%0 Journal Article
%T 基于改进蜣螂优化算法的移动机器人多目标点路径规划<br>Multi-Objective Point Path Planning for Mobile Robots Based on Improved Dung Beetle Optimisation Algorithm
%A 王龙锋
%A 王星星
%J Journal of Sensor Technology and Application
%P 162-174
%@ 2331-0243
%D 2025
%I Hans Publishing
%R 10.12677/jsta.2025.132017
%X 针对标准蜣螂优化算法求解移动机器人多目标点路径规划问题存在求解精度低、收敛速度慢与易陷入局部最优等问题&#65292;本文提出一种改进蜣螂优化算法(IDBO)。首先&#65292;采用Logistic-tent混沌映射生成初始化种群&#65292;提高种群多样性&#65307;其次&#65292;设计一种对数调整因子改善小蜣螂觅食方式&#65292;提升算法前期搜索能力与后期开发能力&#65307;最后&#65292;对蜣螂种群嵌入精英差分变异&#65292;并通过贪婪选择更优解&#65292;提升算法跳出局部最优的能力。仿真结果表明&#65292;在地图1、地图2和地图3的环境下&#65292;本文改进蜣螂优化算法平均路径长度均少于DBO算法&#65292;相较于DBO算法平均路径长度分别减少了22.54%、20.86%、15.61%。因此&#65292;对于多目标点路径规划问题的求解&#65292;本文改进蜣螂优化算法对于求解多目标点路径规划问题收敛精度、寻优速度、规划路径质量与鲁棒性均表现优异。<br>The present paper proposes an Improved Dung Beetle Optimisation Algorithm (IDBO) as a solution to the multi-objective point path planning problem of mobile robots, which has the problems of low solution accuracy, slow convergence speed and easy to fall into the local optimum. Firstly, a logistic-tent chaotic mapping is employed to generate an initial population, thereby enhancing population diversity. Secondly, a logarithmic adjustment factor is designed to improve the foraging mode of small dung beetles, thus enhancing pre-searching ability and post-exploitation ability of the algorithm; and lastly, an elite differential variant is embedded in the dung beetle population, and a better solution is chosen through greedy selection to enhance the ability of the algorithm to jump out of the local optimum. The simulation results demonstrate that the average path length of the improved dung beetle optimisation algorithm is shorter than that of the DBO algorithm in environments 1, 2 and 3. The average path lengths are reduced by 22.54%, 20.86% and 15.61%, respectively, in comparison with the DBO algorithm. Consequently, the enhanced dung beetle optimisation algorithm in this study demonstrates notable proficiency in terms of convergence accuracy, optimisation speed, planning path quality and robustness for addressing multi-objective path planning challenges.
%K 移动机器人&#65292
%K 路径规划&#65292
%K Logistic-tent混沌映射&#65292
%K 对数调整因子&#65292
%K 精英差分变异<br>Mobile Robots
%K Path Planning
%K Logistic-Tent Chaotic Mapping
%K Logarithmic Adjustment Factor
%K Elite Differential Variance
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=109713