Obstacle avoidance is a critical component of the navigation stack required for mobile robots to operate effectively in complex and unknown environments. In this research, three end-to-end Convolutional Neural Networks (CNNs) were trained and evaluated offline and deployed on a differential-drive mobile robot for real-time obstacle avoidance to generate low-level steering commands from synchronized color and depth images acquired by an Intel RealSense D415 RGB-D camera in diverse environments. Offline evaluation showed that the NetConEmb model achieved the best performance with a notably low MedAE of 0.58×10−3 rad/s. In comparison, the lighter NetEmb architecture, which reduces the number of trainable parameters by approximately 25\% and converges faster, produced comparable results with an RMSE of 21.68×10−3 rad/s, close to the 21.42×10−3 rad/s obtained by NetConEmb. Real-time navigation further confirmed NetConEmb's robustness, achieving a 100\% success rate in both known and unknown environments, while NetEmb and NetGated succeeded only in navigating the known environment.
@article{arxiv.2509.08095,
title = {Real-Time Obstacle Avoidance for a Mobile Robot Using CNN-Based Sensor Fusion},
author = {Lamiaa H. Zain},
journal= {arXiv preprint arXiv:2509.08095},
year = {2025}
}