还提供了一种在无信号灯路口实现车路协同的装置的一个实施例，该装置实施例包括：信息单元(图中未示出)，被配置成获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；其中，获取平面坐标系中的障碍物的坐标包括：以平面坐标系中十字路口的中心点为坐标原点，获取与十字路口相邻的四个街区的坐标；每个街区包括：一个最大圆、与所述最大圆的外切正方形邻近所述原点的两条边相内切的多个小圆，所述最大圆的外切正方形的边平行于所述平面坐标系的坐标轴，所述多个小圆的半径与最大圆的半径成等比衰减数列；轨迹单元(图中未示出)，被配置成将所述用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系 中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；动作单元(图中未示出)，被配置成基于所述规划的轨迹信息，驱动各个车辆行驶。
下面参考图13，其示出了适于用来实现本公开的实施例的电子设备(例如图1中的服务器)1300的结构示意图。图13示出的服务器仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图13所示，电子设备1300可以包括处理装置(例如中央处理器、图形处理器等)1301，其可以根据存储在只读存储器(ROM)1302中的程序或者从存储装置1308加载到随机访问存储器(RAM)1303中的程序而执行各种适当的动作和处理。在RAM 1003中，还存储有电子设备1300操作所需的各种程序和数据。处理装置1301、ROM 1302以及RAM 1303通过总线1304彼此相连。输入/输出(I/O)接口1305也连接至总线1304。
通常，以下装置可以连接至I/O接口1305：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置1306；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置1307；包括例如磁带、硬盘等的存储装置1308；以及通信装置1309。通信装置1309可以允许电子设备1300与其他设备进行无线或有线通信以交换数据。虽然图13示出了具有各种装置的电子设备1300，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图13中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程 序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置1309从网络上被下载和安装，或者从存储装置1308被安装，或者从ROM 1302被安装。在该计算机程序被处理装置1301执行时，执行本公开的实施例的方法中限定的上述功能。需要说明的是，本公开的实施例的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开的实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述服务器所包含的；也可以是单独 存在，而未装配入该服务器中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；将用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；基于规划的轨迹信息，驱动各个车辆行驶。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的实施例的操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。 例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (14)

  1. 一种在无信号灯路口实现车路协同的方法，包括：
    获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；
    将所述用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；
    基于所述规划的轨迹信息，驱动各个车辆行驶。
  2. 根据权利要求1所述的方法，其中，所述各个车辆的通行动作类别包括：
    各个车辆行驶至任意目标车道上所需的左转弯动作、直行动作或右转弯动作中的一种。
  3. 根据权利要求1所述的方法，其中，所述获取平面坐标系中的障碍物的坐标包括：
    基于障碍物的尺寸信息以及障碍物在道路上的位置信息，将障碍物以正方形的形式映射至平面坐标系中；
    以所述正方形的多个内切圆替换所述正方形，其中每个内切圆均与所述正方形中靠近平面坐标系原点的内角所相邻的两条边相切。
  4. 根据权利要求1所述的方法，其中，所述获取平面坐标系中的各个车辆的坐标，包括：
    基于各个车辆的尺寸信息和车辆在道路上的位置信息，将各个车辆以矩形的形式映射至平面坐标系中；
    以所述矩形的对称双外接圆替换所述矩形，得到所述矩形的对称双 外接圆在平面坐标系中的圆心的坐标和半径，其中所述对称双外接圆为能够包含所述矩形的最小对称双外接圆。
  5. 根据权利要求3所述的方法，其中，所述以所述正方形的多个内切圆替换所述正方形，包括：
    将以所述正方形边长为直径，以所述正方形的中心为圆心的圆作为所述正方形的最大内切圆；
    将与正方形中靠近平面坐标系原点的内角所相邻的两条边相切的多个圆形作为正方形的多个小内切圆，且所述多个小内切圆的半径与最大内切圆的半径成等比衰减数列。
  6. 根据权利要求1所述的方法，其中，所述基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，包括：
    基于道路区域宽度信息、障碍物的坐标以及各个车辆的坐标，确定每个车辆在任一通行动作类别下不与所述障碍物在任一时刻t发生碰撞的第一躲避碰撞约束条件；
    基于所述第一躲避碰撞约束条件和所述道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域；
    基于各个车辆的坐标，确定在所述可通行区域内同一通行动作类别下的任意两个车辆不发生碰撞以及不同通行动作类别下的任意两个车辆不发生碰撞的第二躲避碰撞约束条件。
  7. 根据权利要求1所述的方法，其中，所述基于所述第一躲避碰撞约束条件和所述道路区域宽度信息，确定每个车辆在任一通行动作类别的可通行区域，包括：
    基于所述第一躲避碰撞约束条件和所述道路区域宽度信息，响应于所述车辆的通行动作类别为左转弯动作，确定该车辆在左转弯动作的可通行区域包括对向道路区域；和/或
    基于所述第一躲避碰撞约束条件和所述道路区域宽度信息，将平面坐标系中道路区域的路口区域作为供每个车辆自由灵活行驶的可通行区域。
  8. 根据权利要求1所述的方法，其中，基于各个车辆运动状态参数和各个车辆坐标确定损失函数，包括：
    基于各个车辆运动状态的参数，确定关于各个车辆运动状态参数变化的第一方程；
    基于各个车辆的坐标，确定关于任两个车辆之间距离的第二方程；
    基于各个车辆的坐标，确定关于各个车辆至平面坐标系X轴和Y轴距离的第三方程；
    基于所述第一方程、第二方程和第三方程，确定损失函数。
  9. 根据权利要求1所述的方法，其中，所述在无信号灯路口实现车路协同的方法应用于车路协同管理系统，所述车路协同管理系统被配置成：
    采用感知设备和通讯设备获取距路口预设距离内各个智能网联车辆的坐标、通行动作类别以及运动状态参数；
    基于获取的各个智能网联车辆的坐标、通行动作类别以及运动状态参数，执行如所述权利要求1-8任意一项所述的在无信号灯路口实现车路协同的方法，直至该车辆驶出路口预定距离为止。
  10. 一种在无信号灯路口实现车路协同的方法，包括：
    获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；
    其中，获取平面坐标系中的障碍物的坐标包括：以平面坐标系中十字路口的中心点为坐标原点，获取与十字路口相邻的四个街区的坐标；每个街区包括：一个最大圆、与所述最大圆的外切正方形邻近所述原点 的两条边相内切的多个小圆，所述最大圆的外切正方形的边平行于所述平面坐标系的坐标轴，所述多个小圆的半径与最大圆的半径成等比衰减数列；
    将所述用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；
    基于所述规划的轨迹信息，驱动各个车辆行驶。
  11. 一种在无信号灯路口实现车路协同的装置，包括：
    获取单元，被配置成获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；
    规划单元，被配置成将所述平面坐标系中的道路区域宽度信息、障碍物的坐标、各个车辆的坐标、各个车辆通行动作类别以及各个车辆运动状态参数输入用于规划车辆行驶轨迹的模型，得到轨迹规划信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；
    驱动单元，被配置成基于所述轨迹规划信息，驱动各个车辆行驶。
  12. 一种在无信号灯路口实现车路协同的装置，包括：
    信息单元，被配置成获取用于轨迹规划的信息，包括：获取平面坐标系中的道路区域宽度信息、障碍物的坐标和各个车辆的坐标，获取各个车辆通行动作类别，以及获取各个车辆运动状态参数；
    其中，获取平面坐标系中的障碍物的坐标包括：以平面坐标系中十 字路口的中心点为坐标原点，获取与十字路口相邻的四个街区的坐标；每个街区包括：一个最大圆、与所述最大圆的外切正方形邻近所述原点的两条边相内切的多个小圆，所述最大圆的外切正方形的边平行于所述平面坐标系的坐标轴，所述多个小圆的半径与最大圆的半径成等比衰减数列；
    轨迹单元，被配置成将所述用于轨迹规划的信息输入用于规划车辆行驶轨迹的模型，得到规划的轨迹信息；其中，所述用于规划车辆行驶轨迹的模型基于平面坐标系中道路区域宽度信息、障碍物的坐标、各个车辆的坐标以及通行动作类别，确定躲避碰撞的约束条件，并且基于各个车辆运动状态参数和各个车辆坐标确定损失函数；
    动作单元，被配置成基于所述规划的轨迹信息，驱动各个车辆行驶。
  13. 一种服务器，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序；
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-10中任一所述的方法。
  14. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-10中任一所述的方法。
PCT/CN2021/082858 2020-04-01 2021-03-25 在无信号灯路口实现车路协同的方法和装置 WO2021197177A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020227038183A KR20220163426A (ko) 2020-04-01 2021-03-25 신호등이 없는 교차로에서 차량-도로 협력 구현 방법 및 장치
EP21780862.5A EP4131210A4 (en) 2020-04-01 2021-03-25 METHOD AND APPARATUS FOR ACHIEVING VEHICLE-ROAD COORDINATION AT AN INTERSECTION WITHOUT TRAFFIC LIGHTS
JP2022557948A JP7477636B2 (ja) 2020-04-01 2021-03-25 信号機なしの交差点での車路連携実現方法および装置
US17/916,383 US20230154330A1 (en) 2020-04-01 2021-03-25 Method and apparatus for achieving vehicle-road coordination at intersection without signal lights

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010248522.9A CN111785062B (zh) 2020-04-01 2020-04-01 在无信号灯路口实现车路协同的方法和装置
CN202010248522.9 2020-04-01

Publications (1)

Publication Number Publication Date
WO2021197177A1 true WO2021197177A1 (zh) 2021-10-07

Family

ID=72753146

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/082858 WO2021197177A1 (zh) 2020-04-01 2021-03-25 在无信号灯路口实现车路协同的方法和装置

Country Status (6)

Country Link
US (1) US20230154330A1 (zh)
EP (1) EP4131210A4 (zh)
JP (1) JP7477636B2 (zh)
KR (1) KR20220163426A (zh)
CN (1) CN111785062B (zh)
WO (1) WO2021197177A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111785062B (zh) * 2020-04-01 2021-09-14 北京京东乾石科技有限公司 在无信号灯路口实现车路协同的方法和装置
CN113450570B (zh) * 2021-07-06 2022-04-12 湖南大学 一种基于无信号灯路口的自主路口管理系统及方法
CN113776550B (zh) * 2021-09-08 2024-04-16 京东鲲鹏(江苏)科技有限公司 一种路线规划方法和装置
CN115171371B (zh) * 2022-06-16 2024-03-19 海信集团控股股份有限公司 一种协作式道路交叉口通行方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108871370A (zh) * 2018-07-03 2018-11-23 北京百度网讯科技有限公司 导航方法、装置、设备和介质
US10288439B2 (en) * 2017-02-22 2019-05-14 Robert D. Pedersen Systems and methods using artificial intelligence for routing electric vehicles
CN109920246A (zh) * 2019-02-22 2019-06-21 重庆邮电大学 一种基于v2x通信与双目视觉的协同局部路径规划方法
WO2019163268A1 (ja) * 2018-02-23 2019-08-29 クラリオン株式会社 履歴情報記憶装置、経路の算出方法、影響範囲配信システム
CN111785062A (zh) * 2020-04-01 2020-10-16 北京京东乾石科技有限公司 在无信号灯路口实现车路协同的方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2556427A (en) * 2016-10-06 2018-05-30 Ford Global Tech Llc Vehicle with environmental context analysis
WO2018215833A1 (en) * 2017-05-23 2018-11-29 1.21 Gigawatts Ltd. Traffic monitoring and management systems and methods
US10559197B2 (en) 2018-04-13 2020-02-11 Toyota Jidosha Kabushiki Kaisha Remote vehicle control at intersections
CN109855639B (zh) * 2019-01-15 2022-05-27 天津大学 基于障碍物预测与mpc算法的无人驾驶轨迹规划方法
CN110884502B (zh) * 2019-12-06 2021-02-26 北京京东乾石科技有限公司 自动驾驶路径规划质量测评方法、装置和系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10288439B2 (en) * 2017-02-22 2019-05-14 Robert D. Pedersen Systems and methods using artificial intelligence for routing electric vehicles
WO2019163268A1 (ja) * 2018-02-23 2019-08-29 クラリオン株式会社 履歴情報記憶装置、経路の算出方法、影響範囲配信システム
CN108871370A (zh) * 2018-07-03 2018-11-23 北京百度网讯科技有限公司 导航方法、装置、设备和介质
CN109920246A (zh) * 2019-02-22 2019-06-21 重庆邮电大学 一种基于v2x通信与双目视觉的协同局部路径规划方法
CN111785062A (zh) * 2020-04-01 2020-10-16 北京京东乾石科技有限公司 在无信号灯路口实现车路协同的方法和装置

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LI BO: "Research on Computational Optimal Control Methods for Automated Vehicle Motion Planning Problems with Complicated Constraints", CHINESE DOCTORAL DISSERTATIONS FULL-TEXT DATABASE, 1 April 2018 (2018-04-01), pages 1 - 142, XP055855391 *
See also references of EP4131210A4 *

Also Published As

Publication number Publication date
EP4131210A1 (en) 2023-02-08
JP7477636B2 (ja) 2024-05-01
KR20220163426A (ko) 2022-12-09
JP2023518589A (ja) 2023-05-02
CN111785062B (zh) 2021-09-14
EP4131210A4 (en) 2024-04-17
US20230154330A1 (en) 2023-05-18
CN111785062A (zh) 2020-10-16

Similar Documents

Publication Publication Date Title
WO2021197177A1 (zh) 在无信号灯路口实现车路协同的方法和装置
US11738770B2 (en) Determination of lane connectivity at traffic intersections for high definition maps
US11353589B2 (en) Iterative closest point process based on lidar with integrated motion estimation for high definition maps
JP2023514905A (ja) 自律型車両のためのビヘイビア・プランニング
WO2021223465A1 (zh) 一种高精度地图构建方法及系统
WO2022001773A1 (zh) 轨迹预测方法及装置
US20230358554A1 (en) Routing graph management in autonomous vehicle routing
WO2019052501A1 (zh) 信息传输方法、交通控制单元和车载单元
WO2022104774A1 (zh) 目标检测方法和装置
Mo et al. A method of vehicle-infrastructure cooperative perception based vehicle state information fusion using improved kalman filter
CN115016474A (zh) 用于车路协同自动驾驶的控制方法、路侧设备、云控平台和系统
JP2021504825A (ja) 自律走行車両運行管理計画
WO2020264060A1 (en) Determining weights of points of a point cloud based on geometric features
WO2022142839A1 (zh) 一种图像处理方法、装置以及智能汽车
US20230326352A1 (en) Platoon driving control method and apparatus, medium, and electronic device
US20200166936A1 (en) Tuning autonomous vehicle dispatch using autonomous vehicle performance
US20220155082A1 (en) Route comparison for vehicle routing
JP2023024276A (ja) 譲るシナリオにおける自律型車両のための行動計画立案
US20210356965A1 (en) Vehicle routing using third party vehicle capabilities
CN111688717B (zh) 用于控制车辆通行的方法和装置
WO2024036984A1 (zh) 目标定位方法及相关系统、存储介质
CN117170402A (zh) 一种基于人工势场的无人机集群避撞方法及系统
US20230008289A1 (en) Route processing method and apparatus
Sankalprajan et al. Analysis of Computational Need of 2D-SLAM Algorithms for Unmanned Ground Vehicle
CN111832142A (zh) 用于输出信息的方法和装置

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: 21780862

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022557948

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20227038183

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021780862

Country of ref document: EP

Effective date: 20221102