# MarineFormer: A Spatio-Temporal Attention Model for USV Navigation in Dynamic Marine Environments

arXiv: https://arxiv.org/abs/2410.13973 · HTML: https://mlsanity.com/paper/2410.13973/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 47 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [A Brief Survey of Deep Reinforcement Learning](https://mlsanity.com/paper/1708.05866/) (2017)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Implicit Quantile Networks for Distributional Reinforcement Learning](https://mlsanity.com/paper/1806.06923/) (2018)
- [Stabilizing Transformers for Reinforcement Learning](https://mlsanity.com/paper/1910.06764/) (2019)
- [Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph](https://mlsanity.com/paper/2203.01821/) (2022)
- [Transformers are Meta-Reinforcement Learners](https://mlsanity.com/paper/2206.06614/) (2022)
- [InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation](https://mlsanity.com/paper/2409.07914/) (2024)
- [Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation](https://mlsanity.com/paper/2409.17435/) (2024)
- [CoBERL: Contrastive BERT for Reinforcement Learning](https://mlsanity.com/paper/2107.05431/) (2021)
- [Recurrent Off-policy Baselines for Memory-based Continuous Control](https://mlsanity.com/paper/2110.12628/) (2021)
- [Robust Unmanned Surface Vehicle Navigation with Distributional Reinforcement Learning](https://mlsanity.com/paper/2307.16240/) (2023)
- [Decentralized Multi-Robot Navigation for Autonomous Surface Vehicles with Distributional Reinforcement Learning](https://mlsanity.com/paper/2402.11799/) (2024)
- [Hierarchical end-to-end autonomous navigation through few-shot waypoint detection](https://mlsanity.com/paper/2409.14633/) (2024)

## Built on by (most cited first, 1 of 1)

- [Design and Implementation of a Dual Uncrewed Surface Vessel Platform for Bathymetry Research under High-flow Conditions](https://mlsanity.com/paper/2502.12539/) (2025)

## Abstract (arXiv)

Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In this work, we demonstrate that incorporating local flow field measurements fundamentally alters the nature of the problem, transforming otherwise unsolvable navigation scenarios into tractable ones. However, the mere availability of flow data is not sufficient; it must be effectively fused with conventional sensory inputs such as ego-state and obstacle states. To this end, we propose MarineFormer, a Transformer-based policy architecture that integrates two complementary attention mechanisms: spatial attention for sensor fusion, and temporal attention for capturing environmental dynamics. MarineFormer is trained end-to-end via reinforcement learning in a 2D simulated environment with realistic flow features and obstacles. Extensive evaluations against classical and state-of-the-art baselines show that our approach improves episode completion success rate by nearly 23% while reducing path length. Ablation studies further highlight the critical role of flow measurements and the effectiveness of our proposed architecture in leveraging them.