Print Email Facebook Twitter Imitrob Title Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators Author Sedlar, Jiri (Czech Technical University) Stepanova, Karla (Czech Technical University) Skoviera, Radoslav (Czech Technical University) Behrens, Jan K. (Czech Technical University) Tuna, Matus (Comenius University) Sejnova, Gabriela (Czech Technical University) Sivic, Josef (Czech Technical University) Babuska, R. (TU Delft Learning & Autonomous Control; Czech Technical University) Date 2023 Abstract This letter introduces a dataset for training and evaluating methods for 6D pose estimation of hand-held tools in task demonstrations captured by a standard RGB camera. Despite the significant progress of 6D pose estimation methods, their performance is usually limited for heavily occluded objects, which is a common case in imitation learning, where the object is typically partially occluded by the manipulating hand. Currently, there is a lack of datasets that would enable the development of robust 6D pose estimation methods for these conditions. To overcome this problem, we collect a new dataset (Imitrob) aimed at 6D pose estimation in imitation learning and other applications where a human holds a tool and performs a task. The dataset contains image sequences of nine different tools and twelve manipulation tasks with two camera viewpoints, four human subjects, and left/right hand. Each image is accompanied by an accurate ground truth measurement of the 6D object pose obtained by the HTC Vive motion tracking device. The use of the dataset is demonstrated by training and evaluating a recent 6D object pose estimation method (DOPE) in various setups. Subject 6D object pose estimationcomputer vision for automationLearning from demonstrationperception for grasping and manipulation To reference this document use: http://resolver.tudelft.nl/uuid:4140665f-7b97-4d7f-86f7-3b46b0a767d7 DOI https://doi.org/10.1109/LRA.2023.3259735 Embargo date 2023-09-20 ISSN 2377-3766 Source IEEE Robotics and Automation Letters, 8 (5), 2788-2795 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2023 Jiri Sedlar, Karla Stepanova, Radoslav Skoviera, Jan K. Behrens, Matus Tuna, Gabriela Sejnova, Josef Sivic, R. Babuska Files PDF Imitrob_Imitation_Learnin ... mators.pdf 3.92 MB Close viewer /islandora/object/uuid:4140665f-7b97-4d7f-86f7-3b46b0a767d7/datastream/OBJ/view