Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions
This addresses safety concerns for physical robot applications, offering a model-free approach that is incremental over existing RL methods.
The paper tackled the problem of ensuring safety in reinforcement learning for robot control by using control Lyapunov barrier functions to provide safety guarantees without a dynamic model, and experimental results showed it outperformed other model-free RL methods in a 2D quadrotor navigation task.
Reinforcement learning (RL) exhibits impressive performance when managing complicated control tasks for robots. However, its wide application to physical robots is limited by the absence of strong safety guarantees. To overcome this challenge, this paper explores the control Lyapunov barrier function (CLBF) to analyze the safety and reachability solely based on data without explicitly employing a dynamic model. We also proposed the Lyapunov barrier actor-critic (LBAC), a model-free RL algorithm, to search for a controller that satisfies the data-based approximation of the safety and reachability conditions. The proposed approach is demonstrated through simulation and real-world robot control experiments, i.e., a 2D quadrotor navigation task. The experimental findings reveal this approach's effectiveness in reachability and safety, surpassing other model-free RL methods.