Certificated Actor-Critic: Hierarchical Reinforcement Learning with Control Barrier Functions for Safe Navigation
This work addresses safe navigation for robots, offering a novel approach to improve performance and safety, though it appears incremental in combining existing techniques.
The paper tackles the limitations of existing safe navigation methods by proposing a model-free reinforcement learning algorithm, Certificated Actor-Critic (CAC), which uses a hierarchical framework and reward functions from Control Barrier Functions, validated through simulation experiments.
Control Barrier Functions (CBFs) have emerged as a prominent approach to designing safe navigation systems of robots. Despite their popularity, current CBF-based methods exhibit some limitations: optimization-based safe control techniques tend to be either myopic or computationally intensive, and they rely on simplified system models; conversely, the learning-based methods suffer from the lack of quantitative indication in terms of navigation performance and safety. In this paper, we present a new model-free reinforcement learning algorithm called Certificated Actor-Critic (CAC), which introduces a hierarchical reinforcement learning framework and well-defined reward functions derived from CBFs. We carry out theoretical analysis and proof of our algorithm, and propose several improvements in algorithm implementation. Our analysis is validated by two simulation experiments, showing the effectiveness of our proposed CAC algorithm.