Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a real-time monitoring framework for robotic systems that operates under uncertainty while adhering to complex task and safety specifications, specifically in maritime navigation. By utilizing data-driven reachable sets, the proposed approach significantly reduces the data requirements typically needed for specification evaluation. The results from simulations and hardware experiments show that this framework enhances risk detection capabilities compared to existing state-of-the-art methods, even in the presence of realistic disturbances.
Real-time monitoring of robotic systems can now achieve superior risk detection under uncertainty with significantly less data.
Robotic systems must operate under uncertainty while satisfying complex task and safety specifications. Monitoring such specifications under uncertainty remains challenging, as existing formulations typically require extensive data or explicit uncertainty distributions. In this paper, we propose a real-time monitoring framework that reduces data requirements by leveraging data-driven reachable sets for specification evaluation. We instantiate the framework for maritime navigation, where complex specifications arise from traffic rules. We develop a data-efficient pipeline for constructing reachable sets and derive a monitoring formulation suitable for real-time deployment. Simulation and hardware experiments demonstrate robust monitoring under realistic disturbances, achieving improved risk detection compared to state-of-the-art metrics.