封闭园区内无人驾驶洗扫车路径规划及控制

Path planning and control of unmanned washing and sweeping vehicles in closed parks

为实现封闭园区自动洗扫车的无人驾驶功能,设计了一种基于封闭园区场景的路径规划与控制算法。采用改进的A-Star算法并融合三阶贝塞尔曲线构建全局路径规划层;基于状态空间采样设计局部路径规划层,考虑洗扫车转向约束、安全碰撞距离、道路边界距离等约束设计代价函数得到最优局部路径;使用Pure-Pursuit跟踪算法对局部路径规划层输出的最优路径进行追踪;搭建Simulink-ROS联仿平台,在Simulink中编写规划控制算法并编译植入到ROS平台下进行仿真验证;最后采用MDC300F车载计算机对算法进行多工况实车实验。结果表明,该规划控制算法能够控制自动环卫洗扫车在多工况场景下完成跟车、避障、会车等无人驾驶功能。

To realize the unmanned function of automatic washing and sweeping vehicles in closed parks,this paper designed a path planning and control algorithm based on a closed park scenario.It constructed the global path planning layer by using the improved A-Star algorithm combined with the third-order Bezier curve.It designed the local path planning layer based on the state space sampling,and obtained the optimal local path by considering the constraints such as the steering constraints of the sweeper,the safe collision distance,and the road boundary distance.It used the Pure-Pursuit tracking algorithm to track the optimal path output by the local path planning layer.Then,it built the Simulink-ROS joint simulation platform,compiled the planning control algorithm in Simulink,and embedded it into the ROS platform for simulation verification.Finally,it used the MDC300F vehicle-mounted computer to carry out the multi-condition real-vehicle experiment of the algorithm.The results show that the planning control algorithm can control the automatic sanitation washing and sweeping vehicle to complete unmanned functions such as following cars,avoiding obstacles,and meeting cars in multiple working conditions.