Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions

arXiv2010.16001MaRDI QIDQ6352614

Aaron D. Ames, Sarah Dean, Andrew J. Taylor, Benjamin Recht, Ryan K. Cosner

Publication date: 29 October 2020

Abstract: Modern nonlinear control theory seeks to develop feedback controllers that endow systems with properties such as safety and stability. The guarantees ensured by these controllers often rely on accurate estimates of the system state for determining control actions. In practice, measurement model uncertainty can lead to error in state estimates that degrades these guarantees. In this paper, we seek to unify techniques from control theory and machine learning to synthesize controllers that achieve safety in the presence of measurement model uncertainty. We define the notion of a Measurement-Robust Control Barrier Function (MR-CBF) as a tool for determining safe control inputs when facing measurement model uncertainty. Furthermore, MR-CBFs are used to inform sampling methodologies for learning-based perception systems and quantify tolerable error in the resulting learned models. We demonstrate the efficacy of MR-CBFs in achieving safety with measurement model uncertainty on a simulated Segway system.

Has companion code repository: https://github.com/rkcosner/cyberpod_sim_ros

This page was built for publication: Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6352614)