On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approach

05/05/2023

∙

Safety has been a critical issue for the deployment of learning-based approaches in real-world applications. To address this issue, control barrier function (CBF) and its variants have attracted extensive attention for safety-critical control. However, due to the myopic one-step nature of CBF and the lack of principled methods to design the class-𝒦 functions, there are still fundamental limitations of current CBFs: optimality, stability, and feasibility. In this paper, we proposed a novel and unified approach to address these limitations with Adaptive Multi-step Control Barrier Function (AM-CBF), where we parameterize the class-𝒦 function by a neural network and train it together with the reinforcement learning policy. Moreover, to mitigate the myopic nature, we propose a novel multi-step training and single-step execution paradigm to make CBF farsighted while the execution remains solving a single-step convex quadratic program. Our method is evaluated on the first and second-order systems in various scenarios, where our approach outperforms the conventional CBF both qualitatively and quantitatively.

READ FULL TEXT

On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approach

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environments

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Bayesian Learning-Based Adaptive Control for Safety Critical Systems

Adaptive Control Barrier Functions for Safety-Critical Systems

Wasserstein Distributionally Robust Control Barrier Function using Conditional Value-at-Risk with Differentiable Convex Programming

Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions

On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approach

Related Research

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environments

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Bayesian Learning-Based Adaptive Control for Safety Critical Systems

Adaptive Control Barrier Functions for Safety-Critical Systems

Wasserstein Distributionally Robust Control Barrier Function using Conditional Value-at-Risk with Differentiable Convex Programming

Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions