Learning for Safety-Critical Control with Control Barrier Functions

Abstract

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

Extended version (12 Pages), Short version submitted to Learning for Dynamics & Control (L4DC) 2020 Conference

References in corpus (10)

• Input-to-State Safety With Control Barrier Functions
• Safe Model-based Reinforcement Learning with Stability Guarantees
• Neural Lander: Stable Drone Landing Control using Learned Dynamics
• Safe Controller Optimization for Quadrotors with Gaussian Processes
• Adaptive Safety with Control Barrier Functions
• Bayesian Learning-Based Adaptive Control for Safety Critical Systems
• The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems
• Learning Barrier Functions for Constrained Motion Planning with Dynamical Systems
• Smooth Imitation Learning for Online Sequence Prediction
• Safe Interactive Model-Based Learning

Cited by in corpus (10)

• High Order Robust Adaptive Control Barrier Functions and Exponentially Stabilizing Adaptive Control Lyapunov Functions
• A Control Barrier Perspective on Episodic Learning via Projection-to-State Safety
• Neural Certificates for Safe Control Policies
• Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions
• Learning Stability Certificates from Data
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise
• Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach
• Structured learning of safety guarantees for the control of uncertain dynamical systems
• Learning Safe Neural Network Controllers with Barrier Certificates
• Unsupervised Joint $k$-node Graph Representations with Compositional Energy-Based Models