Explainable Reinforcement Learning for Human-Robot Collaboration

摘要

Reinforcement learning (RL) is getting popular in the robotics field due to its nature to learn from dynamic environments. However, it is unable to provide explanations of why an output was generated. Explainability becomes therefore important in situations where humans interact with robots, such as in human-robot collaboration (HRC) scenarios. Attempts to address explainability in robotics usually are restricted to explain a specific decision taken by the RL model, but not to understand the complete behavior of the robot. In addition, the explainability methods are restricted to be used by domain experts as queries and responses are not translated to natural language. This work overcomes these limitations by proposing an explainability solution for RL models applied to HRC. It is mainly formed by the adaptation of two methods: (i) Reward decomposition gives an insight into the factors that impacted the robot's choice by decomposing the reward function. It further provides sets of relevant reasons for each decision taken during the robot's operation; (ii) Autonomous policy explanation provides a global explanation of the robot's behavior by answering queries in the form of natural language, thus making understandable to any human user. Experiments in simulated HRC scenarios revealed an increased understanding of the optimal choices made by the robots. Additionally, our solution demonstrated as a powerful debugging tool to find weaknesses in the robot's policy and assist in its improvement.