路网约束下异构机器人系统路径规划方法

由无人机(Unmanned aerial vehicles, UAV)和地面移动机器人组成的异构机器人系统在协作执行任务时, 可以充分发挥两类机器人各自的优势. 无人机运动灵活, 但通常续航能力有限; 地面机器人载荷多, 适合作为无人机的着陆平台和移动补给站, 但运动受路网约束. 本文研究这类异构机器人系统协作路径规划问题. 为了降低完成任务的时间代价, 提出一种由蚁群算法(Ant colony optimization, ACO)和遗传算法(Genetic algorithm, GA)相结合的两步法对地面机器人和无人机的路线进行解耦, 同时规划地面机器人和无人机的路线. 第1步使用蚁群算法为地面机器人搜索可行路线. 第2步对无人机的最优路径建模, 采用遗传算法求解并将无人机路径长度返回至第1步中, 用于更新路网的信息素参数, 从而实现异构协作系统路径的整体优化. 另外, 为了进一步降低无人机的飞行时间代价, 研究了无人机在其续航能力内连续完成多任务的协作路径规划问题. 最后, 通过大量仿真实验验证了所提方法的有效性.

Path Planning for Heterogeneous Robot System With Road Network Constraints

The heterogeneous robot system, composed of unmanned aerial vehicles (UAVs) and ground mobile robots, can give full play to the respective advantages of the two types of robots when performing tasks in cooperation. UAVs have the characteristics of flexibility, but they usually have limited endurance. Ground robots can bear large loads and are suitable for use as landing platforms and mobile replenishment stations for UAVs, but their movement is constrained by the road network. This paper studies the cooperative path planning of the heterogeneous robot systems. In order to reduce the time cost of the task, this paper proposes a two-step strategy combining ant colony optimization (ACO) and genetic algorithm (GA) to decouple the routes of mobile robot and UAV, and plans the routes of mobile robot and UAV at the same time. In the first step, ant colony optimization is used to search for feasible routes of the mobile robot. In the second step, we derive the model of the UAV＇s optimal path and use the genetic algorithm to solve it. The UAV path length is returned to the first step to update the pheromone in the road network. Then, we realize the overall optimization of the heterogeneous collaborative system path. In order to further reduce the flight time cost of UAVs, this paper also studies the problem of cooperative path planning for UAVs to continuously complete multiple tasks within their endurance capabilities. Finally, a large number of simulation experiments verify the effectiveness of the proposed method.