A System for Robotic Extraction of Fasteners

Automating the extraction of mechanical fasteners from end-of-life (EOL) electronic waste is challenging due to unpredictable conditions and unknown fastener locations relative to robotic coordinates. This study develops a system for extracting cross-recessed screws using a Deep Convolutional Neural Network (DCNN) for screw detection, integrated with industrial robot simulation software. The simulation models the tooling, camera, environment, and robot kinematics, enabling real-time control and feedback between the robot and the simulation environment. The system, tested on a robotic platform with custom tooling, including force and torque sensors, aimed to optimize fastener removal. Key performance indicators included the speed and success rate of screw extraction, with success rates ranging from 78 to 89% on the first pass and 100% on the second. The system uses a state-based program design for fastener extraction, with real-time control via a web-socket interface. Despite its potential, the system faces limitations, such as longer cycle times, with single fastener extraction taking over 30 s. These challenges can be mitigated by refining the tooling, DCNN model, and control logic for improved efficiency.