CN-122015896-A - Unmanned vehicle path planning method and device, electronic equipment and readable storage medium

CN122015896ACN 122015896 ACN122015896 ACN 122015896ACN-122015896-A

Abstract

The application relates to a unmanned vehicle path planning method, a device, electronic equipment and a readable storage medium, which comprise the steps of initializing a population in a preset chaotic mapping mode, adjusting exploration probability based on a diversity index and a convergence index, determining a preset iteration strategy for iterating the population based on the adjusted exploration probability, iterating each body in the population based on the preset iteration strategy to obtain an iterative population, determining the fitness value of each body in the iterative population, updating a global historical optimal path based on a candidate path corresponding to the fitness value, repeatedly executing the steps of monitoring the diversity index and the convergence index of the population, adjusting exploration probability based on the diversity index and the convergence index until the iteration termination condition is met, and taking the current global historical optimal path as a target planning path to enable the unmanned vehicle to run based on the target planning path. By the method provided by the application, the target planning path considering the path length, the smoothness and the obstacle avoidance requirement is output.

Inventors

GAO JIUZHOU
YUE JUNHUA
QU YIMING
ZHAO YULIANG
HAN CHENGHAO
JIA XUE
ZHANG YUHONG
SUN WEI
WANG XIANGRUI
LI YULI
ZHANG LIHUI

Assignees

吉林建筑大学

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (10)

1. A method for unmanned vehicle path planning, comprising: Acquiring a starting point position, a target point position and environment map information of an unmanned vehicle, and initializing a population by a preset chaotic mapping mode based on the starting point position, the target point position and the environment map information, wherein the environment map information comprises road boundaries and positions of known fixed obstacles, and each individual in the population represents a candidate path from the starting point position to the target point position; Monitoring a diversity index and a convergence index of the population, and adjusting an exploration probability based on the diversity index and the convergence index; Determining a preset iteration strategy for iterating the population based on the adjusted exploration probability, and iterating each individual in the population based on the preset iteration strategy to obtain an iterative population, wherein the preset iteration strategy comprises a Lewy flight search strategy and a local development weighted combination search strategy; Determining the fitness value of each individual in the iterative population, and updating a global historical optimal path based on the candidate path corresponding to the fitness value; Repeatedly executing the steps of monitoring the diversity index and the convergence index of the population, and adjusting the exploration probability based on the diversity index and the convergence index until an iteration termination condition is met, wherein the iteration termination condition comprises that the absolute value of the change amount of the adaptation value corresponding to the global history optimal path in continuous multiple iterations is smaller than the preset change amount; and taking the current global history optimal path as a target planning path so that the unmanned vehicle runs based on the target planning path.
2. The method of claim 1, wherein initializing the population by the predetermined chaotic map comprises: Determining the dimension and population scale corresponding to the path planning; Randomly generating a multidimensional vector based on the dimension as an initial chaotic variable; according to the preset chaotic mapping mode, iteratively calculating a chaotic sequence by taking the initial chaotic variable as a starting value and the population scale as the length of the chaotic sequence; and linearly transforming the chaotic sequence to an actual value range corresponding to the path solution space to obtain the population.
3. The method of claim 1, wherein the adjusting the exploration probability based on the diversity index and the convergence index comprises: determining an iteration attenuation term, a diversity weight and a convergence weight, wherein the iteration attenuation term is reduced along with the increase of iteration times; determining a diversity influence value based on the diversity index and the diversity weight, and determining a convergence influence value based on the convergence index and the convergence weight; And determining the sum of the iterative decay term, the diversity influence value and the convergence influence value as an exploration probability.
4. The method of claim 1, wherein the determining, based on the adjusted exploration probabilities, a preset iteration strategy for iterating each of the individuals in the population, iterating the population based on the preset iteration strategy to obtain an iterated population, comprises: Generating a random number in a preset numerical range; for each individual, iterating the individual based on the Lewy flight search strategy under the condition that the random number is smaller than the adjusted exploration probability so as to obtain an iterated population; and under the condition that the random number is not smaller than the adjusted exploration probability, iterating the individual based on the local development weighted combination search strategy to obtain an iterated population.
5. The method of claim 1, wherein said determining an fitness value for each of the individuals in the iterative population, updating a global historical optimal path based on the candidate path corresponding to the fitness value, comprises: Determining elite individuals from the iterative population according to a preset proportion range based on the fitness value of each individual in the iterative population; For each elite individual, generating a corresponding cauchy random vector based on a standard cauchy distribution; determining a difference vector between a current global optimal individual and the elite individual, and carrying out weighted calculation on the cauchy random vector and the difference vector to obtain a guiding disturbance vector of the elite individual; The guiding disturbance vector is overlapped to a corresponding elite individual, and an elite fitness value corresponding to the perturbed elite individual is determined; and determining the candidate path corresponding to the minimum value in the elite fitness values before and after disturbance as the current global history optimal path.
6. The method as recited in claim 1, further comprising: monitoring real-time environment information in the running process of the unmanned vehicle according to a target planning path; based on the environment map information and the real-time environment information, under the condition that a dynamic obstacle appears in front of the target planning path, predicting a collision risk area of collision between the dynamic obstacle and the unmanned vehicle; marking the collision risk area as a temporary forbidden area, taking the current position of the unmanned vehicle as a starting point position, executing the step of acquiring the starting point position, the target point position and the environment map information of the unmanned vehicle, and acquiring an updated target planning path based on the starting point position, the target point position and the environment map information, wherein the updated target planning path is another path avoiding the temporary forbidden area.
7. The method according to claim 6, wherein the predicting a collision risk area where the dynamic obstacle collides with the unmanned vehicle in the case where the dynamic obstacle appears in front of the target planned path is determined based on the environment map information and the real-time environment information, comprises: in the case where the dynamic obstacle and the unmanned vehicle travel in opposite directions and there is a path junction, a collision risk area where a collision occurs at the path junction is predicted based on a movement speed of the dynamic obstacle and a travel speed of the unmanned vehicle, and/or, Under the condition that the dynamic obstacle intersects with the running direction of the unmanned vehicle and a crossing node exists, the dynamic obstacle and the unmanned vehicle are predicted to reach a collision risk area where the crossing node collides within the same preset time window, and/or, In case the dynamic obstacle and the unmanned vehicle travel in the same direction and the traveling speed of the unmanned vehicle is greater than the moving speed of the dynamic obstacle, predicting a collision risk area where the unmanned vehicle collides in the course of catching up the dynamic obstacle, and/or, And under the condition that a plurality of dynamic obstacles and the unmanned vehicle coexist in the same environment, respectively predicting collision risk areas between the dynamic obstacles and the unmanned vehicle and new collision risk areas between the dynamic obstacles and the following dynamic obstacles due to avoiding the previous dynamic obstacles.
8. An unmanned vehicle path planning apparatus, comprising: The system comprises an initialization module, a control module and a control module, wherein the initialization module is used for acquiring a starting point position, a target point position and environment map information of an unmanned vehicle, initializing a population by a preset chaotic mapping mode based on the starting point position, the target point position and the environment map information, wherein the environment map information comprises a road boundary and the position of a known fixed obstacle, and each individual in the population represents a candidate path from the starting point position to the target point position; the adjustment module is used for monitoring the diversity index and the convergence index of the population and adjusting the exploration probability based on the diversity index and the convergence index; The processing module is used for determining a preset iteration strategy for iterating the population based on the adjusted exploration probability, and iterating each individual in the population based on the preset iteration strategy to obtain an iterative population, wherein the preset iteration strategy comprises a Lewy flight search strategy and a local development weighted combination search strategy; A preferential module, configured to determine fitness values of the individuals in the iterative population, and update a global historical optimal path based on the candidate paths corresponding to the fitness values; The termination module is used for repeatedly executing the steps of monitoring the diversity index and the convergence index of the population, and adjusting the exploration probability based on the diversity index and the convergence index until an iteration termination condition is met, wherein the iteration termination condition comprises that the absolute value of the change amount of the adaptation value corresponding to the global history optimal path in a plurality of continuous iterations is smaller than the preset change amount; and the control module is used for taking the current global history optimal path as a target planning path so that the unmanned vehicle runs based on the target planning path.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.
10. A readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.

Description

Unmanned vehicle path planning method and device, electronic equipment and readable storage medium Technical Field The present application relates to the field of path planning technologies, and in particular, to a method and apparatus for unmanned vehicle path planning, an electronic device, and a readable storage medium. Background In the aspects of optimization algorithm and intelligent control, a meta-heuristic algorithm such as a hawk optimizer is used for solving the nonlinear optimization problem, and a population can be randomly generated in a solution space through a pseudo-random number generator, but the population distribution is possibly uneven, the whole solution space cannot be systematically covered, and particularly in a high-dimensional problem, the initial stage of the algorithm is easily caused to lack global representativeness, the subsequent global exploration efficiency is influenced, and the convergence speed is slow or the local optimum is sunk too early. In the prior art, aiming at the problem of exploration and development balance, the stage conversion can be controlled through a preset fixed parameter or linear time-varying strategy, but the strategy lacks the perception of the actual running state of the algorithm, cannot be dynamically adjusted according to population diversity and convergence situation, and is easy to cause premature convergence or inefficient exploration. Aiming at the problem of local optimization, random disturbance strategies such as Gaussian disturbance are often adopted to apply disturbance to elite individuals, but the disturbance is not strong in directivity, blindness exists, solutions can be possibly guided to worse areas, and the efficiency of jumping out of the local optimization is low. However, the prior art still has the defects of insufficient population initialization ergodic performance, stiff exploration and development conversion mechanism and lack of direction guidance of local disturbance, so that the accuracy, speed and robustness of an algorithm are limited when the algorithm solves complex and dynamic optimization problems, and the problems of low global exploration efficiency, easy premature convergence and poor dynamic environment adaptability of the algorithm in the prior art are solved. Disclosure of Invention In view of the above, the embodiments of the present application provide a method, an apparatus, an electronic device, and a readable storage medium for unmanned vehicle path planning, so as to solve the problems of low global exploration efficiency, easy premature convergence, and poor dynamic environment adaptability of the algorithm in the prior art. In a first aspect of the embodiment of the present application, a method for planning a path of an unmanned vehicle is provided, including: Acquiring a starting point position, a target point position and environment map information of the unmanned vehicle, initializing a population by a preset chaotic mapping mode based on the starting point position, the target point position and the environment map information, wherein the environment map information comprises a road boundary and the position of a known fixed obstacle, and each individual in the population represents a candidate path from the starting point position to the target point position; Determining a preset iteration strategy for iterating the population based on the adjusted exploration probability, iterating each body in the population based on the preset iteration strategy to obtain an iteration population, wherein the preset iteration strategy comprises a Lev flight search strategy and a local development weighted combination search strategy, determining the fitness value of each body in the iteration population, updating a global historical optimal path based on a candidate path corresponding to the fitness value, repeatedly executing the steps of monitoring the diversity index and the convergence index of the population, and adjusting the exploration probability based on the diversity index and the convergence index until an iteration termination condition is met, wherein the iteration termination condition comprises that the absolute value of the change amount of the fitness value corresponding to the global historical optimal path in a plurality of continuous iterations is smaller than the preset change amount, and taking the current global historical optimal path as a target planning path to enable the unmanned vehicle to run based on the target planning path. In a second aspect of the embodiment of the present application, there is provided an unmanned vehicle path planning apparatus, including: The system comprises an initial point position, a target point position and environment map information of an unmanned vehicle, an initialization module, a processing module, a priority module and a termination module, wherein the initial point position, the target point position and the environment map informatio