An Autonomous AI-Vision Robotic System with Mecanum Wheels for Real-Time Object Sorting and Navigation

Badri Mohapatra (AISSMS IOIT, INDIA)
Snehal Nalge (AISSMS IOIT, INDIA)
Tejas Sonale (AISSMS IOIT, INDIA)

International Journal of Informatics, Information System and Computer Engineering (INJIISCOM)
Vol. 6 No. 2 (2025): INJIISCOM: VOLUME 6, ISSUE 2, DECEMBER 2025

This study presents an autonomous robotic system combining AI vision, a Mecanum wheel-based mobile platform, and a servo-driven robotic arm for real-time object sorting and navigation in dynamic environments. The system employs an Arduino-based control framework with multi-sensor fusion (ultrasonic, infrared, and Bluetooth) to achieve obstacle avoidance, line following, and voice-command responsiveness. A novel color-based object classification algorithm is implemented, achieving a sorting accuracy of 94.2% for standardized packages in experimental trials. The Mecanum wheels enable omnidirectional mobility, reducing navigation time by 38% compared to conventional differential drives in constrained spaces. Experimental results demonstrate the system’s efficacy in smart manufacturing and automated logistics, offering a flexible, low-cost framework for scalable robotics