Teaching a Robot the Semantics of Assembly Tasks

• Published in: IEEE transactions on systems, man, and cybernetics. Systems man, and cybernetics. Systems, 2018-05, Vol.48 (5), p.670-692
• Main Authors: Savarimuthu, Thiusius Rajeeth, Buch, Anders Glent, Schlette, Christian, Wantia, Nils, Robmann, Jurgen, Martinez, David, Alenya, Guillem, Torras, Carme, Ude, Ales, Nemec, Bojan, Kramberger, Aljaz, Worgotter, Florentin, Aksoy, Eren Erdal, Papon, Jeremie, Haller, Simon, Piater, Justus, Kruger, Norbert
• Format: Article
• Language: English
• Subjects: artificial intelligence; Benchmark testing; Classificació INSPEC; Context; Cybernetics; Data structures; Informàtica; Intel·ligència artificial; Learning; learning (artificial intelligence); Learning by demonstration (LbD); manipulators; object recognition; Planning; Representations; Robot sensing systems; robotic assembly; Semantics; Trajectory; vision; Àrees temàtiques de la UPC
• ISSN: 2168-2216; 2168-2232
• DOI: 10.1109/TSMC.2016.2635479

We present a three-level cognitive system in a learning by demonstration context. The system allows for learning and transfer on the sensorimotor level as well as the planning level. The fundamentally different data structures associated with these two levels are connected by an efficient mid-level representation based on so-called "semantic event chains." We describe details of the representations and quantify the effect of the associated learning procedures for each level under different amounts of noise. Moreover, we demonstrate the performance of the overall system by three demonstrations that have been performed at a project review. The described system has a technical readiness level (TRL) of 4, which in an ongoing follow-up project will be raised to TRL 6.