Multi-Robot Multi-Source Localization in Complex Flows with Physics-Preserving Environment Models
Benjamin Shaffer, Victoria Edwards, Brooks Kinch, Nathaniel Trask, M. Ani Hsieh
AI summary
Problem
Accurately localizing unobservable sources in complex, chaotic flows requires real-time environmental modeling, but computationally intensive physics simulations are infeasible on resource-constrained robots, while existing data-driven methods lack physical consistency.
Approach
Each robot runs a lightweight, structure-preserving finite element model conditioned on sensor data to compute an information-theoretic metric, guiding an infotaxis-style control strategy that selects maximally informative sensing locations.
Key results
- Lower source reconstruction error than transformer baselines
- Faster error reduction than baseline sampling strategies
- Scalable distributed coordination via local history fusion
- Accurate source-to-field mapping via learned flux coupling
Why it matters
Provides a deployable framework for real-time environmental monitoring and hazardous leak tracking by resource-constrained autonomous robot teams.
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.