Multi-robot Multi-source Localization in Complex Flows with Physics-Preserving Environment Models
This addresses the challenge of efficient and accurate source localization for multi-robot teams in dynamic environments, representing an incremental improvement over existing sensing and machine learning approaches.
The paper tackles the problem of multi-robot source localization in complex flows, such as chemical leaks or oil spills, by using distributed mobile sensing with machine-learned environment models to guide sampling, achieving faster error reduction and more accurate localization compared to baseline methods.
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.