差分克隆选择算法在多机器人任务分配中的应用

Application of Differential Clonal Selection Algorithm in Multi-robot Task Assignment

针对传统克隆选择算法进化过程中易出现退化以及陷入局部最优解的问题,提出了一种差分克隆选择算法。该算法从局部搜索和全局搜索两方面提出改进。局部搜索方面使用自适应的差分变异算子使算法在优良解附近进一步探索,避免陷入局部最优。全局搜索方面使用全交叉操作使种群保存良好的多样性,扩大全局搜索范围,增加算法跳出局部最优解的可能性。最后,将所提算法、传统克隆选择算法和遗传算法同时应用于智能制造系统中多机器人多任务分配问题进行实验,结果表明差分克隆选择算法具有更高的收敛精度和较好的跳出局部最优解的能力。

A differential clonal selection algorithm was proposed to solve the problem that the traditional clonal selection algorithm would degenerate and easily fall into the local optimal solution.The algorithm is improved from local search and global search.In local search,the adaptive differential mutation operator is used to make the algorithm explore further near the good solution and avoid falling into the local optimal.In global search,the use of full cross operation makes the population preserve good diversity,and expands the global search scope to increase the possibility of the algorithm jumping out of the local optimal solution.Finally,the proposed algorithm,traditional clonal selection algorithm and genetic algorithm are simultaneously applied to the multi-robot multi-task assignment problem in intelligent manufacturing system.The experimental results show that the differential clonal selection algorithm has better convergence accuracy and the ability to jump out of the local optimal solution.