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
Decentralized Scheduling for Cooperative Localization With Deep Reinforcement Learning
Chalmers University of Technology, Sweden.
Universitat Autonoma de Barcelona, Spain.
RISE - Research Institutes of Sweden, Safety and Transport, Measurement Science and Technology. Chalmers University of Technology, Sweden.ORCID iD: 0000-0002-1210-1680
Chalmers University of Technology, Sweden.
Show others and affiliations
2019 (English)In: IEEE Transactions on Vehicular Technology, ISSN 0018-9545, E-ISSN 1939-9359, Vol. 68, no 5, p. 4295-4305, article id 8701533Article in journal (Refereed) Published
Abstract [en]

Cooperative localization is a promising solution to the vehicular high-accuracy localization problem. Despite its high potential, exhaustive measurement and information exchange between all adjacent vehicles are expensive and impractical for applications with limited resources. Greedy policies or hand-engineering heuristics may not be able to meet the requirement of complicated use cases. In this paper, we formulate a scheduling problem to improve the localization accuracy (measured through the Cramér-Rao lower bound) of every vehicle up to a given threshold using the minimum number of measurements. The problem is cast as a partially observable Markov decision process and solved using decentralized scheduling algorithms with deep reinforcement learning, which allow vehicles to optimize the scheduling (i.e., the instants to execute measurement and information exchange with each adjacent vehicle) in a distributed manner without a central controlling unit. Simulation results show that the proposed algorithms have a significant advantage over random and greedy policies in terms of both required numbers of measurements to localize all nodes and achievable localization precision with limited numbers of measurements.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2019. Vol. 68, no 5, p. 4295-4305, article id 8701533
Keywords [en]
cooperative localization, deep Q-learning, deep reinforcement learning, Machine-learning for vehicular localization, policy gradient, Information dissemination, Learning algorithms, Machine learning, Markov processes, Reinforcement learning, Scheduling, Scheduling algorithms, Vehicles, Decentralized scheduling, Engineering heuristics, Information exchanges, Localization accuracy, Partially observable Markov decision process, Q-learning, Deep learning
National Category
Natural Sciences
Identifiers
URN: urn:nbn:se:ri:diva-42824DOI: 10.1109/TVT.2019.2913695Scopus ID: 2-s2.0-85066614096OAI: oai:DiVA.org:ri-42824DiVA, id: diva2:1384790
Available from: 2020-01-10 Created: 2020-01-10 Last updated: 2020-01-10Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Steinmetz, Erik

Search in DiVA

By author/editor
Steinmetz, Erik
By organisation
Measurement Science and Technology
In the same journal
IEEE Transactions on Vehicular Technology
Natural Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 8 hits
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
v. 2.35.9