The hierarchy of global and local planners is one of the most commonly utilized system designs in robot autonomous navigation. While the global planner generates a reference path from the current to goal locations based on the pre-built static map, the local planner produces a collision-free, kinodynamic trajectory to follow the reference path while avoiding perceived obstacles. The reference path should be replanned regularly to accommodate new obstacles that were absent in the pre-built map, but when to execute replanning remains an open question. In this work, we conduct an extensive simulation experiment to compare various replanning strategies and confirm that effective strategies highly depend on the environment as well as on the global and local planners. We then propose a new adaptive replanning strategy based on deep reinforcement learning, where an agent learns from experiences to decide appropriate replanning timings in the given environment and planning setups. Our experimental results demonstrate that the proposed replanning agent can achieve performance on par or even better than current best-performing strategies across multiple situations in terms of navigation robustness and efficiency.

翻译：全局与局部规划器的层次结构是机器人自主导航中最常用的系统设计之一。全局规划器基于预构建的静态地图生成从当前位置到目标位置的参考路径，而局部规划器则生成无碰撞、满足运动动力学约束的轨迹以跟踪参考路径，同时避开感知到的障碍物。参考路径需要定期重新规划以适应预构建地图中未出现的新障碍物，但何时执行重规划仍是一个开放性问题。本研究通过大量仿真实验比较了多种重规划策略，证实高效策略高度依赖于环境以及全局与局部规划器的选择。我们提出了一种基于深度强化学习的自适应重规划策略，其中智能体通过经验学习在给定环境和规划设置中决定合适的重规划时机。实验结果表明，在多种情境下的导航鲁棒性和效率方面，所提出的重规划智能体能够达到甚至超越当前最优策略的性能。