摘要
针对移动机器人在动态环境中常遇到的非最优路径问题,提出了基于混沌反控制并具有一定预测能力的路径规划算法。算法结合神经网络和距离传播模型,无需先验知识并且能适应动态不确定环境。通过在关键位置控制机器人进行混沌运动,可以减少等距情况下随机选择所造成的非最优路径出现的几率。在目标振荡运动且速度快于机器人的情况下,通过分析目标的轨迹和方向可以预测目标的短期运动趋势,进而实现有效追踪。仿真结果表明该算法对于减少非最短路径和路径中的尖点具有一定的作用,对于追踪速度较快的目标也有较大的成功率。
To solve the non optimized path problem that is often encountered for a mobile robot in a dynamic environment,a path planning algorithm based on chaos anti-control that possesses some prediction capability is presented.The algorithm combines the neural-network and the distance transportation model to get rid of prior knowledge to adapt to dynamic or unknown environments.The probability of the appearance of a non optimized path is reduced through random selection under an equal distance environment by controlling the chaos movements of the robot at critical locations.When a target oscillates and moves faster than the robot,its near future movement trend can be predicted by analyzing its trajectory and direction,hence an effective tracking is realized.Simulation results demonstrate that the proposed algorithm can decrease non shortest paths and nodes to a certain extent and the success rate in pursuing a comparative faster target is moderately high.
出处
《计算机应用与软件》
CSCD
2011年第1期235-238,共4页
Computer Applications and Software
