AI-Enabled Elderly Care Robot

Abstract

The increasing average human age and a growing number of old age population over the globe have emerged the need for automation in the health care domain. Eventually, health care robots will contribute to manage the workload of the care providers in the future health care domain. Elderly people face a major challenge to identify and pronounce names of daily use objects and different family and friends due to dementia-related issues. One of the many tasks by AI-Enabled elderly care humanoid robots will be communication with such patients. They will aid them to remember objects and persons they find difficult to identify and recognize due to dementia. This study has investigated the potential of the JD humanoid robot for object identification in such a scenario. The study has presented a prototype AI-Enabled elderly care robot that can aid elder persons to identify different objects. The robot is trained on ImageNet data set for object identification. Further, a personalized data set comprising of faces of different persons labeled by names of family and friends are also used to train robots for family recognition aid. The JD Humanoid robot captures an image of an object/person and also tracks it as the object/face moves. It identifies input images and outputs in audio format the name of the object/person to guide the elderly person. The third feature of the robot is the notifications of daily routine tasks for elder people like reminders for prayer, exercise walk, and medicine intake. Testing results have shown an object and person identification with 95% accuracy.