SKID RAW: Skill Discovery from Raw Trajectories

Daniel Tanneberg, Kai Ploeger, Elmar Rueckert, Jan Peters

Research output: Contribution to journalArticleResearchpeer-review

2 Citations (Scopus)

Abstract

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.
Original languageEnglish
Article number9387162
Pages (from-to)4696-4703
Number of pages8
Journal IEEE robotics and automation letters
Volume6
Issue number3
Early online date25 Mar 2021
DOIs
Publication statusPublished - Jul 2021

Bibliographical note

Publisher Copyright: © 2016 IEEE.

Keywords

  • Deep learning methods
  • learning categories and concepts
  • representation learning

Cite this