Can the Appearance of a Robot Affect Its Effectiveness as a Workplace Well-Being Coach?

Recently Study carried out by researchers from the University of Cambridge revealed that the physical appearance of robotic health trainers influenced participants’ engagement with them. The study, conducted at a technology consulting firm, involved 26 employees taking part in four weeks of weekly robot-led wellbeing sessions. Two different robot trainers were used for the experiment, both with identical voices, facial expressions and scripts.

Employees who interacted with the toy-like robot reported feeling more connected to their ‘coach’ than those who worked with the humanoid-like robot. Researchers believe these results stem from the fact that people’s perceptions of robots are influenced by popular culture, where imagination is the only limit. As a result, real-world robots often fall short of these expectations.

The simpler appearance of a toy-like robot might lead participants to have lower expectations, making it easier for them to relate to it. On the other hand, those who interact with humanoid robots find their expectations do not match reality, as the robots are unable to carry out interactive conversations.

Despite the discrepancy between expectations and reality, this study demonstrates the potential of robots as a valuable tool for enhancing mental well-being in the workplace. The findings were presented at the ACM/IEEE International Conference on Human-Robot Interaction in Stockholm on March 15.

The World Health Organization recommends that employers promote and protect mental wellbeing in the workplace. However, implementation of welfare practices is often hindered by inadequate resources and personnel. Although robots have shown initial promise in addressing this gap, most of the research has been conducted in laboratories.

Dr. Micol Spitale, first author of the paper, explained the motivation behind the research, saying, “We wanted to get the robots out of the lab and study how they could be useful in the real world.”

The researchers partnered with local technology firm Cambridge Consultants to design a workplace wellbeing program using robots. For four weeks, employees are guided through various wellness exercises by one of two robots: the QTRobot robot (QT) or the Misty II robot (Misty).

QT, a child-like humanoid robot, is about 90cm tall, while Misty, a toy-like robot, is 36cm tall. The two robots have a screen face that is capable of displaying different facial expressions. The robots are programmed with trainer-like personalities, displaying a high degree of openness and conscientiousness.

Participants are guided through a positive psychology exercise by a robot in an office meeting room, with each session beginning with the robot prompting participants to recall positive experiences or express gratitude. The robot will then ask follow-up questions. After the session, participants rated the robot through questionnaires and interviews.

The study found that participants who worked with the toy-like Misty robot reported better job connections and more positive perceptions of the robot compared to those who worked with the child-like QT robot. Spitale argues that Misty’s toy-like appearance could have influenced this result.

Professor Hatice Gunes, who led the research, stressed the importance of perfecting robot interactivity to meet user expectations. He said, “It is very difficult to build a robot that is capable of having natural conversations. New developments in the big language model could really be useful in this regard.”

Minja Axelsson, a co-author of the study, pointed out that preconceived notions about how robots should look or behave may hinder the adoption of robotics in areas where robots could be useful. The participants in this study, while aware that robots were not as advanced as fictional robots, nevertheless felt that well-being exercises were worthwhile and open to the idea of ​​talking to robots in the future.

The research team is now focused on increasing the responsiveness of the robot trainer during coaching practices and interactions.