Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations
This work addresses safety-critical problems for human-robot interaction, though it appears incremental by combining existing techniques.
The paper tackles the challenge of ensuring safety and stability in reinforcement learning for human-aligned tasks by proposing an algorithm that integrates neural ordinary differential equations with control barrier and Lyapunov functions, resulting in fewer safety violations and better sample efficiency in simulations.
Reinforcement learning (RL) excels in applications such as video games, but ensuring safety as well as the ability to achieve the specified goals remains challenging when using RL for real-world problems, such as human-aligned tasks where human safety is paramount. This paper provides safety and stability definitions for such human-aligned tasks, and then proposes an algorithm that leverages neural ordinary differential equations (NODEs) to predict human and robot movements and integrates the control barrier function (CBF) and control Lyapunov function (CLF) with the actor-critic method to help to maintain the safety and stability for human-aligned tasks. Simulation results show that the algorithm helps the controlled robot to reach the desired goal state with fewer safety violations and better sample efficiency compared to other methods in a human-aligned task.