Learning robot assembly skills from single demonstrations improves flexibility
State-of-the-Art in Learning-by-Demonstration with Passive Observation for Industrial Assembly Automation
Robotics
Summary
Teaching robots how to assemble products by watching just one example helps factories quickly switch between different product versions. The authors looked at studies where robots learn by observing without extra help, focusing on how they understand what they see and use that knowledge on new tasks. They found that paying attention to objects rather than the whole scene helps robots reuse what they learned with less retraining. This can make manufacturing more adaptable and efficient.
Learning-by-Demonstrationrobot programmingpassive observationone-shot learningindustrial assemblyperception architectureobject-centric perceptiongeneralizationhigh-mix low-volume manufacturingrobot skill transfer
Authors
David Koetter, Oliver Petrovic, Christian Brecher
Abstract
Learning-by-Demonstration (LbD) enables intuitive robot programming by capturing expert skills, which is crucial for agility in high-mix, low- volume manufacturing. This systematic literature review analyzes passive LbD for industrial assembly processes, focusing on the perception architecture and the generalization of the perceived demonstration. We specifically investigate one-shot approaches where only a single demonstration is required. The review evaluates how systems adapt to new assemblies using this limited data. We identify a shift towards object-centric perception, allowing learned primitives to be transferred to new product variants with minimal training.