# Real-Time Obstacle Avoidance for a Mobile Robot Using CNN-Based Sensor Fusion

arXiv: https://arxiv.org/abs/2509.08095 · HTML: https://mlsanity.com/paper/2509.08095/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 5 of 5)

- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey](https://mlsanity.com/paper/2011.13112/) (2020)
- [A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation](https://mlsanity.com/paper/1803.04119/) (2018)
- [Deep Learning Based Motion Planning For Autonomous Vehicle Using Spatiotemporal LSTM Network](https://mlsanity.com/paper/1903.01712/) (2019)
- [Imitation Learning for Obstacle Avoidance Using End-to-End CNN-Based Sensor Fusion](https://mlsanity.com/paper/2507.08112/) (2025)

## Abstract (arXiv)

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.