Robotic Assembly
Robotic assembly focuses on automating the process of joining multiple parts to create a complete product, aiming for increased efficiency, precision, and adaptability in manufacturing and other domains. Current research emphasizes developing robust and generalizable assembly strategies using various machine learning approaches, including reinforcement learning, imitation learning, and large language models to generate assembly sequences and control robot actions, often incorporating visual and tactile feedback. These advancements hold significant potential for improving manufacturing processes, enabling flexible automation in diverse settings, and advancing human-robot collaboration in complex assembly tasks.
Papers
Deep Learning-Based Connector Detection for Robotized Assembly of Automotive Wire Harnesses
Hao Wang, Björn Johansson
Overview of Computer Vision Techniques in Robotized Wire Harness Assembly: Current State and Future Opportunities
Hao Wang, Omkar Salunkhe, Walter Quadrini, Dan Lämkull, Fredrik Ore, Björn Johansson, Johan Stahre