POINT: Partially Observable Imitation Network for Traffic Signal Control
Abstract
Smart traffic signals bring together transportation infrastructure and advance technologies to improve the mobility and efficiency of urban transportation network. Adaptive traffic signal control studies can be categorized into modeling-based approaches and learning-based approaches. In order to take advantages of these two systems, this study developed an offline-online combined Partial Observable Imitation Network for Traffic signal control (POINT). In the offline system, the traffic signal timing optimization problem was formulated as a Mixed Integer Nonlinear Programming (MINLP) given complete traffic information, i.e., second-by-second speeds and locations of all vehicles. Furthermore, the objective of MINLP is to minimize total travel delays considering individual vehicle trajectories under Connected Vehicle (CV) environment. The calculated optimal solutions under various traffic conditions were considered as the ”expert” decisions. In the online system, an imitation neural network model was developed to learn the ”expert” signal plans generated from offline system. Given partial observable traffic conditions in real time, e.g., the aggregate-level of traffic volume, the POINT model can compute the signal timing parameters in the online system. The numerical results demonstrated that the proposed method outperformed other state-of-the-art signal control method under high and unbalanced traffic demand levels in terms of reducing travel delays and queuemore »
- Authors:
-
[1];
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Tacoma Public Utilities, Tacoma, WA (United States)
- Univ. of Washington, Seattle, WA (United States)
- Tsinghua Univ., Shenzhen (China)
- Futurewei Technologies, Santa Clara, CA (United States). MAPLE Lab.
- Publication Date:
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1830120
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Sustainable Cities and Society
- Additional Journal Information:
- Journal Volume: 76; Journal Issue: 2022; Journal ID: ISSN 2210-6707
- Publisher:
- Elseiver
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 33 ADVANCED PROPULSION SYSTEMS; Adaptive traffic signal control system; Imitation network; Vehicle trajectories; Connected vehicle
Citation Formats
Li, Wan, Wang, Boyu, Liu, Zhanlin, Li, Qiang, and Qi, Guo-Jun. POINT: Partially Observable Imitation Network for Traffic Signal Control. United States: N. p., 2021.
Web. doi:10.1016/j.scs.2021.103461.
Li, Wan, Wang, Boyu, Liu, Zhanlin, Li, Qiang, & Qi, Guo-Jun. POINT: Partially Observable Imitation Network for Traffic Signal Control. United States. https://doi.org/10.1016/j.scs.2021.103461
Li, Wan, Wang, Boyu, Liu, Zhanlin, Li, Qiang, and Qi, Guo-Jun. Fri .
"POINT: Partially Observable Imitation Network for Traffic Signal Control". United States. https://doi.org/10.1016/j.scs.2021.103461. https://www.osti.gov/servlets/purl/1830120.
@article{osti_1830120,
title = {POINT: Partially Observable Imitation Network for Traffic Signal Control},
author = {Li, Wan and Wang, Boyu and Liu, Zhanlin and Li, Qiang and Qi, Guo-Jun},
abstractNote = {Smart traffic signals bring together transportation infrastructure and advance technologies to improve the mobility and efficiency of urban transportation network. Adaptive traffic signal control studies can be categorized into modeling-based approaches and learning-based approaches. In order to take advantages of these two systems, this study developed an offline-online combined Partial Observable Imitation Network for Traffic signal control (POINT). In the offline system, the traffic signal timing optimization problem was formulated as a Mixed Integer Nonlinear Programming (MINLP) given complete traffic information, i.e., second-by-second speeds and locations of all vehicles. Furthermore, the objective of MINLP is to minimize total travel delays considering individual vehicle trajectories under Connected Vehicle (CV) environment. The calculated optimal solutions under various traffic conditions were considered as the ”expert” decisions. In the online system, an imitation neural network model was developed to learn the ”expert” signal plans generated from offline system. Given partial observable traffic conditions in real time, e.g., the aggregate-level of traffic volume, the POINT model can compute the signal timing parameters in the online system. The numerical results demonstrated that the proposed method outperformed other state-of-the-art signal control method under high and unbalanced traffic demand levels in terms of reducing travel delays and queue length.},
doi = {10.1016/j.scs.2021.103461},
journal = {Sustainable Cities and Society},
number = 2022,
volume = 76,
place = {United States},
year = {Fri Oct 29 00:00:00 EDT 2021},
month = {Fri Oct 29 00:00:00 EDT 2021}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
PAMSCOD: Platoon-based arterial multi-modal signal control with online data
journal, February 2012
- He, Qing; Head, K. Larry; Ding, Jun
- Transportation Research Part C: Emerging Technologies, Vol. 20, Issue 1
Reinforcement Learning for True Adaptive Traffic Signal Control
journal, May 2003
- Abdulhai, Baher; Pringle, Rob; Karakoulas, Grigoris J.
- Journal of Transportation Engineering, Vol. 129, Issue 3
Comparative study of real-world driving cycles, energy consumption, and CO2 emissions of electric and gasoline motorcycles driving in a congested urban corridor
journal, February 2019
- Koossalapeerom, Triluck; Satiennam, Thaned; Satiennam, Wichuda
- Sustainable Cities and Society, Vol. 45
Dynamic Traffic Signal Timing Optimization Strategy Incorporating Various Vehicle Fuel Consumption Characteristics
journal, June 2016
- Zhao, Junfeng; Li, Wan; Wang, Junmin
- IEEE Transactions on Vehicular Technology, Vol. 65, Issue 6
SMART TSS: Defining transportation system behavior using big data analytics in smart cities
journal, August 2018
- Gohar, Moneeb; Muzammal, Muhammad; Ur Rahman, Arif
- Sustainable Cities and Society, Vol. 41
Multiagent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC): Methodology and Large-Scale Application on Downtown Toronto
journal, September 2013
- El-Tantawy, Samah; Abdulhai, Baher; Abdelgawad, Hossam
- IEEE Transactions on Intelligent Transportation Systems, Vol. 14, Issue 3
An Experimental Review of Reinforcement Learning Algorithms for Adaptive Traffic Signal Control
book, May 2016
- Mannion, Patrick; Duggan, Jim; Howley, Enda
- Autonomic Road Transport Support Systems
Integrating computer vision and traffic modeling for near-real-time signal timing optimization of multiple intersections
journal, May 2021
- Zhou, Shenghua; Ng, S. Thomas; Yang, Yifan
- Sustainable Cities and Society, Vol. 68
Analysis of particulate matter and carbon monoxide emission rates from vehicles in a Shanghai tunnel
journal, May 2020
- Yang, Qinghai; Shen, Henggen; Liang, Zhen
- Sustainable Cities and Society, Vol. 56
Connected Vehicles Based Traffic Signal Timing Optimization
journal, December 2019
- Li, Wan; Ban, Xuegang
- IEEE Transactions on Intelligent Transportation Systems, Vol. 20, Issue 12
Algorithm 909: NOMAD: Nonlinear Optimization with the MADS Algorithm
journal, February 2011
- Le Digabel, Sébastien
- ACM Transactions on Mathematical Software, Vol. 37, Issue 4
Automated, electric, or both? Investigating the effects of transportation and technology scenarios on metropolitan greenhouse gas emissions
journal, July 2018
- Wang, An; Stogios, Christos; Gai, Yijun
- Sustainable Cities and Society, Vol. 40
Holonic multi-agent system for traffic signals control
journal, May 2013
- Abdoos, Monireh; Mozayani, Nasser; Bazzan, Ana L. C.
- Engineering Applications of Artificial Intelligence, Vol. 26, Issue 5-6