Contact-Aware Covariance Control of Stochastic Contact-Rich Systems
Keywords: Feedback Manipulation, Chance-Constrained Optimization, Bilevel Optimization, Covariance Steering, Contact-Implicit Trajectory Optimization
TL;DR: We propose model-based optimization algorithm for designing feedback controller through contact with probabilistic guarantees.
Abstract: Planning and control for uncertain contact systems is challenging as it is not clear how to propagate uncertainty for planning. We use a particle filter-based approach to propagate moments for stochastic complementarity system. To circumvent the issues of open-loop chance constrained planning, we propose a contact-aware controller for covariance steering of the complementarity system. Our optimization problem is formulated as Non-Linear Programming (NLP) using bilevel optimization. We verify that our contact-aware controller is able to steer the covariance of the states for stochastic contact-rich tasks.
Submission Number: 5
Loading