# Stonefish: Supporting Machine Learning Research in Marine Robotics

arXiv: https://arxiv.org/abs/2502.11887 · HTML: https://mlsanity.com/paper/2502.11887/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning](https://mlsanity.com/paper/1810.05762/) (2018)
- [UNav-Sim: A Visually Realistic Underwater Robotics Simulator and Synthetic Data-generation Framework](https://mlsanity.com/paper/2310.11927/) (2023)
- [DAVE Aquatic Virtual Environment: Toward a General Underwater Robotics Simulator](https://mlsanity.com/paper/2209.02862/) (2022)
- [Investigation of the Challenges of Underwater-Visual-Monocular-SLAM](https://mlsanity.com/paper/2306.08738/) (2023)
- [A reinforcement learning control approach for underwater manipulation under position and torque constraints](https://mlsanity.com/paper/2011.12360/) (2020)
- [Digital Twins Below the Surface: Enhancing Underwater Teleoperation](https://mlsanity.com/paper/2402.07556/) (2024)
- [Integrating a Digital Twin Concept in the Zero Emission Sea Transporter (ZEST) Project for Sustainable Maritime Transport using Stonefish Simulator](https://mlsanity.com/paper/2408.02277/) (2024)

## Built on by (most cited first, 11 of 11)

- [MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics](https://mlsanity.com/paper/2503.09203/) (2025)
- [Distributed AI Agents for Cognitive Underwater Robot Autonomy](https://mlsanity.com/paper/2507.23735/) (2025)
- [USIM and U0: A Vision-Language-Action Dataset and Model for General Underwater Robots](https://mlsanity.com/paper/2510.07869/) (2025)
- [ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Research](https://mlsanity.com/paper/2506.22174/) (2025)
- [eStonefish-Scenes: A Sim-to-Real Validated and Robot-Centric Event-based Optical Flow Dataset for Underwater Vehicles](https://mlsanity.com/paper/2505.13309/) (2025)
- [Advancing Shared and Multi-Agent Autonomy in Underwater Missions: Integrating Knowledge Graphs and Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.20370/) (2025)
- [UEOF: A Benchmark Dataset for Underwater Event-Based Optical Flow](https://mlsanity.com/paper/2601.10054/) (2026)
- [Sim-to-reality adaptation for Deep Reinforcement Learning applied to an underwater docking application](https://mlsanity.com/paper/2603.12020/) (2026)
- [MMUSV-Sim: A Perception-Oriented Simulation and Data-Generation Platform for Multi-USV Cooperative Perception](https://mlsanity.com/paper/2608.14207/) (2026)
- [World-Model-Grounded LLM Planning for AUV and ASV Navigation Near Offshore Wind Farms](https://mlsanity.com/paper/2608.19661/) (2026)
- [Towards Scaling Marine Perception with Synthetic Data](https://mlsanity.com/paper/2609.20680/) (2026)

## Abstract (arXiv)

Simulations are highly valuable in marine robotics, offering a cost-effective and controlled environment for testing in the challenging conditions of underwater and surface operations. Given the high costs and logistical difficulties of real-world trials, simulators capable of capturing the operational conditions of subsea environments have become key in developing and refining algorithms for remotely-operated and autonomous underwater vehicles. This paper highlights recent enhancements to the Stonefish simulator, an advanced open-source platform supporting development and testing of marine robotics solutions. Key updates include a suite of additional sensors, such as an event-based camera, a thermal camera, and an optical flow camera, as well as, visual light communication, support for tethered operations, improved thruster modelling, more flexible hydrodynamics, and enhanced sonar accuracy. These developments and an automated annotation tool significantly bolster Stonefish's role in marine robotics research, especially in the field of machine learning, where training data with a known ground truth is hard or impossible to collect.