MarineGym: Accelerated Training for Underwater Vehicles with High-Fidelity RL Simulation

Shuguang Chu, Zebin Huang, Mingwei Lin, Dejun Li, Ignacio Carlucho

Research output: Working paperPreprint

27 Downloads (Pure)

Abstract

Reinforcement Learning (RL) is a promising solution, allowing Unmanned Underwater Vehicles (UUVs) to learn optimal behaviors through trial and error. However, existing simulators lack efficient integration with RL methods, limiting training scalability and performance. This paper introduces MarineGym, a novel simulation framework designed to enhance RL training efficiency for UUVs by utilizing GPU acceleration. MarineGym offers a 10,000-fold performance improvement over real-time simulation on a single GPU, enabling rapid training of RL algorithms across multiple underwater tasks. Key features include realistic dynamic modeling of UUVs, parallel environment execution, and compatibility with popular RL frameworks like PyTorch and TorchRL. The framework is validated through four distinct tasks: station-keeping, circle tracking, helical tracking, and lemniscate tracking. This framework sets the stage for advancing RL in underwater robotics and facilitating efficient training in complex, dynamic environments.
Original languageEnglish
Publication statusPublished - 18 Oct 2024

Keywords

  • cs.RO

Fingerprint

Dive into the research topics of 'MarineGym: Accelerated Training for Underwater Vehicles with High-Fidelity RL Simulation'. Together they form a unique fingerprint.

Cite this