粒子群优化算法融合行为动力学的路径规划方法研究

Research on Path Planning Method of Particle Swarm Optimization Algorithm and Fusion Behavior Dynamics

针对未知环境下采用竞争行为动力学协调方法进行移动机器人路径规划时存在机器人运动速度参数确定困难,并且在各基本行为竞争时容易产生行为参数振荡现象而导致规划出来的路径不优化等问题,提出了基于粒子群优化算法融合行为动力学进行路径规划的方法。该方法在行为动力学模型的基础上利用粒子群优化算法(Particle swarm optimization,PSO)对路径规划过程中的基本行为进行融合,代替了竞争行为动力学的行为参数协调,从而使移动机器人能够根据传感器采集的实时环境信息自动获取各个基本行为的权值。通过把该方法与基于竞争动力学行为协调方法的机器人路径规划进行了仿真对比实验,实验结果验证了该方法的可行性和优越性。

When using competitive behavior dynamics coordination methods to mobile robot path planning in unknown environment, the robot motion velocity parameters are difficult determined and it is easy to generate parameter oscillation in behavior competition, leading to the path of planning not optimization. A new path planning method based on particle swarm optimization for behavior dynamics algorithm is proposed. In this method, the particle swarm optimization algorithm is used to integrate the basic behaviors in path planning process based on the behavior dynamics model, which instead of the behavior parameter coordination of the competitive behavior dynamics. So that the robot can automatically obtain the weight of each basic behavior according to the real-time environment information collected by the vision senor. By comparing the proposed method with the competitive behavior dynamic coordination methods, the experiment results verify the feasibility and superiority of the proposed method.