Speech-Controlled Robot Enabling Cognitive Training and Stimulation in Dementia Prevention for Severely Disabled People

Abstract

The current German medical S3-guideline on dementia recommends the use of cognitive training and stimulation, e.g. through shared games, for mild cognitive impairment and mild dementia. The use of cobots, which allow direct human-robot collaboration, enables people with paralyzed upper limbs to actively participate in social activities. This research presents a novel approach through the development of a voice-controlled board game specifically tailored to the inclusion needs of people with severe disabilities. The human voice commands recorded via USB microphones are digitally filtered. Speech recognition of the control commands is performed using a Convolutional Neural Network (CNN) based on the VGG- 16 architecture. The robot´s activity is controlled utilizing the ROS 2 robot operating system. A portable table-based complete system with a 3D-printed Tic-Tac-Toe playing field and robot assistant for severely disabled paralyzed people has been developed. The robot control system employs a pick-and-place mechanism, seamlessly integrating with speech recognition to enhance gameplay interaction. The CNN model achieves an impressive accuracy rate of 97%, ensuring reliable speech recognition performance throughout gameplay. The targeted integration of robotic technologies and artificial intelligence opens new avenues in the prevention of mental illness, care support and inclusion of older and disabled people.

Keywords

• healthcare-robotics
• vulnerable disabled people
• speech-control
• convolutional neural networks (cnn)
• dementia prevention