Designing wearable obstacle detection and avoidance technology for the visually-impaired
Assistive technology for the visually impaired is developed regularly, but many of these solutions are either bulky, difficult to maneuver, or expensive. Visually impaired people need a way to avoid obstacles and move around in safety. Due to limited visibility, the person cannot tell with confidence if there is an obstacle approaching them. This project proposes a wearable obstacle and avoidance system for the visually impaired housed on an embedded microcontroller. The system consists of both RFID and sonar localization techniques for static and dynamic obstacles. Both approaches work well in terms of obstacle detection and avoidance, but further research is needed to integrate the processes to complement each other fully. A simultaneous localization and mapping (SLAM) approach, though computationally expensive, is also considered. The results show that it is possible to combine both RFID and sonar localization; however, this approach might be better suited for a less constrained system.
Capstone Project submitted to the Department of Engineering, Ashesi University in partial fulfillment of the requirements for the award of Bachelor of Science degree in Computer Engineering, May 2021