Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise

Abstract

Controllers for autonomous systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modelled as process noise, and common assumptions are that the underlying distributions are known and/or Gaussian. In practice, however, these assumptions may be unrealistic and can lead to poor approximations of the true noise distribution. We present a novel planning method that does not rely on any explicit representation of the noise distributions. In particular, we address the problem of computing a controller that provides probabilistic guarantees on safely reaching a target. First, we abstract the continuous system into a discrete-state model that captures noise by probabilistic transitions between states. As a key contribution, we adapt tools from the scenario approach to compute probably approximately correct (PAC) bounds on these transition probabilities, based on a finite number of samples of the noise. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP). This iMDP is robust against uncertainty in the transition probabilities, and the tightness of the probability intervals can be controlled through the number of samples. We use state-of-the-art verification techniques to provide guarantees on the iMDP, and compute a controller for which these guarantees carry over to the autonomous system. Realistic benchmarks show the practical applicability of our method, even when the iMDP has millions of states or transitions.

References in corpus (10)

• Safe Model-based Reinforcement Learning with Stability Guarantees
• Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy Optimization
• Learning for Safety-Critical Control with Control Barrier Functions
• Gaussian Assumption: the Least Favorable but the Most Useful
• Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints
• PAC Statistical Model Checking for Markov Decision Processes and Stochastic Games
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise
• ProbReach: Verified Probabilistic Delta-Reachability for Stochastic Hybrid Systems
• Benchmarks for cyber-physical systems: A modular model library for building automation systems (Extended version)
• Unified Multi-Rate Control: from Low Level Actuation to High Level Planning

Cited by in corpus (3)

• Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise
• Correct-by-Construction Control for Stochastic and Uncertain Dynamical Models via Formal Abstractions