Print Email Facebook Twitter Learning from Few Demonstrations with Frame-Weighted Motion Generation Title Learning from Few Demonstrations with Frame-Weighted Motion Generation Author Sun, Jianyong (TU Delft Mechanical, Maritime and Materials Engineering) Contributor Kober, J. (mentor) Zhu, J. (mentor) Gienger, Michael (mentor) Peternel, L. (graduation committee) Stienen, A.H.A. (graduation committee) Degree granting institution Delft University of Technology Programme Mechanical Engineering | Vehicle Engineering | Cognitive Robotics Date 2022-12-22 Abstract Learning from Demonstration (LfD) aims to learn versatile skills from human demonstrations. The field has been gaining popularity since it facilitates transferring knowledge to robots without requiring much expert knowledge. During task executions, the robot motion is usually influenced by constraints imposed by environments. In light of this, task-parameterized (TP) learning encodes relevant contextual information in reference frames, enabling better skill generalization to new situations. However, most TP learning algorithms require multiple demonstrations in various environment conditions to ensure sufficient statistics for a meaningful model. It is not a trivial task for robot users to create different situations and perform demonstrations under all of them. Therefore, this paper presents a novel concept to learn motion policy from few demonstrations through explicitly solving reference frame weights along the task trajectory. Experimental results in both simulation and real robotic environments validate our approach. Subject Learning from DemonstrationFew DemonstrationsFrame WeightsData Augmentation To reference this document use: http://resolver.tudelft.nl/uuid:88639dbd-c0c3-44a9-a4fd-f92548e79bd0 Part of collection Student theses Document type master thesis Rights © 2022 Jianyong Sun Files PDF Thesis_Jianyong.pdf 10.73 MB Close viewer /islandora/object/uuid:88639dbd-c0c3-44a9-a4fd-f92548e79bd0/datastream/OBJ/view