Self-correcting online navigation via leveraged Gaussian processes

Seunggyu Chang, Sungjoon Choi, Songhwai Oh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a novel online learning navigation algorithm is proposed to incorporate negative data generated from failure in an online manner. While existing methods require additional knowledge about what to do at failed situations, the proposed method alleviates this by utilizing failures as a clue of what not to do without requiring additional knowledge of what to do. By combining the benefits of leveraged Gaussian processes and sparse online Gaussian processes, we proposed an online learning framework for navigation and its update rule which instantly learns which actions to avoid from the failures while navigating. Our navigation method is successfully validated on a static planar world and dynamic worlds on both simulation and real-world dataset.

Original languageEnglish
Title of host publication2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages868-873
Number of pages6
ISBN (Electronic)9781509030552
DOIs
Publication statusPublished - 2017 Jul 25
Externally publishedYes
Event14th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2017 - Jeju, Korea, Republic of
Duration: 2017 Jun 282017 Jul 1

Publication series

Name2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2017

Other

Other14th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2017
Country/TerritoryKorea, Republic of
CityJeju
Period17/6/2817/7/1

Keywords

  • Learning from failure
  • Online learning navigation

ASJC Scopus subject areas

  • Computer Science Applications
  • Biomedical Engineering
  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Self-correcting online navigation via leveraged Gaussian processes'. Together they form a unique fingerprint.

Cite this