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

arXiv: https://arxiv.org/abs/2603.04057 · HTML: https://mlsanity.com/paper/2603.04057/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 39 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles](https://mlsanity.com/paper/2301.06512/) (2023)
- [COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning](https://mlsanity.com/paper/2006.09540/) (2020)
- [DAVE Aquatic Virtual Environment: Toward a General Underwater Robotics Simulator](https://mlsanity.com/paper/2209.02862/) (2022)
- [A Deep Reinforcement Learning Framework and Methodology for Reducing the Sim-to-Real Gap in ASV Navigation](https://mlsanity.com/paper/2407.08263/) (2024)
- [Learning to navigate efficiently and precisely in real environments](https://mlsanity.com/paper/2401.14349/) (2024)
- [NeuronsGym: A Hybrid Framework and Benchmark for Robot Tasks with Sim2Real Policy Learning](https://mlsanity.com/paper/2302.03385/) (2023)

## Abstract (arXiv)

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 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.