MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics

2025-03-12 · Shuguang Chu, Zebin Huang, Yutong Li, Mingwei Lin, Ignacio Carlucho, Yvan R. Petillot, Canjun Yang

This work presents the MarineGym, a high-performance reinforcement learning (RL) platform specifically designed for underwater robotics. It aims to address the limitations of existing underwater simulation environments in terms of RL compatibility, training efficiency, and standardized benchmarking. MarineGym integrates a proposed GPU-accelerated hydrodynamic plugin based on Isaac Sim, achieving a rollout speed of 250,000 frames per second on a single NVIDIA RTX 3060 GPU. It also provides five models of unmanned underwater vehicles (UUVs), multiple propulsion systems, and a set of predefined tasks covering core underwater control challenges. Additionally, the DR toolkit allows flexible adjustments of simulation and task parameters during training to improve Sim2Real transfer. Further benchmark experiments demonstrate that MarineGym improves training efficiency over existing platforms and supports robust policy adaptation under various perturbations. We expect this platform could drive further advancements in RL research for underwater robotics. For more details about MarineGym and its applications, please visit our project page: https://marine-gym.com/.

📄 PDF Abstract BibTeX arXiv:2503.09203

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingGPUreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Average-Power-Budgeted Underwater Vehicle Control via Constrained Reinforcement Learning

2026-06-24 · Yinuo Wang, Gavin Tao, Yuze Liu arxiv

Underwater vehicles operate from a fixed onboard energy budget that propulsion rapidly depletes, so a controller that completes its task while drawing less thruster power directly extends mission range and endurance. Rei…

Reinforcement Learning

Toward 6-DOF Autonomous Underwater Vehicle Energy-Aware Position Control based on Deep Reinforcement Learning: Preliminary Results

2025-02-25 · Gustavo Boré, Vicente Sufán, Sebastián Rodríguez-Martínez, Giancarlo Troni

The use of autonomous underwater vehicles (AUVs) for surveying, mapping, and inspecting unexplored underwater areas plays a crucial role, where maneuverability and power efficiency are key factors for extending the use o…

Deep Reinforcement Learning Model Predictive Control Position

SafeDiver: Cooperative AUV-USV Assisted Diver Communication via Multi-agent Reinforcement Learning Approach

2025-09-15 · Tinglong Deng, Hang Tao, Xinxiang Wang, Yinyan Wang 외 arxiv

As underwater human activities are increasing, the demand for underwater communication service presents a significant challenge. Existing underwater diver communication methods face hurdles due to inherent disadvantages …

Multi-agent Reinforcement Learning

Task-Semantic Graph-Driven Distributed Agent Networking for Underwater Target Tracking

2026-05-15 · Shengchao Zhu, Guangjie Han, Chuan Lin, Yu He arxiv

Autonomous underwater vehicle (AUV) swarms are emerging as intelligent underwater networks, where each node must sense, communicate, process local data, and make decisions under severe acoustic constraints. Persistent un…

Multi-agent Reinforcement Learning

Cross domain Persistent Monitoring for Hybrid Aerial Underwater Vehicles

2026-02-23 · Ricardo B. Grando, Victor A. Kich, Alisson H. Kolling, Junior C. D. Jesus 외 arxiv

Hybrid Unmanned Aerial Underwater Vehicles (HUAUVs) have emerged as platforms capable of operating in both aerial and underwater environments, enabling applications such as inspection, mapping, search, and rescue in chal…

Reinforcement Learning Transfer Learning