摘要
针对移动机器人的路径规划中存在的避障和路径搜索等问题,文章提出了一种基于精英反向学习(elite opposition-based learning,EOBL)的烟花爆炸式免疫遗传算法(fireworks explosive immune genetic algorithm,FEIGA)。在FEIGA算法的基础上,引入EOBL机制扩大全局搜索,即在进行爆炸操作时,对当前最佳个体执行反向学习,生成其搜索边界内的反向搜索种群,引导算法向包含全局最优的解空间逼近,以提高算法的平衡和探索能力。函数优化结果表明,与其他算法相比,EOBL-FEIGA收敛速度更快,搜索精度更高,有效地解决了免疫遗传算法(immune genetic algorithm,IGA)存在的局部搜索能力弱、易早熟收敛的问题,克服了FEIGA算法易陷入局部最优解的不足。路径规划结果表明,在不同的复杂环境下,EOBL-FEIGA能实现机器人的最优路径搜索和避障,有较强的搜索能力和鲁棒性。
To solve the problems that exist in mobile robot path planning,such as obstacle avoidance and path search,a new type of fireworks explosive immune genetic algorithm based on elite opposition-based learning(EOBL-FEIGA)was put forward.Developed on the fireworks explosive immune genetic algorithm(FEIGA),the global search was expanded by introducing elite opposition-based learning(EOBL)mechanism.In every explosion operation,opposition-based learning(OBL)was executed by the current best individual to generate an opposition search populations in its search boundaries,thus the search space of the algorithm was guided to approximate the optimum space.This mechanism is helpful to improve the balance and exploring of the FEIGA.Function optimization results show that compared with other algorithms,EOBL-FEIGA has higher convergence rate and accuracy for numerical optimization,and has effectively solved the shortcomings that exist in immune genetic algorithm(IGA)and FEIGA.The results of path planning simulation show that EOBL-FEIGA shows strong search ability and robustness,and can realize the robot optimal path search and obstacle avoidance in different complex environments.
作者
韩江
闵杰
HAN Jiang;MIN Jie(School of Mechanical Engineering, Hefei University of Technology, Hefei 230009, China)
出处
《合肥工业大学学报（自然科学版）》
CAS
北大核心
2020年第4期433-437,共5页
Journal of Hefei University of Technology：Natural Science
基金
安徽省科技重大专项资助项目(17030901036)。
