A path planning method for intelligent light trucks

Abstract

A smart light truck path planning method includes: building multiple road obstacle avoidance scenarios for light trucks, obtaining the coordinates of the starting point, end point, and obstacle locations in the road obstacle avoidance scenarios; introducing a target distance evaluation function, a headway evaluation function, and a curvature evaluation function into a dynamic window algorithm to obtain a primary-improved dynamic window algorithm; dynamically adjusting the weights of the primary-improved dynamic window algorithm using a global adaptive weight value adjustment strategy to obtain a secondary-improved dynamic window algorithm; optimizing the path variance in the secondary-improved dynamic window algorithm using an improved artificial lemming optimization algorithm to obtain a tertiary-improved dynamic window algorithm; and performing path planning for the light truck based on the coordinates of the starting point, end point, and obstacle locations using the tertiary-improved dynamic window algorithm to obtain an obstacle avoidance path. The present invention can improve the smoothness of the planned trajectory and enhance path planning performance.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle technology, and in particular to a path planning method for an intelligent light truck. Background Art

[0002] Intelligent vehicle path planning is a cutting-edge technology based on perception, decision-making, planning, and control. With the development of intelligent vehicles, intelligent light trucks are also becoming increasingly common. Path planning generates an optimal path for a vehicle to smoothly reach its destination from its starting point within a given road environment. This optimal path must meet the following requirements: shortest distance, shortest time, lowest energy consumption, and effective obstacle avoidance.

[0003] Traditional path planning algorithms primarily include artificial potential field algorithms, dynamic window algorithms (DWAs), A* algorithms, and Dijkstra algorithms. The dynamic window algorithm is widely used in automotive path planning due to its wide applicability, ease of application, and strong real-time performance. However, traditional dynamic window algorithms lack smoothness in obstacle avoidance scenarios and are prone to falling into local optima in areas with dense obstacles. Furthermore, traditional dynamic window algorithms are not designed for the driving characteristics of light trucks. For light trucks, adjustments to their obstacle avoidance strategies are necessary, such as requiring longer obstacle avoidance distances and ensuring the smoothness and continuity of the planned path due to their long bodies. Summary of the Invention

[0004] In view of this, the present invention provides an intelligent light truck path planning method to solve the problems of the existing technology in obstacle avoidance scenarios, such as insufficient trajectory smoothness, easy to fall into local optimality in areas with dense obstacles, and not being designed for the driving characteristics of light trucks.

[0005] An intelligent light truck path planning method, comprising:

[0006] Step S1: construct multiple road obstacle avoidance scenarios for light trucks and obtain the coordinates of the starting point, end point, and obstacles in the road obstacle avoidance scenarios;

[0007] Step S2, introducing the target distance evaluation function, the vehicle head distance evaluation function, and the curvature evaluation function into the dynamic window algorithm to obtain an improved dynamic window algorithm;

[0008] Step S3, dynamically adjusting the weight value of the first-improved dynamic window algorithm using a global adaptive weight value adjustment strategy to obtain a second-improved dynamic window algorithm;

[0009] Step S4, using an improved artificial lemmings optimization algorithm to optimize the path variance in the quadratically improved dynamic window algorithm to obtain a tertiary improved dynamic window algorithm, wherein the improved artificial lemmings optimization algorithm is based on the artificial lemmings optimization algorithm, introduces the surrounding prey mechanism in the whale algorithm to improve the foraging model of the artificial lemmings algorithm, and introduces the exploring prey mechanism in the whale algorithm to improve the migration model of the artificial lemmings algorithm;

[0010] In step S5, based on the coordinates of the starting point, the end point and the position of the obstacle in the road obstacle avoidance scene, a three-times improved dynamic window algorithm is used to plan the path of the light truck to obtain an obstacle avoidance path.

[0011] The intelligent light truck path planning method provided by the present invention has the following beneficial effects:

[0012] (1) Based on the traditional dynamic window algorithm, the present invention improves the evaluation function by adding a target distance evaluation function, a headway distance evaluation function, and a curvature evaluation function. Furthermore, a global adaptive weight value adjustment strategy is used to dynamically adjust the weight values ​​of the improved dynamic window algorithm. This effectively solves the problems of insufficient trajectory smoothness in obstacle scenes and the tendency to fall into local optimality in areas with dense obstacles, and improves obstacle avoidance efficiency. Furthermore, when designing the target distance evaluation function, the headway distance evaluation function, and the curvature evaluation function, adjustments can be made for light trucks, setting a longer obstacle avoidance distance. This allows for smoothness and continuity in the planned path, taking into account the long body of light trucks.

[0013] (2) In order to adapt to multiple complex obstacle scenarios and improve the global exploration and local optimization capabilities of the dynamic window algorithm, the present invention adopts an improved artificial lemming optimization algorithm to optimize the path variance in the quadratically improved dynamic window algorithm, which can improve the safety and reliability of path planning. The present invention introduces the prey encirclement mechanism and prey exploration mechanism of the whale algorithm to balance global exploration and local development, while improving rapid response and real-time performance, thereby effectively avoiding dynamic obstacles and significantly improving the path planning performance of the dynamic window algorithm in dynamic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart of a method for intelligent light truck path planning provided by an embodiment of the present invention;

[0015] Figure 2 A comparison chart of the obstacle avoidance effects of the present invention and the traditional DWA algorithm in scenario 1;

[0016] Figure 3 This is a comparison chart of the obstacle avoidance effects of the present invention and the traditional DWA algorithm in scenario 2. DETAILED DESCRIPTION

[0017] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0018] See also Figure 1 , an embodiment of the present invention provides an intelligent light truck path planning method, comprising steps S1 to S5:

[0019] Step S1: construct multiple road obstacle avoidance scenarios for light trucks and obtain the coordinates of the starting point, end point and obstacles in the road obstacle avoidance scenarios.

[0020] Step S2: introducing the target distance evaluation function, the vehicle head distance evaluation function, and the curvature evaluation function into the dynamic window algorithm to obtain an improved dynamic window algorithm.

[0021] Among them, the expression of the target distance evaluation function is:

[0022] ;

[0023] in, is the Euclidean distance between the current point and the target point, and are the x-axis coordinate and y-axis coordinate of the last point in the driving trajectory, and are the x-axis coordinate and y-axis coordinate of the target point respectively.

[0024] The expression of the headway distance evaluation function is:

[0025] ;

[0026] in, Indicates the minimum headway distance, Indicates taking the minimum value, is the parallelogram distance between the left end of the vehicle head and the obstacle, is the parallelogram distance between the right end of the vehicle front and the obstacle.

[0027] The expression of the curvature evaluation function is:

[0028] ;

[0029] ;

[0030] ;

[0031] in, represents the curvature evaluation value, The first The curvature of a point, is the mean curvature, is the total number of midpoints in the driving trajectory, is the change in the direction angle of adjacent line segments in the driving trajectory, and are the first direction angle and the second direction angle of the adjacent line segments in the driving trajectory, is the time interval, Represents the remainder operation.

[0032] In the headway distance evaluation function, the following formula is satisfied:

[0033] ;

[0034] ;

[0035] ;

[0036] ;

[0037] ;

[0038] ;

[0039] in, and are the x-axis and y-axis coordinates of the obstacle, and are the x-axis coordinate and y-axis coordinate of the left end of the vehicle head, and are the x-axis coordinate and y-axis coordinate of the right end of the vehicle head, is the vehicle width for light trucks, e.g. 2m, is the wheelbase of a light truck, e.g. 3m, and are the x-axis and y-axis coordinates of the light truck, Represents the heading angle of the light truck.

[0040] Step S3: Dynamically adjust the weight value of the first-improved dynamic window algorithm using a global adaptive weight value adjustment strategy to obtain a second-improved dynamic window algorithm.

[0041] Among them, the expression of the global adaptive adjustment strategy of the weight value is:

[0042] ;

[0043] ;

[0044] ;

[0045] ;

[0046] ;

[0047] ;

[0048] in, is the weight value of the target distance evaluation function after adaptive adjustment, is the weight value of the headway distance evaluation function after adaptive adjustment, is the weight value of the curvature evaluation function after adaptive adjustment, is the weight value of the target distance evaluation function before adaptive adjustment, is the weight value of the vehicle headway distance evaluation function before adaptive adjustment, is the weight value of the curvature evaluation function before adaptive adjustment, 、 、 、 、 、 is the control parameter, is the first adjustment function, is the second adjustment function, is the third adjustment function, is the real-time speed of the light truck, is the maximum speed of a light truck, is the real-time load of the light truck, The maximum load capacity of a light truck.

[0049] Among them, the total evaluation function of the quadratically improved dynamic window algorithm is The expression is:

[0050] ;

[0051] in, is the orientation evaluation function, is the obstacle distance evaluation function, is the speed evaluation function, is the weight value toward the evaluation function, is the weight value of the obstacle distance evaluation function, is the weight value of the speed evaluation function.

[0052] Step S4, using an improved artificial lemmings optimization algorithm to optimize the path variance in the quadratically improved dynamic window algorithm to obtain a tertiary improved dynamic window algorithm, wherein the improved artificial lemmings optimization algorithm is based on the artificial lemmings optimization algorithm, introduces the surrounding prey mechanism in the whale algorithm to improve the foraging model of the artificial lemmings algorithm, and introduces the exploring prey mechanism in the whale algorithm to improve the migration model of the artificial lemmings algorithm.

[0053] Among them, the foraging model of the improved artificial lemming algorithm satisfies the following formula:

[0054] ;

[0055] ;

[0056] ;

[0057] in, The first Lemming individuals in the The position at the iteration, For the foraging model The position of the optimal solution at the iteration; is the coefficient vector of the foraging model, which is used to control the behavior of surrounding prey; is the distance between the whale and prey in the foraging model; is a linear decreasing coefficient, which decreases linearly from 1 to 0 as the number of iterations increases; is a random number ranging from [0,1]; The first Lemming individuals in the The position at the iteration.

[0058] For the migration model, the prey exploration mechanism of the whale algorithm is introduced. When migrating, the lemmings not only consider their own migration behavior, but also learn from the whale's way of exploring prey, randomly selecting an individual as a target and moving towards it. The migration model of the improved artificial lemming algorithm satisfies the following formula:

[0059] ;

[0060] ;

[0061] in, The migration model Lemming individuals in the The position at the iteration, is a randomly selected individual position, is the coefficient vector of the migration model, is the distance between whales and prey in the migration model, The migration model Lemming individuals in the The position at the iteration.

[0062] At the same time, in order to enhance the global exploration and local development capabilities of the improved artificial lemmings algorithm, the population size is dynamically adjusted according to the diversity and fitness distribution of the population. The improved artificial lemmings optimization algorithm also satisfies the following formula:

[0063] ;

[0064] in, For the The population size at the iteration, For the The population size at the iteration, is the adjustment step of population size, is the diversity index of the population (such as the average distance between individuals in the population), is the diversity threshold, which is used to determine whether the population size needs to be adjusted.

[0065] Improved fitness function of artificial lemming optimization algorithm The expression is:

[0066] ;

[0067] ;

[0068] ;

[0069] ;

[0070] ;

[0071] ;

[0072] in, is the path length value; is the path penalty value, which is used to measure the feasibility of the path; for The weight coefficient of is the path length variance, which is mainly used to measure the volatility of the distance between path points; for The weight coefficient is used to control the smoothness optimization intensity. ; and For the adjacent Waypoints and The coordinates of the path points, is the total number of path points, is the minimum distance between a light truck and an obstacle, is the distance adjustment threshold, For example, 1m, is the minimum safe distance, For the Waypoints and The distance between the waypoints, is the average road section length.

[0073] In step S5, based on the coordinates of the starting point, the end point and the position of the obstacle in the road obstacle avoidance scene, a three-times improved dynamic window algorithm is used to plan the path of the light truck to obtain an obstacle avoidance path.

[0074] Among them, the coordinates of the starting point, end point and obstacle positions in the road obstacle avoidance scene are input into the three-times improved dynamic window algorithm, which can be used to plan the path of the light truck and obtain the obstacle avoidance path.

[0075] The following simulation test is conducted. Two complex grid obstacle environments are set up in this simulation, namely Scenario 1 and Scenario 2. The simulation test compares and analyzes the differences in path planning performance between the present invention and the traditional DWA algorithm. The evaluation indicators include path length, curvature change and obstacle safety distance satisfaction. The results are as follows Figure 2 、 Figure 3 and as shown in Table 1.

[0076] Table 1

[0077]

[0078] from Figure 2 、 Figure 3 As can be seen from Table 1, with respect to path length, the present invention optimizes the path search strategy and reduces detours to a certain extent by introducing target distance evaluation functions, headway evaluation functions, and curvature evaluation functions. In both Scenario 1 and Scenario 2, the path lengths of the present invention are shorter than those of the traditional DWA algorithm, demonstrating its superior path optimization capabilities, effectively shortening travel distances and improving path efficiency. Regarding curvature variation, the present invention achieves smaller changes than the traditional DWA algorithm, and while ensuring safety distances, it also makes the planned path smoother, which helps reduce mechanical wear and motion impact on the vehicle during actual driving.

[0079] In summary, the intelligent light truck path planning method according to the above embodiment has the following beneficial effects:

[0080] (1) Based on the traditional dynamic window algorithm, the present invention improves the evaluation function by adding a target distance evaluation function, a headway distance evaluation function, and a curvature evaluation function. Furthermore, a global adaptive weight value adjustment strategy is used to dynamically adjust the weight values ​​of the improved dynamic window algorithm. This effectively solves the problems of insufficient trajectory smoothness in obstacle scenes and the tendency to fall into local optimality in areas with dense obstacles, and improves obstacle avoidance efficiency. Furthermore, when designing the target distance evaluation function, the headway distance evaluation function, and the curvature evaluation function, adjustments can be made for light trucks, setting a longer obstacle avoidance distance. This allows for smoothness and continuity in the planned path, taking into account the long body of light trucks.

[0081] (2) In order to adapt to multiple complex obstacle scenarios and improve the global exploration and local optimization capabilities of the dynamic window algorithm, the present invention adopts an improved artificial lemming optimization algorithm to optimize the path variance in the quadratically improved dynamic window algorithm, which can improve the safety and reliability of path planning. The present invention introduces the prey encirclement mechanism and prey exploration mechanism of the whale algorithm to balance global exploration and local development, while improving rapid response and real-time performance, thereby effectively avoiding dynamic obstacles and significantly improving the path planning performance of the dynamic window algorithm in dynamic environments.

[0082] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. An intelligent light truck path planning method, characterized in that: include: Step S1: construct multiple road obstacle avoidance scenarios for light trucks and obtain the coordinates of the starting point, end point, and obstacles in the road obstacle avoidance scenarios; Step S2, introducing the target distance evaluation function, the vehicle head distance evaluation function, and the curvature evaluation function into the dynamic window algorithm to obtain an improved dynamic window algorithm; Step S3, dynamically adjusting the weight value of the first-improved dynamic window algorithm using a global adaptive weight value adjustment strategy to obtain a second-improved dynamic window algorithm; Step S4, using an improved artificial lemmings optimization algorithm to optimize the path variance in the quadratically improved dynamic window algorithm to obtain a tertiary improved dynamic window algorithm, wherein the improved artificial lemmings optimization algorithm is based on the artificial lemmings optimization algorithm, introduces the surrounding prey mechanism in the whale algorithm to improve the foraging model of the artificial lemmings algorithm, and introduces the exploring prey mechanism in the whale algorithm to improve the migration model of the artificial lemmings algorithm; Step S5, based on the coordinates of the starting point, end point, and obstacle locations in the road obstacle avoidance scenario, a three-fold improved dynamic window algorithm is used to perform path planning for the light truck to obtain an obstacle avoidance path; In step S3, the expression of the global adaptive adjustment strategy of the weight value is: ； ； ； ； ； ； in, is the weight value of the target distance evaluation function after adaptive adjustment, is the weight value of the headway distance evaluation function after adaptive adjustment, is the weight value of the curvature evaluation function after adaptive adjustment, is the weight value of the target distance evaluation function before adaptive adjustment, is the weight value of the vehicle headway distance evaluation function before adaptive adjustment, is the weight value of the curvature evaluation function before adaptive adjustment, 、 、 、 、 、 is the control parameter, is the first adjustment function, is the second adjustment function, is the third adjustment function, is the real-time speed of the light truck, is the maximum speed of a light truck, is the real-time load of the light truck, The maximum load capacity of a light truck.

2. The intelligent light truck path planning method according to claim 1, characterized in that: In step S2, the expression of the target distance evaluation function is: ； in, is the Euclidean distance between the current point and the target point, and are the x-axis coordinate and y-axis coordinate of the last point in the driving trajectory, and are the x-axis coordinate and y-axis coordinate of the target point respectively; The expression of the headway distance evaluation function is: ； in, Indicates the minimum headway distance, Indicates taking the minimum value, is the parallelogram distance between the left end of the vehicle head and the obstacle, is the parallelogram distance between the right end of the vehicle head and the obstacle; The expression of the curvature evaluation function is: ； ； ； in, represents the curvature evaluation value, The first The curvature of a point, is the mean curvature, is the total number of midpoints in the driving trajectory, is the change in the direction angle of adjacent line segments in the driving trajectory, and are the first direction angle and the second direction angle of the adjacent line segments in the driving trajectory, is the time interval, Represents the remainder operation.

3. The intelligent light truck path planning method according to claim 2, characterized in that: In the headway distance evaluation function, the following formula is satisfied: ； ； ； ； ； ； in, and are the x-axis and y-axis coordinates of the obstacle, and are the x-axis coordinate and y-axis coordinate of the left end of the vehicle head, and are the x-axis coordinate and y-axis coordinate of the right end of the vehicle head, is the vehicle width of a light truck, is the wheelbase of a light truck, and are the x-axis and y-axis coordinates of the light truck, Represents the heading angle of the light truck.

4. The intelligent light truck path planning method according to claim 1, characterized in that: In step S3, the total evaluation function of the secondary improved dynamic window algorithm is The expression is: ； in, is the orientation evaluation function, is the obstacle distance evaluation function, is the speed evaluation function, is the weight value toward the evaluation function, is the weight value of the obstacle distance evaluation function, is the weight value of the speed evaluation function.

5. The intelligent light truck path planning method according to claim 4, characterized in that: In step S4, the foraging model of the improved artificial lemming algorithm satisfies the following formula: ； ； ； in, The first Lemming individuals in the The position at the iteration, For the foraging model The position of the optimal solution at the iteration, is the coefficient vector of the foraging model, is the distance between the whale and the prey in the foraging model, is the linear decreasing coefficient, is a random number, The first Lemming individuals in the The position at the iteration; The migration model of the improved artificial lemming algorithm satisfies the following formula: ； ； in, The migration model Lemming individuals in the The position at the iteration, is a randomly selected individual position, is the coefficient vector of the migration model, is the distance between whales and prey in the migration model, The migration model Lemming individuals in the The position at the iteration; The improved artificial lemming optimization algorithm also satisfies the following formula: ； in, For the The population size at the iteration, For the The population size at the iteration, is the adjustment step of population size, is the diversity index of the population, is the diversity threshold; Improved fitness function of artificial lemming optimization algorithm The expression is: ； ； ； ； ； ； in, is the path length value, is the path penalty value, for The weight coefficient of is the path length variance, for The weight coefficient of and For the adjacent Waypoints and The coordinates of the path points, is the total number of path points, is the minimum distance between a light truck and an obstacle, is the distance adjustment threshold, is the minimum safe distance, For the Waypoints and The distance between the waypoints, is the average road section length.

Images