TITLE:
Vision-Guided Robotic Arm for Tomato Quality Classification and Sorting
AUTHORS:
Shrawan Thakur, Sudan Jha, Pranaya Mulepati
KEYWORDS:
Index Terms-IoT, AI, ML, Computer Vision, Edge Computing, Agricultural Automation, Tomato Harvesting, Deep Learning
JOURNAL NAME:
Advances in Artificial Intelligence and Robotics Research,
Vol.1 No.2,
November
18,
2025
ABSTRACT: The DOFBOT Robotic Hand, powered by the NVIDIA Jetson Nano processor, represents a cutting-edge fusion of computer vision and robotic automation for precision agriculture. This research presents an advanced system capable of distinguishing between ripe (red) and unripe (green) tomatoes using sophisticated image processing algorithms and deep learning techniques. The system integrates ImageNet and ResNet pre-trained models for enhanced color recognition capabilities, achieving superior response times compared to traditional laptop-based processing. The robotic arm successfully identifies, plucks, and collects ripe tomatoes while maintaining high accuracy rates. This study demonstrates the effectiveness of edge computing in agricultural automation, with the Jetson Nano providing significantly improved response times over conventional cloud-based processing systems. The integration of state-of-the-art computer vision algorithms with precision robotics marks a significant advancement in automated agricultural harvesting systems.