【作者】 赵冬斌； 易建强；

【Author】 Zhao Dongbin, Yi Jianqiang Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing 100080

【机构】 中国科学院自动化研究所复杂系统与智能科学重点实验室；

【摘要】 本文研究了蚁群优化算法在机器人结构空间规划的问题。机器人规划就是在复杂的结构空间中,找到一条由起始点到目标点避障的可行路径。针对这个问题,已经提出了很多的求解算法,但采用蚁群优化算法的研究还很少。受旅行商问题求解的最大最小蚁群优化算法启发,提出了一种改进的机器人规划的蚁群优化算法。算法具有一些突出的特性,如路径剪裁机理等。通过在不同环境下的仿真试验,验证了算法总能以很高的概率得到机器人规划问题的最优解。更多还原

【Abstract】 Ant colony optimization algorithms are investigated in this paper for robot planning in configuration space. The robot planning problem is to find a feasible path from a beginning to a goal while avoiding obstacles in a clustered environment. Lots of attentions have been paid on such problems, but little is with the ant colony optimization algorithms. Originated from the MAX-MIN Ant System (MMAS) algorithm for traveling salesman problem, a modified ant colony optimization algorithm for robot planning is proposed. The algorithm has some distinguished features, such as a path pruning mechanism, etc. The optimal solution can be achieved effectively in different environments with a high probability.更多还原