Learning-based distributionally robust motion control with Gaussian processes
This work addresses safety concerns in autonomous driving by providing a robust control tool for scenarios with uncertain obstacle dynamics, representing an incremental improvement in risk-aware motion control.
The paper tackles the problem of ensuring safety in learning-based robotic systems by developing a distributionally robust model predictive control method that limits risk even when learned obstacle distributions are inaccurate, demonstrated through simulations with a nonlinear car-like vehicle model.
Safety is a critical issue in learning-based robotic and autonomous systems as learned information about their environments is often unreliable and inaccurate. In this paper, we propose a risk-aware motion control tool that is robust against errors in learned distributional information about obstacles moving with unknown dynamics. The salient feature of our model predictive control (MPC) method is its capability of limiting the risk of unsafety even when the true distribution deviates from the distribution estimated by Gaussian process (GP) regression, within an ambiguity set. Unfortunately, the distributionally robust MPC problem with GP is intractable because the worst-case risk constraint involves an infinite-dimensional optimization problem over the ambiguity set. To remove the infinite-dimensionality issue, we develop a systematic reformulation approach exploiting modern distributionally robust optimization techniques. The performance and utility of our method are demonstrated through simulations using a nonlinear car-like vehicle model for autonomous driving.