Change search
ReferencesLink to record
Permanent link

Direct link
Adaptive Group-Based Signal Control Using Reinforcement Learning with Eligibility Traces
KTH, School of Architecture and the Built Environment (ABE), Transport Science, Transport Planning, Economics and Engineering. (Traffic Simulation and Control Group)ORCID iD: 0000-0002-1375-9054
KTH, School of Architecture and the Built Environment (ABE), Transport Science, Transport Planning, Economics and Engineering. (Traffic Simulation and Control Group)
2015 (English)In: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, IEEE conference proceedings, 2015, 2412-2417 p.Conference paper (Refereed)Text
Abstract [en]

Group-based signal controllers are widely deployed on urban networks in the Nordic countries. However, group-based signal controls are usually implemented with rather simple timing logics, e.g. vehicle actuated timing. In addition, group-based signal control systems with pre-defined signal parameter settings show relatively poor performances in a dynamically changed traffic environment. This study, therefore, presents an adaptive group-based signal control system capable of changing control strategies with respect to non-stationary traffic demands. In this study, signal groups are formulated as individual agents. The signal group agent learns from traffic environments and makes intelligent timing decisions according to the perceived system states. Reinforcement learning with multiple-step backups is applied as the learning algorithm. Agents on-line update their knowledge based on a sequence of states during the learning process rather than purely on the basis of single previous state. The proposed signal control system is integrated into a software-in-the-loop simulation (SILS) framework for evaluation purpose. In the testbed experiments, the proposed adaptive group-based control system is compared to a benchmark signal control system, the well-established group-based fixed-time control system. The simulation results demonstrate that learning-based and adaptive group-based signal control system owns its advantage in dealing with dynamic traffic environments in terms of improving traffic mobility efficiency.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2015. 2412-2417 p.
Keyword [en]
Computer software, Control systems, Intelligent systems, Intelligent vehicle highway systems, Knowledge based systems, Learning algorithms, Reinforcement learning, Sustainable development, Traffic signals, Transportation, Control strategies, Dynamic traffic environment, Eligibility traces, Non-stationary traffics, Signal control systems, Signal parameters, Software-in-the-loop simulations, Traffic environment, Adaptive control systems
National Category
Control Engineering Computer Systems
Identifiers
URN: urn:nbn:se:kth:diva-181132DOI: 10.1109/ITSC.2015.389ISI: 000376668802079ScopusID: 2-s2.0-84950235947ISBN: 9781467365956ISBN: 9781467365956ISBN: 9781467365956ISBN: 9781467365956OAI: oai:DiVA.org:kth-181132DiVA: diva2:901950
Conference
18th IEEE International Conference on Intelligent Transportation Systems, ITSC 2015, 15 September 2015 through 18 September 2015
Note

QC 20160209

Available from: 2016-02-09 Created: 2016-01-29 Last updated: 2016-06-27Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Jin, JunchenMa, Xiaoliang
By organisation
Transport Planning, Economics and Engineering
Control EngineeringComputer Systems

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 35 hits
ReferencesLink to record
Permanent link

Direct link