Privacy concerns can potentially make camera-based object classification unsuitable for robot navigation. To address this problem, we propose a novel object classification system using only a 2D-LiDAR sensor on mobile robots. The proposed system enables semantic understanding of the environment by applying the YOLOv8n model to classify objects such as tables, chairs, cupboards, walls, and door frames using only data captured by a 2D-LiDAR sensor. The experimental results show that the resulting YOLOv8n model achieved an accuracy of 83.7% in real-time classification running on Raspberry Pi 5, despite having a lower accuracy when classifying door-frames and walls. This validates our proposed approach as a privacy-friendly alternative to camera-based methods and illustrates that it can run on small computers onboard mobile robots.
DOCUMENT
In mobile robotics, LASER scanners have a wide spectrum of indoor and outdoor applications, both in structured and unstructured environments, due to their accuracy and precision. Most works that use this sensor have their own data representation and their own case-specific modeling strategies, and no common formalism is adopted. To address this issue, this manuscript presents an analytical approach for the identification and localization of objects using 2D LiDARs. Our main contribution lies in formally defining LASER sensor measurements and their representation, the identification of objects, their main properties, and their location in a scene. We validate our proposal with experiments in generic semi-structured environments common in autonomous navigation, and we demonstrate its feasibility in multiple object detection and identification, strictly following its analytical representation. Finally, our proposal further encourages and facilitates the design, modeling, and implementation of other applications that use LASER scanners as a distance sensor.
DOCUMENT
