Uncertainty-Aware Active Source Tracking of Marine Pollution using Unmanned Surface Vehicles

2025-09-24

AI Summary

Addressing the challenges of rapid, precise pollution source localization and insufficient uncertainty quantification in marine pollution incidents, this paper proposes an uncertainty-aware pollution source tracking framework for unmanned surface vehicles (USVs). The method integrates high-fidelity pollutant dispersion simulation with Bayesian probabilistic inference to maintain a real-time-updated posterior distribution over the source location. An information-gain-driven active sensing path planner, implemented within the ROS framework, enables closed-loop feedback control and dynamically optimizes sampling strategies to reduce estimation uncertainty. Our key contribution lies in deeply embedding uncertainty quantification into the perception–decision–action loop, significantly enhancing localization robustness and autonomy under complex, time-varying ocean currents. Extensive multi-scenario simulations demonstrate consistent high-precision localization (mean error <15 m) and substantial uncertainty reduction (posterior entropy decrease >40%) across diverse source locations, flow fields, and initial deployment configurations, validating the framework’s reliability and environmental adaptability.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Planning under Uncertainty
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper proposes an uncertainty-aware marine pollution source tracking framework for unmanned surface vehicles (USVs). By integrating high-fidelity marine pollution dispersion simulation with informative path planning techniques, we demonstrate effective identification of pollution sources in marine environments. The proposed approach is implemented based on Robot Operating System (ROS), processing real-time sensor data to update probabilistic source location estimates. The system progressively refines the estimation of source location while quantifying uncertainty levels in its predictions. Experiments conducted in simulated environments with varying source locations, flow conditions, and starting positions demonstrate the framework's ability to localise pollution sources with high accuracy. Results show that the proposed approach achieves reliable source localisation efficiently. This work contributes to the development of full autonomous environmental monitoring capabilities essential for rapid response to marine pollution incidents.

Problem

• Tracking marine pollution sources using unmanned surface vehicles
• Integrating dispersion simulation with path planning for source identification
• Processing real-time sensor data to refine probabilistic location estimates

Innovation

• Uncertainty-aware framework for unmanned surface vehicles
• Integrates pollution simulation with path planning
• ROS-based real-time probabilistic source estimation