Vehicle path planning method and system for vehicle-road cooperation

Abstract

The invention discloses a vehicle path planning method and system for vehicle-infrastructure cooperation. The method comprises the following steps: S1, cloud global path planning; s2, edge calculation center local path planning; s3, the vehicle terminal executes and feeds back; and S4, multi-source data fusion and traffic flow prediction. According to the invention, on-end global path planning is carried out, the cloud carries out global path planning on each automatic driving vehicle according to a logistics scheduling demand or a vehicle driving destination, and an edge calculation center carries out local path planning according to a specific traffic condition of a current area where the vehicle is located after receiving the overall path planning sent by the cloud. After the instructions are executed and fed back to the vehicle terminal, the vehicle terminal can execute corresponding operations such as acceleration, deceleration and steering after receiving the instructions, so that the problem of path planning in a large-scale road network is solved, and the problems including development of a path planning algorithm suitable for a dynamic environment are solved. And parallel computing, distributed computing and other technologies are utilized to improve the operation efficiency of the algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle path planning for vehicle-road collaboration, and in particular to a vehicle path planning method and system for vehicle-road collaboration. Background Art

[0002] In the 1980s, my country's smart car technology began to develop gradually. Although there is a certain gap with the development of smart cars abroad, China's smart car research and development is rapid. In recent years, major universities, research institutes, car companies and my country's leading technology companies have achieved good results in vehicle path planning technology.

[0003] In a complex road network, the computational complexity of finding the optimal path grows exponentially, which requires the algorithm to have efficient search and computing capabilities to cope with path planning problems in large-scale road networks. In addition, the actual road environment is dynamic, including various factors such as traffic signals, other vehicles, and pedestrians. This requires the algorithm to be able to perceive and understand environmental information in real time and adjust the path based on real-time information.

[0004] To this end, we propose a vehicle path planning method and system for vehicle-road collaboration to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a vehicle path planning method and system for vehicle-road collaboration, so as to solve the problem proposed in the above background technology that the computational complexity of finding the optimal path in a complex road network grows exponentially, which requires the algorithm to have efficient search and computing capabilities to cope with the path planning problem in large-scale road networks. In addition, the actual road environment is dynamic, including various factors such as traffic signals, other vehicles, pedestrians, etc., which requires the algorithm to be able to perceive and understand environmental information in real time and adjust the path according to real-time information.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A vehicle path planning method for vehicle-road collaboration comprises the following steps:

[0008] S1. Cloud-based global path planning: The cloud-based system performs global path planning for each autonomous vehicle based on logistics scheduling requirements or the vehicle’s destination. This step usually includes determining the vehicle’s starting point, end point, and key nodes along the way, and generating an overall path plan.

[0009] S2. Local path planning in the edge computing center: After receiving the overall path planning sent by the cloud, the edge computing center will perform local path planning based on the specific traffic conditions in the area where the vehicle is currently located. This step usually includes extracting local paths within the coverage area, establishing a traffic environment model, and analyzing the expected trajectories of other traffic objects.

[0010] S3, vehicle terminal execution and feedback: The edge computing center sends local path planning and driving control instructions to the vehicle terminal. After receiving these instructions, the vehicle terminal will perform corresponding driving operations, such as acceleration, deceleration, and steering.

[0011] S4. Multi-source data fusion and traffic flow prediction: In order to improve the accuracy and real-time performance of route planning, the vehicle-road cooperative system will also use multi-source data fusion technology, which includes fusing the vehicle's own perception data, the roadside infrastructure's perception data, and the cloud's historical traffic data.

[0012] In a further embodiment, in step S1, the cloud performs scheduling control on each autonomous driving vehicle according to logistics scheduling requirements, and gives overall path planning and driving control instructions, which include vehicle wake-up, start-up, driving, parking, power-off, sleep and various lighting controls. The cloud sends the overall path planning to the relevant edge computing centers and allocates the real-time control rights of the autonomous driving vehicle to the corresponding edge computing center. When allocating control rights, the cloud will consider whether the vehicle is in the overlapping area of ​​multiple edge computing centers, and decide the next closest edge computing center to control the vehicle accordingly.

[0013] In a further embodiment, in step S1, the cloud sends the overall path planning to the relevant edge computing centers, and allocates real-time control rights of the autonomous driving vehicle to the corresponding edge computing centers. When allocating control rights, the cloud will consider the vehicle's current position, speed and target path factors to ensure the continuity and real-time nature of the path planning.

[0014] In a further embodiment, in step S2, the edge computing center will also mark the warning risk areas of the autonomous driving vehicle according to the anthropomorphic warning risk field management mechanism, and avoid these risk areas in the local path planning. This mechanism can assign risk levels to each vehicle according to factors such as vehicle type, driving habits, and the number of violations, and update the risk areas in real time. The edge computing center marks the physical danger areas in the overall path planning, and marks the warning risk areas of the autonomous driving vehicle according to the anthropomorphic warning risk field management mechanism. The edge computing center extracts the local path within the coverage area from the overall path, and establishes a traffic environment model for each autonomous driving vehicle on the local path based on the perception results fed back by each edge computing unit in the received area. By analyzing the expected trajectories of other traffic objects, the local path planning of the controlled vehicle is determined, and the planning should avoid physical danger areas and warning risk areas.

[0015] In a further embodiment, in S3, the edge computing center sends the local path planning and driving control instructions to the vehicle terminal, and the vehicle terminal executes the driving control instructions and collects road information to determine whether the road has qualified lane lines. If there are clear lane lines in the road information and the lane lines are consistent with the local path planning, the vehicle terminal starts its own adaptive cruise and lane keeping functions, and controls the vehicle to travel along the qualified lane lines according to the local path planning. If there are no clear lane lines in the road information or the lane lines are inconsistent with the local planned path, the edge computing center takes over the control of the vehicle, sends the virtual lane lines to the vehicle terminal, and controls the vehicle to travel along the virtual lane lines. During the driving process, if a dangerous event occurs, the edge computing center will actively take over the control of the vehicle and perform risk avoidance control on the vehicle.

[0016] In a further embodiment, S4 realizes the prediction of road network traffic flow by training a time graph convolutional neural network model. These prediction results can be used as an important basis for path planning, helping the system to avoid congested sections in advance or choose a better driving route.

[0017] A vehicle path planning system for vehicle-road collaboration includes the following steps:

[0018] (1) On-board terminal, installed on the vehicle, used to collect data on the vehicle's location, speed, and direction, and transmit this data to roadside equipment or the traffic management center. At the same time, the on-board terminal can also receive road condition information and driving assistance services from the traffic management center; (2) Roadside equipment, installed on the road, used to communicate with the on-board terminal, collect vehicle data, and transmit road condition information to the traffic management center. Roadside equipment can also realize information exchange between vehicles and road infrastructure; (3) Traffic management center, which is responsible for collecting and analyzing traffic data from vehicle terminals and roadside equipment, identifying abnormal road conditions, and synchronizing the information to the vehicle terminals of other vehicles. The traffic management center can also optimize traffic signals, improve traffic flow, and reduce congestion; (4) Data center, which stores and manages traffic data and provides data support for the traffic management center. The data center can also analyze historical data to provide a scientific basis for future traffic planning and decision-making; (5) Application system, based on traffic data and road condition information, provides various intelligent traffic application services, such as real-time navigation, intelligent parking, and traffic signal optimization. The application system can also provide drivers with intelligent journey planning to help them choose the best driving route and avoid congested areas.

[0019] In a further embodiment, in the system, the vehicle senses the state of the road and traffic environment through various sensors installed on the vehicle, such as cameras, radars, and inertial sensors. At the same time, the vehicle obtains its own position information through GPS positioning and other technologies, and collects data on vehicle speed, acceleration, and direction; data transmission and communication: the collected vehicle and road information is transmitted through vehicle-to-vehicle communication, vehicle-to-road facility communication, and vehicle-to-traffic management center communication. Wireless communication technologies, such as 5G and LTE-V, are widely used in the field of vehicle communication to quickly and accurately transmit information to relevant parties; information processing and analysis, the traffic management center receives, integrates and analyzes the data transmitted by the vehicle, monitors and evaluates the driving status, traffic flow, congestion, etc. in real time, and uses big data analysis and machine learning technology to mine data to provide a scientific basis for decision-making; path planning and optimization: based on real-time road condition information and decision support from the traffic management center, the vehicle path planning system can provide the driver with the best driving route. The system can also dynamically adjust the driving route according to changes in traffic conditions to avoid congested areas.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] 1. The present invention adopts a vehicle path planning method of vehicle-road collaboration, with global path planning on the end. The cloud performs global path planning for each autonomous driving vehicle according to logistics scheduling requirements or the vehicle's destination. At the same time, after receiving the overall path planning sent by the cloud, the edge computing center will perform local path planning according to the specific traffic conditions of the vehicle's current area, and then execute and feedback to the vehicle terminal. After receiving these instructions, the vehicle terminal will perform corresponding driving operations, such as acceleration, deceleration, and steering, so as to cope with the path planning problem in large-scale road networks, and solve the problems including developing path planning algorithms suitable for dynamic environments, and using technologies such as parallel computing and distributed computing to improve the algorithm's operating efficiency.

[0022] 2. In the vehicle-road collaborative vehicle path planning system of the present invention, through the on-board terminal, the roadside equipment cooperates with the traffic management center and the data center to provide various intelligent traffic application services based on traffic data and road condition information, such as real-time navigation, intelligent parking, and traffic signal optimization. The application system can also provide intelligent itinerary planning for the driver to help him choose the best driving route and avoid congested areas. This algorithm can perceive and understand environmental information in real time, adjust the path according to the real-time information, and use the sensor fusion and data processing technology on the vehicle to improve the perception and decision-making ability of the algorithm. DETAILED DESCRIPTION

[0023] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0024] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0025] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] A vehicle path planning method for vehicle-road collaboration of the present invention comprises the following steps:

[0027] S1. Cloud-based global path planning: The cloud-based system performs global path planning for each autonomous vehicle based on logistics scheduling requirements or the vehicle’s destination. This step usually includes determining the vehicle’s starting point, end point, and key nodes along the way, and generating an overall path plan.

[0028] S2. Local path planning in the edge computing center: After receiving the overall path planning sent by the cloud, the edge computing center will perform local path planning based on the specific traffic conditions in the area where the vehicle is currently located. This step usually includes extracting local paths within the coverage area, establishing a traffic environment model, and analyzing the expected trajectories of other traffic objects.

[0029] S3, vehicle terminal execution and feedback: The edge computing center sends local path planning and driving control instructions to the vehicle terminal. After receiving these instructions, the vehicle terminal will perform corresponding driving operations, such as acceleration, deceleration, and steering.

[0030] S4. Multi-source data fusion and traffic flow prediction: In order to improve the accuracy and real-time performance of route planning, the vehicle-road cooperative system will also use multi-source data fusion technology, which includes fusing the vehicle's own perception data, the roadside infrastructure's perception data, and the cloud's historical traffic data.

[0031] In step S1, the cloud dispatches and controls each autonomous driving vehicle according to the logistics scheduling requirements, and gives overall path planning and driving control instructions. These instructions include vehicle wake-up, start-up, driving, parking, power-off, sleep and various lighting controls. The cloud sends the overall path planning to the relevant edge computing centers and allocates the real-time control of the autonomous driving vehicle to the corresponding edge computing center. When allocating control rights, the cloud will consider whether the vehicle is in the overlapping area of ​​multiple edge computing centers, and decide the next closest edge computing center to control the vehicle accordingly; and in step S2, the edge computing center will also mark the warning risk area of ​​the autonomous driving vehicle according to the anthropomorphic warning risk field management mechanism, and avoid these risk areas in the local path planning. This mechanism can assign a risk level to each vehicle according to the factors of vehicle type, driving habits and number of violations, and update the risk area in real time. The edge computing center marks the physical danger area in the overall path planning, and marks the warning risk area of ​​the autonomous driving vehicle according to the anthropomorphic warning risk field management mechanism. The edge computing center extracts the local path in the coverage area from the overall path, and establishes a traffic environment model for each autonomous driving vehicle on the local path based on the perception results fed back by each edge computing unit in the received area. By analyzing the expected trajectories of other traffic objects, the local path planning of the controlled vehicle is determined, and the planning should avoid physical danger areas and warning risk areas; step S3, the edge computing center sends the local path planning and driving control instructions to the vehicle terminal, the vehicle terminal executes the driving control instructions, and collects road information to determine whether the road has qualified lane lines. If there are clear lane lines in the road information and the lane lines are consistent with the local path planning, the vehicle terminal starts its own adaptive cruise and lane keeping functions, and controls the vehicle to drive along the qualified lane lines according to the local path planning. If there are no clear lane lines in the road information or the lane lines are inconsistent with the local planned path, the edge computing center takes over the control of the vehicle, sends virtual lane lines to the vehicle terminal, and controls the vehicle to drive along the virtual lane lines. During the driving process, if a dangerous event occurs, the edge computing center will actively take over the control of the vehicle and perform risk avoidance control on the vehicle; Step S4, by training the time graph convolutional neural network model, realizes the prediction of road network traffic flow. These prediction results can be used as an important basis for path planning, helping the system to avoid congested sections in advance or choose a better driving path.

[0032] The vehicle path planning system for vehicle-road collaboration consists of: (1) an on-board terminal, which is installed on the vehicle and is used to collect data on the vehicle's position, speed, and direction, and transmit this data to roadside equipment or a traffic management center. At the same time, the on-board terminal can also receive road condition information and driving assistance services from the traffic management center; (2) roadside equipment, which is installed on the road and is used to communicate with the on-board terminal, collect vehicle data, and transmit road condition information to the traffic management center. Roadside equipment can also realize information exchange between vehicles and road infrastructure; (3) Traffic management center, which is responsible for collecting and analyzing traffic data from vehicle terminals and roadside equipment, identifying abnormal road conditions, and synchronizing the information to the vehicle terminals of other vehicles. The traffic management center can also optimize traffic signals, improve traffic flow, and reduce congestion; (4) Data center, which stores and manages traffic data and provides data support for the traffic management center. The data center can also analyze historical data to provide a scientific basis for future traffic planning and decision-making; (5) Application system, based on traffic data and road condition information, provides various intelligent traffic application services, such as real-time navigation, intelligent parking, and traffic signal optimization. The application system can also provide drivers with intelligent journey planning to help them choose the best driving route and avoid congested areas. Vehicles perceive the status of roads and traffic environments through various sensors installed on the vehicles, such as cameras, radars, and inertial sensors. At the same time, the vehicle obtains its own location information through GPS positioning and other technologies, and collects data on vehicle speed, acceleration, and direction; data transmission and communication: the collected vehicle and road information is transmitted through vehicle-to-vehicle communication, vehicle-to-road facility communication, and vehicle-to-traffic management center communication. Wireless communication technologies, such as 5G and LTE-V, are widely used in the field of vehicle communications to quickly and accurately transmit information to relevant parties; information processing and analysis: the traffic management center receives, integrates and analyzes the data transmitted by the vehicle, and conducts real-time monitoring and evaluation of driving status, traffic flow, congestion, etc., and uses big data analysis and machine learning technology to mine data to provide a scientific basis for decision-making; path planning and optimization: based on real-time road conditions information and decision support from the traffic management center, the vehicle path planning system can provide the driver with the best driving route. The system can also dynamically adjust the driving route according to changes in traffic conditions to avoid congested areas.

[0033] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations within the meaning and scope of the equivalent elements of the claims be included in the invention. Any marking in a claim should not be considered as limiting the claim to which it relates.

[0034] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A vehicle path planning method for vehicle-road collaboration, comprising the following steps: S1. Cloud-based global path planning: The cloud-based system performs global path planning for each autonomous vehicle based on logistics scheduling requirements or the vehicle’s destination. This step usually includes determining the vehicle’s starting point, end point, and key nodes along the way, and generating an overall path plan. S2. Local path planning in the edge computing center: After receiving the overall path planning sent by the cloud, the edge computing center will perform local path planning based on the specific traffic conditions in the area where the vehicle is currently located. This step usually includes extracting local paths within the coverage area, establishing a traffic environment model, and analyzing the expected trajectories of other traffic objects. S3, vehicle terminal execution and feedback: The edge computing center sends local path planning and driving control instructions to the vehicle terminal. After receiving these instructions, the vehicle terminal will perform corresponding driving operations, such as acceleration, deceleration, and steering. S4. Multi-source data fusion and traffic flow prediction: In order to improve the accuracy and real-time performance of route planning, the vehicle-road cooperative system will also use multi-source data fusion technology, which includes fusing the vehicle's own perception data, the roadside infrastructure's perception data, and the cloud's historical traffic data.

2. The vehicle path planning method for vehicle-road collaboration according to claim 1, characterized in that: In step S1, the cloud dispatches and controls each autonomous driving vehicle according to the logistics dispatch requirements, and gives the overall path planning and driving control instructions, which include vehicle wake-up, start-up, driving, parking, power-off, sleep and various lighting controls. The cloud sends the overall path planning to the relevant edge computing centers and allocates the real-time control rights of the autonomous driving vehicle to the corresponding edge computing center. When allocating control rights, the cloud will consider whether the vehicle is in the overlapping area of ​​multiple edge computing centers, and decide the next closest edge computing center to control the vehicle accordingly.

3. The vehicle path planning method for vehicle-road collaboration according to claim 1, characterized in that: In step S1, the cloud sends the overall path planning to the relevant edge computing centers and allocates the real-time control rights of the autonomous driving vehicle to the corresponding edge computing centers. When allocating control rights, the cloud will consider the vehicle's current position, speed and target path factors to ensure the continuity and real-time nature of the path planning.

4. The vehicle path planning method for vehicle-road collaboration according to claim 1, characterized in that: In step S2, the edge computing center will also mark the warning risk areas of the autonomous driving vehicle according to the anthropomorphic warning risk field management mechanism, and avoid these risk areas in the local path planning. This mechanism can assign risk levels to each vehicle according to factors such as vehicle type, driving habits, and the number of violations, and update the risk areas in real time. The edge computing center marks the physical danger areas in the overall path planning, and marks the warning risk areas of the autonomous driving vehicle according to the anthropomorphic warning risk field management mechanism. The edge computing center extracts the local paths within the coverage area from the overall path, and establishes a traffic environment model for each autonomous driving vehicle on the local path based on the perception results fed back by each edge computing unit in the received area. By analyzing the expected trajectories of other traffic objects, the local path planning of the controlled vehicle is determined, and the planning should avoid physical danger areas and warning risk areas.

5. The vehicle path planning method and system for vehicle-road collaboration according to claim 1, characterized in that: In S3, the edge computing center sends the local path planning and driving control instructions to the vehicle terminal. The vehicle terminal executes the driving control instructions and collects road information to determine whether the road has qualified lane lines. If there are clear lane lines in the road information and the lane lines are consistent with the local path planning, the vehicle terminal starts its own adaptive cruise and lane keeping functions, and controls the vehicle to drive along the qualified lane lines according to the local path planning. If there are no clear lane lines in the road information or the lane lines are inconsistent with the local planned path, the edge computing center takes over the control of the vehicle, sends virtual lane lines to the vehicle terminal, and controls the vehicle to drive along the virtual lane lines. During driving, if a dangerous event occurs, the edge computing center will take over the control of the vehicle and perform risk avoidance control on the vehicle.

6. The vehicle path planning method for vehicle-road collaboration according to claim 1, characterized in that: The S4, by training the time graph convolutional neural network model, realizes the prediction of road network traffic flow. These prediction results can be used as an important basis for path planning, helping the system to avoid congested sections in advance or choose a better driving path.

7. The vehicle path planning system for vehicle-road collaboration according to claim 1, characterized in that: The system comprises: (1) a vehicle-mounted terminal installed on the vehicle, which is used to collect data on the vehicle's position, speed, and direction, and transmit the data to roadside equipment or a traffic management center. At the same time, the vehicle-mounted terminal can also receive road condition information and driving assistance services from the traffic management center; (2) Roadside equipment, installed on the road, used to communicate with vehicle terminals, collect vehicle data, and transmit road condition information to the traffic management center. Roadside equipment can also realize information exchange between vehicles and road infrastructure; (3) Traffic management center, responsible for collecting and analyzing traffic data from vehicle terminals and roadside equipment, identifying abnormal road condition information, and synchronizing the information to the vehicle terminals of other vehicles. The traffic management center can also optimize traffic signals, improve traffic flow, and reduce congestion; (4) Data center, storing and managing traffic data, providing data support for the traffic management center. The data center can also analyze historical data to provide a scientific basis for future traffic planning and decision-making; (5) Application system, based on traffic data and road condition information, provides various intelligent traffic application services, such as real-time navigation, intelligent parking, and traffic signal optimization. The application system can also provide drivers with intelligent trip planning to help them choose the best driving route and avoid congested areas.

8. The vehicle path planning system for vehicle-road collaboration according to claim 7, characterized in that: In the system, vehicles sense the status of roads and traffic environments through various sensors installed on the vehicles, such as cameras, radars, and inertial sensors. At the same time, vehicles obtain their own location information through technologies such as GPS positioning, and collect data on vehicle speed, acceleration, and direction; data transmission and communication: the collected vehicle and road information is transmitted through vehicle-to-vehicle communication, vehicle-to-road facility communication, and vehicle-to-traffic management center communication. Wireless communication technologies, such as 5G and LTE-V, are widely used in the field of vehicle communication to quickly and accurately transmit information to relevant parties; information processing and analysis: the traffic management center receives, integrates and analyzes data transmitted by vehicles, conducts real-time monitoring and evaluation of driving status, traffic flow, congestion, etc., and uses big data analysis and machine learning technology to mine data to provide a scientific basis for decision-making; path planning and optimization: based on real-time road condition information and decision support from the traffic management center, the vehicle path planning system can provide the driver with the best driving route. The system can also dynamically adjust the driving route according to changes in traffic conditions to avoid congested areas.