Sensor Data Fusion for a Mobile Robot Using Neural Networks

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 1; p. 305
• Main Authors: Barreto-Cubero, Andres J., Gómez-Espinosa, Alfonso, Escobedo Cabello, Jesús Arturo, Cuan-Urquizo, Enrique, Cruz-Ramírez, Sergio R.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 31.12.2021; MDPI
• Subjects: Algorithms; artificial neural network; Control algorithms; Digital cameras; Experiments; Fault diagnosis; Fault tolerance; Fuzzy logic; improved LiDAR; Infrastructure; Kalman filters; Lasers; Localization; mobile robot; Neural networks; Neural Networks, Computer; occupancy grid map; Robotics; Robots; sensor data fusion; Sensors; Values; artificial neural network; improved LiDAR; mobile robot; sensor data fusion; occupancy grid map
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22010305

Mobile robots must be capable to obtain an accurate map of their surroundings to move within it. To detect different materials that might be undetectable to one sensor but not others it is necessary to construct at least a two-sensor fusion scheme. With this, it is possible to generate a 2D occupancy map in which glass obstacles are identified. An artificial neural network is used to fuse data from a tri-sensor (RealSense Stereo camera, 2D 360° LiDAR, and Ultrasonic Sensors) setup capable of detecting glass and other materials typically found in indoor environments that may or may not be visible to traditional 2D LiDAR sensors, hence the expression improved LiDAR. A preprocessing scheme is implemented to filter all the outliers, project a 3D pointcloud to a 2D plane and adjust distance data. With a Neural Network as a data fusion algorithm, we integrate all the information into a single, more accurate distance-to-obstacle reading to finally generate a 2D Occupancy Grid Map (OGM) that considers all sensors information. The Robotis Turtlebot3 Waffle Pi robot is used as the experimental platform to conduct experiments given the different fusion strategies. Test results show that with such a fusion algorithm, it is possible to detect glass and other obstacles with an estimated root-mean-square error (RMSE) of 3 cm with multiple fusion strategies.