摘要
对移动机器人在三维工作环境中障碍物位置和形状已知条件下的全局路径规划问题进行研究。机器人的初始路径取为出发点到目标点的直线路径,引入人工神经网络结构和模拟退火温度定义路径能量函数;根据多面体形障碍物的形状特征设定各边界面不等的模拟退火初始温度,并且对路径点位于障碍物内、外的不同情况建立不同的运动方程;提出一种基于神经网络结构能量函数的路径规划算法及其优化算法,对所提路径规划算法进行仿真研究。研究结果表明,该算法是一种有效的移动机器人三维路径规划算法;算法计算简单,不存在组合爆炸问题;可避免路径规划的某些局部极小值问题;优化算法能够规划出移动机器人最短避障路径,并且可加快路径规划收敛速度。
Global path planning was studied for a moving robot in a 3D environment filled with obstacles whose shapes and positions were known. An aggressive algorithm for path planning was presented. The obstacles were described by an energy function defined using neural networks. Different initial simulated anneal temperatures of each surface of objects can be set according to the shape of them. The different path generating equations were used, depending on the path points inside or outside the obstacles, which allows high speed of the calculations and fast convergence. The simulation results show that the computation is simple, some local minimum problems can be avoided, and the constructed path is optimal and piecewise linear.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2009年第2期471-477,共7页
Journal of Central South University:Science and Technology
基金
国家自然科学基金资助项目(10572125)
河南省自然科学基金资助项目(0611052500)
关键词
全局路径规划
能量函数
神经网络
模拟退火
global path planning
energy function
neural network
simulated annealing
