Automatic driving vehicle obstacle avoidance control method and system conforming to road driving specifications

Abstract

The invention provides an automatic driving vehicle obstacle avoidance control method and system conforming to road driving specifications, and belongs to the field of intelligent driving, and the method comprises the steps: S1, building a vehicle dynamics model according to an automatic driving vehicle, calibrating the automatic driving vehicle according to the vehicle dynamics model, and obtaining the current position and the current speed of the automatic driving vehicle; s2, acquiring environment information of the autonomous vehicle, and constructing a driving area map; s3, based on the driving area map, using an A * algorithm to detect and search global path points, and generating a global driving path; s4, constructing a dangerous potential field based on the driving area map, and generating an obstacle avoidance path; s5, improving a gravitational potential field function of an artificial potential field in the artificial potential field method to obtain an improved artificial potential field, and performing local path planning based on the global driving path and the obstacle avoidance path by using the improved artificial potential field to generate a vehicle driving track; and S6, performing steering control on the autonomous vehicle through the vehicle dynamics model, and executing an obstacle avoidance strategy. According to the invention, efficient path planning and obstacle avoidance control are realized by improving the artificial potential field and the A * algorithm, the safety and compliance of the autonomous vehicle can be ensured, and flexible path adjustment can be realized in a complex dynamic environment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to an obstacle avoidance control method and system for an autonomous driving vehicle that complies with road driving regulations. Background Art

[0002] In recent years, driverless technology, as an important part of the smart car industry, has attracted much attention for its great potential in improving urban accessibility and optimizing traffic connectivity. Good path planning can not only improve passenger experience, but also reduce environmental pollution, which is of great significance to alleviating modern urban traffic problems. The obstacle avoidance control of autonomous vehicles is mainly based on environmental recognition based on perception technology, and uses artificial intelligence for path planning.

[0003] However, existing autonomous vehicles achieve the desired path planning effect by establishing numerous constraints, which results in high complexity of models and algorithms, greatly reducing the flexibility of vehicle control and making unmanned driving safety unsafe. Autonomous vehicles do not consider the impact of the vehicle's own dynamic characteristics on the driving process during driving, resulting in deviations in the planned path during actual execution, and insufficient consideration of actual road driving regulations, resulting in vehicle behavior that does not comply with traffic regulations.

[0004] Therefore, finding a method that can ensure the vehicle's dynamic obstacle avoidance and safe driving while complying with actual road driving regulations is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] In view of this, the present invention proposes an obstacle avoidance control method and system for an autonomous driving vehicle that complies with road driving regulations. The method and system can achieve efficient path planning and obstacle avoidance control by improving the artificial potential field and the A* algorithm, which can not only ensure the safety and compliance of the autonomous driving vehicle, but also realize flexible path adjustment in complex dynamic environments.

[0006] The technical solution of the present invention is achieved in this way:

[0007] In a first aspect, the present invention provides an obstacle avoidance control method for an autonomous driving vehicle that complies with road driving regulations, comprising the following steps:

[0008] S1. establishing a vehicle dynamics model according to the autonomous driving vehicle, calibrating the autonomous driving vehicle according to the vehicle dynamics model, and obtaining a current position and a current speed of the autonomous driving vehicle;

[0009] S2, obtaining environmental information of the autonomous driving vehicle and constructing a driving area map based on the environmental information;

[0010] S3, based on the driving area map, use the A* algorithm to detect and search for global path points and generate a global driving path;

[0011] S4, constructing a danger potential field based on the driving area map, and generating an obstacle avoidance path according to the danger potential field;

[0012] S5. improving the gravitational potential field function of the artificial potential field in the artificial potential field method to obtain an improved artificial potential field, and using the improved artificial potential field to perform local path planning based on the global driving path and the obstacle avoidance path to generate a vehicle driving trajectory;

[0013] S6. Steering control of the autonomous driving vehicle is performed through the vehicle dynamics model, and the vehicle drives according to the vehicle's driving trajectory and executes obstacle avoidance strategies.

[0014] On the basis of the above technical solution, preferably, the obstacle avoidance strategy specifically includes:

[0015] Step 1: Determine whether the autonomous driving vehicle enters the obstacle potential field:

[0016] If so, the surrounding potential field conditions are judged, the autonomous driving vehicle is controlled to change lanes, and the speed is gradually reduced;

[0017] If not, proceed to the next step;

[0018] Step 2: Determine whether the speed of the autonomous driving vehicle is the initial speed:

[0019] If so, the autonomous driving vehicle is controlled to travel at a constant speed along the center line of the lane according to the vehicle's driving trajectory;

[0020] If not, the autonomous driving vehicle is controlled to gradually accelerate along the center line of the lane and return to the initial speed according to the vehicle's driving trajectory;

[0021] Step 3: Determine whether the autonomous driving vehicle has entered the target area and whether the driving time of the autonomous driving vehicle exceeds the planned time based on the current position;

[0022] If the autonomous vehicle enters the target area and the driving time exceeds the planned time, an error signal is generated and output;

[0023] If the autonomous driving vehicle enters the target area and the driving time does not exceed the planned time, the autonomous driving vehicle repeats steps 1 and 2 until the autonomous driving vehicle completes the obstacle avoidance path.

[0024] If the autonomous vehicle does not enter the target area and the driving time exceeds the planned time, an error signal is generated and output;

[0025] If the autonomous driving vehicle does not enter the target area and the driving time does not exceed the planned time, return to step 1 until the autonomous driving vehicle completes the obstacle avoidance path.

[0026] On the basis of the above technical solution, preferably, the obstacle potential field includes a vehicle obstacle potential field and a road obstacle potential field.

[0027] On the basis of the above technical solution, preferably, the expression of the improved artificial potential field is as follows:

[0028]

[0029] Among them, U att (q) represents the improved artificial potential field, r target represents the area where the target point is located, K att represents the gravitational gain system, ρ s Represents the distance between the current position of the autonomous vehicle and the destination.

[0030] On the basis of the above technical solution, preferably, the expression of the dangerous potential field is as follows:

[0031] U total =U road +U block +U obs ;

[0032]

[0033]

[0034] Among them, U total represents the total repulsive potential field, U road represents the road potential field, U block represents the potential field of road obstacles, U obs represents the potential field of the road obstacle vehicle, F road represents the road repulsion, k road represents the road hazard potential field gain coefficient, r c Indicates the distance between the vehicle and the traffic marking, l w Indicates lane width, F block represents the repulsion force of road obstacles, k block Represents the gain coefficient of the roadblock hazard potential field, s block Represents the roadblock type parameter, r b Indicates the distance between the vehicle and the roadblock. represents the range of action of the roadblock potential field, F obs represents the repulsion force of the obstacle vehicle, l v represents the distance between the controlled vehicle and the roadblock, S represents the area occupied by the autonomous driving vehicle, and k v represents the gain coefficient of the obstacle vehicle, L represents the length of the autonomous driving vehicle, r vrepresents the Manhattan distance between the obstacle vehicle and the controlled vehicle, W represents the width of the autonomous driving vehicle, Indicates the safe distance between vehicles.

[0035] Based on the above technical solution, preferably, in step S6, steering control of the automatic driving vehicle specifically includes:

[0036] Use rear-wheel drive to give the vehicle forward speed, driving the autonomous vehicle to move its position;

[0037] The front wheel state of the autonomous vehicle is calculated based on the current vehicle angle combined with the steering angle. The calculation formula is:

[0038]

[0039] Where θ represents the turning angle of the autonomous vehicle, represents the front wheel steering angle of the autonomous vehicle, v fx Represents the cosine component of the front wheel speed of the autonomous vehicle, v fy represents the sinusoidal component of the front wheel speed of the autonomous vehicle, and v represents the speed of the rear wheel drive of the autonomous vehicle.

[0040] More preferably, step S2 specifically includes:

[0041] Obtain software map information and build a simple map model;

[0042] A database is established based on the information points around the autonomous driving vehicle and the connectivity between the information points, and the simplified map model is improved to obtain a driving area map; the information points around the autonomous driving vehicle include image data dynamic points, static points and reference points.

[0043] In a second aspect, the present invention provides an obstacle avoidance control system for an autonomous driving vehicle that complies with road driving regulations, and adopts the obstacle avoidance control method for an autonomous driving vehicle as described above, comprising:

[0044] A model building module, configured to establish a vehicle dynamics model according to the autonomous driving vehicle, calibrate the autonomous driving vehicle according to the vehicle dynamics model, and obtain a current position and a current speed of the autonomous driving vehicle;

[0045] A map construction module configured to obtain environmental information of the autonomous driving vehicle and construct a driving area map based on the environmental information;

[0046] A global path planning module is configured to detect and search global path points based on a driving area map using an A* algorithm to generate a global driving path;

[0047] A potential field environment building module, which is configured to build a dangerous potential field based on a driving area map and generate an obstacle avoidance path according to the dangerous potential field;

[0048] A local path planning module is configured to improve the gravitational potential field function of the artificial potential field in the artificial potential field method to obtain an improved artificial potential field, and use the improved artificial potential field to perform local path planning based on the global driving path and the obstacle avoidance path to generate a vehicle driving trajectory;

[0049] The road driving module is configured to control the steering of the autonomous vehicle through the vehicle dynamics model, drive according to the vehicle's driving trajectory and execute obstacle avoidance strategies.

[0050] In a third aspect, the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions enable the computer to implement the autonomous driving vehicle obstacle avoidance control method as described above.

[0051] In a fourth aspect, the present invention provides an electronic device, comprising at least one processor, a memory, a communication interface and a bus; wherein:

[0052] The processor, memory, and communication interface communicate with each other via the bus;

[0053] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the autonomous driving vehicle obstacle avoidance control method as described above.

[0054] The automatic driving vehicle obstacle avoidance control method of the present invention has the following beneficial effects compared with the prior art:

[0055] (1) By improving the artificial potential field and A* algorithm, efficient path planning and obstacle avoidance control are achieved, which not only ensures the safety and compliance of the autonomous driving vehicle, but also enables flexible path adjustment in complex dynamic environments, significantly improving the practicality and reliability of the autonomous driving system;

[0056] (2) By constructing a hazard potential field, not only can the collision with static obstacles and dynamic vehicles be effectively avoided, but also the vehicle can be ensured to always stay within the lane and comply with traffic rules, thus improving the safety and compliance of autonomous vehicles in complex traffic environments;

[0057] (3) By improving the traditional artificial potential field method, an improved artificial potential field method is obtained, which enables the vehicle to approach the target point more smoothly. At the same time, the adaptability of the algorithm in a dynamic environment is improved, so that the autonomous driving vehicle can respond to emergencies more flexibly, and the overall performance and stability of the system are improved;

[0058] (4) By judging in real time whether the vehicle has entered the obstacle potential field and combining speed adjustment and lane changing operations, the obstacle avoidance strategy can achieve a more intelligent and smooth obstacle avoidance process. At the same time, by setting time limits and error reporting mechanisms, it can also effectively prevent the system from falling into an infinite loop or being unable to reach the target for a long time, greatly improving the reliability and practicality of the autonomous driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 This is a flow chart of the obstacle avoidance control method for an autonomous driving vehicle of the present invention;

[0061] Figure 2 A schematic diagram of a vehicle dynamics model of the obstacle avoidance control method for an autonomous driving vehicle of the present invention;

[0062] Figure 3 A schematic diagram of a grid of a driving area map model of an obstacle avoidance control method for an autonomous driving vehicle of the present invention;

[0063] Figure 4 A* algorithm global path planning flow chart of the automatic driving vehicle obstacle avoidance control method of the present invention;

[0064] Figure 5 Schematic diagram of the danger potential field of the obstacle avoidance control method for an autonomous driving vehicle of the present invention, wherein (a) is a 3D danger potential field diagram of a vehicle obstacle, (b) is a 3D danger potential field diagram of a road and lane, and (c) is a 3D danger potential field diagram of a road obstacle;

[0065] Figure 6 A schematic diagram of a flow chart of global path planning combined with local dynamic obstacle avoidance in the obstacle avoidance control method for an autonomous driving vehicle of the present invention;

[0066] Figure 7 It is a module diagram of the obstacle avoidance control system of the autonomous driving vehicle of the present invention. DETAILED DESCRIPTION

[0067] 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.

[0068] like Figure 1 As shown, the present invention provides an obstacle avoidance control method for an autonomous driving vehicle that complies with road driving regulations, comprising the following steps:

[0069] S1. Establish a vehicle dynamics model according to the autonomous driving vehicle, calibrate the autonomous driving vehicle according to the vehicle dynamics model, and obtain the current position and current speed of the autonomous driving vehicle.

[0070] like Figure 2 As shown, in one embodiment of the present application, a vehicle dynamics model is established according to the length, width, front and rear wheelbase and speed of the autonomous driving vehicle. Then, the vehicle state of the autonomous driving vehicle at any time is q = (x, y, w), and the formula is as follows:

[0071]

[0072] Where θ represents the turning angle of the autonomous vehicle, represents the front wheel steering angle of the autonomous vehicle, l represents the front and rear wheel track of the autonomous vehicle, x represents the component of the speed on the horizontal axis, y represents the component of the speed on the vertical axis, and w represents the angular velocity of the autonomous vehicle.

[0073] S2. Obtain environmental information of the autonomous driving vehicle and construct a driving area map based on the environmental information.

[0074] like Figure 3 As shown, specifically, step S2 specifically includes:

[0075] Obtain software map information and build a simple map model;

[0076] A database is established based on the information points around the autonomous driving vehicle and the connectivity between the information points, and the simplified map model is improved to obtain a driving area map; the information points around the autonomous driving vehicle include dynamic points, static points and reference points of image data around the autonomous driving vehicle.

[0077] In one embodiment of the present application, laser radar, camera and infrared camera are used to obtain environmental information of the autonomous driving vehicle.

[0078] In one embodiment of the present application, map software is used to obtain environmental information about information points around the autonomous driving vehicle and between the information points, and to construct a formal area map.

[0079] S3. Based on the driving area map, use the A* algorithm to detect and search for global path points and generate a global driving path.

[0080] Among them, the calculation formula of the A* algorithm is as follows:

[0081] f(n)=g(n)+h(n)

[0082] Among them, n represents the current information node, f(n) represents the total cost, g(n) represents the actual cost of traveling to the current information point, and h(n) represents the estimated cost of traveling from the current information point to the target point.

[0083] In one embodiment of the present application, the A* algorithm is used to detect and search global path points to generate a global driving path, specifically including:

[0084] Set the minimum time interval Δt, use the distance traveled by the vehicle within the minimum time interval as the step length, and construct a grid map of the driving area;

[0085] According to the grid map and the location information of the target point, the distance between each information point is calculated;

[0086] Use the A* algorithm to generate a global path with the optimal distance cost based on the distance information between each information point.

[0087] like Figure 4 As shown, the A* algorithm specifically includes:

[0088] Set the distance of the current position to 0, the distance of other nodes to infinity, calculate the heuristic function value of the starting node, and then add it to the open queue;

[0089] Determine whether the open queue is empty:

[0090] If so, path planning fails;

[0091] If not, take out the node with the smallest f(n) in the open queue, record it as the current node, add it to the close list, and mark it as visited, and determine whether the current node is the target point:

[0092] If so, the global path planning is successful and the optimal path point sequence is output;

[0093] If not, expand the current node, find the minimum cost value, set the current node as the parent node of the minimum cost value node, and add the neighbor node to the open list.

[0094] S4. construct a danger potential field based on the driving area map, and generate an obstacle avoidance path according to the danger potential field.

[0095] Under normal circumstances, the autonomous vehicle will try to keep the center line of the road and avoid traffic violations caused by long-term driving on the road traffic markings; when the autonomous vehicle encounters obstacles such as roadblocks and vehicles ahead, it can perform smooth lane changes. Dangerous potential field refers to the use of artificial potential field method to construct the repulsive potential field of objects around the vehicle to meet the vehicle driving specifications.

[0096] Specifically, the expression of the dangerous potential field is as follows:

[0097] U total =U road +U block +U obs

[0098]

[0099] Among them, U total represents the total repulsive potential field, U road represents the road potential field, U block represents the potential field of road obstacles, U obs represents the potential field of the road obstacle vehicle, F road represents the road repulsion, k road represents the road hazard potential field gain coefficient, r c Indicates the distance between the vehicle and the traffic marking, l w Indicates lane width, F block represents the repulsion force of road obstacles, k block Represents the gain coefficient of the roadblock hazard potential field, s block Represents the roadblock type parameter, r b Indicates the distance between the vehicle and the roadblock. represents the range of action of the roadblock potential field, F obs represents the repulsion force of the obstacle vehicle, l v represents the distance between the controlled vehicle and the roadblock, S represents the area occupied by the autonomous driving vehicle, and k v represents the gain coefficient of the obstacle vehicle, L represents the length of the autonomous driving vehicle, r v represents the Manhattan distance between the obstacle vehicle and the controlled vehicle, W represents the width of the autonomous driving vehicle, Indicates the safe distance between vehicles.

[0100] By constructing a hazard potential field, not only can we effectively avoid collisions with static obstacles and dynamic vehicles, but we can also ensure that the vehicle always stays within the lane and abides by traffic rules, thereby improving the safety and compliance of autonomous vehicles in complex traffic environments.

[0101] like Figure 5 As shown, in one embodiment of the present application, by performing a negative gradient operation on the potential field force, the corresponding potential field value is obtained, and a 3D danger potential field map is drawn based on the length, width distance and potential field value of the object. The closer the autonomous driving vehicle is to the object, the greater the repulsive potential field value is, and the greater the repulsive force is, thereby achieving obstacle avoidance. Figure 5 (a) is the 3D danger potential field diagram of the vehicle obstacle. Figure 5 (b) is the 3D hazard potential field diagram of roads and lanes. Figure 5(c) is the 3D danger potential field diagram of road obstacles.

[0102] S5. improving the gravitational potential field function of the artificial potential field in the artificial potential field method to obtain an improved artificial potential field, and using the improved artificial potential field to perform local path planning based on the global driving path and the obstacle avoidance path to generate a vehicle driving trajectory;

[0103] Specifically, the expression of the improved artificial potential field is as follows:

[0104]

[0105] Among them, U att (q) represents the improved artificial potential field, r target represents the area where the target point is located, K att represents the gravitational gain system, ρ s Represents the distance between the current position of the autonomous vehicle and the destination.

[0106] It can be understood that the artificial potential field is a virtual standpoint created using the artificial potential field method, and the artificial potential field function is used to define the potential energy value of each point in the space. The artificial potential field function is used to describe the artificial potential field.

[0107] By improving the traditional artificial potential field method, an improved artificial potential field method is obtained, which enables the vehicle to approach the target point more smoothly. At the same time, it also improves the adaptability of the algorithm in dynamic environments, enables autonomous driving vehicles to respond to emergencies more flexibly, and improves the overall performance and stability of the system.

[0108] S6. Steering control of the autonomous driving vehicle is performed through the vehicle dynamics model, and the vehicle drives according to the vehicle's driving trajectory and executes obstacle avoidance strategies.

[0109] The obstacle avoidance strategy specifically includes:

[0110] Step 1: Determine whether the autonomous driving vehicle enters an obstacle potential field; the obstacle potential field includes a vehicle obstacle potential field and a road obstacle potential field;

[0111] If so, the surrounding potential field conditions are judged, the autonomous driving vehicle is controlled to change lanes, and the speed is gradually reduced;

[0112] If not, proceed to the next step;

[0113] Step 2: Determine whether the speed of the autonomous driving vehicle is the initial speed:

[0114] If so, the autonomous driving vehicle is controlled to travel at a constant speed along the center line of the lane according to the vehicle's driving trajectory;

[0115] If not, the autonomous driving vehicle is controlled to gradually accelerate along the center line of the lane and return to the initial speed according to the vehicle's driving trajectory;

[0116] Step 3: Determine whether the autonomous driving vehicle has entered the target area and whether the driving time of the autonomous driving vehicle exceeds the planned time based on the current position;

[0117] If the autonomous vehicle enters the target area and the driving time exceeds the planned time, an error signal is generated and output;

[0118] If the autonomous driving vehicle enters the target area and the driving time does not exceed the planned time, the autonomous driving vehicle repeats steps 1 and 2 until the autonomous driving vehicle completes the obstacle avoidance path.

[0119] If the autonomous vehicle does not enter the target area and the driving time exceeds the planned time, an error signal is generated and output;

[0120] If the autonomous driving vehicle does not enter the target area and the driving time does not exceed the planned time, return to step 1 until the autonomous driving vehicle completes the obstacle avoidance path.

[0121] By judging in real time whether the vehicle has entered the obstacle potential field, combined with speed adjustment and lane changing operations, the obstacle avoidance strategy can achieve a more intelligent and smooth obstacle avoidance process. At the same time, by setting time limits and error reporting mechanisms, it can also effectively prevent the system from falling into an infinite loop or being unable to reach the target for a long time, greatly improving the reliability and practicality of the autonomous driving system.

[0122] like Figure 6 As shown, in one embodiment of the present application, local target information is determined based on global path planning of the A* algorithm;

[0123] Based on the local path planning of the improved artificial potential field, it is determined whether the local target point has been traversed:

[0124] If so, the autonomous vehicle reaches the target location;

[0125] If not, continue to use the improved artificial potential field for local path planning until the autonomous vehicle reaches the target position.

[0126] In one embodiment of the present application, the vehicle is always in the dangerous potential field range of the road surface, and is affected by the potential field forces of the curb and lane, so as to maintain the vehicle lane driving behavior and avoid collision with the curb during dynamic obstacle avoidance;

[0127] The lane hazard potential field is divided into the upper lane marking and the lower lane marking, which respectively give the controlled vehicle potential field force. When the vehicle deviates to one lane, the potential field force of the corresponding lane increases, and the potential field force of the other lane on the opposite side decreases, causing the vehicle to return to the center line of the lane.

[0128] In one embodiment of the present application, the vehicle obstacle potential field is rectangular, and when the distance between the autonomous driving vehicle and one side of the obstacle vehicle is less than the minimum safety distance, the vehicle enters the vehicle obstacle danger potential field;

[0129] The road obstacle potential field is circular. When the current autonomous driving vehicle is less than the maximum radius of the circular road obstacle, it enters the obstacle danger potential field.

[0130] The potential field change gradient of road obstacles varies depending on their type. Road obstacles with high risk factors, such as potholes and pedestrians, will have a larger potential field change gradient to increase the safety of autonomous vehicles.

[0131] Furthermore, in step S6, steering control is performed on the autonomous driving vehicle, specifically including:

[0132] Use rear-wheel drive to give the vehicle forward speed, driving the autonomous vehicle to move; at this time, the state of the rear-mounted autonomous vehicle is [v rx , v ry The formula for ] is as follows:

[0133] [v rx , v ry ]=[vcosθ,vsinθ];

[0134] Among them, v rx Represents the cosine component of the rear wheel speed of the autonomous vehicle, v ry represents the sinusoidal component of the rear wheel speed of the autonomous vehicle;

[0135] The front wheel state of the autonomous vehicle is calculated based on the current vehicle angle combined with the steering angle. The calculation formula is:

[0136]

[0137] Where θ represents the turning angle of the autonomous vehicle, represents the front wheel steering angle of the autonomous vehicle, v fx Represents the cosine component of the front wheel speed of the autonomous vehicle, v fy represents the sinusoidal component of the front wheel speed of the autonomous vehicle, and v represents the speed of the rear wheel drive of the autonomous vehicle.

[0138] It is understandable that if the front wheel steering angle of the autonomous vehicle The controlled vehicle will move around a circle with a radius of r by changing the front wheel steering angle of the autonomous vehicle. Simulate the driver's steering behavior to achieve vehicle movement and direction change.

[0139] This application achieves efficient path planning and obstacle avoidance control by improving the artificial potential field and A* algorithm, which not only ensures the safety and compliance of autonomous driving vehicles, but also enables flexible path adjustment in complex dynamic environments, significantly improving the practicality and reliability of the autonomous driving system.

[0140] like Figure 7 As shown, the present invention provides an obstacle avoidance control system for an autonomous driving vehicle that complies with road driving regulations, and adopts the obstacle avoidance control method for an autonomous driving vehicle as described above, including:

[0141] A model building module, configured to establish a vehicle dynamics model according to the autonomous driving vehicle, calibrate the autonomous driving vehicle according to the vehicle dynamics model, and obtain a current position and a current speed of the autonomous driving vehicle;

[0142] A map construction module configured to obtain environmental information of the autonomous driving vehicle and construct a driving area map based on the environmental information;

[0143] A global path planning module is configured to detect and search global path points based on a driving area map using an A* algorithm to generate a global driving path;

[0144] A potential field environment building module, which is configured to build a dangerous potential field based on a driving area map and generate an obstacle avoidance path according to the dangerous potential field;

[0145] A local path planning module is configured to improve the gravitational potential field function of the artificial potential field in the artificial potential field method to obtain an improved artificial potential field, and use the improved artificial potential field to perform local path planning based on the global driving path and the obstacle avoidance path to generate a vehicle driving trajectory;

[0146] The road driving module is configured to control the steering of the autonomous vehicle through the vehicle dynamics model, drive according to the vehicle's driving trajectory and execute obstacle avoidance strategies.

[0147] The present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions enable the computer to implement the automatic driving vehicle obstacle avoidance control method as described above.

[0148] The present invention provides an electronic device, comprising at least one processor, a memory, a communication interface and a bus; wherein the processor, the memory and the communication interface communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the obstacle avoidance control method for an autonomous driving vehicle as described above.

[0149] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An obstacle avoidance control method for an autonomous driving vehicle that complies with road driving regulations, It is characterized in that The following steps are involved: S1. establishing a vehicle dynamics model according to the autonomous driving vehicle, calibrating the autonomous driving vehicle according to the vehicle dynamics model, and obtaining a current position and a current speed of the autonomous driving vehicle; S2, obtaining environmental information of the autonomous driving vehicle and constructing a driving area map based on the environmental information; S3, based on the driving area map, use the A* algorithm to detect and search for global path points and generate a global driving path; S4, constructing a danger potential field based on the driving area map, and generating an obstacle avoidance path according to the danger potential field; S5. improving the gravitational potential field function of the artificial potential field in the artificial potential field method to obtain an improved artificial potential field, and using the improved artificial potential field to perform local path planning based on the global driving path and the obstacle avoidance path to generate a vehicle driving trajectory; S6. Steering control of the autonomous driving vehicle is performed through the vehicle dynamics model, and the vehicle drives according to the vehicle's driving trajectory and executes obstacle avoidance strategies.

2. The obstacle avoidance control method for an autonomous driving vehicle that complies with road driving regulations as claimed in claim 1, It is characterized in that The obstacle avoidance strategy specifically includes: Step 1: Determine whether the autonomous driving vehicle enters the obstacle potential field: If so, the surrounding potential field conditions are judged, the autonomous driving vehicle is controlled to change lanes, and the speed is gradually reduced; If not, proceed to the next step; Step 2: Determine whether the speed of the autonomous driving vehicle is the initial speed: If so, the autonomous driving vehicle is controlled to travel at a constant speed along the center line of the lane according to the vehicle's driving trajectory; If not, the autonomous driving vehicle is controlled to gradually accelerate along the center line of the lane and return to the initial speed according to the vehicle's driving trajectory; Step 3: Determine whether the autonomous driving vehicle has entered the target area and whether the driving time of the autonomous driving vehicle exceeds the planned time based on the current position; If the autonomous vehicle enters the target area and the driving time exceeds the planned time, an error signal is generated and output; If the autonomous driving vehicle enters the target area and the driving time does not exceed the planned time, the autonomous driving vehicle repeats steps 1 and 2 until the autonomous driving vehicle completes the obstacle avoidance path. If the autonomous vehicle does not enter the target area and the driving time exceeds the planned time, an error signal is generated and output; If the autonomous driving vehicle does not enter the target area and the driving time does not exceed the planned time, return to step 1 until the autonomous driving vehicle completes the obstacle avoidance path.

3. The obstacle avoidance control method for an autonomous driving vehicle that complies with road driving regulations as claimed in claim 2, It is characterized in that The obstacle potential field includes a vehicle obstacle potential field and a road obstacle potential field.

4. The method for controlling an obstacle avoidance of an autonomous driving vehicle that complies with road driving regulations as claimed in claim 1, It is characterized in that The expression of the improved artificial potential field is as follows: Among them, U att (q) represents the improved artificial potential field, r target represents the area where the target point is located, K att represents the gravitational gain system, ρ s Represents the distance between the current position of the autonomous vehicle and the destination.

5. The obstacle avoidance control method for an autonomous driving vehicle that complies with road driving regulations as claimed in claim 4, It is characterized in that The expression of the dangerous potential field is as follows: IN total =U road +U block +U obs ; Among them, U total represents the total repulsive potential field, U road represents the road potential field, U block represents the potential field of road obstacles, U obs represents the potential field of the road obstacle vehicle, F road represents the road repulsion, k road represents the road hazard potential field gain coefficient, r c Indicates the distance between the vehicle and the traffic marking, l w Indicates lane width, F block represents the repulsion force of road obstacles, k block Represents the gain coefficient of the roadblock hazard potential field, s block Represents the roadblock type parameter, r b Indicates the distance between the vehicle and the roadblock. represents the range of action of the roadblock potential field, F obs represents the repulsion force of the obstacle vehicle, l v represents the distance between the controlled vehicle and the roadblock, S represents the area occupied by the autonomous driving vehicle, and k v represents the gain coefficient of the obstacle vehicle, L represents the length of the autonomous driving vehicle, r v represents the Manhattan distance between the obstacle vehicle and the controlled vehicle, W represents the width of the autonomous driving vehicle, Indicates the safe distance between vehicles.

6. The method for controlling obstacle avoidance of an autonomous driving vehicle that complies with road driving regulations as claimed in claim 5, It is characterized in that In step S6, steering control is performed on the autonomous driving vehicle, specifically including: Use rear-wheel drive to give the vehicle forward speed, driving the autonomous vehicle to move its position; The front wheel state of the autonomous vehicle is calculated based on the current vehicle angle combined with the steering angle. The calculation formula is: Where θ represents the turning angle of the autonomous vehicle, represents the front wheel steering angle of the autonomous vehicle, v fx Represents the cosine component of the front wheel speed of the autonomous vehicle, v fy represents the sinusoidal component of the front wheel speed of the autonomous vehicle, and v represents the speed of the rear wheel drive of the autonomous vehicle.

7. The obstacle avoidance control method for an autonomous driving vehicle that complies with road driving regulations as claimed in claim 1, It is characterized in that Step S2 specifically includes: Obtain software map information and build a simple map model; A database is established based on the information points around the autonomous driving vehicle and the connectivity between the information points, and the simplified map model is improved to obtain a driving area map; the information points around the autonomous driving vehicle include image data dynamic points, static points and reference points.

8. An obstacle avoidance control system for an autonomous driving vehicle that complies with road driving regulations, It is characterized in that The method for controlling obstacle avoidance of an autonomous driving vehicle according to any one of claims 1 to 7 comprises: A model building module, configured to establish a vehicle dynamics model according to the autonomous driving vehicle, calibrate the autonomous driving vehicle according to the vehicle dynamics model, and obtain a current position and a current speed of the autonomous driving vehicle; A map construction module configured to obtain environmental information of the autonomous driving vehicle and construct a driving area map based on the environmental information; A global path planning module is configured to detect and search global path points based on a driving area map using an A* algorithm to generate a global driving path; A potential field environment building module, which is configured to build a dangerous potential field based on a driving area map and generate an obstacle avoidance path according to the dangerous potential field; A local path planning module is configured to improve the gravitational potential field function of the artificial potential field in the artificial potential field method to obtain an improved artificial potential field, and use the improved artificial potential field to perform local path planning based on the global driving path and the obstacle avoidance path to generate a vehicle driving trajectory; The road driving module is configured to control the steering of the autonomous vehicle through the vehicle dynamics model, drive according to the vehicle's driving trajectory and execute obstacle avoidance strategies.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to implement the automatic driving vehicle obstacle avoidance control method as described in any one of claims 1-7.

10. An electronic device, It is characterized in that Includes at least one processor, a memory, a communication interface and a bus; wherein, The processor, memory, and communication interface communicate with each other via the bus; The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the obstacle avoidance control method for an autonomous driving vehicle as described in any one of claims 1-7.

Images