Published Paper Details:

ROBOTIC wheelchairs are made to increase the mobility of the elderly or crippled, hence enhancing their quality of life. In order to do this, autonomous navigation has undergone extensive research and evolved into a crucial feature for robotic wheelchairs. Identifying regions and anomalies in photos pixel-by-pixel is referred to as segmenting drivable areas and road abnormalities. It plays a key role in autonomous navigation. Robotic wheelchairs might bump or possibly roll over while travelling over road anomalies without properly separating drivable sections and road oddities, which could harm human riders. In this research, we propose a self-supervised learning strategy to describe the solution to this problem for the purpose of segmenting drivable areas and road anomalies. The proposed method can automatically generate segmentation labels for drivable areas and road anomalies. Then, we train RGB-D data based semantic segmentation neural networks and get predicted labels. We firstly develop a pipeline named Self- Supervised Label Generator (SSLG) to automatically label drivable areas and road anomalies. Then, we use the segmentation labels generated by the SSLG to train several RGB-D data-based semantic segmentation neural networks.