Enhanced Precision Control of a 4-DOF Robotic Arm Using Numerical Code Recognition for Automated Object Handling

This research develops a 4-DOF robotic arm system that utilizes numerical codes for accurate, automated object handling, supporting advancements in sustainable industrial automation aligned with the UN Sustainable Development Goals (SDGs), particularly Industry, Innovation, and Infrastructure (SDG 9). Key contributions include the integration of EasyOCR for reliable code recognition and a control mechanism that enables precise positioning. The robotic system combines a webcam for visual sensing, servo motors for movement, and a gripper for object manipulation. EasyOCR effectively recognizes numerical codes on randomly positioned objects against a uniform background while the microcontroller calculates servo angles to guide the arm accurately to target positions. Testing results show a success rate exceeding 94% for detecting codes 1 to 4, with minor servo angle errors requiring adjustments in arm extension by 30 mm to 50 mm. Positional error analysis reveals an average error of less than 1.5 degrees. Although environmental factors like lighting can influence code visibility, this approach outperforms traditional methods in adaptability and precision. Future research will focus on enhancing code recognition under variable lighting and expanding the system's adaptability for diverse object types, broadening its applications in industries demanding high efficiency.