000075945 001__ 75945
000075945 005__ 20211008114732.0
000075945 0247_ $$2doi$$a10.1109/IROS.2017.8206514
000075945 0248_ $$2sideral$$a104797
000075945 037__ $$aART-2017-104797
000075945 041__ $$aeng
000075945 100__ $$0(orcid)0000-0002-3567-3294$$aAzagra, P.$$uUniversidad de Zaragoza
000075945 245__ $$aA multimodal dataset for object model learning from natural human-robot interaction
000075945 260__ $$c2017
000075945 5060_ $$aAccess copy available to the general public$$fUnrestricted
000075945 5203_ $$aLearning 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.
000075945 536__ $$9info:eu-repo/grantAgreement/ES/UZ/JIUZ-2015-TEC-03$$9info:eu-repo/grantAgreement/ES/MINECO-FEDER/DPI2015-69376-R$$9info:eu-repo/grantAgreement/ES/MINECO/DPI2015-67275$$9info:eu-repo/grantAgreement/ES/MINECO/DPI2015-65962-R$$9info:eu-repo/grantAgreement/EC/FP7/610878/EU/Semi-Autonomous 3rd Hand/3rd HAND$$9info:eu-repo/grantAgreement/EC/FP7/248663/EU/European Coordinated Research on Long-term Challenges in Information and Communication Sciences and Technologies/CHIST- ERA$$9info:eu-repo/grantAgreement/EUR/FP7/PCIN-2015-122$$9info:eu-repo/grantAgreement/ES/DGA/T04
000075945 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000075945 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000075945 700__ $$aGolemo, F.
000075945 700__ $$aMollard, Y.
000075945 700__ $$aLopes, M.
000075945 700__ $$0(orcid)0000-0003-1368-1151$$aCivera, J.$$uUniversidad de Zaragoza
000075945 700__ $$0(orcid)0000-0002-7580-9037$$aMurillo, A.C.$$uUniversidad de Zaragoza
000075945 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000075945 773__ $$g2017, 9-17418366 (2017), 6134-6141$$pProc. IEEE/RSJ Int. Conf. Intell. Rob. Syst.$$tProceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems$$x2153-0858
000075945 8564_ $$s426540$$uhttps://zaguan.unizar.es/record/75945/files/texto_completo.pdf$$yPostprint
000075945 8564_ $$s134038$$uhttps://zaguan.unizar.es/record/75945/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000075945 909CO $$ooai:zaguan.unizar.es:75945$$particulos$$pdriver
000075945 951__ $$a2021-10-08-11:37:30
000075945 980__ $$aARTICLE