Graph-Based RL for Sequential Rendezvous Planning with Multiple Patrolling USVs
Graph-Based RL for Sequential Rendezvous Planning with Multiple Patrolling USVs
This paper introduces a framework combining grid-based path planning, surrogate travel-time prediction, and graph-based reinforcement learning to optimize sequential rendezvous operations for multiple unmanned surface vehicles (USVs). The proposed method utilizes a Feasible Transition Graph (FTG) to model spatiotemporal relationships and employs a surrogate model to predict travel times efficiently. Evaluation results indicate statistically significant average objective reductions of 10.5%, 3.5%, and 1.5% compared to greedy, MLP-RL, and 2-step lookahead greedy baselines, respectively, while requiring approximately 1/35 of the computation time of the latter.
The study presents a graph-based reinforcement learning framework for coordinating multiple unmanned surface vehicles (USVs) in patrol missions, achieving statistically significant reductions in mission completion time and tardiness while reducing computational requirements by approximately 35-fold compared to baseline methods.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S3
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ority-dependent due dates. We propose a framework combining grid-based path planning, surrogate travel-time prediction, and graph-based reinforcement learning. The path planner accounts for ocean currents and approximates turn-rate constraints through multi-stage maneuvers, with path feasibility empirically validated through trajectory-tracking simulations. For rendezvous sequencing, a Feasible Transition Graph (FTG)
Open source S3
tive reductions of 10.5%, 3.5%, and 1.5% compared with greedy, MLP-RL, and 2-step lookahead greedy, respectively. The policy achieves these improvements while requiring approximately 1/35 of the latter's computation time. It maintains its advantage over MLP-RL under unseen priority-tier settings, with larger gains as fleet size increases.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org