TU Darmstadt / ULB / TUprints

SKID RAW: Skill Discovery From Raw Trajectories

Tanneberg, Daniel ; Ploeger, Kai ; Rueckert, Elmar ; Peters, Jan (2022)
SKID RAW: Skill Discovery From Raw Trajectories.
In: IEEE Robotics and Automation Letters, 6 (3)
doi: 10.26083/tuprints-00020536
Article, Secondary publication, Postprint

[img] Text
Copyright Information: In Copyright.

Download (4MB)
Item Type: Article
Type of entry: Secondary publication
Title: SKID RAW: Skill Discovery From Raw Trajectories
Language: English
Date: 2022
Place of Publication: Darmstadt
Publisher: IEEE
Journal or Publication Title: IEEE Robotics and Automation Letters
Volume of the journal: 6
Issue Number: 3
DOI: 10.26083/tuprints-00020536
Corresponding Links:
Origin: Secondary publication service

Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching tasks that involve sequences of different skills, with varying order and number of these skills, it is desirable to only demonstrate full task executions instead of all individual skills. For this purpose, we propose a novel approach that simultaneously learns to segment trajectories into reoccurring patterns and the skills to reconstruct these patterns from unlabelled demonstrations without further supervision. Moreover, the approach learns a skill conditioning that can be used to understand possible sequences of skills, a practical mechanism to be used in, for example, human-robot-interactions for a more intelligent and adaptive robot behaviour. The Bayesian and variational inference based approach is evaluated on synthetic and real human demonstrations with varying complexities and dimensionality, showing the successful learning of segmentations and skill libraries from unlabelled data.

Status: Postprint
URN: urn:nbn:de:tuda-tuprints-205363
Classification DDC: 000 Generalities, computers, information > 004 Computer science
600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 20 Department of Computer Science > Intelligent Autonomous Systems
TU-Projects: EC/H2020|640554|SKILLS4ROBOTS
Date Deposited: 18 Nov 2022 13:41
Last Modified: 24 Mar 2023 07:33
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/20536
PPN: 506259536
Actions (login required)
View Item View Item