RNfinity
Research Infinity Logo, Orange eye of horus, white eye of Ra
  • Home
  • Submit
    Research Articles
    Ebooks
  • Articles
    Academic
    Ebooks
  • Info
    Home
    Subject
    Submit
    About
    News
    Submission Guide
    Contact Us
  • Login/sign up
    Login
    Register

Physics Maths Engineering

Adaptive Path Planning for Subsurface Plume Tracing with an Autonomous Underwater Vehicle

rnfinity

info@rnfinity.com

orcid logo

Zhiliang Wu,

Zhiliang Wu

School of Mechanical Engineering, Tianjin University, Tianjin 300354, China


Shuozi Wang,

Shuozi Wang

School of Mechanical Engineering, Tianjin University, Tianjin 300354, China


Xusong Shao,

Xusong Shao

School of Mechanical Engineering, Tianjin University, Tianjin 300354, China


Fang Liu,

Fang Liu

Yichang Research Institute of Testing Technology, Yichang 443003, China


Zefeng Bao

Zefeng Bao

China Automotive Technology and Research Center, Tianjin 300300, China


  Peer Reviewed

copyright icon

© attribution CC-BY

  • 0

rating
497 Views

Added on

2024-11-22

Doi: http://dx.doi.org/10.3390/robotics13090132

Related Subjects
Physics
Math
Chemistry
Computer science
Engineering
Earth science
Biology

Abstract

Key Questions

1. What challenges do autonomous underwater vehicles (AUVs) address in plume tracing?

AUVs provide autonomous, efficient, and adaptive solutions for tracing subsurface plumes in hostile or inaccessible marine environments.

2. What is the advantage of using Double Deep Q-Network (DDQN) for path planning?

DDQN-based path planning allows AUVs to adaptively learn and optimize their survey paths, outperforming traditional methods like lawnmower patterns in efficiency and adaptability.

3. How does the proposed method compare to traditional survey patterns?

The DDQN approach demonstrated superior performance in numerical simulations, enabling faster and more precise plume source detection compared to the lawnmower strategy.

4. What are the implications for large-scale marine exploration?

The findings suggest that reinforcement learning-based adaptive path planning can significantly enhance the effectiveness of AUVs in large-scale environmental monitoring and exploration.

Abstract

Background

Oil spills in marine environments cause severe ecological and economic damage. Subsurface plume tracing is critical for understanding oil movement and its environmental impact. Autonomous underwater vehicles (AUVs) are emerging as pivotal tools for addressing these challenges.

Methods

This study presents an adaptive path planning approach using the Double Deep Q-Network (DDQN) algorithm. The plume tracing problem is modeled as a Markov Decision Process (MDP), enabling AUVs to iteratively learn optimal survey paths through reinforcement learning.

Results

The proposed method was validated through numerical simulations and real-world experiments. Results indicated that DDQN outperformed traditional strategies, such as the lawnmower pattern, in efficiency and plume source detection accuracy.

Conclusions

Reinforcement learning-based path planning is a promising solution for adaptive plume tracing. Future work will focus on enhancing AUV capabilities for multi-agent systems and complex marine environments.

Summary Video Not Available

Review 0

Login

ARTICLE USAGE


Article usage: Nov-2024 to May-2025
Show by month Manuscript Video Summary
2025 May 119 119
2025 April 75 75
2025 March 61 61
2025 February 52 52
2025 January 51 51
2024 December 61 61
2024 November 78 78
Total 497 497
Show by month Manuscript Video Summary
2025 May 119 119
2025 April 75 75
2025 March 61 61
2025 February 52 52
2025 January 51 51
2024 December 61 61
2024 November 78 78
Total 497 497
Related Subjects
Physics
Math
Chemistry
Computer science
Engineering
Earth science
Biology
copyright icon

© attribution CC-BY

  • 0

rating
497 Views

Added on

2024-11-22

Doi: http://dx.doi.org/10.3390/robotics13090132

Related Subjects
Physics
Math
Chemistry
Computer science
Engineering
Earth science
Biology

Follow Us

  • Xicon
  • Contact Us
  • Privacy Policy
  • Terms and Conditions

5 Braemore Court, London EN4 0AE, Telephone +442082758777

© Copyright 2025 All Rights Reserved.