Approximate Robust Control of Uncertain Dynamical Systems

Abstract

This work studies the design of safe control policies for large-scale non-linear systems operating in uncertain environments. In such a case, the robust control framework is a principled approach to safety that aims to maximize the worst-case performance of a system. However, the resulting optimization problem is generally intractable for non-linear systems with continuous states. To overcome this issue, we introduce two tractable methods that are based either on sampling or on a conservative approximation of the robust objective. The proposed approaches are applied to the problem of autonomous driving.

References in corpus (1)

• On the Sample Complexity of the Linear Quadratic Regulator

Cited by in corpus (5)

• Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledge
• Interval Prediction for Continuous-Time Systems with Parametric Uncertainties
• Budgeted Reinforcement Learning in Continuous State Space
• Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic
• Towards Learning Generalizable Driving Policies from Restricted Latent Representations