Path Planning with Turnabouts for Mobile Robots in Narrow Road Using PER-DDPG

This study proposes a local path planning with turnabouts for mobile robots navigating narrow roads, utilizing a deep deterministic policy gradient with prioritized experience replay (PER-DDPG) algorithm. A narrow road is defined as one that is impossible for a robot without the use of turnabouts. Such roads are common in confined environments, including factories and historical areas. While previous research has addressed local path planning in narrow roads, it has typically been limited to simple non-branching scenarios. In contrast, this study extends path planning capabilities to more complex environments, including branching narrow roads. The proposed method uses PER-DDPG to generate feasible local paths with turnabouts. The effectiveness of the approach is validated through both simulations and real-world experiments.