Analysis of Proximity and Risk for Trust Evaluation in Human-Robot Collaboration^*

Abstract

In the emerging phase of industrialization, Industry 5.0, humans will be working alongside advanced technologies such as Artificial Intelligence (AI) and robots to improve the manufacturing process. As a result, it is crucial to evaluate trust in the robot from a human perspective in order to provide a safe environment and balance workloads. Relevant trust indicators in the industrial context include proximity between human and robot, as well as risk associated with robot’s performance. In this study, a chemical industry scenario was developed, where a robot assists a human in mixing chemicals. An experiment was conducted for analysing how proximity and risk impact the trust level of the participants. According to the results, there was a higher average trust score in the low proximity (i.e. robot not close to the human) and low risk sections compared to the high proximity and high risk sections of the experiment, respectively. Moreover, statistical analysis indicates that risk had a higher impact on trust than proximity. The findings of this study encourage further research in this area since tools such as AI could be used to control the robot’s behavior according to the level of trust between the human and the robot.