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

10/16/2020

∙

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.

READ FULL TEXT

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

Learning-based distributionally robust motion control with Gaussian processes

Risk-Sensitive Motion Planning using Entropic Value-at-Risk

Wasserstein Distributionally Robust Motion Control for Collision Avoidance Using Conditional Value-at-Risk

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach

Leveraging Distributional Bias for Reactive Collision Avoidance under Uncertainty: A Kernel Embedding Approach

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

Related Research

Learning-based distributionally robust motion control with Gaussian processes

Risk-Sensitive Motion Planning using Entropic Value-at-Risk

Wasserstein Distributionally Robust Motion Control for Collision Avoidance Using Conditional Value-at-Risk

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach

Leveraging Distributional Bias for Reactive Collision Avoidance under Uncertainty: A Kernel Embedding Approach