Guided by Guardrails: Control Barrier Functions as Safety Instructors for Robotic Learning
This work addresses safety challenges for learning-based robotic systems, which is crucial for their adoption in daily life, though it is incremental as it builds on existing RL and CBF methods.
The paper tackled the problem of safety in reinforcement learning for robotics by modeling temporal consequences of unsafe actions with continuous negative rewards, and found that integrating Control Barrier Functions (CBFs) helped robots avoid unsafe zones and improved learning outcomes in simulated and real-world experiments.
Safety stands as the primary obstacle preventing the widespread adoption of learning-based robotic systems in our daily lives. While reinforcement learning (RL) shows promise as an effective robot learning paradigm, conventional RL frameworks often model safety by using single scalar negative rewards with immediate episode termination, failing to capture the temporal consequences of unsafe actions (e.g., sustained collision damage). In this work, we introduce a novel approach that simulates these temporal effects by applying continuous negative rewards without episode termination. Our experiments reveal that standard RL methods struggle with this model, as the accumulated negative values in unsafe zones create learning barriers. To address this challenge, we demonstrate how Control Barrier Functions (CBFs), with their proven safety guarantees, effectively help robots avoid catastrophic regions while enhancing learning outcomes. We present three CBF-based approaches, each integrating traditional RL methods with Control Barrier Functions, guiding the agent to learn safe behavior. Our empirical analysis, conducted in both simulated environments and real-world settings using a four-wheel differential drive robot, explores the possibilities of employing these approaches for safe robotic learning.