End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks

TL;DR

This paper introduces a safe reinforcement learning framework that combines model-free RL, control barrier functions, and online system modeling to ensure safety and improve learning efficiency in continuous control tasks.

Contribution

The paper presents RL-CBF, a novel controller synthesis algorithm that guarantees safety with high probability during learning, integrating model-free RL with model-based safety constraints.

Findings

RL-CBF guarantees safety during learning.

The approach improves sample efficiency over existing methods.

The method successfully controls an inverted pendulum and autonomous vehicle scenarios.

Abstract

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a controller architecture that combines (1) a model-free RL-based controller with (2) model-based controllers utilizing control barrier functions (CBFs) and (3) on-line learning of the unknown system dynamics, in order to ensure safety during learning. Our general framework leverages the success of RL algorithms to learn high-performance controllers, while the CBF-based controllers both guarantee safety and guide the learning process by constraining the set of explorable polices. We utilize Gaussian Processes (GPs) to model the system dynamics and its uncertainties. Our novel controller synthesis algorithm, RL-CBF, guarantees safety with high probability during the learning process, regardless of the RL algorithm used, and demonstrates greater policy exploration efficiency. We test our algorithm on (1) control of an inverted pendulum and (2) autonomous car-following with wireless vehicle-to-vehicle communication, and show that our algorithm attains much greater sample efficiency in learning than other state-of-the-art algorithms and maintains safety during the entire learning process.