Pretraga

Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1157675

Dynamic Variable Speed Limit Zones Allocation Using Distributed Multi-Agent Reinforcement Learning

Kušić, Krešimir; Ivanjko, Edouard; Vrbanić, Filip; Gregurić, Martin; Dusparic, Ivana
Dynamic Variable Speed Limit Zones Allocation Using Distributed Multi-Agent Reinforcement Learning // 2021 IEEE International Intelligent Transportation Systems Conference
Indianapolis (IN), Sjedinjene Američke Države: Institute of Electrical and Electronics Engineers (IEEE), 2021. str. 3238-3245 doi:10.1109/itsc48978.2021.9564739 (predavanje, recenziran, cjeloviti rad (in extenso), znanstveni)

CROSBI ID: 1157675 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Dynamic Variable Speed Limit Zones Allocation Using Distributed Multi-Agent Reinforcement Learning

Autori
Kušić, Krešimir ; Ivanjko, Edouard ; Vrbanić, Filip ; Gregurić, Martin ; Dusparic, Ivana

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2021 IEEE International Intelligent Transportation Systems Conference / - : Institute of Electrical and Electronics Engineers (IEEE), 2021, 3238-3245

ISBN
978-1-7281-9142-3

Skup
24th IEEE International Conference on Intelligent Transportation Systems (ITSC 2021)

Mjesto i datum
Indianapolis (IN), Sjedinjene Američke Države, 19.09.2021. - 22.09.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Recenziran

Ključne riječi
Microscopy ; Conferences ; Collaboration ; Telecommunication traffic ; Reinforcement learning ; Traffic control ; Dynamic scheduling

Sažetak
Variable Speed Limit (VSL) has been proven to be an effective motorway traffic control strategy. However, VSL strategies with static VSL zones may operate suboptimally under traffic conditions with spatially and temporally varying congestion intensities. To enable efficient operation of the VSL system under varying congestion intensities, we propose a novel Distributed Spatio-Temporal multi-agent VSL (DWL-ST-VSL) strategy with dynamic adjustment of the VSL zone configuration. According to the current traffic conditions, DWL-ST-VSL continuously adjusts not only the speed limits but also the length and position of the VSL zones. Each agent uses Reinforcement-Learning (RL) to optimize two goals: maximizing travel speed and resolving congestion. Cooperation between VSL agents is performed using the Distributed W-Learning (DWL) algorithm. We evaluate the proposed strategy using two collaborative agents controlling two segments upstream of the congestion area in SUMO microscopic simulation on two traffic scenarios with medium and high traffic load. The results show a significant improvement in traffic conditions compared to the baselines (W-learning based VSL and simple proportional speed controller) with static VSL zones.

Izvorni jezik
Engleski



POVEZANOST RADA

Ustanove:
Fakultet prometnih znanosti, Zagreb

Profili:

Avatar Url Martin Gregurić (autor)

Avatar Url Edouard Ivanjko (autor)

Avatar Url Filip Vrbanić (autor)

Avatar Url Krešimir Kušić (autor)

Poveznice na cjeloviti tekst rada:

doi

Citiraj ovu publikaciju:

Kušić, Krešimir; Ivanjko, Edouard; Vrbanić, Filip; Gregurić, Martin; Dusparic, Ivana
Dynamic Variable Speed Limit Zones Allocation Using Distributed Multi-Agent Reinforcement Learning // 2021 IEEE International Intelligent Transportation Systems Conference
Indianapolis (IN), Sjedinjene Američke Države: Institute of Electrical and Electronics Engineers (IEEE), 2021. str. 3238-3245 doi:10.1109/itsc48978.2021.9564739 (predavanje, recenziran, cjeloviti rad (in extenso), znanstveni)
Kušić, K., Ivanjko, E., Vrbanić, F., Gregurić, M. & Dusparic, I. (2021) Dynamic Variable Speed Limit Zones Allocation Using Distributed Multi-Agent Reinforcement Learning. U: 2021 IEEE International Intelligent Transportation Systems Conference doi:10.1109/itsc48978.2021.9564739.
@article{article, author = {Ku\v{s}i\'{c}, Kre\v{s}imir and Ivanjko, Edouard and Vrbani\'{c}, Filip and Greguri\'{c}, Martin and Dusparic, Ivana}, year = {2021}, pages = {3238-3245}, DOI = {10.1109/itsc48978.2021.9564739}, keywords = {Microscopy, Conferences, Collaboration, Telecommunication traffic, Reinforcement learning, Traffic control, Dynamic scheduling}, doi = {10.1109/itsc48978.2021.9564739}, isbn = {978-1-7281-9142-3}, title = {Dynamic Variable Speed Limit Zones Allocation Using Distributed Multi-Agent Reinforcement Learning}, keyword = {Microscopy, Conferences, Collaboration, Telecommunication traffic, Reinforcement learning, Traffic control, Dynamic scheduling}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, publisherplace = {Indianapolis (IN), Sjedinjene Ameri\v{c}ke Dr\v{z}ave} }
@article{article, author = {Ku\v{s}i\'{c}, Kre\v{s}imir and Ivanjko, Edouard and Vrbani\'{c}, Filip and Greguri\'{c}, Martin and Dusparic, Ivana}, year = {2021}, pages = {3238-3245}, DOI = {10.1109/itsc48978.2021.9564739}, keywords = {Microscopy, Conferences, Collaboration, Telecommunication traffic, Reinforcement learning, Traffic control, Dynamic scheduling}, doi = {10.1109/itsc48978.2021.9564739}, isbn = {978-1-7281-9142-3}, title = {Dynamic Variable Speed Limit Zones Allocation Using Distributed Multi-Agent Reinforcement Learning}, keyword = {Microscopy, Conferences, Collaboration, Telecommunication traffic, Reinforcement learning, Traffic control, Dynamic scheduling}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, publisherplace = {Indianapolis (IN), Sjedinjene Ameri\v{c}ke Dr\v{z}ave} }

Časopis indeksira:


  • Web of Science Core Collection (WoSCC)
    • Conference Proceedings Citation Index - Science (CPCI-S)
  • Scopus

Citati:

    Altmetrijski pokazatelji:


    Podijeli:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font
    CROSBI koristi kolačiće (cookies) kako bi poboljšao funkcionalnost stranice.