Safety Beyond the Training Data: Robust Out-of-Distribution MPC via Conformalized System Level Synthesis
This addresses safety challenges in robotics and autonomous systems when models are deployed in out-of-distribution scenarios, representing an incremental advance by combining existing techniques with novel integration.
The paper tackles the problem of ensuring safety and robustness in planning and control when using learned dynamics models beyond the training data distribution, by developing a framework that integrates conformal prediction with system level synthesis, resulting in improved safety and robustness on nonlinear systems like a 4D car and a 12D quadcopter compared to baselines.
We present a novel framework for robust out-of-distribution planning and control using conformal prediction (CP) and system level synthesis (SLS), addressing the challenge of ensuring safety and robustness when using learned dynamics models beyond the training data distribution. We first derive high-confidence model error bounds using weighted CP with a learned, state-control-dependent covariance model. These bounds are integrated into an SLS-based robust nonlinear model predictive control (MPC) formulation, which performs constraint tightening over the prediction horizon via volume-optimized forward reachable sets. We provide theoretical guarantees on coverage and robustness under distributional drift, and analyze the impact of data density and trajectory tube size on prediction coverage. Empirically, we demonstrate our method on nonlinear systems of increasing complexity, including a 4D car and a {12D} quadcopter, improving safety and robustness compared to fixed-bound and non-robust baselines, especially outside of the data distribution.