摘要
为了改善机器人路径规划中效率低、寻优速度慢等问题,设计一种改进的瞪羚优化算法。首先,在原始瞪羚优化算法初始化后引入正交学习机制,防止瞪羚优化算法在搜索过程中失衡,扩大直接寻优区域,从而保持解的多样性;其次,在瞪羚优化算法中引入Rosenbrock直接旋转策略,对搜索更新机制进行改进,从而提升算法寻优效率;最后,基于不同环境进行机器人路径规划仿真。仿真结果表明,改进的瞪羚优化算法相比其他对比算法各项指标得到不同程度提升,寻优效率更高,可以有效帮助机器人完成规划任务。
In order to improve the low efficiency and slow optimization speed of robot path planning,a improved gazelle optimization algorithm(IGOA)is proposed.Firstly,the orthogonal learning mechanism is introduced after initialization to prevent the unbalance of the algorithm in the search process and expand the direct optimization area,so as to maintain the diversity of solutions.Secondly,Rosenbrock's direct rotation strategy is introduced in the algorithm to improve the search and update mechanism,so as to improve the efficiency of the algorithm.Finally,robot path planning simulation is carried out based on different environments.The simulation results show that compared with other comparison algorithms,the improved gazelle optimization algorithm is more efficient and can effectively help the robot to complete the planning task.
作者
邓毅
廖秋丽
Deng Yi;Liao Qiuli(Department of Physics and Engineering Technology,Guilin Normal College,Guangxi Guilin,541199,China;School of Electrical Engineering and Automation,Guilin University of Electronic Technology,Guangxi Guilin,541004,China)
出处
《机械设计与制造工程》
2024年第1期51-54,共4页
Machine Design and Manufacturing Engineering
基金
2022年桂林师范高等专科学校教学改革研究项目(JGA202204)。
关键词
瞪羚优化算法
正交学习
机器人
路径规划
gazelle optimization algorithm
orthogonal learning
robot
path planning
