Autonomous Monocular Navigation for Robotic Vehicles using ESP32-CAM and TOF Sensor with ROS2 Integration

• Milton Miranda Neto UFU https://orcid.org/0000-0002-1568-4201
• Alexandre Cardoso UFU https://orcid.org/0000-0002-2023-9647
• Ígor Andrade Moraes UEMG
• Gerson Flávio Mendes de Lima UFU https://orcid.org/0000-0003-4195-4030

DOI: https://doi.org/10.5753/latinoware.2025.16604

Resumo

This research presents the development and implementation of a cost-effective autonomous monocular navigation framework for robotic vehicles. The proposed system leverages an ESP32-CAM module for real-time object recognition through the YOLO algorithm, complemented by a TOF400C-VL53L1X sensor for precise distance measurements. Our approach addresses the growing need for affordable autonomous navigation solutions by integrating low-power embedded systems with established robotics frameworks. The ESP32-CAM processes visual data and transmits object detection information, including classification and distance metrics, to a Raspberry Pi 5 controller running ROS2. Experimental validation demonstrates the system’s capability to achieve reliable object detection with 78.8% precision at 3.22 FPS, while maintaining sub-2cm distance measurement accuracy across a 4-meter operational range. The complete system exhibits a 92% navigation success rate across diverse environmental scenarios, validating its practical applicability for autonomous robotic platforms.

Palavras-chave: Autonomous Navigation, Computer Vision, Embedded Systems, YOLO, ROS2, Robotics

Referências

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016, pp. 779–788.

STMicroelectronics, VL53L1X: Time-of-Flight long-distance ranging sensor based on ST’s FlightSense technology, Geneva, Switzerland, August 2024, datasheet Rev. 4. [Online]. Available: [link]

Espressif Systems, ESP32-CAM Datasheet, Shanghai, China, 2020, version 1.6. [Online]. Available: [link] datasheet en.pdf

Raspberry Pi Foundation, “Raspberry pi 5,” Cambridge, UK, 2023. [Online]. Available: [link]

S. Macenski, F. Martín, R. White, and J. Clavero, “The marathon 2: A navigation system,” in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS ). Las Vegas, NV, USA: IEEE, 2020, pp. 2718–2725.

micro-ROS Project, “micro-ros: Ros 2 on microcontrollers,” 2024. [Online]. Available: [link]