Nao robot had to be taught only Tai Chi moves for it to move like a Tai Chi instructor

Tai Chi, a moving meditative art, may soon be a skill you can master with ease with a cute and friendly robot teaching you all the moves. The Tai Chi instructor is a 2 feet tall Nao robot a highly sophisticated robotic system, that is custom programmed for specific functions. Zhi Zheng, an assistant professor at RIT's Kate Gleason College of Engineering custom designed Tai Chi skilled Nao robot primarily to assist older adults in coping with mental and physical disorders as part of her assistive technology research. Unlike the earlier robotic systems, which are confined to a specific environment, the Nao robot can adapt to different environmental settings providing insights into how people interact with robots in such diverse settings.

Zhi Zheng specializes in assistive therapy techniques for elderly people and applies robotics and virtual reality technology in her research that pivots on human-machine intelligence. As part of the larger interdisciplinary team entailing artificial intelligence (AI) and robotics in designing assistive technologies designed to identify and treat mental health disorders, particularly in elderly people. As quoted in the RIT journal, she says, "My major research direction is for individuals with developmental disorders. Many core technologies are transferable to other populations such as older adults with mild cognitive impairment." The Intelligent Interaction Research Lab, which was instrumental in designing the Noa robot, essentially takes funded and technology-mediated initiatives which include gerontology, particularly for chronic conditions like Autism Spectrum Disorder (ASD).

Optimizing the robot for a specific task is a relatively easy job compared to building the system from scratch. The programs that go into the control unit determine the tasks the robots can perform, in this case, it was teaching the robot the Tai Chi moves.  "We don't have to build our robot hardware because there are good commercial platforms available. How it behaves solely depends on how we design the control programs. The central part of our research is how we control the robots to do the cognitive and physical instruction properly" Zheng said. The team could teach Tai Chi to the NAO robot using motion tracking cameras for physical movements and programming for meditative breathing.

For elderly people who exhibit general reluctance towards physical exercise and find it expensive to hire an instructor, Zhen thought, Tai Chi would be a fitting solution. When a feasibility study was held in 2020, her team found that older people found the robot charming, and they could understand its commands with ease. The experiment included 20 participants whose facial expressions were recorded for analyzing the emotional response and were convinced of the feasibility of robot-led sessions. Since then, the project has got a tremendous push to include community-based field studies. Zhen opines, "There is a big difference. Everything in the lab is controlled, and people can be nervous and cautious. That does not really reflect their natural reactions. Now the field is trying to understand and study what if we move the technology out of the engineering building to a community center, for example. People are relaxed, and their reactions will be more natural using new technology. Technology has to be easily controlled by a non-expert—that relates to our interface design. We want our robot to be operated by a leader or a social worker at the community center—because technology is designed to serve people. It has to fit in the community."  Having more than 20 years of experience in teaching and practicing Tai Chi, coupled with her experience in the study of human-robot interactions, she could better combine psychology with human-centred AI applications, a key area RIT research is focussed on. Therefore, if and when an NAO robot teaches Tai Chi, do not hesitate to groove into its graceful moves, alone or in a group.