一种新型混合优化算法在机器人路径规划中的应用  

Application of a new kind of mixed optimal algorithm on robotic path planning

作　　者：王仲民[1] 戚厚军[1] 闫兵[1] 李充宁[1] 

机构地区：[1]天津职业技术师范学院机械工程系,天津300222

出　　处：《机械设计》2003年第6期43-44,59,共3页Journal of Machine Design

基　　金：天津职业技术师范学院青年基金资助项目 (ZK0 2 - 0 01)

摘　　要：针对模拟退火算法收敛速度慢这一缺点 ,提出了一种基于模拟退火算法和复合形法相结合的新型混合优化算法 ,并成功应用于机器人神经网络路径规划中。该算法不仅继承了模拟退火算法能得到全局最优解的优点 ,又能搜索到理想的下降方向 ,提高了算法的收敛速度。仿真实验研究表明 :这种新型混合优化算法 ,计算简单 ,收敛速度快 。Aimed at the defect of low convergent speed in algorithm of simulated annealing and based on a kind of combination of simulated annealing a lgorithm and compound shape method,a new mixed optimal algorithm was put forward and being applied successfully to path planning of robotic neural network.This algorithm could not only carry forward the advantage of simulated annealing algo rithm for obtaining the overall optimal solution,but also search out the ideal d escending direction,thus raised the convergent speed of the algorithm.The simula tive experiment demonstrates that this new kind of mixed optimal algorithm is si mple in computation,rapid in convergent speed and good in robustness of initial value.

关 键 词：机器人 路径规划 混合优化算法 模拟退火算法 复合形法 神经网络 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] O242.23[自动化与计算机技术—控制科学与工程]