Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Yimian, Xu, Jingzehua, Xie, Guanwen, Zhang, Shuai, Li, Yi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915644345155584
author Ding, Yimian
Xu, Jingzehua
Xie, Guanwen
Zhang, Shuai
Li, Yi
author_facet Ding, Yimian
Xu, Jingzehua
Xie, Guanwen
Zhang, Shuai
Li, Yi
contents This study presents a novel environment-aware reinforcement learning (RL) framework designed to augment the operational capabilities of autonomous underwater vehicles (AUVs) in underwater environments. Departing from traditional RL architectures, the proposed framework integrates an environment-aware network module that dynamically captures flow field data, effectively embedding this critical environmental information into the state space. This integration facilitates real-time environmental adaptation, significantly enhancing the AUV's situational awareness and decision-making capabilities. Furthermore, the framework incorporates AUV structure characteristics into the optimization process, employing a large language model (LLM)-based iterative refinement mechanism that leverages both environmental conditions and training outcomes to optimize task performance. Comprehensive experimental evaluations demonstrate the framework's superior performance, robustness and adaptability.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15082
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks
Ding, Yimian
Xu, Jingzehua
Xie, Guanwen
Zhang, Shuai
Li, Yi
Systems and Control
This study presents a novel environment-aware reinforcement learning (RL) framework designed to augment the operational capabilities of autonomous underwater vehicles (AUVs) in underwater environments. Departing from traditional RL architectures, the proposed framework integrates an environment-aware network module that dynamically captures flow field data, effectively embedding this critical environmental information into the state space. This integration facilitates real-time environmental adaptation, significantly enhancing the AUV's situational awareness and decision-making capabilities. Furthermore, the framework incorporates AUV structure characteristics into the optimization process, employing a large language model (LLM)-based iterative refinement mechanism that leverages both environmental conditions and training outcomes to optimize task performance. Comprehensive experimental evaluations demonstrate the framework's superior performance, robustness and adaptability.
title Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks
topic Systems and Control
url https://arxiv.org/abs/2506.15082