基于改进变色龙算法的移动机器人避障研究  

Research on Mobile Robot Obstacle Avoidance Based on Improved Chameleon Swarm Algorithm

作　　者：季云[1] 曹弋[2] JI Yun;CAO Yi(Changzhou College of Information Technology,Changzhou 213164,China;School of Transportation Engineering,Dalian Jiaotong University,Dalian 116028,China)

机构地区：[1]常州信息职业技术学院,常州213164 [2]大连交通大学交通运输工程学院,大连116028

出　　处：《组合机床与自动化加工技术》2022年第11期48-51,共4页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金(11702049);2019年江苏省省级工程研究中心-江苏省中小企业工业互联网创新与应用工程研究中心([2019]1125)。

摘　　要：针对标准变色龙算法(CSA)在避障过程中易陷入局部极值、寻路速度慢等不足,提出了一种改进的变色龙算法。首先在种群初始化阶段,使用Bernoulli混沌映射代替随机分布,从而丰富群体的多样性。另外,为了均衡变色龙算法的全局及局部性能,设计了一种种群记忆机制,具体通过邻域搜索策略、基于经验的交叉策略和贪婪选择策略跟踪迭代过程中的最优解,从而对变色龙的搜索加以引导。最后在三种环境下进行仿真,结果表明改进的变色龙算法较对比的其他算法,路径距离更短且规划效率更高。实物实验也验证了改进变色龙算法的有效性。Aiming at the shortcomings of standard chameleon swarm algorithm(CSA)in obstacle avoidance,such as tend to get into local extremum and slow path finding speed,an improved chameleon swarm algorithm was proposed.At first,Bernoulli chaos map was used to replace random distribution in the population initialization stage,so as to enrich the diversity of the population.In addition,to balance the global and local performance of the chameleon swarm algorithm,a population memory mechanism is designed to track the optimal solution in the iterative process through neighborhood search strategy,experience-based crossover strategy and greedy selection strategy,so as to guide the chameleon search.Finally,simulation results in three environments show that the improved chameleon swarm algorithm has shorter path distance and higher planning efficiency compared with other algorithms.The effectiveness of the improved chameleon swarm algorithm is also verified by physical experiment.

关 键 词：变色龙算法 Bernoulli映射 记忆机制 机器人避障 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]