{"ID":2873172,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.08095","arxiv_id":"2509.08095","title":"Real-Time Obstacle Avoidance for a Mobile Robot Using CNN-Based Sensor Fusion","abstract":"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 $0.58 \\times 10^{-3}$ 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 $21.68 \\times 10^{-3}$ rad/s, close to the $21.42 \\times 10^{-3}$ 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.","short_abstract":"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-...","url_abs":"https://arxiv.org/abs/2509.08095","url_pdf":"https://arxiv.org/pdf/2509.08095v2","authors":"[\"Lamiaa H. Zain\"]","published":"2025-09-09T19:05:37Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}