Interactive Reinforcement Learning for Table Balancing Robot

Abstract

With the development of robotics, the use of robots in daily life is increasing, which has led to the need for anyone to easily train robots to improve robot use. Interactive reinforcement learning(IARL) is a method for robot training based on human-robot interaction; prior studies on IARL provide only limited types of feedback or require appropriately designed shaping rewards, which is known to be difficult and time consuming. Therefore, in this study, we propose interactive deep reinforcement learning models based on voice feedback. In the proposed system, a robot learns the task of cooperative table balancing through deep Q-network using voice feedback provided by humans in real time, with automatic speech recognition(ASR) and sentiment analysis to understand human voice feedback. As a result, an optimal policy convergence rate of up to 96% was realized, and performance was improved in all voice feedback-based models.

Table-Balancing Cooperative Robot Based on Deep Reinforcement Learning

“…Future research will expand on the proposed method to broaden the range of human action states and robot actions, as well as to implement a more delicate human-robot balancing method and apply it in real life by advancing the learning method. An extended study of the customized table-balancing-robot method, voice-interactive reinforcement learning for table-balancing robots [41], has already been presented at an international conference. Furthermore, as a follow-up method, the method was developed by applying transfer learning and continual learning to expand the object handled by the proposed robot and is currently organizing data for publication.…”