This thesis focuses on studying the perception of electric wheelchairs through obstacle detection and free space mapping for indoor environments. We compare the performance of Camera and LiDAR sensors for detecting obstacles and present a fusionbased approach for accurate dimension calculation. Our DIHP-RANSAC algorithm maps the obstacle-free space faster and more accurately. Filtering irrelevant points and storing historical ground plane information significantly reduces processing time.Additionally, we detect potholes and provide a pathway based on the wheelchair's dimensions. Our approach accurately detects obstacle-free regions in real-time processing, contributing to implementing perception and localization systems for electric wheelchairs.I would like to thank my committee members, Dr. Amiya Nayak and Dr. Mark Lanthier I would like to express my profound gratitude to my family members, namely, my mother, father, Swati, Daisy, and Shubham, for their unwavering support and incessant motivation throughout the course of my academic pursuits. I would also like to thank my colleagues at Carleton University, Computer Science Department, for their help and support.