Multi-Agent Reinforcement Learning for UAV-Based Chemical Plume Source Localization

TL;DR

This paper introduces a multi-agent deep reinforcement learning framework that enhances UAV-based chemical plume source localization, improving accuracy and efficiency over traditional methods.

Contribution

The study develops a novel MARL-based approach utilizing virtual anchor nodes for coordinated UAV sensing in chemical source localization.

Findings

MARL framework outperforms fluxotaxis in accuracy

Enhanced UAV coordination improves localization efficiency

Virtual anchor nodes enable effective collaborative sensing

Abstract

Undocumented orphaned wells pose significant health and environmental risks to nearby communities by releasing toxic gases and contaminating water sources, with methane emissions being a primary concern. Traditional survey methods such as magnetometry often fail to detect older wells effectively. In contrast, aerial in-situ sensing using unmanned aerial vehicles (UAVs) offers a promising alternative for methane emission detection and source localization. This study presents a robust and efficient framework based on a multi-agent deep reinforcement learning (MARL) algorithm for the chemical plume source localization (CPSL) problem. The proposed approach leverages virtual anchor nodes to coordinate UAV navigation, enabling collaborative sensing of gas concentrations and wind velocities through onboard and shared measurements. Source identification is achieved by analyzing the historical trajectory of anchor node placements within the plume. Comparative evaluations against the fluxotaxis method demonstrate that the MARL framework achieves superior performance in both localization accuracy and operational efficiency.