Object Detection and Navigation Strategy for Obstacle Avoidance Applied to Autonomous Wheel Chair Driving

Abstract

The primary aim of this study is to develop machine learning or deep-learning aided procedures that enhances the capability of a commercial non-autonomous wheelchair towards autonomy. The paper addresses the computer vision work for obstacle detection applied to an autonomous wheelchair operation. The computer vision tasks including the depth image classification are accommodated in a small form factored and resource constraint computers such as Raspberry Pie and Google Coral. The tasks and strategies also include classifying the images using a pretrained model (TensorFlow lite), detecting and measure the degree of obstacle avoidance by pairing RGB image classification with depth images. The objective has been further extended to develop a simulation platform for autonomous wheelchair driving where navigation and path mapping construction algorithm evaluations are visually offered using MATLAB®.