Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Barrier-Certified Adaptive Reinforcement Learning With Applications to Brushbot Navigation
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Decision and Control Systems (Automatic Control). Georgia Inst Technol, Georgia Robot & Intelligent Syst Lab, Atlanta, GA 30332 USA.;RIKEN, Ctr Adv Intelligence Project, Tokyo 1030027, Japan..
Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA..
Georgia Inst Technol, Sch Mech Engn, Atlanta, GA 30313 USA..
Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA..
2019 (English)In: IEEE Transactions on robotics, ISSN 1552-3098, E-ISSN 1941-0468, Vol. 35, no 5, p. 1186-1205Article in journal (Refereed) Published
Abstract [en]

This paper presents a safe learning framework that employs an adaptive model learning algorithm together with barrier certificates for systems with possibly nonstationary agent dynamics. To extract the dynamic structure of the model, we use a sparse optimization technique. We use the learned model in combination with control barrier certificates that constrain policies (feedback controllers) in order to maintain safety, which refers to avoiding particular undesirable regions of the state space. Under certain conditions, recovery of safety in the sense of Lyapunov stability after violations of safety due to the nonstationarity is guaranteed. In addition, we reformulate an action-value function approximation to make any kernel-based nonlinear function estimation method applicable to our adaptive learning framework. Lastly, solutions to the barrier-certified policy optimization are guaranteed to be globally optimal, ensuring the greedy policy improvement under mild conditions. The resulting framework is validated via simulations of a quadrotor, which has previously been used under stationarity assumptions in the safe learnings literature, and is then tested on a real robot, the brushbot, whose dynamics is unknown, highly complex, and nonstationary.

Place, publisher, year, edition, pages
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC , 2019. Vol. 35, no 5, p. 1186-1205
Keywords [en]
Brushbot, control barrier certificate, kernel adaptive filter, safe learning, sparse optimization
National Category
Robotics
Identifiers
URN: urn:nbn:se:kth:diva-262956DOI: 10.1109/TRO.2019.2920206ISI: 000489787000008Scopus ID: 2-s2.0-85077794298OAI: oai:DiVA.org:kth-262956DiVA, id: diva2:1374993
Note

QC 20191203

Available from: 2019-12-03 Created: 2019-12-03 Last updated: 2020-02-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Ohnishi, Motoya

Search in DiVA

By author/editor
Ohnishi, Motoya
By organisation
Decision and Control Systems (Automatic Control)
In the same journal
IEEE Transactions on robotics
Robotics

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf