TU Darmstadt / ULB / TUprints

Online Learning of an Open-Ended Skill Library for Collaborative Tasks

Koert, Dorothea ; Trick, Susanne ; Ewerton, Marco ; Lutter, Michael ; Peters, Jan (2022)
Online Learning of an Open-Ended Skill Library for Collaborative Tasks.
International Conference on Humanoid Robots (Humanoids). Beijing, China (06.-09.11.2018)
doi: 10.26083/tuprints-00020545
Conference or Workshop Item, Secondary publication, Postprint

[img] Text
Copyright Information: In Copyright.

Download (1MB)
Item Type: Conference or Workshop Item
Type of entry: Secondary publication
Title: Online Learning of an Open-Ended Skill Library for Collaborative Tasks
Language: English
Date: 2022
Place of Publication: Darmstadt
Publisher: IEEE
Book Title: 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)
Collation: 8 Seiten
Event Title: International Conference on Humanoid Robots (Humanoids)
Event Location: Beijing, China
Event Dates: 06.-09.11.2018
DOI: 10.26083/tuprints-00020545
Corresponding Links:
Origin: Secondary publication service

Intelligent robotic assistants can potentially improve the quality of life for elderly people and help them maintain their independence. However, the number of different and personalized tasks render pre-programming of such assistive robots prohibitively difficult. Instead, to cope with a continuous and open-ended stream of cooperative tasks, new collaborative skills need to be continuously learned and updated from demonstrations. To this end, we introduce an online learning method for a skill library of collaborative tasks that employs an incremental mixture model of probabilistic interaction primitives. This model chooses a corresponding robot response to a human movement where the human intention is extracted from previously demonstrated movements. Unlike existing batch methods of movement primitives for human-robot interaction, our approach builds a library of skills online, in an open-ended fashion and updates existing skills using new demonstrations. The resulting approach was evaluated both on a simple benchmark task and in an assistive human-robot collaboration scenario with a 7DoF robot arm.

Status: Postprint
URN: urn:nbn:de:tuda-tuprints-205458
Classification DDC: 000 Generalities, computers, information > 004 Computer science
Divisions: 20 Department of Computer Science > Intelligent Autonomous Systems
TU-Projects: EC/H2020|640554|SKILLS4ROBOTS
Date Deposited: 18 Nov 2022 13:59
Last Modified: 23 Mar 2023 16:33
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/20545
PPN: 502453842
Actions (login required)
View Item View Item