Related Experiment Video
Updated: Oct 7, 2025
11:18
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
10.5K
Sensor Data Fusion for a Mobile Robot Using Neural Networks.
Andres J Barreto-Cubero1, Alfonso Gómez-Espinosa1, Jesús Arturo Escobedo Cabello1
1Tecnologico de Monterrey, Escuela de Ingenieria y Ciencias, Av. Epigmenio González 500, Fracc. San Pablo, Querétaro 76130, Mexico.
Sensors (Basel, Switzerland)
|January 11, 2022
Summary
This study introduces an improved LiDAR system using sensor fusion for mobile robots. It accurately detects glass and other obstacles, enhancing navigation safety and efficiency in indoor environments.
Area of Science:
- Robotics
- Artificial Intelligence
- Sensor Fusion
Background:
- Mobile robots require accurate mapping for navigation.
- Detecting diverse materials, like glass, necessitates multi-sensor approaches.
- Traditional 2D LiDAR struggles with certain obstacles.
Purpose of the Study:
- To develop a robust sensor fusion scheme for enhanced mobile robot perception.
- To improve the detection of glass and other challenging obstacles.
- To generate accurate 2D occupancy grid maps (OGM) for improved navigation.
Main Methods:
- Implemented a tri-sensor setup: RealSense Stereo camera, 2D 360° LiDAR, and Ultrasonic Sensors.
- Utilized an artificial neural network for data fusion.
- Applied preprocessing: outlier filtering, 3D pointcloud projection, and distance data adjustment.
Main Results:
- Achieved accurate distance-to-obstacle readings by integrating multi-sensor data.
- Generated a 2D Occupancy Grid Map (OGM) incorporating all sensor information.
- Demonstrated effective detection of glass and other obstacles with an RMSE of 3 cm.
Conclusions:
- The proposed sensor fusion strategy significantly enhances obstacle detection capabilities for mobile robots.
- The artificial neural network effectively fuses data from multiple sensors for improved mapping.
- This approach offers a more reliable navigation solution, especially in complex indoor environments.
