基于异质交互式文化混合算法的机器人探测任务规划

Robot Detection Mission Planning Based on Heterogeneous Interactive Cultural Hybrid Algorithm

  • 摘要: 针对机器人任务规划的混合算法缺乏通用结构框架的问题,借鉴文化进化的双重结构思想,提出一种交互式仿生群协进化混合算法体系框架.它包括基于佳点集遗传算法的上层知识空间、基于离散粒子群优化的底层主群空间、自上而下的影响机制和自下而上的接受机制,以实现异质种群交互;通过预留用户评价接口,实现了算法的人机交互.为提高粒子群优化性能,运用佳点集初始化主群空间,使初始粒子均匀分布于可行解内;提出新的粒子进化模型并定义粒子进化力指标,提高了种群的多样性和算法稳定性;通过引入邻域局部搜索策略增强算法的搜索能力.最后,采用TSPLIB标准数据对异质交互式文化混合算法(HICHA)进行测试,实验结果表明,该算法无论是在收敛速度或稳定性方面,还是在求解质量方面,均优于其它算法.HICHA为机器人探测任务规划问题的解决提供了新思路.

     

    Abstract: Aiming at the problem that robot mission planning hybrid algorithms lack a general architecture,a new interactive bionics-swarm co-evolutionary hybrid algorithm system architecture is presented by using cultural evolutionary double structure idea for reference.The architecture includes the upper ceiling knowledge space based on good-point set genetic algorithm(GGA),the bottom ceiling population space based on discrete particle swarm optimization(DPSO),the top-down influence mechanism and the bottom-up acceptance mechanism,to realize heterogeneous population interaction.Addtionally, customer estimation interface is reserved to realize human-computer interaction.In order to improve particle swarm optimization performance,the population space is initialized with good-point set to distribute the initial particles uniformly in feasible solutions.A novel evolution model is presented and the particle evolution ability index is defined,which increases the population's diversity and improves the algorithm's stability.A neighborhood local search strategy is introduced to enhance search capability of the arithmetic.At last,the heterogeneous interactive cultural hybrid algorithm(HICHA) is tested with TSPLIB standard data.Experimental results show that HICHA is better than the other algorithms in stability,convergence speed and solution quality.HICHA provides a new way for solving the robot detection mission planning problem.

     

/

返回文章
返回