Integrating low-cost vision for autonomous tracking in assistive robots

Abstract

This study presents the implementation of a real-time tracking system for the ARMOS TurtleBot, a robot designed for assistive applications in domestic environments. The system integrates two OmniVision 7670 (OV7670) camera modules positioned 7 cm apart to emulate human-like stereoscopic vision, enabling depth perception and three-dimensional object tracking. An embedded system platform 32-bit (ESP32) microcontroller captures and processes images from both cameras, calculates disparities, and transmits data to a Raspberry Pi via WebSockets. The Raspberry Pi, equipped with robot operating system (ROS), performs further analysis using open computer vision (OpenCV) and visualizes results in real-time with ROS visualization (RViz), allowing the robot to autonomously track moving objects such as humans or pets. Key optimizations, including image resolution reduction and data filtering, were implemented to enhance processing efficiency within the hardware constraints. The proposed approach demonstrates the feasibility of low-cost, real-time object tracking in assistive robotics, highlighting its potential for applications that require humanrobot interaction in dynamic indoor settings. This work contributes to the field by providing a practical solution for integrating stereoscopic vision and real-time decision-making capabilities into small-scale robots, promoting further research and development in affordable robotic assistance systems.