Autonomous Indoor Navigation for Wheelchairs using Signboards

Abstract

Several studies have shown that people with disabilities benefit substantially from access to a means of independent mobility. While the requirements of many individuals with disabilities can be satisfied with manual or powered wheelchairs, a segment of the disabled community finds it difficult or impossible to use wheelchairs independently. This paper presents an autonomous indoor navigation system for wheelchairs based on sign board recognition. The system uses a deep learning model to detect signboards from surroundings and Azure Text Analytics API is used to extract the text from the signboard images. The system runs on a Raspberry Pi minicomputer and can be installed on any powered wheelchair. Experimental results and comparisons prove the efficiency of the proposed system.