Controlled Robotic Arm With Real Time Object Detection

Abstract

The advancement of artificial intelligence and computer vision has enabled robots to perceive and interact with their surroundings more intelligently. This project presents the design and implementation of a controlled robotic arm integrated with real-time object detection. The system employs a camera module to continuously capture visual input, which is processed using a deep learning– based object detection algorithm such as YOLOv8. Detected objects are identified, classified, and mapped to corresponding robotic actions through a microcontroller interface. The robotic arm responds autonomously by tracking, picking, or sorting objects based on their type and spatial location. The combination of computer vision, machine learning, and embedded control allows precise and efficient task execution without manual supervision. The proposed system demonstrates improved accuracy, responsiveness, and adaptability for real-world automation applications, including manufacturing, warehouse sorting, and assistive robotics. Overall, this work highlights how integrating intelligent vision systems with robotic control can enhance autonomy, reduce human effort, and increase operational reliability.