The study introduces OkayPlan, a Global Path Planning (GPP) algorithm designed for Unmanned Surface Vehicles (USVs) operating in dynamic environments. Traditional GPP algorithms assume static environments, which limits their applicability to USVs that typically navigate dynamic surroundings. OkayPlan overcomes this by leveraging particle swarm optimization to generate safe, short paths in real-time. It also features a Dynamic Prioritized Initialization mechanism and a relaxation strategy for autonomous tuning in dynamic settings. Comparative experiments demonstrated OkayPlan’s superiority in safety, length optimality, and computational efficiency.
Publication date: 12 Jan 2024
Project Page: https://github.com/XinJingHao/OkayPlan
Paper: https://arxiv.org/pdf/2401.05019
