Scientific African (Mar 2023)
Design and prototyping of a robotic hand for sign language using locally-sourced materials
Abstract
People living with disability constitute a significant percentage of the world population. For many people with disabilities, assistance and support are prerequisites for participating in societal activities. This research work developed a hardware prototype of a robotic hand forfor sign language communication with persons living with hard-of-hearing disabilities (deaf and/or dumb). The prototype has three basic modules: the input unit, the control unit, and the robotic hand. The input unit is designed as an Android-based mobile application with speech recognition capabilities while the control unit is ATMEGA 2560 microcontroller board. The robotic hand is constructed using locally available materials (bathroom Slippers, expandable rubber, straw pipe, and tiny rope) together with three servo motors and is designed to look and perform movements similar to a human hand. The prototype was evaluated quantitatively in terms of empirical accuracy and response time. It was also evaluated qualitatively by thirty-five (35) users which included fifteen (15) experience ASL users, eighteen (18) non-experience ASL users, and two (2) ASL experts, who completed questionnaires to rate the prototype on a 5-point Likert scale in terms of five parameters: functionality, reliability, ease of use, efficiency, and portability. An accuracy of 78.43% with an average response time of 2 s was obtained from empirical experiments. Statistical analysis of user responses showed that 97%, 68%, 77%, 80%, and 83% of users rated the system as above average for functionality, reliability, ease of use, efficiency, and portability, respectively. The robotic hand effectively communicates American Sign Language which includes English Alphabets, numbers (1–9), and some selected common words, which can be demonstrated with a single hand for hard of hearing persons. To the best of our knowledge, this work is the first ASL robotic hand that is based on locally sourced cost-effective materials, and we build on flaws from existing literature, most of which are either template-based, not real-time, or expensive. In terms of future work, the prototype can be improved by extending the single robotic hand to a fully robotic body with two hands.
