NAOMOBBY, development of a computer vision and robotics-based software tool to support rehabilitation in upper limb physical therapies

Abstract

Nowadays, 21% of Colombian population, and the 35% of the population in Cauca Valley have limited movement of body, arms, hands or legs. Then, the quality of life of these people is highly affected, since they have limitations in daily living activities. Physical rehabilitation therapies allow the restoration of movement and maximum functional capacity in people. Successful physical therapies depend on empathy and motivation with the rehabilitation process (RP), then the more empathy of patients with the RP, the more patient willingness regarding the rehabilitation therapy. Motivation is crucial in rehabilitation, and it is used as a fundamental rehabilitation out-come. This work has the aim to present the software tool called NAOMOBBY to support physical rehabilitation therapies of shoulder, elbow and wrist joints. NAOMOBBY includes a GUI for therapist, a Kinect sensor and an interactive humanoid robot NAO to increase the patient willingness regarding the RP. NAOMOBBY includes the following modules: configuration/management, movement reproduction, and results report using GAS methodology. NAOMOBBY was tested using quantitative and field tests. Quantitative tests measure the error in the Kinect sensor of the NAO robot joint motions to bring users a suitable feedback. Quantitative results were obtained using three basic functional motions. The mean square error for these three motions were 0,373%, 0,096%, and 1,129% respectively. Field tests were conducted at the SURGIR neuro-rehabilitation center using 3 physiotherapists who considered the NAOMOBBY software tool as a novel, easy to use, and that encourage patients to perform the physical therapy.