Personal assistant robot using reinforcement learning: DARWIN-OP2 as a case study

Abstract

The use of robots as personal assistants has gained significant interest in recent years. In this research, our motivation is to employ a robot as a personal assistant to optimize the office ergonomics for students. Our personal assistant system consists of DARWIN-OP2 robot, reinforcement algorithm, ROS, communication with robot (using text to speech and speech to text capabilities), and bad posture detection. We conducted a case study on the personal assistant system. The robot receives feedback from student subjects through verbal chatting. Then, the robot executes some tasks such as performing actions or suggesting verbal advice’s to improve the student’s ergonomics. The study included a user evaluation of the robot’s performance, which involved a group of 31 student participants using the robot for a certain period of time. The results show that the DARWIN-OP2 robot is able to effectively and correctly provide valuable health exercises that relieved users’ pains. Additionally, student subjects reported high levels of satisfaction with the robot’s performance and perceived the robot as a helpful personal assistant as it helped in improving their ergonomics. In particular, evaluations of the system, using the group of 31 students, show the system scores 7.7 (out of 10) in speech recognition; 9.7 in health advice’s pain relief; and 9 in users’ opinion on using DARWIN-OP2 as a personal assistant.