Game Theory-Based Signal Control Considering Both Pedestrians and Vehicles in Connected Environment
<p>The tested intersection and pedestrian movements 1–8.</p> "> Figure 2
<p>Phase sequence of the tested intersection.</p> "> Figure 3
<p>Calculation of the disagreement point.</p> "> Figure 4
<p>NB controller architecture.</p> "> Figure 5
<p>Vehicle and pedestrian generation workflow.</p> "> Figure 6
<p>Average queue length for all movements under a balanced demand scenario. Note: nbt/wbt = northbound/westbound (through moving); nbl/wbl = northbound/westbound (left turning); nbr/wbr = northbound/westbound (right turning).</p> "> Figure 7
<p>Average queue length for all movements under the unbalanced demand scenario. Note: nbt/wbt = northbound/westbound (through moving); nbl/wbl = northbound/westbound (left turning); nbr/wbr = northbound/westbound (right turning).</p> ">
Abstract
:1. Introduction
1.1. Research Background
1.2. Signal Control Considering Pedestrians
1.3. GT-Based Signal Control Studies
- We introduce an NB-based game-theoretic signal control approach, taking pedestrians into consideration for the first time (to the best of our knowledge), with the objective of minimizing and equalizing queued vehicles and pedestrians across the different phases;
- Various demand levels and demand patterns have been tested to demonstrate the effectiveness, superiority, and stability of the proposed NB signal control approach in comparison to the actuated signal control;
- We also take conflicts between pedestrians and right-turning vehicles into consideration, conducting a sensitivity analysis on right-turning vehicles to reveal the superiority of the proposed NB signal control approach.
2. Materials and Methods
2.1. Problem Definition
2.2. Game Theory and Nash Bargaining
2.3. Game Modeling
2.3.1. Intersection Information
2.3.2. Payoff Function
2.3.3. Disagreement Point
3. Results
3.1. Experiment Settings
- Car-following behavior: IDM (Intelligent Driver Model);
- Vehicle length: 4 m;
- Vehicle maximum speed: 16.7 m/s;
- Minimum gap between vehicles: 2 m;
- Pedestrian walking speed: 1.4 m/s;
- Vehicle threshold speed: 1.4 m/s;
- Pedestrian threshold speed: 0.2 m/s;
- Vehicle arrival time interval: 7.0 s;
- Pedestrian arrival time interval: 9.5 s;
- Traffic flow generation probability for the main road: a;
- Traffic flow generation probability for a branch road: b.
- APD: Average pedestrian delay (s/ped), the average delay of each pedestrian due to a red light;
- AVD: Average vehicle delay (s/veh), the average delay of each vehicle due to a red light;
- AQL: Average queue length (veh), the average number of vehicles from the junction until the final vehicle in the queue;
- ACE: Average CO2 emissions (g), the average amount of CO2 emitted by the vehicles;
- AFC: Average fuel consumption (g), the average amount of fuel the vehicles use.
3.2. Results of Balanced Demand Scenarios
3.3. Results of Unbalanced Demand Scenarios
3.4. Sensitivity Analysis of Right-Turning Vehicles
4. Conclusions and Future Work
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Cookson, G.; Pishue, B. INRIX Global Traffic Scorecard. Available online: https://inrix.com/scorecard/ (accessed on 31 October 2023).
- Hatim, S.M.; Elias, S.J.; Awang, N.; Darus, M.Y. VANETs and Internet of Things (IoT): A Discussion. Indones. J. Electr. Eng. Comput. Sci. 2018, 12, 218–224. [Google Scholar] [CrossRef]
- Liang, X.; Du, X.; Wang, G.; Han, Z. Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks. IEEE Trans. Veh. Technol. 2019, 68, 1243–1253. [Google Scholar] [CrossRef]
- Liu, W.; Qin, G.; He, Y.; Jiang, F. Distributed Cooperative Reinforcement Learning-Based Traffic Signal Control That Integrates V2X Networks’ Dynamic Clustering. IEEE Trans. Veh. Technol. 2017, 66, 8667–8681. [Google Scholar] [CrossRef]
- Yazdani, M.; Sarvi, M.; Asadi Bagloee, S.; Nassir, N.; Price, J.; Parineh, H. Intelligent Vehicle Pedestrian Light (IVPL): A Deep Reinforcement Learning Approach for Traffic Signal Control. Transp. Res. Part C Emerg. Technol. 2023, 149, 103991. [Google Scholar] [CrossRef]
- Ishaque, M.M.; Noland, R.B. Multimodal Microsimulation of Vehicle and Pedestrian Signal Timings. Transp. Res. Rec. 2005, 1939, 107–114. [Google Scholar] [CrossRef]
- Li, M.; Alhajyaseen, W.K.M.; Nakamura, H. A Traffic Signal Optimization Strategy Considering Both Vehicular and Pedestrian Flows. In Proceedings of the Compendium of Papers CD-ROM, the 89th Annual Meeting of the Transportation Research Board, Washington, DC, USA, 10–14 January 2010. [Google Scholar]
- Liang, X.; Guler, S.I.; Gayah, V.V. Traffic Signal Control Optimization in a Connected Vehicle Environment Considering Pedestrians. Transp. Res. Rec. 2020, 2674, 499–511. [Google Scholar] [CrossRef]
- Yang, Z.; Benekohal, R.F. Use of Genetic Algorithm for Phase Optimization at Intersections with Minimization of Vehicle and Pedestrian Delays. Transp. Res. Rec. 2011, 2264, 54–64. [Google Scholar] [CrossRef]
- Ma, W.; Liao, D.; Liu, Y.; Lo, H.K. Optimization of Pedestrian Phase Patterns and Signal Timings for Isolated Intersection. Transp. Res. Part C Emerg. Technol. 2015, 58, 502–514. [Google Scholar] [CrossRef]
- Yu, C.; Ma, W.; Han, K.; Yang, X. Optimization of Vehicle and Pedestrian Signals at Isolated Intersections. Transp. Res. Part B Methodol. 2017, 98, 135–153. [Google Scholar] [CrossRef]
- Xu, K.; Huang, J.; Kong, L.; Yu, J.; Chen, G. PV-TSC: Learning to Control Traffic Signals for Pedestrian and Vehicle Traffic in 6G Era. IEEE Trans. Intell. Transp. Syst. 2023, 24, 7552–7563. [Google Scholar] [CrossRef]
- Tian, D.; Zhou, J.; Wang, Y.; Sheng, Z.; Duan, X.; Leung, V.C.M. Channel Access Optimization with Adaptive Congestion Pricing for Cognitive Vehicular Networks: An Evolutionary Game Approach. IEEE Trans. Mob. Comput. 2020, 19, 803–820. [Google Scholar] [CrossRef]
- Huang, K.; Chen, X.; Di, X.; Du, Q. Dynamic Driving and Routing Games for Autonomous Vehicles on Networks: A Mean Field Game Approach. Transp. Res. Part C Emerg. Technol. 2021, 128, 103189. [Google Scholar] [CrossRef]
- Büchel, B.; Corman, F. Review on Statistical Modeling of Travel Time Variability for Road-Based Public Transport. Front. Built Environ. 2020, 6, 70. [Google Scholar] [CrossRef]
- Linglong, T.; Xiaohua, Z.; Dunli, H.; Yanzhang, S.; Ren, W. A Study of Single Intersection Traffic Signal Control Based on Two-Player Cooperation Game Model. In Proceedings of the 2010 WASE International Conference on Information Engineering, Beidai, China, 14–15 August 2010; Volume 2, pp. 322–327. [Google Scholar]
- Abdelghaffar, H.M.; Yang, H.; Rakha, H.A. Isolated Traffic Signal Control Using a Game Theoretic Framework. In Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016; pp. 1496–1501. [Google Scholar]
- Abdelghaffar, H.M.; Rakha, H.A. A Novel Decentralized Game-Theoretic Adaptive Traffic Signal Controller: Large-Scale Testing. Sensors 2019, 19, 2282. [Google Scholar] [CrossRef]
- Elouni, M.; Abdelghaffar, H.M.; Rakha, H.A. Adaptive Traffic Signal Control: Game-Theoretic Decentralized vs. Centralized Perimeter Control. Sensors 2021, 21, 274. [Google Scholar] [CrossRef]
- Dong, H.; Dai, Z. A Multi Intersections Signal Coordinate Control Method Based on Game Theory. In Proceedings of the 2011 International Conference on Electronics, Communications and Control (ICECC), Ningbo, China, 9–11 September 2011; IEEE: Ningbo, China; pp. 1232–1235. [Google Scholar]
- Clempner, J.B.; Poznyak, A.S. Modeling the Multi-Traffic Signal-Control Synchronization: A Markov Chains Game Theory Approach. Eng. Appl. Artif. Intell. 2015, 43, 147–156. [Google Scholar] [CrossRef]
- Xinhai, X.; Lunhui, X. Traffic Signal Control Agent Interaction Model Based on Game Theory and Reinforcement Learning. In Proceedings of the 2009 International Forum on Computer Science-Technology and Applications, Chongqing, China, 25–27 December 2009; Volume 1, pp. 164–168. [Google Scholar]
- Daeichian, A.; Haghani, A. Fuzzy Q-Learning-Based Multi-Agent System for Intelligent Traffic Control by a Game Theory Approach. Arab. J. Sci. Eng. 2018, 43, 3241–3247. [Google Scholar] [CrossRef]
- Abdoos, M. A Cooperative Multiagent System for Traffic Signal Control Using Game Theory and Reinforcement Learning. IEEE Intell. Transp. Syst. Mag. 2021, 13, 6–16. [Google Scholar] [CrossRef]
- Babatunde, J.; Osman, O.A.; Stevanovic, A.; Dobrota, N. Fuel-Based Nash Bargaining Approach for Adaptive Signal Control in an N-Player Cooperative Game. Transp. Res. Rec. J. Transp. Res. Board 2023, 2677, 036119812311616. [Google Scholar] [CrossRef]
- Yu, X.-H.; Recker, W.W. Stochastic Adaptive Control Model for Traffic Signal Systems. Transp. Res. Part C Emerg. Technol. 2006, 14, 263–282. [Google Scholar] [CrossRef]
- “Brian” Park, B.; Yun, I.; Ahn, K. Stochastic Optimization for Sustainable Traffic Signal Control. Int. J. Sustain. Transp. 2009, 3, 263–284. [Google Scholar] [CrossRef]
- Yun, I.; Park, B. (Brian) Stochastic Optimization for Coordinated Actuated Traffic Signal Systems. J. Transp. Eng. 2012, 138, 819–829. [Google Scholar] [CrossRef]
- Wang, S.; Ahmed, N.U.; Yeap, T.H. Optimum Management of Urban Traffic Flow Based on a Stochastic Dynamic Model. IEEE Trans. Intell. Transp. Syst. 2019, 20, 4377–4389. [Google Scholar] [CrossRef]
- Nash, J.F. The Bargaining Problem. Econometrica 1950, 18, 155–162. [Google Scholar] [CrossRef]
Symbol | Definition |
---|---|
c | a cycle length of 144 s |
a minimum green duration of 15 s | |
a maximum green duration of 45 s | |
green duration for phase | |
a yellow duration of 4 s | |
a red duration of 2 s | |
a conversion factor of 1.54 | |
phase index of the intersection | |
the beginning time of each cycle | |
vehicle arrival time interval | |
pedestrian arrival time interval | |
vehicle arrival probability of lane | |
pedestrian arrival probability of movement | |
time interval between and the end of the green time of phase | |
the number of queued vehicles of lane at time | |
the number of arrival vehicles of lane during | |
the number of departure vehicles of lane | |
the vehicle departure rate of lane | |
the number of queued pedestrians of movement at time | |
the number of arrival pedestrians of movement during | |
the number of departure pedestrians of movement | |
the pedestrian departure rate of movement | |
estimated weighted sum of people after applying a green time for phase |
Probabilities | a = 0.7 b = 0.7 | a = 0.75 b = 0.75 | a = 0.8 b = 0.8 | |
---|---|---|---|---|
APD | Act | 59.10 | 63.98 | 64.84 |
NB | 51.73 | 53.20 | 53.21 | |
Reduction | 12.47% | 16.85% | 17.94% | |
AVD | Act | 50.93 | 66.61 | 102.29 |
NB | 49.56 | 54.58 | 86.34 | |
Reduction | 2.69% | 18.06% | 15.59% | |
AQL | Act | 10.86 | 13.91 | 20.55 |
NB | 10.08 | 11.37 | 16.27 | |
Reduction | 7.18% | 18.26% | 20.83% | |
ACE | Act | 289.24 | 328.10 | 411.66 |
NB | 285.63 | 299.10 | 374.92 | |
Reduction | 1.25% | 8.84% | 8.92% | |
AFC | Act | 92.26 | 104.25 | 131.31 |
NB | 91.11 | 95.04 | 119.60 | |
Reduction | 1.25% | 8.84% | 8.92% |
Probabilities | a = 0.8 b = 0.7 | a = 0.9 b = 0.6 | a = 1.0 b = 0.5 | |
---|---|---|---|---|
APD | Act | 62.72 | 59.23 | 53.30 |
NB | 52.88 | 52.73 | 51.28 | |
Reduction | 15.69% | 10.97% | 3.79% | |
AVD | Act | 69.36 | 81.34 | 85.39 |
NB | 53.29 | 56.00 | 60.50 | |
Reduction | 23.17% | 31.15% | 29.15% | |
AQL | Act | 14.37 | 16.24 | 17.72 |
NB | 11.18 | 11.52 | 12.00 | |
Reduction | 22.20% | 29.06% | 32.28% | |
ACE | Act | 334.21 | 359.44 | 366.47 |
NB | 294.76 | 301.25 | 311.80 | |
Reduction | 11.80% | 16.19% | 14.92% | |
AFC | Act | 106.60 | 114.70 | 116.89 |
NB | 94.02 | 96.09 | 99.45 | |
Reduction | 11.80% | 16.22% | 14.92% |
Time Interval | 3.6 s | 4.8 s | 7.2 s | 14.4 s | |
---|---|---|---|---|---|
APD | Act | 65.10 | 64.95 | 64.94 | 64.68 |
NB | 53.63 | 53.28 | 53.22 | 52.98 | |
Reduction | 17.62% | 17.97% | 18.05% | 18.09% | |
AVD | Act | 72.50 | 21.10 | 16.43 | 12.86 |
NB | 45.56 | 16.46 | 12.74 | 10.17 | |
Reduction | 37.16% | 21.99% | 22.46% | 20.92% | |
AQL | Act | 26.26 | 8.63 | 5.09 | 2.41 |
NB | 17.20 | 6.86 | 4.04 | 1.78 | |
Reduction | 34.50% | 20.51% | 20.63% | 26.20% | |
ACE | Act | 309.17 | 209.24 | 200.66 | 194.09 |
NB | 253.99 | 198.97 | 192.16 | 187.49 | |
Reduction | 17.85% | 4.91% | 4.24% | 3.40% | |
AFC | Act | 98.61 | 66.74 | 64.00 | 61.91 |
NB | 81.01 | 63.46 | 61.29 | 59.80 | |
Reduction | 17.85% | 4.91% | 4.23% | 3.41% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, A.; Zhang, K.; Li, M.; Shao, J.; Li, S. Game Theory-Based Signal Control Considering Both Pedestrians and Vehicles in Connected Environment. Sensors 2023, 23, 9438. https://doi.org/10.3390/s23239438
Wang A, Zhang K, Li M, Shao J, Li S. Game Theory-Based Signal Control Considering Both Pedestrians and Vehicles in Connected Environment. Sensors. 2023; 23(23):9438. https://doi.org/10.3390/s23239438
Chicago/Turabian StyleWang, Anyou, Ke Zhang, Meng Li, Junqi Shao, and Shen Li. 2023. "Game Theory-Based Signal Control Considering Both Pedestrians and Vehicles in Connected Environment" Sensors 23, no. 23: 9438. https://doi.org/10.3390/s23239438