A Control Barrier Perspective on Episodic Learning via Projection-to-State Safety

Abstract

In this paper we seek to quantify the ability of learning to improve safety guarantees endowed by Control Barrier Functions (CBFs). In particular, we investigate how model uncertainty in the time derivative of a CBF can be reduced via learning, and how this leads to stronger statements on the safe behavior of a system. To this end, we build upon the idea of Input-to-State Safety (ISSf) to define Projection-to-State Safety (PSSf), which characterizes degradation in safety in terms of a projected disturbance. This enables the direct quantification of both how learning can improve safety guarantees, and how bounds on learning error translate to bounds on degradation in safety. We demonstrate that a practical episodic learning approach can use PSSf to reduce uncertainty and improve safety guarantees in simulation and experimentally.

6 pages, 2 figures, submitted to L-CSS + CDC 2020

References in corpus (1)

• Learning for Safety-Critical Control with Control Barrier Functions

Cited by in corpus (8)

• Learning Hybrid Control Barrier Functions from Data
• ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers
• Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions
• Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State Safety
• BarrierNet: A Safety-Guaranteed Layer for Neural Networks
• Rollover Prevention for Mobile Robots with Control Barrier Functions: Differentiator-Based Adaptation and Projection-to-State Safety
• Imitation Learning with Stability and Safety Guarantees
• Provably Correct Training of Neural Network Controllers Using Reachability Analysis