Digital traffic path planning method for safe driving
By optimizing the inflection points in the path and matching and comparison of the obstacle curve, the problem of traditional path planning in complex traffic environments is solved, the stability and efficiency of vehicle driving are improved, and the driving is significantly improved. Safety and comfort.
Patent Information
- Application Number
- CN202410895264.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-05
- Publication Date
- 2024-11-19
AI Technical Summary
Traditional path planning methods are difficult to make accurate and timely decisions in complex and changeable traffic environments, especially in turning scenarios, which easily form discontinuous paths, resulting in vehicle out of control or reduced driving efficiency.
By optimizing the inflection points in the path, using the matching and comparison of the arc inflection point route and the obstacle curve, a smooth vehicle driving path is generated to ensure that the vehicle is more stable during driving, reducing speed change and lane change operations, and improving driving Efficiency and safety.
On the premise of ensuring safety, a highly flexible adjustment curve is generated, which can adapt to complex traffic environments in real time, significantly improve the safety and smoothness of driving, avoid unnecessary sharp turns and sudden lane changes, and improve driving Comfort and safety.
Smart Images

Figure CN118980384A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of path planning, and in particular to a digital traffic path planning method for safe driving. Background Art
[0002] The traffic environment faced by unmanned vehicles is extremely complex and changeable. Various factors such as vehicles, pedestrians, traffic signals, and road construction on the road can have a significant impact on the driving path. As the basis of path planning, high-precision maps have high acquisition and maintenance costs, high technical difficulty, and it is difficult to reflect the dynamic changes of the traffic environment in real time. Traditional path planning methods often seem to be powerless in the face of such complex and changeable traffic environments, and it is difficult to make accurate and timely decisions. More importantly, the existing path planning methods have obvious shortcomings in dealing with complex scenes such as turns. When turning left or right at an intersection, due to the large turning angle, the planned path often forms an obvious inflection point at the turn. If the unmanned vehicle strictly follows these coordinate points, the discontinuity of the path will cause the vehicle to lose control, thereby causing a traffic accident. In addition, in order to pass these inflection points, the vehicle needs to slow down, change lanes, and other operations, and the time cost of passing the intersection will also increase accordingly, further reducing driving efficiency. Summary of the invention
[0003] The present application provides a digital traffic path planning method for safe driving. By optimizing the arc shape of the turning points in the path, the vehicle can be more stable during driving to improve the safety of vehicle driving. At the same time, the frequent speed changes and lane changes of the vehicle are reduced, which can improve the efficiency of vehicle driving.
[0004] The present application provides a digital traffic path planning method for safe driving, comprising:
[0005] S101, locating the real-time positions of the target vehicle and obstacles in the path, calculating the vertical distance from the obstacles to the sidelines on both sides of the road, and drawing a circle with the vertical distance as the diameter, which is the obstacle avoidance area;
[0006] The distance from the preset obstacle to the two side lines is the first priority, and the starting position of the target obstacle avoidance curve is the second priority;
[0007] According to the two priority principles, several obstacle avoidance areas are compared. The optimal obstacle avoidance area is the area with the larger diameter. If the diameters are similar, the area closer to the target obstacle curve is the optimal obstacle avoidance area.
[0008] S102, the length of the first length range is smaller than the second length range, the first length range and the second length range are both one path segment, by acquiring the real-time positions of vehicles and pedestrians within the first length range, establishing obstacle models according to the real-time positions, selecting sampling points within the first length range according to the obstacle models, and forming a plurality of curves to be adjusted between the sampling points and the target vehicle;
[0009] S103, connecting the position of the end point of the curve to be adjusted with the path points in the obstacle bypassing area, wherein the connected curves are a plurality of obstacle bypassing curves covering a second length range, wherein the path points are evenly distributed in the obstacle bypassing area, and the selection of the path points should bypass the obstacle model;
[0010] S104, matching and comparing the smoothness and curvature of the plurality of curves to be adjusted with the parameters of the vehicle, extracting the adjustment curve, and selecting a target obstacle avoidance curve from the plurality of obstacle avoidance curves through a path planning algorithm according to the distance to the obstacle and the smoothness;
[0011] Connect the adjustment curve and the target obstacle avoidance curve to generate the final vehicle driving path;
[0012] S105, optimizing the inflection point between the adjustment curve and the target obstacle avoidance curve to obtain an arc-shaped inflection point route.
[0013] Preferably, the inflection point optimization method comprises:
[0014] S201, determining the position point A when the target vehicle starts to turn, the turning point B during the driving process, and the position point C when the turning ends, and at the same time, confirming the driving direction of the target vehicle at the positions of points A, B, and C, wherein the distance from point A to point B is equal to the distance from point B to point C;
[0015] S202, constructing an arc trajectory, connecting line segment AC, taking the midpoint O of line segment AC, and taking AO as the radius to generate arc AC;
[0016] S203, select a number of points on the arc AC at equal distances as new trajectory points, and replace point B with the new trajectory points to generate an optimized trajectory arc AC.
[0017] Preferably, the steps of matching and comparing the smoothness and curvature of the curve to be adjusted with the parameters of the vehicle to extract the adjustment curve are as follows:
[0018] A1. Collect the wheelbase, maximum speed and stability parameters of the target vehicle;
[0019] A2. Calculate the curvature change rate of each curve, and evaluate the smoothness of the curve to be adjusted based on the change rate; calculate the curvature of the curve to be adjusted to evaluate the curvature;
[0020] A3. The minimum curvature of the curve to be adjusted is greater than the minimum turning radius of the target vehicle, so the adjustment curve is extracted.
[0021] Preferably, the step of selecting a target obstacle avoidance curve from a plurality of obstacle avoidance curves by a path planning algorithm according to the distance to the obstacle and the smoothness is as follows:
[0022] C1. Determine the size and location of obstacles in the environment;
[0023] C2. Based on the location information of obstacles, the path planning algorithm generates a series of obstacle avoidance curves;
[0024] C3, the path planning algorithm calculates the minimum distance between each obstacle-avoiding curve and the obstacle by calculating the rate of change of the curve curvature and the rate of change of acceleration;
[0025] C4. Based on the calculated minimum distance, curvature change rate and acceleration change rate, the path planning algorithm conducts a comprehensive evaluation and selects the target obstacle avoidance curve.
[0026] Preferably, the selection of the sampling points is based on uniformity, representativeness and safety, wherein uniformity means that the sampling points are evenly distributed within the first length range, representativeness means that the sampling points can reflect the characteristics and changes of the first length range, and safety means that the sampling points should be selected without source flow obstacles.
[0027] Preferably, when the distance between two adjacent trajectory points on the optimized trajectory is greater than a distance threshold x, interpolation is performed between the two trajectory points.
[0028] Preferably, the interpolation includes linear interpolation or curve interpolation, and the number of points y to be interpolated by the linear interpolation is preset, then y=(d / x-1), and the distance between adjacent points after interpolation is d / (y+1), where d is the distance between two adjacent trajectory points.
[0029] Preferably, the interpolation steps are as follows:
[0030] B1. Distance calculation: calculate the distance between two adjacent trajectory points;
[0031] B2, distance judgment and interpolation requirements, compare the distance between adjacent trajectory points with the distance threshold x;
[0032] B3, linear interpolation, adding new trajectory points evenly between two trajectory points;
[0033] B4, interpolation implementation, insert y points between the two points that need to be interpolated;
[0034] B5. Curve interpolation: Curve interpolation defines the shape of the curve through nodes and line segments;
[0035] B6. Track update: replace the original track points with new track points.
[0036] Preferably, the first length range is smaller than the second length range, and the end point of the first length range is the starting point of the second length range.
[0037] Preferably, the vertical distances from the real-time obstacle to the sidelines on both sides of the road are calculated, and the road is divided into at least two obstacle bypassing areas according to the distance information, and the two areas are located on both sides of the obstacle respectively.
[0038] One or more technical solutions provided in this application have at least the following technical effects or advantages: Under the premise of ensuring safety, it is possible to adjust the driving environment in a small range and generate an adjustment curve. This adjustment curve has high flexibility and can be optimized in real time according to the complexity and variability of real-time traffic. Subsequently, based on this large-scale environmental information and the known real-time position of obstacles, a target obstacle avoidance curve is further generated.
[0039] The adjustment curve and the target obstacle avoidance curve together constitute a complete driving path. This design enables the entire driving process to adapt to changing environments more flexibly, thereby significantly improving driving safety.
[0040] To further improve driving smoothness and safety, the system will also fine-tune the turning point between the adjustment curve and the target obstacle avoidance curve. This step is designed to ensure that the vehicle can achieve smoother and more coherent steering during driving, thereby avoiding unnecessary sharp turns or sudden lane changes, greatly improving driving comfort and safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 A schematic diagram of a flow chart of a digital traffic path planning method for safe driving according to the present invention;
[0042] Figure 2 A schematic diagram of a flow chart of an inflection point optimization method according to an embodiment of the present invention;
[0043] Figure 3 A schematic diagram of a process for determining an adjustment curve according to an embodiment of the present invention;
[0044] Figure 4 FIG. 4 is a schematic diagram of an interpolation process according to an embodiment of the present invention. DETAILED DESCRIPTION
[0045] To facilitate the understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.
[0046] It should be noted that the terms “vertical”, “horizontal”, “up”, “down”, “left”, “right” and similar expressions used in this document are only for illustrative purposes and do not represent the only implementation method.
[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items.
[0048] Embodiment 1: Figure 1 1 is a flow chart of a method for digital traffic path planning for safe driving according to an embodiment of the present invention, comprising the following steps:
[0049] S101, locate the real-time position of the target vehicle and the obstacle in the path, obtain the accurate position information of the target vehicle and the dynamic obstacle in real time according to the satellite positioning system (the position information usually includes data such as longitude and latitude coordinates, speed and direction, etc.), analyze the relative position relationship between the real-time obstacle and the sidelines on both sides of the road through data processing of the road map, calculate the vertical distance between the real-time obstacle and the sidelines on both sides of the road, draw a circle with the vertical distance as the diameter, and the circle is the obstacle bypassing area. According to the distance information, the road is divided into at least two obstacle bypassing areas, and the two areas are respectively located on both sides of the obstacle;
[0050] The distance from the obstacle to the two sidelines is preset as the first priority, and the starting position of the target obstacle bypassing curve is the second priority. That is to say, if the distance from the obstacle to one sideline is significantly greater than the distance to the other sideline, the side with the larger distance will be preferentially selected as the obstacle bypassing area. This is because the side with the larger distance usually means a larger bypassing space, thereby reducing the risk of collision with other objects on the road. If the distance from the obstacle to the two sidelines is equal (or almost equal), the second priority principle is selected, that is, the starting position of the target obstacle bypassing curve. In this case, the obstacle bypassing area closer to the starting position of the target obstacle bypassing curve is selected as the optimal obstacle bypassing area. Such an area can ensure that the target vehicle maintains a smaller heading change during the bypassing process, thereby improving driving stability and safety.
[0051] Finally, once the optimal obstacle avoidance area is determined, the target vehicle will follow the guidance of the area to avoid obstacles on the road. At the same time, the satellite positioning system needs to continuously monitor the position changes of the target vehicle and obstacles, and update the selection of the obstacle avoidance area in real time as needed.
[0052] S102, the length of the first length range is smaller than the second length range, the first length range and the second length range are both one path segment, by acquiring the real-time positions of vehicles and pedestrians within the first length range, establishing obstacle models according to the real-time positions, selecting sampling points within the first length range according to the obstacle models, and forming a plurality of curves to be adjusted between the sampling points and the target vehicle;
[0053] The selection of sampling points should be based on uniformity, representativeness and safety. Uniformity means that the sampling points are evenly distributed within the first length range, representativeness means that the sampling points can reflect the characteristics and changes of the first length range, and safety means that the sampling points should be far away from obstacles to ensure that there will be no collision or interference during the sampling process. These sampling points are longitudinal and lateral points within the lane range, and their positions are selected based on the real-time positions of vehicles and pedestrians. Each sampling point is a potential key point on the path, and they form multiple driving paths with the position of the target vehicle. The selection of sampling points is not random, but follows certain principles and strategies. According to the distribution, speed, direction and other factors of vehicles and pedestrians, as well as the structure and conditions of the road (such as the number of lanes, lane width, traffic signs, etc.), appropriate sampling points are selected to ensure that the path we generate not only conforms to the actual traffic conditions, but also meets the driving needs of the target vehicle.
[0054] S103, connecting the position of the end point of the curve to be adjusted with the path points in the obstacle bypassing area, wherein the connected curves are a plurality of obstacle bypassing curves covering a second length range, wherein the path points are evenly distributed in the obstacle bypassing area, and the selection of the path points should bypass the obstacle model;
[0055] It should be understood that the first length range is a shorter path segment, and its length and position can be adjusted according to actual conditions, which is usually to ensure the smoothness of the path and meet specific requirements. For example, in a driving system, it is necessary to ensure that the vehicle has a predefined deceleration area before approaching an obstacle. This area is defined as the first length range. Next, the second length range is a longer path segment that starts at the end of the first length range and continues to extend to the farthest point required to bypass the obstacle. The size of this range depends on the size and shape of the obstacle and the requirements of the path planning algorithm. For example, if the obstacle is a large building, then the second length range needs to be long enough to ensure that the vehicle can safely bypass the building.
[0056] Importantly, the end point of the first length range is exactly the starting point of the second length range. This design allows for more flexible planning of the obstacle avoidance curve, because the starting point of the second length range is known (i.e., the end point of the first length range), and we only need to determine the remaining obstacle avoidance curve within the second length range. In this way, we do not have to worry about the position of the entire adjustment curve being limited, thereby increasing the flexibility of obstacle avoidance curve selection.
[0057] Specifically, after a first length range is determined, an obstacle avoidance curve within a second length range is planned based on the location and size of the obstacle. Various path planning algorithms, such as the A* algorithm, the Dijkstra algorithm, or optimization-based methods, are used to find the best target obstacle avoidance curve. These algorithms take into account factors such as path length, smoothness, safety, etc. to ensure that the generated obstacle avoidance curve meets both obstacle avoidance requirements and good driving performance.
[0058] In summary, by defining the first length range and the second length range and ensuring that the end point of the first length range is the starting point of the second length range, the obstacle avoidance curve can be planned more flexibly, thereby meeting various requirements and constraints in path planning.
[0059] S104, matching and comparing the smoothness and curvature of the plurality of curves to be adjusted with the parameters of the vehicle, extracting the adjustment curve, and selecting a target obstacle avoidance curve from the plurality of obstacle avoidance curves through a path planning algorithm according to the distance to the obstacle and the smoothness;
[0060] like Figure 3 As shown, the smoothness and curvature of the curve to be adjusted are matched and compared with the parameters of the vehicle to extract the adjustment curve. The steps are as follows:
[0061] A1. Collect the wheelbase, maximum speed and stability parameters of the target vehicle. The wheelbase of the vehicle determines the minimum turning radius of the vehicle, and the roll angle and centrifugal force threshold of the vehicle are used to evaluate the stability of the vehicle on the curve.
[0062] A2. Calculate the curvature change rate of each curve, and evaluate the smoothness of the curve to be adjusted based on the change rate. A curve with high smoothness means a small change in curvature, and the vehicle is subject to less impact and vibration when driving; calculate the curvature of the curve to be adjusted to evaluate the curvature. The larger the curvature radius, the smaller the curvature, and the smaller the centrifugal force the vehicle is subject to when turning. At the same time, the length and continuity of the curve also need to be considered to ensure that the vehicle can smoothly enter and exit the curve to be adjusted;
[0063] A3. The minimum curvature of the curve to be adjusted is greater than the minimum turning radius of the target vehicle to ensure that the vehicle can pass through the curve smoothly, thereby extracting the adjustment curve.
[0064] The process of extracting the adjustment curve involves complex algorithms and calculations, using collision detection algorithms, optimal control algorithms and other technologies to evaluate the feasibility and pros and cons of each potential path. Then, the optimal path is selected as the adjustment curve for the target vehicle based on the evaluation results.
[0065] According to the distance and smoothness to the obstacle, a target obstacle avoidance curve is selected from the several obstacle avoidance curves through a path planning algorithm, and the steps are as follows:
[0066] C1. Determine the size and location of obstacles in the environment. This information can be obtained through sensors (such as lidar, cameras, etc.) and converted into a data format that can be recognized by computers after processing;
[0067] C2. Based on the location information of obstacles, the path planning algorithm generates a series of obstacle avoidance curves. These curves should ensure that the vehicle or robot can safely bypass the obstacles while maintaining a certain driving efficiency.
[0068] C3. The path planning algorithm calculates the minimum distance between each obstacle-avoiding curve and the obstacle. The larger the distance, the safer the curve. By calculating the rate of change of the curve curvature and the rate of change of acceleration, a path with high smoothness means that the vehicle or robot is subject to less impact and vibration during driving, thereby improving driving stability and comfort.
[0069] C4. Based on the calculated minimum distance, curvature change rate and acceleration change rate, the path planning algorithm conducts a comprehensive evaluation and selects the target obstacle avoidance curve.
[0070] In this process, the dynamic data of the vehicle (such as acceleration, steering angle, etc.) and real-time traffic information (such as traffic signals, road conditions, etc.) are combined to further optimize the adjustment curve. This ensures that the target vehicle can maintain a safe and efficient driving state in a complex and changing driving environment, and connects the adjustment curve with the target obstacle avoidance curve to generate the final vehicle driving path.
[0071] S105, optimizing the inflection point between the adjustment curve and the target obstacle avoidance curve to obtain an arc-shaped inflection point route.
[0072] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:
[0073] The end point of the adjustment curve is connected to the starting point of the target obstacle avoidance curve, so that during the path planning process, the path can be adjusted in real time according to factors such as traffic conditions and weather conditions. At the same time, there is more flexible choice space when planning the path, providing better path planning for the target vehicle and making the vehicle more efficient during driving.
[0074] Example 2: In the field of path planning, especially when facing an intersection with a large turning angle, the planned path will form an obvious inflection point at the turn. This discontinuous path is a huge challenge for driving a vehicle. When driving a vehicle along these coordinate points with inflection points, the vehicle's driving trajectory will become unstable due to the instantaneous change in direction, and may even cause the vehicle to lose control.
[0075] The embodiment of the present application needs to convert the inflection point into a smooth arc on the basis of the above embodiment, and optimize the inflection point to a certain extent.
[0076] In some embodiments, Figure 2 As shown, the inflection point optimization method includes:
[0077] S201, determine the key position and direction, determine the position point A when the target vehicle starts to turn, after determining point A, it is necessary to determine the direction of the front of the vehicle according to the position of the adjustment curve, determine the turning point B during driving and the position point C at the end of turning, where the distance from point A to point B is equal to the distance from point B to point C.
[0078] S202, constructing an arc trajectory, connecting point A and point C to form a line segment AC, finding the midpoint O of the line segment AC, which needs to be determined based on the steering ability and driving speed of the target vehicle, taking AO as the radius and point O as the center, and generating arc AC, which can ensure that the vehicle can travel safely and smoothly along the arc;
[0079] S203, refine the trajectory and generate an optimized trajectory. On the arc AC, we need to select several points at equal distances as new trajectory points. These new trajectory points will replace the original point B and be used to generate the optimized driving trajectory.
[0080] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:
[0081] By optimizing the turning points in the path, unnecessary transfers and detours of the target vehicle can be reduced, making the path more efficient. At the same time, sharp turns and frequent lane changes during driving can be reduced, improving driving comfort and safety, and enabling the target vehicle to better adapt to complex and changing traffic environments.
[0082] Embodiment 3: Through optimization, the turning points in the original path are transformed into smooth arcs, the distance between two adjacent points is calculated, and a maximum allowable distance threshold x is set according to the driving characteristics and safety requirements of the vehicle. When the distance between two adjacent trajectory points on the optimized trajectory is greater than the distance threshold x, interpolation is performed between the two trajectory points. The inserted trajectory points have a smooth transition to reduce jumps and discontinuities.
[0083] like Figure 4 As shown, the interpolation steps are as follows:
[0084] B1. Distance calculation. Traverse the optimized trajectory points and calculate the distance between two adjacent trajectory points. Assume that the adjacent trajectory points are P1 and P2, and the distance between them is recorded as d.
[0085] B2. Distance judgment and interpolation requirements. If d is greater than the set maximum allowable distance threshold x, it means that the distance between the two points is too large and interpolation processing is required. In this example, when x is 3 meters, if d is greater than 3 meters, a new trajectory point needs to be inserted between P1 and P2.
[0086] B3. Linear interpolation. Linear interpolation is to add new points evenly between two points. Assuming that the number of points to be inserted is y, the calculation formula of y is y=(d / x-1). In this example, when d is 14 meters and x is 3 meters, y=(14 / 3-1)=7. After interpolation, the distance between adjacent points becomes d / (y+1). In this example, after interpolation, the distance between adjacent points becomes 14 / (7+1)=1.75 meters.
[0087] B4. Interpolation is implemented. Y new trajectory points are inserted between P1 and P2 according to a linear relationship. These new trajectory points will be evenly distributed between P1 and P2, making the trajectory smoother.
[0088] B5. Curve interpolation (such as Bezier curve). If a smoother transition effect is required, consider using Bezier curve or other curve interpolation methods. Bezier curve can define the shape of the curve through control points (i.e. nodes) and line segments (i.e. control lines). Between P1 and P2, control points and control lines are set as required to generate a smooth Bezier curve. New trajectory points are evenly selected on the Bezier curve to ensure that the newly generated trajectory points can smoothly connect the original two points P1 and P2.
[0089] B6. Trajectory update: add the new trajectory points generated after interpolation to the optimized trajectory, replacing or supplementing the original trajectory points. The updated trajectory will have higher smoothness and continuity, and be more suitable for the vehicle's driving needs.
[0090] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:
[0091] Through the interpolation method, after the turning points of the original path are converted into arcs, the smoothness and continuity of the trajectory can be optimized through further interpolation processing, ensuring that the vehicle can travel safely and smoothly along the optimized trajectory.
[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A digital traffic path planning method for safe driving, It is characterized in that include: S101, locating the real-time positions of the target vehicle and obstacles in the path, calculating the vertical distance from the obstacles to the sidelines on both sides of the road, and drawing a circle with the vertical distance as the diameter, which is the obstacle avoidance area; The distance from the preset obstacle to the two side lines is the first priority, and the starting position of the target obstacle avoidance curve is the second priority; According to the two priority principles, several obstacle avoidance areas are compared. The optimal obstacle avoidance area is the area with the larger diameter. If the diameters are similar, the area closer to the target obstacle curve is the optimal obstacle avoidance area. S102, the length of the first length range is smaller than the second length range, the first length range and the second length range are both one path segment, by acquiring the real-time positions of vehicles and pedestrians within the first length range, establishing obstacle models according to the real-time positions, selecting sampling points within the first length range according to the obstacle models, and forming a plurality of curves to be adjusted between the sampling points and the target vehicle; S103, connecting the position of the end point of the curve to be adjusted with the path points in the obstacle bypassing area, wherein the connected curves are a plurality of obstacle bypassing curves covering a second length range, wherein the path points are evenly distributed in the obstacle bypassing area, and the selection of the path points should bypass the obstacle model; S104, matching and comparing the smoothness and curvature of the plurality of curves to be adjusted with the parameters of the vehicle, extracting the adjustment curve, and selecting a target obstacle avoidance curve from the plurality of obstacle avoidance curves through a path planning algorithm according to the distance to the obstacle and the smoothness; Connect the adjustment curve and the target obstacle avoidance curve to generate the final vehicle driving path; S105, optimizing the inflection point between the adjustment curve and the target obstacle avoidance curve to obtain an arc-shaped inflection point route.
2. A digital traffic path planning method for safe driving as claimed in claim 1, It is characterized in that The inflection point optimization method comprises: S201, determining the position point A when the target vehicle starts to turn, the turning point B during the driving process, and the position point C when the turning ends, and at the same time, confirming the driving direction of the target vehicle at the positions of points A, B, and C, wherein the distance from point A to point B is equal to the distance from point B to point C; S202, constructing an arc trajectory, connecting line segment AC, taking the midpoint O of line segment AC, and taking AO as the radius to generate arc AC; S203, select a number of points on the arc AC at equal distances as new trajectory points, and replace point B with the new trajectory points to generate an optimized trajectory arc AC.
3. A digital traffic path planning method for safe driving as claimed in claim 1, It is characterized in that The steps of matching and comparing the smoothness and curvature of the curve to be adjusted with the parameters of the vehicle to extract the adjustment curve are as follows: A1. Collect the wheelbase, maximum speed and stability parameters of the target vehicle; A2. Calculate the curvature change rate of each curve, and evaluate the smoothness of the curve to be adjusted based on the change rate; Calculate the curvature of the curve to be adjusted to evaluate the curvature; A3. The minimum curvature of the curve to be adjusted is greater than the minimum turning radius of the target vehicle, so the adjustment curve is extracted.
4. A digital traffic path planning method for safe driving as claimed in claim 1, It is characterized in that The steps of selecting a target obstacle avoidance curve from a plurality of obstacle avoidance curves according to the distance and smoothness to the obstacle are as follows: C1. Determine the size and location of obstacles in the environment; C2. Based on the location information of obstacles, the path planning algorithm generates a series of obstacle avoidance curves; C3, the path planning algorithm calculates the minimum distance between each obstacle-avoiding curve and the obstacle by calculating the rate of change of the curve curvature and the rate of change of acceleration; C4. Based on the calculated minimum distance, curvature change rate and acceleration change rate, the path planning algorithm conducts a comprehensive evaluation and selects the target obstacle avoidance curve.
5. A digital traffic path planning method for safe driving as claimed in claim 1, It is characterized in that The selection of the sampling points should be based on uniformity, representativeness and safety, wherein uniformity means that the sampling points are evenly distributed within the first length range, representativeness means that the sampling points can reflect the characteristics and changes of the first length range, and safety means that the sampling points should be selected without source flow obstacles.
6. A digital traffic path planning method for safe driving as claimed in claim 2, It is characterized in that When the distance between two adjacent trajectory points on the optimized trajectory is greater than the distance threshold x, interpolation is performed between the two trajectory points.
7. A digital traffic path planning method for safe driving as claimed in claim 6, It is characterized in that The interpolation includes linear interpolation or curve interpolation. The number of points y to be interpolated by the linear interpolation is preset, then y=(d / x-1), and the distance between adjacent points after interpolation is d / (y+1), where d is the distance between two adjacent trajectory points.
8. A digital traffic path planning method for safe driving as claimed in claim 6, It is characterized in that The steps of interpolation are as follows: B1. Distance calculation: calculate the distance between two adjacent trajectory points; B2, distance judgment and interpolation requirements, compare the distance between adjacent trajectory points with the distance threshold x; B3, linear interpolation, adding new trajectory points evenly between two trajectory points; B4, interpolation implementation, insert y points between the two points that need to be interpolated; B5. Curve interpolation: Curve interpolation defines the shape of the curve through nodes and line segments; B6. Track update: replace the original track points with new track points.
9. A digital traffic path planning method for safe driving as claimed in claim 1, It is characterized in that The first length range is smaller than the second length range, and the end point of the first length range is the starting point of the second length range.
10. A digital traffic path planning method for safe driving as claimed in claim 1, It is characterized in that The vertical distance from the real-time obstacle to the sidelines on both sides of the road is calculated, and the road is divided into at least two obstacle avoidance areas based on the distance information, and the two areas are located on both sides of the obstacle.
