Sim2Sea: Sim-to-Real Policy Transfer for Maritime Vessel Navigation in Congested Waters

TL;DR

Sim2Sea introduces a comprehensive framework combining scalable simulation, advanced policy design, and domain randomization to enable reliable zero-shot sim-to-real transfer for autonomous vessel navigation in congested waters.

Contribution

The paper presents a novel integrated approach with a GPU-accelerated simulator, dual-stream spatiotemporal policy, and targeted domain randomization for maritime navigation.

Findings

Achieves faster convergence and safer trajectories in simulation.

Successfully transfers policies zero-shot to real unmanned vessels.

Demonstrates effective navigation in congested waters with real-world deployment.

Abstract

Autonomous navigation in congested maritime environments is a critical capability for a wide range of real-world applications. However, it remains an unresolved challenge due to complex vessel interactions and significant environmental uncertainties. Existing methods often fail in practical deployment due to a substantial sim-to-real gap, which stems from imprecise simulation, inadequate situational awareness, and unsafe exploration strategies. To address these, we propose \textbf{Sim2Sea}, a comprehensive framework designed to bridge simulation and real-world execution. Sim2Sea advances in three key aspects. First, we develop a GPU-accelerated parallel simulator for scalable and accurate maritime scenario simulation. Second, we design a dual-stream spatiotemporal policy that handles complex dynamics and multi-modal perception, augmented with a velocity-obstacle-guided action masking mechanism to ensure safe and efficient exploration. Finally, a targeted domain randomization scheme helps bridge the sim-to-real gap. Simulation results demonstrate that our method achieves faster convergence and safer trajectories than established baselines. In addition, our policy trained purely in simulation successfully transfers zero-shot to a 17-ton unmanned vessel operating in real-world congested waters. These results validate the effectiveness of Sim2Sea in achieving reliable sim-to-real transfer for practical autonomous maritime navigation.