75945 20211008114732.0 doi 10.1109/IROS.2017.8206514 sideral 104797 ART-2017-104797 eng Azagra, P. Universidad de Zaragoza (orcid)0000-0002-3567-3294 A multimodal dataset for object model learning from natural human-robot interaction 2017 Access copy available to the general public Unrestricted Learning object models in the wild from natural human interactions is an essential ability for robots to perform general tasks. In this paper we present a robocentric multimodal dataset addressing this key challenge. Our dataset focuses on interactions where the user teaches new objects to the robot in various ways. It contains synchronized recordings of visual (3 cameras) and audio data which provide a challenging evaluation framework for different tasks. Additionally, we present an end-to-end system that learns object models using object patches extracted from the recorded natural interactions. Our proposed pipeline follows these steps: (a) recognizing the interaction type, (b) detecting the object that the interaction is focusing on, and (c) learning the models from the extracted data. Our main contribution lies in the steps towards identifying the target object patches of the images. We demonstrate the advantages of combining language and visual features for the interaction recognition and use multiple views to improve the object modelling. Our experimental results show that our dataset is challenging due to occlusions and domain change with respect to typical object learning frameworks. The performance of common out-of-the-box classifiers trained on our data is low. We demonstrate that our algorithm outperforms such baselines. info:eu-repo/grantAgreement/ES/DGA/T04 info:eu-repo/grantAgreement/EUR/FP7/PCIN-2015-122 info:eu-repo/grantAgreement/EC/FP7/248663/EU/European Coordinated Research on Long-term Challenges in Information and Communication Sciences and Technologies/CHIST- ERA info:eu-repo/grantAgreement/EC/FP7/610878/EU/Semi-Autonomous 3rd Hand/3rd HAND info:eu-repo/grantAgreement/ES/MINECO/DPI2015-65962-R info:eu-repo/grantAgreement/ES/MINECO/DPI2015-67275 info:eu-repo/grantAgreement/ES/MINECO-FEDER/DPI2015-69376-R info:eu-repo/grantAgreement/ES/UZ/JIUZ-2015-TEC-03 info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Golemo, F. Mollard, Y. Lopes, M. Civera, J. Universidad de Zaragoza (orcid)0000-0003-1368-1151 Murillo, A.C. Universidad de Zaragoza (orcid)0000-0002-7580-9037 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 2017, 9-17418366 (2017), 6134-6141 Proc. IEEE/RSJ Int. Conf. Intell. Rob. Syst. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems 2153-0858 426540 http://zaguan.unizar.es/record/75945/files/texto_completo.pdf Postprint 134038 http://zaguan.unizar.es/record/75945/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:75945 articulos driver 2021-10-08-11:37:30 ARTICLE