Anti-blocking vehicle path planning system and method with cooperative vehicle and road
By using a central processor and multiple sensors in the vehicle-road collaborative system for environmental perception and information fusion, the vehicle path is planned in real time, and the existing system cannot respond in a timely manner when encountering bursts of people is improved, and the safety of the vehicle is improved Effects of reducing traffic capacity and risk of blockage.
Patent Information
- Application Number
- CN202411221594.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing vehicle-road collaborative vehicle path planning system cannot respond in time when encountering pedestrians suddenly jumping out of the roadside, resulting in an increase in the risk of blockage.
The perception module, fusion module, positioning module and command module driven by a central processor are used to sense the surrounding environment through a variety of sensors (such as cameras, millimeter wave radars, lidars), and integrate information for deep learning, and plan and adjust vehicle paths in real time. Ensure safe passage of vehicles.
It improves the speed and safety of the vehicle when encountering emergencies, reduces the risk of congestion, ensures that the vehicle can adjust its route in a timely manner, and avoids accidents.
Smart Images

Figure CN119028161A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of traffic control, and in particular to a vehicle path planning system and method for anti-jamming vehicle-road collaboration. Background Art
[0002] Vehicle-road collaboration is a road traffic system that implements dynamic real-time information interaction between vehicles and roads in all directions. Vehicle-road collaboration carries out active vehicle safety control and road collaborative management based on the collection and integration of dynamic traffic information in all time and space, fully realizing effective collaboration between people, vehicles and roads, ensuring traffic safety and improving traffic efficiency. After searching, the Chinese patent publication number CN113593240B discloses a vehicle path planning method and system for vehicle-road collaboration, including The present invention discloses a vehicle path planning method and system for vehicle-road collaboration, specifically involving the field of traffic control, including: taking one of the sub-areas in the designated area as the target area; classifying vehicles with the location in the target area as the navigation destination into a target group, the target group including several internal vehicles located in the target area and several external vehicles located outside the target area; performing path planning for any one of the several internal vehicles based on the time spent; performing path planning for any one of the several external vehicles based on the spatial distribution balance. The vehicle path planning method is used for navigation path planning for vehicles whose navigation destination is within the target area and whose vehicles are located outside the target area, which can reduce the probability of new congestion of vehicles outside the target area and ensure smooth passage of vehicles.
[0003] The above patent has the following shortcomings: when the system is in use, if it encounters some pedestrians suddenly jumping out from the roadside, it cannot react. In view of this, we propose a vehicle path planning system and method for anti-blocking vehicle-road collaboration. Summary of the invention
[0004] The purpose of the present invention is to provide a vehicle path planning system and method for anti-congestion vehicle-road collaboration to solve the problems raised in the above background technology.
[0005] To achieve the above object, the present invention provides the following technical solutions: A vehicle path planning system and method for anti-jamming vehicle-road collaboration, including: a central processing unit, a perception module, a fusion module, a positioning module, a command module, and a path planning module; the central processing unit: the perception module, the fusion module, the positioning module, the command module, and the path planning module all operate under the central processing unit, and are used to regulate and control all systems to work in an orderly manner, and to send data and manage system data to facilitate communication and management; the central processing unit: is the final execution of information processing and program operation; the perception module: perceives the situation around the vehicle through a camera, a millimeter-wave radar Q, an ultrasonic radar, and a laser radar; the fusion module: is responsible for using sensor fusion to provide a comprehensive view of the detected object; the positioning module: is responsible for determining the location of the vehicle itself, and is used to accurately determine the specific location in the lane; the path planning module: is responsible for planning the vehicle trajectory to achieve a specific goal; the command module: uses the planned path as input to control the driving vehicle.
[0006] Preferably, the perception module obtains two-dimensional image information through a monocular camera, which lacks depth information in the three-dimensional world and retains color information. It is a dense matrix, and uses pixels to depict objects on the image. The basic type is to use RGB three-channel expression and present colors; The binocular camera requires a transformation matrix between two cameras. This structure is more similar to human eyes. It restores the depth information of objects in the three-dimensional world through two perspectives. However, the amount of calculation for the two cameras at each moment is very large. Depth cameras can measure the distance of each pixel in real time. However, due to this emission-reception measurement method, its scope of use is relatively limited. RGB-D cameras that use infrared to measure depth values are easily interfered by sunlight or infrared light emitted by other sensors, so they cannot be used outdoors. When multiple cameras are used at the same time, they will interfere with each other. For objects made of transmissive materials, since reflected light cannot be received, the position of these points cannot be measured. In addition, depth cameras have some disadvantages in terms of cost and power consumption. Millimeter-wave radars are divided into long-range radars (LRR) and short-range radars (SRR). Since millimeter waves attenuate weakly in the atmosphere, they can detect and sense farther distances. Long-range radars can achieve perception and detection of more than 200 meters. Due to the many advantages of millimeter-wave radars, they currently account for a large proportion of automotive anti-collision sensors. Unlike the data coordinates returned by lidar, they return the distance and angle information of object points. Multiple sensors are required to perceive the environment together to obtain more reliable data. Therefore, multi-sensor fusion is indispensable in unmanned driving. Unmanned driving perception under multi-sensor fusion effectively combines the advantages of each sensor, obtains more reliable data, obtains a wider range of usage environments, and transmits the obtained information to the central processor.
[0007] Preferably, the fusion module transmits information sensed by the perception module through the central processor, and can comprehensively utilize the different characteristics of multiple information sources to obtain relevant information from multiple angles, thereby improving the reliability and accuracy of the entire system.
[0008] Preferably, the positioning module can accurately understand the precise distance between itself and the surrounding environment, and requires the vehicle to have a high positioning accuracy. At present, the most commonly used vehicle positioning method is to combine GPS with INS. The map-based car positioning method is also a commonly used driving car positioning method, and its main feature is simultaneous positioning and map generation.
[0009] Preferably, the path planning module conducts in-depth learning and analysis of the surrounding environment through the data collected by the perception module and the map and other information collected by the positioning module, so as to make corresponding decisions and plans. For example, when the road is blocked or an accident occurs, the module can adjust the route in time to ensure driving safety. Path planning technology can be divided into global path planning and local path planning. Global path planning is to determine the feasible and optimal path based on the known map using known local information such as obstacle positions and road boundaries. It combines optimization and feedback mechanisms well. Local path planning is to decide the trajectory of the current front section of the unmanned platform based on the local environmental information perceived by the sensor under the guidance of the drivable area generated by the global path planning. Global path planning is for situations where the surrounding environment is known, and local path planning is suitable for situations where the environment is unknown. Path planning algorithms include visibility graph method, grid method, artificial potential field method, probabilistic landmark method, random search tree algorithm, and particle swarm algorithm.
[0010] Preferably, the command module makes decisions based on the information obtained by the perception central processor from the perception module, the positioning module, and the fusion module, and then makes decisions on the next behavior, and then controls the vehicle. The decision-making technology mainly includes fuzzy reasoning, reinforcement learning, neural networks, Bayesian networks and other technologies. The behavior of the decision-making control system is divided into three schemes: reactive, reflective and comprehensive. Reactive control is a feedback control process, which continuously adjusts the steering wheel angle and vehicle speed according to the deviation between the current position of the vehicle and the expected path until the destination is reached. Reflective control is a low-level behavior used to judge and respond quickly to emergencies during the journey. Comprehensive control adds a machine learning module to the reaction layer to convert part of the decision-making layer behavior into sensor-based reaction layer behavior, thereby improving the response speed of the system.
[0011] Preferably, the perception module is responsible for providing a real-world model for the path planning module, and is composed of two sub-modules: road environment perception and vehicle motion sensing. It is based on artificial intelligence theory and completes tasks such as planning, reasoning, and decision-making of vehicle behavior and motion. The entire module is centered on a trajectory prediction algorithm and is divided into two sub-modules: high-level behavior planning and low-level motion planning. The command module is the executive part of the motion planning layer, which compares the actual motion posture of the vehicle with the expected motion posture in real time, and uses an intelligent control algorithm to control actuators such as the steering wheel, accelerator, and brake of the vehicle. The most typical reasoning method is fuzzy reasoning, and the most commonly used control algorithm is the PID algorithm.
[0012] A vehicle path planning method for anti-jamming vehicle-road collaboration includes the following steps: Step 1: The perception module's monocular camera, binocular camera, depth camera, and millimeter-wave radar sense the vehicle's surroundings, such as the road environment perception and vehicle motion sensing sub-modules, and transmit the information to the central processor.
[0013] Step 2: The central processing unit inputs the information into the fusion module, which uses the different characteristics of multiple information sources to obtain relevant information from multiple angles, thereby improving the reliability and accuracy of the entire system. The precise distance between itself and the surrounding environment is then input into the central processing unit through the positioning module by combining GPS and INS.
[0014] Step 3: The central processing unit inputs information into the path planning module and the command module. Through the data collected by the perception module and the map information collected by the positioning module, it conducts in-depth learning and analysis of the surrounding environment to make corresponding decisions and plans. If a traffic jam occurs, the command module will transmit the deviation between the current position of the vehicle and the expected path to the display screen inside the car. The owner chooses the road based on the information. At the same time, the command module makes judgments on emergencies during the journey and responds quickly.
[0015] Compared with the prior art, it has the following beneficial effects: 1. This anti-jamming vehicle-road collaborative vehicle path planning system and method inputs information into the path planning module and the command module through the central processing unit, and conducts in-depth learning and analysis of the surrounding environment through the data collected by the perception module and the map and other information collected by the positioning module, so as to make corresponding decisions and plans. If a traffic jam occurs, the command module will transmit the deviation between the current position of the vehicle and the expected path to the display screen inside the vehicle, and the owner will choose the road according to the information. At the same time, the command module will judge and respond quickly to emergencies during the driving process.
[0016] 2. This anti-jamming vehicle-road collaborative vehicle path planning system and method enables the vehicle to accurately understand the precise distance between itself and the surrounding environment through the positioning module. Even if the vehicle is lost, the information can still be input into the central processing unit through the positioning module, and the central processing unit will then input the information into the mobile terminal.
[0017] 3. This anti-jamming vehicle-road collaborative vehicle path planning system and method enables the vehicle to better grasp the environment in which it is located through the perception module, and obtain various information in the environment in its environmental perception link, such as the location, speed, movement range, traffic rules, etc. of obstacles. Unmanned vehicles generally use multiple sensors, such as lidar, camera, millimeter wave radar, etc., which convert the collected information into digital signals, which are then processed by the central processing unit, which effectively eliminates the blind spots of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in 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.
[0020] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.
[0021] In the description of this patent, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", and "set" should be understood in a broad sense, for example, fixedly connected, set, detachably connected, set, or integrally connected, set. For ordinary technicians in this field, the specific meanings of the above terms in this patent are understood according to specific circumstances.
[0022] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "several" is two or more, unless otherwise clearly and specifically defined.
[0023] After searching, the Chinese patent publication number CN113593240B discloses a vehicle path planning method and system for vehicle-road collaboration, including The present invention discloses a vehicle path planning method and system for vehicle-road collaboration, specifically involving the field of traffic control, including: taking one of the sub-areas in the designated area as the target area; classifying vehicles with the location in the target area as the navigation destination into a target group, the target group including several internal vehicles located in the target area and several external vehicles located outside the target area; performing path planning for any one of the several internal vehicles based on the time spent; performing path planning for any one of the several external vehicles based on the spatial distribution balance. The vehicle path planning method is used for navigation path planning for vehicles whose navigation destination is within the target area and whose vehicles are located outside the target area, which can reduce the probability of new congestion of vehicles outside the target area and ensure smooth passage of vehicles.
[0024] The above patent has the following shortcomings: when the system is in use, if it encounters some pedestrians suddenly jumping out from the roadside, it cannot react. In view of this, we propose a vehicle path planning system and method for anti-blocking vehicle-road collaboration.
[0025] like Figure 1 As shown, a vehicle path planning system and method for anti-jamming vehicle-road collaboration include a central processing unit, a perception module, a fusion module, a positioning module, a command module, and a path planning module; central processing unit: the perception module, the fusion module, the positioning module, the command module, and the path planning module all operate under the central processing unit, which is used to regulate and control all systems to work in an orderly manner, and to send data and manage system data to facilitate communication management; central processing unit: is the final execution of information processing and program running; perception module: perceives the situation around the vehicle through cameras, millimeter-wave radars Q, ultrasonic radars, and lidars; fusion module: is responsible for using sensor fusion to provide a comprehensive view of the detected object; positioning module: is responsible for determining the location of the vehicle itself, which is used to accurately determine the specific location in the lane; path planning module: is responsible for planning the vehicle trajectory to achieve a specific goal; command module: uses the planned path as input to control the driving vehicle.
[0026] The perception module obtains two-dimensional image information through a monocular camera. It lacks the depth information in the three-dimensional world but retains the color information. It is a dense matrix that depicts objects with pixels on the image. The basic type is to use RGB three-channel expression and present colors.
[0027] The binocular camera requires a transformation matrix between the two cameras. This structure is more similar to human eyes, and it can restore the depth information of objects in the three-dimensional world through two perspectives. However, the amount of calculation required by the two cameras at each moment is very large.
[0028] Depth cameras can measure the distance of each pixel in real time. However, due to this emission-reception measurement method, its scope of use is relatively limited. RGB-D cameras that use infrared to measure depth values are easily interfered by sunlight or infrared light emitted by other sensors, so they cannot be used outdoors. When multiple cameras are used at the same time, they will interfere with each other. For objects made of transmissive materials, the positions of these points cannot be measured because reflected light cannot be received. In addition, depth cameras have some disadvantages in terms of cost and power consumption.
[0029] Millimeter-wave radars are divided into long-range radars (LRR) and short-range radars (SRR). Since millimeter waves attenuate weakly in the atmosphere, they can detect and sense farther distances. Long-range radars can achieve perception and detection of more than 200 meters. Due to the many advantages of millimeter-wave radars, they currently account for a large proportion of automotive anti-collision sensors. Unlike the data coordinates returned by lidar, they return the distance and angle information of object points. Multiple sensors are required to perceive the environment together to obtain more reliable data. Therefore, multi-sensor fusion is indispensable in unmanned driving. Unmanned driving perception under multi-sensor fusion effectively combines the advantages of each sensor, obtains more reliable data, obtains a wider range of usage environments, and transmits the obtained information to the central processor.
[0030] The fusion module transmits information perceived by the perception module through the central processor, and can comprehensively utilize the different characteristics of multiple information sources to obtain relevant information from multiple angles, thereby improving the reliability and accuracy of the entire system.
[0031] The positioning module can accurately understand the precise distance between itself and the surrounding environment, and requires the vehicle to have a high positioning accuracy. At present, the most commonly used vehicle positioning method is to combine GPS with INS. The map-based car positioning method is also a commonly used driving car positioning method. Its main feature is simultaneous positioning and map generation.
[0032] The path planning module conducts in-depth learning and analysis of the surrounding environment through the data collected by the perception module and the map and other information collected by the positioning module, so as to make corresponding decisions and plans. For example, when the road is blocked or an accident occurs, the module can adjust the route in time to ensure driving safety. Path planning technology can be divided into global path planning and local path planning. Global path planning is to determine the feasible and optimal path based on the known map using known local information such as obstacle locations and road boundaries. It combines optimization and feedback mechanisms well. Local path planning is to decide the trajectory of the unmanned platform on the current front section of the road based on the local environmental information perceived by the sensor under the guidance of the drivable area generated by the global path planning. Global path planning is for situations where the surrounding environment is known, and local path planning is suitable for situations where the environment is unknown. Path planning algorithms include visibility graph method, grid method, artificial potential field method, probabilistic landmark method, random search tree algorithm, and particle swarm algorithm.
[0033] The command module makes decisions based on the information obtained by the perception central processor from the perception module, positioning module, and fusion module, and then decides on the next behavior and controls the vehicle. The decision-making technology mainly includes fuzzy reasoning, reinforcement learning, neural network, Bayesian network and other technologies. The behavior of the decision-making control system is divided into three schemes: reactive, reflective and comprehensive. Reactive control is a feedback control process. According to the deviation between the current posture of the vehicle and the expected path, the steering wheel angle and vehicle speed are continuously adjusted until the destination is reached. Reflective control is a low-level behavior used to judge and respond quickly to emergencies during the journey. Comprehensive control adds a machine learning module to the reaction layer to convert part of the decision-making layer behavior into sensor-based reaction layer behavior, thereby improving the response speed of the system.
[0034] The perception module is responsible for providing a real-world model for the path planning module. It consists of two sub-modules: road environment perception and vehicle motion sensing. Based on artificial intelligence theory, it completes tasks such as planning, reasoning, and decision-making of vehicle behavior and motion. The entire module is centered on the trajectory prediction algorithm and is divided into two sub-modules: high-level behavior planning and low-level motion planning. The command module is the executive part of the motion planning layer. It compares the actual motion posture of the vehicle with the expected motion posture in real time, and uses intelligent control algorithms to control the steering wheel, accelerator, brake and other actuators of the vehicle. The most typical reasoning method is fuzzy reasoning, and the most commonly used control algorithm is the PID algorithm.
[0035] The working principle of the present invention is as follows: the information perceived around the vehicle, such as the road environment perception and vehicle motion sensing two sub-modules, is transmitted to the central processing unit through the monocular camera, binocular camera, depth camera and millimeter wave radar of the perception module, and the information is input into the fusion module by the central processing unit. The fusion module obtains relevant information from multiple directions by utilizing the different characteristics of multiple information sources, thereby improving the reliability and accuracy of the entire system. The precise distance between itself and the surrounding environment is input into the central processing unit through the positioning module by combining GPS and INS. The central processing unit inputs the information into the path planning module and the command module. The surrounding environment is deeply studied and analyzed through the data collected by the perception module and the map and other information collected by the positioning module, thereby making corresponding decisions and plans. If a traffic jam is encountered, the command module will transmit the deviation between the current posture of the vehicle and the expected path to the display screen inside the vehicle. The owner selects the road according to the information. At the same time, the command module makes judgments on emergencies during the driving process and responds quickly.
[0036] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A vehicle path planning system and method for anti-jamming vehicle-road collaboration, It is characterized in that include: Central processing unit, perception module, fusion module, positioning module, command module, path planning module; Central Processing Unit: The perception module, fusion module, positioning module, command module, and path planning module all operate under the central processing unit, which is used to regulate and control all systems to work in an orderly manner, to send data and manage system data, and to facilitate communication and management; CPU: It is the final execution of information processing and program running; Perception module: uses cameras, millimeter-wave radar Q, ultrasonic radar, and lidar to perceive the situation around the vehicle; Fusion module: responsible for providing a comprehensive view of the detected object using sensor fusion; Positioning module: responsible for determining the location of the vehicle, and for accurately determining the specific location in the lane; Path planning module: responsible for planning the vehicle trajectory to reach a specific goal; Command module: takes the planned path as input to control the driving vehicle.
2. The vehicle path planning system and method for anti-jamming vehicle-road collaboration according to claim 1, Features: The perception module obtains two-dimensional image information through a monocular camera, which lacks the depth information in the three-dimensional world and retains the color information. It is a dense matrix that depicts objects with pixels on the image. The basic type is to use RGB three-channel expression and present colors; The binocular camera requires a transformation matrix between two cameras. This structure is more similar to human eyes. It restores the depth information of objects in the three-dimensional world through two perspectives. However, the amount of calculation for the two cameras at each moment is very large. Depth cameras can measure the distance of each pixel in real time. However, due to this emission-reception measurement method, its scope of use is relatively limited. RGB-D cameras that use infrared to measure depth values are easily interfered by sunlight or infrared light emitted by other sensors, so they cannot be used outdoors. When multiple cameras are used at the same time, they will interfere with each other. For objects made of transmissive materials, since reflected light cannot be received, the position of these points cannot be measured. In addition, depth cameras have some disadvantages in terms of cost and power consumption. Millimeter-wave radars are divided into long-range radars and short-range radars. Since millimeter waves attenuate weakly in the atmosphere, they can detect and sense farther distances. Long-range radars can achieve perception and detection of more than 200 meters. Due to the many advantages of millimeter-wave radars, they currently account for a large proportion of automotive anti-collision sensors. Unlike the data coordinates returned by lidar, they return the distance and angle information of object points. Multiple sensors are required to perceive the environment together to obtain more reliable data. Therefore, multi-sensor fusion is indispensable in unmanned driving. Unmanned driving perception under multi-sensor fusion effectively combines the advantages of each sensor, obtains more reliable data, obtains a wider range of usage environments, and transmits the obtained information to the central processor.
3. The vehicle path planning system and method for anti-jamming vehicle-road collaboration according to claim 2, Features: The fusion module transmits information sensed by the perception module through the central processor, and can comprehensively utilize the different characteristics of multiple information sources to obtain relevant information from multiple angles, thereby improving the reliability and accuracy of the entire system.
4. The vehicle path planning system and method for anti-jamming vehicle-road collaboration according to claim 3, Features: The positioning module can accurately understand the precise distance between itself and the surrounding environment, and requires the vehicle to have a high positioning accuracy. At present, the most commonly used vehicle positioning method is to combine GPS with INS. The map-based car positioning method is also a commonly used driving car positioning method, and its main feature is simultaneous positioning and map generation.
5. The vehicle path planning system and method for anti-jamming vehicle-road collaboration according to claim 4, Features: The path planning module conducts in-depth learning and analysis of the surrounding environment through the data collected by the perception module and the map and other information collected by the positioning module, so as to make corresponding decisions and plans. For example, when the road is blocked or an emergency occurs, the module can adjust the route in time to ensure driving safety. Path planning technology can be divided into global path planning and local path planning. Global path planning is to determine the feasible and optimal path based on the known map using known local information such as obstacle locations and road boundaries. It combines optimization and feedback mechanisms well. Local path planning is to decide the trajectory of the unmanned platform on the current front section of the road under the guidance of the drivable area generated by the global path planning based on the local environmental information perceived by the sensor. Global path planning is aimed at the situation where the surrounding environment is known, and local path planning is suitable for the situation where the environment is unknown. Path planning algorithms include visibility graph method, grid method, artificial potential field method, probabilistic landmark method, random search tree algorithm, and particle swarm algorithm.
6. The anti-jamming vehicle-road cooperative vehicle path planning system and method according to claim 5, Features: The command module makes decisions based on the information obtained by the perception central processor from the perception module, positioning module, and fusion module, and then makes decisions on the next behavior and then controls the vehicle. The decision-making technology mainly includes fuzzy reasoning, reinforcement learning, neural network, Bayesian network and other technologies. The behavior of the decision-making control system is divided into three schemes: reactive, reflective and comprehensive. Reactive control is a feedback control process. According to the deviation between the current posture of the vehicle and the expected path, the steering wheel angle and vehicle speed are continuously adjusted until the destination is reached. Reflective control is a low-level behavior used to judge and respond quickly to emergencies during the journey. Comprehensive control adds a machine learning module to the reaction layer to convert part of the decision-making layer behavior into sensor-based reaction layer behavior, thereby improving the response speed of the system.
7. The anti-jamming vehicle-road cooperative vehicle path planning system and method according to claim 6, Features: The perception module is responsible for providing a real-world model for the path planning module. It consists of two sub-modules: road environment perception and vehicle motion sensing. Based on artificial intelligence theory, it completes tasks such as planning, reasoning, and decision-making of vehicle behavior and motion. The entire module is centered on the trajectory prediction algorithm and is divided into two sub-modules: high-level behavior planning and low-level motion planning. The command module is the executive part of the motion planning layer. It compares the actual motion posture of the vehicle with the expected motion posture in real time, and uses an intelligent control algorithm to control the steering wheel, accelerator, brake and other actuators of the vehicle. The most typical reasoning method is fuzzy reasoning, and the most commonly used control algorithm is the PID algorithm.
8. The anti-jamming vehicle-road cooperative vehicle path planning method according to claim 7, The following steps are involved: Step 1: The perception module's monocular camera, binocular camera, depth camera, and millimeter-wave radar sense the vehicle's surroundings, such as the road environment perception and vehicle motion sensing sub-modules, and transmit the information to the central processor.
9. Step 2 The central processing unit inputs the information into the fusion module, which uses the different characteristics of multiple information sources to obtain relevant information from multiple angles, thereby improving the reliability and accuracy of the entire system. The precise distance between itself and the surrounding environment is then input into the central processing unit through the positioning module by combining GPS and INS.
10. Step 3 The central processing unit inputs information into the path planning module and the command module. Through the data collected by the perception module and the map information collected by the positioning module, it conducts in-depth learning and analysis of the surrounding environment to make corresponding decisions and plans. If a traffic jam occurs, the command module will transmit the deviation between the current position of the vehicle and the expected path to the display screen inside the car. The owner chooses the road based on the information. At the same time, the command module makes judgments on emergencies during the journey and responds quickly.
Citation Information
Patent Citations
A method and system for vehicle route planning in vehicle-road cooperation
CN113593240B
