RAT iLQR: A Risk Auto-Tuning Controller to Optimally Account for Stochastic Model Mismatch

Links: arxiv, code, bibtex

Abtract

Successful robotic operation in stochastic environments relies on accurate characterization of the underlying probability distributions, yet this is often imperfect due to limited knowledge. This work presents a control algorithm that is capable of handling such distributional mismatches. Specifically, we propose a novel nonlinear MPC for distributionally robust control, which plans locally optimal feedback policies against a worst-case distribution within a given KL divergence bound from a Gaussian distribution. Leveraging mathematical equivalence between distributionally robust control and risk-sensitive optimal control, our framework also provides an algorithm to dynamically adjust the risk-sensitivity level online for risk-sensitive control. The benefits of the distributional robustness as well as the automatic risk-sensitivity adjustment are demonstrated in a dynamic collision avoidance scenario where the predictive distribution of human motion is erroneous.

Bibtex

@article{nishimura2021ratilqr,
    title={RAT iLQR: A Risk Auto-Tuning Controller to Optimally Account for Stochastic Model Mismatch},
    author={Haruki Nishimura and Negar Mehr and Adrien Gaidon and Mac Schwager},
    journal={RA-L},
    year={2021},
}