Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions

TL;DR

This paper introduces a novel safe reinforcement learning approach that combines disturbance observers with control barrier functions, enabling efficient exploration and safety guarantees without the need for model learning.

Contribution

The proposed method leverages disturbance observers to accurately estimate uncertainties and incorporate them into CBFs, improving safety and efficiency in model-free RL.

Findings

Outperforms state-of-the-art safe RL algorithms in safety violation rate

Reduces sample and computational requirements

Ensures safety throughout the learning process

Abstract

Safe reinforcement learning (RL) with assured satisfaction of hard state constraints during training has recently received a lot of attention. Safety filters, e.g., based on control barrier functions (CBFs), provide a promising way for safe RL via modifying the unsafe actions of an RL agent on the fly. Existing safety filter-based approaches typically involve learning of uncertain dynamics and quantifying the learned model error, which leads to conservative filters before a large amount of data is collected to learn a good model, thereby preventing efficient exploration. This paper presents a method for safe and efficient RL using disturbance observers (DOBs) and control barrier functions (CBFs). Unlike most existing safe RL methods that deal with hard state constraints, our method does not involve model learning, and leverages DOBs to accurately estimate the pointwise value of the uncertainty, which is then incorporated into a robust CBF condition to generate safe actions. The DOB-based CBF can be used as a safety filter with model-free RL algorithms by minimally modifying the actions of an RL agent whenever necessary to ensure safety throughout the learning process. Simulation results on a unicycle and a 2D quadrotor demonstrate that the proposed method outperforms a state-of-the-art safe RL algorithm using CBFs and Gaussian processes-based model learning, in terms of safety violation rate, and sample and computational efficiency.