Traffic flow theory
Effects of connectivity and automation on traffic flow dynamics
The introduction of connected and automated vehicles will bring changes to the highway driving environment. Connected Vehicle technology provides real-time information about the surrounding traffic condition and the traffic management center’s decisions. Such information is expected to improve drivers’ efficiency, response, and comfort while enhancing safety and mobility. Connected Vehicle technology can also further increase efficiency and reliability of automated vehicles, though, currently, these vehicles could be operated solely with their on-board sensors, without communication.
Accordingly, there is need for a comprehensive framework that can capture the impact of these technologies on congestion, safety, emissions, and energy consumption. We are currently developing such a framework that utilizes different models with technology-appropriate assumptions to simulate different vehicle types with distinct communication capabilities.
Utilizing this tool in conjunction with the data/models from our human-automated vehicle interaction research, we are able to capture the large scale impact of connectivity and automation on transportation systems. We have used this tool in various studies.
Cazares, J. G., M., Khajeh-Hosseini, and A. Talebpour. Deep Learning Based Model of Automated Vehicles. Submitted for Publications in Transportation Research Record: Journal of the Transportation Research Board of National Academies.
Samimi Abianeh, A., M. W., Burris, W., Li, H., Zhong, A., Talebpour, and K. C., Sinha. Modeling Stated Preference Travel Response to Real-Time Rerouting Advice. Submitted for Publications in Transportation Research Record: Journal of the Transportation Research Board of National Academies.
Elfar, A., C., Xavier, A., Talebpour, and H.S., Mahmassani. Traffic Shockwave Detection in a Connected Environment Using the Speed Distribution of Individual Vehicles. Accepted for Publications in Transportation Research Record: Journal of the Transportation Research Board of National Academies.
Elfar, A., A., Talebpour, and H.S., Mahmassani. Machine Learning Approach to Short-term Traffic Congestion Prediction in a Connected Environment. Accepted for Publications in Transportation Research Record: Journal of the Transportation Research Board of National Academies.
Talebpour, A., H. S. Mahmassani, and A., Elfer. Investigating the Effects of Reserved Lanes for Autonomous Vehicles on Congestion and Travel Time Reliability. Transportation Research Record: Journal of the Transportation Research Board of National Academies. No. 2622, 2017, pp. 1-12.
Mittal, A., H. S., Mahmassani, and A. Talebpour. Network Flow Relations and Travel Time Reliability in a Connected Environment. Transportation Research Record: Journal of the Transportation Research Board of National Academies. No. 2622, 2017, pp. 24-37.
Talebpour, A., and H. S., Mahmassani. Influence of connected and autonomous vehicles on traffic flow stability and throughput. Transportation Research Part C: Emerging Technologies, 71, 2016, pp. 143-163.
Hamdar, S. H., L., Qin, and A., Talebpour. Weather and road geometry impact on longitudinal driving behavior: Exploratory analysis using an empirically supported acceleration modeling framework. Transportation Research Part C: Emerging Technologies, 67, 2016, pp. 193-213.
Pedestrians are active agents that undergo a repeated decision-making process while walking. These anisotropic, interactive, and feedback-oriented agents observe their surroundings, anticipate the future state of the network, and decide on their next movements accordingly, while ensuring a collision-free path toward their destination. Aiming at capturing these behavioral characteristics of human agents while walking, we put forward a novel learning-based game theoretical approach for modeling pedestrian motion in dynamic environments. The proposed game structure provides a technical foundation to analyze optimal decision-making by pedestrians where the outcome of the game for each player's choice depends primarily on the strategies played by other players. This, in turn, ensures the frequently observed collision avoidance behavior of pedestrians while walking. The influence of nearby pedestrians on one's decision-making process and the feedback-oriented behavior of human agents are also captured via incorporating a learning structure. Optimum moving strategies are selected based on Nash equilibria calculations, where everyone is playing optimally given what all other players are playing.
Simulation of pedestrian dynamics and lane formation
Game setup where a pedestrian plays a game with other pedestrians in his/her visibility zone
Rahmati, Y. and A., Talebpour. A Learning-Based Game Theoretical Framework for 1 Modeling Crowd Dynamics, Accepted for Publication in Physical Review E.