Multi-robot Multi-source Localization in Complex Flows with Physics-Preserving Environment Models

2025-09-17

AI Summary

Localizing chemical leaks or oil spills in complex, dynamic flow fields poses significant challenges due to sparse sensor measurements, chaotic and time-varying advection–diffusion dynamics, intricate environmental geometry, and limited onboard computational resources for multi-robot systems. Method: We propose a lightweight, machine learning–enhanced finite-element environmental modeling framework that integrates physics-based constraints with an approximate mutual information criterion, enabling a low-communication, distributed sensing and navigation architecture. By unifying information entropy evaluation with infotaxis-based control, the approach achieves computationally efficient, high-precision adaptive sampling. Results: Experiments demonstrate substantially accelerated convergence of localization error and superior source localization accuracy compared to state-of-the-art machine learning baselines. The method exhibits strong robustness and practicality under realistic flow-field complexity, validating its effectiveness for resource-constrained multi-robot deployment.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search
• Machine Learning: Multimodal Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Source localization in a complex flow poses a significant challenge for multi-robot teams tasked with localizing the source of chemical leaks or tracking the dispersion of an oil spill. The flow dynamics can be time-varying and chaotic, resulting in sporadic and intermittent sensor readings, and complex environmental geometries further complicate a team's ability to model and predict the dispersion. To accurately account for the physical processes that drive the dispersion dynamics, robots must have access to computationally intensive numerical models, which can be difficult when onboard computation is limited. We present a distributed mobile sensing framework for source localization in which each robot carries a machine-learned, finite element model of its environment to guide information-based sampling. The models are used to evaluate an approximate mutual information criterion to drive an infotaxis control strategy, which selects sensing regions that are expected to maximize informativeness for the source localization objective. Our approach achieves faster error reduction compared to baseline sensing strategies and results in more accurate source localization compared to baseline machine learning approaches.

Problem

• Localizing chemical leak sources in complex flows
• Addressing sporadic sensor readings from chaotic dynamics
• Overcoming limited onboard computation for dispersion modeling

Innovation

• Distributed mobile sensing with machine-learned models
• Finite element environment models for dispersion dynamics
• Mutual information criterion guiding infotaxis control strategy