RICAIP Training: Automated Assembly Picking System for Cluttered Environments with Live Collision-Free Trajectory Planning

RICAIP and ZeMA | Zentrum für Mechatronik und Automatisierungstechnik (Center for Mechatronics and Automation Technology GmbH) in Saarbrücken, Germany, are pleased to invite you to an online RICAIP Training on assembly-picking system.

This RICAIP event is solely for the research teams of RICAIP Partners (CIIRC CTU, CEITEC BUT, ZeMA, DFKI and VSB TUO).

It requires sequence planning, object detection, pose estimation, and trajectory planning. Given a general CAD model, the existing ASAP (Automated Sequence Planning for complex Robotic Assembly with physical Feasibility) method generates a physically feasible assembly sequence. We have further optimised ASAP to address common structural challenges in LEGO assemblies. Then, we address cluttered-bin detection challenges using a voting-based strategy that reduces false positives across varying point cloud scales.

Our image processing method combines best-fit and iterative closest point (ICP) techniques, enabling robust millimeter-level 3D localisation. Gripping points are identified for collision-free trajectories using the k–dimensional Tree (K-d Tree) and rapidly-exploring random trees (RRT) algorithms, and verified via a digital twin before execution. The system is validated in a Lego assembly case and benchmarked against industrial tools.

Xiaomei Xu, M.Sc.RWTH

Research assistant at

Short bio

I have been working as a research assistant at ZeMA in the Robotics group since April 2020. In 2019, I completed my master’s degree in Mechanical Automation Engineering from RWTH Aachen University and worked during my thesis on the iCellFactory project at the WZL Machine Tool Laboratory to focus on industrial robot path planning and digital twin simulation.

During my studies, I completed various internships, e.g. at the VW Academy Hannover where I supported the set-up and roll-out of the VWN Campus Digitalization and supervised workshops as well as at the Jülich Forschungzentrum in the field of metal stressing and shaping.

My research interests include the application of 3D camera technology in the industrial field to improve object recognition and 3D pose estimation under the bin-picking challenge. A fully assembled product is randomly scanned using a 3D camera, resulting in the reconstruction of its CAD model. Extending beyond bin picking systems, I continue to advance research on self-developed object detection tools and collision-free trajectory planning, supported by digital twin technology in live processes. By integrating an autonomous bin picking system with automated assembly sequence planning, this framework evolves into a fully functional assembly picking system