基于自回归模型的移动机器人路径规划

Path Planning for Mobile Robot Based on Autoregressive Model

文章研究了全局环境未知且存在动态障碍物情况下的移动机器人路径规划问题;采用全局规划和局部规划相结合的方法,提出了动态未知环境下移动机器人的一种在线实时路径规划方法;该法利用自回归模型来预测动态障碍物的运动轨迹,并把预测位置上的动态障碍物视为是瞬时静态的,然后对该"静态"障碍物进行避碰路径规划;仿真实验结果表明该法有效可行,具有优化性、实时规划性、高度的稳定性和良好的避障能力。

Proposed an uncertain environment path planning method for mobile robot in the presence of moving obstacles. Combining the global planning with the local planning, this dissertation presents a new approach to on--line real--time path planning with respect to the dynamic uncertain environment. With current sampling position, the autoregressive model predicts motion trajectories of moving obstacles. And the predicted positions arc treated as instantaneously static. So moving obstacles in the predicted positions can be considered as static in the path planning process. Simulation ex amples demonstrated the effectiveness, feasibility, real--time capability, high stability and perfect performance of obstacle avoidance.