The e-Bike motor assembly: Towards advanced robotic manipulation for flexible manufacturing

Leonel Rozo, Andras G. Kupcsik, Philipp Schillinger, Meng Guo, Robert Krug, Niels van Duijkeren, Markus Spies, Patrick Kesper, Sabrina Hoppe, Hanna Ziesche, Mathias Bürger, Kai Oliver Arras

Abstract: Highlights•We show the potential of advanced learning methods on the e-Bike motor assembly.•Our framework includes a self-supervised method to teach perception systems onsite.•We exploit general representations of object-centric motion and force-aware skills.•We provide a sequencing method that exploits a human-designed plan for complex tasks.•We test our framework in the e-Bike motor assembly and the box packing for logistics.