Real-Time Path Correction for Assembly Line Robots Using Sensor Fusion

Abstract

Industry 4.0 has transformed modern manufacturing, where industrial robots must operate continuously under dynamic and uncertain conditions such as vibrations, part tolerances, tool wear, thermal effects, and human–robot interaction. These disturbances can cause deviations between planned and executed paths, leading to assembly errors and reduced product quality. Therefore, real-time path correction has become essential for adaptive and high-precision robotic operations. Traditional robots rely on offline programming and open-loop control, which perform well in structured environments but struggle with real-time uncertainties like moving objects, conveyor variations, and sensor noise. Closed-loop systems enhanced with real-time sensory feedback address these challenges; however, single-sensor approaches are insufficient. Vision sensors provide rich spatial data but suffer from latency and lighting sensitivity, force–torque sensors offer precise contact feedback without global context, and inertial sensors are fast but prone to drift. This paper proposes a sensor-fusion-based framework for real-time path correction in assembly-line robots. Vision, force–torque, and inertial sensors are integrated using a Kalman filter for accurate state estimation, combined with a Model Predictive Control (MPC) strategy to generate real-time corrective motion commands. The system is validated through simulation and experimental pick-and-place and precision insertion tasks. Results demonstrate significant improvements in positional accuracy, force control, and task performance compared to single-sensor and open-loop methods, achieving sub-millimeter path correction accuracy and robustness to object movement and conveyor speed variations. The proposed approach enhances the reliability and adaptability of robotic assembly systems in smart manufacturing environments.