Search

The emerging technologies of connected and automated vehicles (CAVs) and deep reinforcement learning (DRL) provide innovative methods and have a great potential for developing new solutions to improve the efficiency of several intersection systems. Based on the multisource data collected from the transportation environments, CAVs with the cooperative adaptive cruise control (CACC) system could merge into platoons and traverse the intersection quickly and smoothly. Meanwhile, the traffic information about the CAVs enables intelligent traffic signal controls with the help of DRL technologies. This research investigates the performance of a state-shared multiagent deep reinforcement learning (MADRL) controlled signal corridor with platooning-based CAVs. A corridor with seven intersections from the Ingolstadt Traffic Scenario (InTAS) in Germany is selected as a case study. The state information is shared between neighboring intersections to overcome the partial information observation of the decentralized agents in the MADRL framework. A platooning framework with specific CACC systems for the leading and following vehicles is proposed. Results indicate that the state-shared MADRL with CAV platoons could significantly decrease the total waiting time, average queue length, and total CO2 emission of the corridor by 80%, 73%, and 54%, respectively, which could be beneficial in further improving the intersection efficiency, designing future intersections, and cooperating signals and CAVs platoons. [ABSTRACT FROM AUTHOR]

As one key basis of traffic flow theory, the fundamental diagram (FD) has wide application in traffic management and control. However, the FD of mixed human-driven vehicles (HVs) and cooperative adaptive cruise control (CACC) vehicles remains unclear. The deterministic and stochastic FD of mixed traffic was obtained. First, the longitudinal control model (LCM) and connected LCM (CLCM) were selected as the car-following model of HVs and CACCs. Next, in deterministic simulation, the mathematical expression of mixed-traffic FD was conducted considering the CACC penetration rate and platooning intensity. Then, the stochastic distribution of perception and response time calibrated by the vehicle trajectory data set NGSIM was introduced to derive the stochastic FD. After that, in stochastic simulation, taking the variance and computation effort into account, the optimal number of simulated vehicles to obtain steady-state FD was obtained. The impact of CACC penetration rates and platooning intensity was also explored. It revealed that the optimal number of simulated vehicles is 400. CACC can improve the capacity and critical density of highways. In mixed traffic, due to the large variance of HV driver response time, scattering remains unchanged regardless of CACC penetration when there are enough vehicles. Pure CACC traffic has minimum scattering. More importantly, the proposed framework is applicable to other CACC, adaptive cruise control (ACC), and HV car-following models, including further experimental models. [ABSTRACT FROM AUTHOR]

: In this paper, we presented a novel adaptive traffic control strategy for urban signalized interchanges based on traditional sensors and emerging connected and automated vehicle (CAV) technologies. The signalized interchanges in this paper refer to those controlled by one traffic signal controller while vehicles must cross two or more stop lines to cross. Examples included diamond interchanges (DIs), diverging diamond interchanges (DDIs), and single-point urban interchanges (SPUIs). With the expansion of urban areas, such interchanges are increasingly common and often become mobility bottlenecks. The traffic signal optimization in this paper was derived from the cumulative vehicle counting curves (A-D curves). An assumption of the A-D curves for control delay estimation is that vehicles are no longer restricted once they cross the stop line. However, at a signalized interchange, vehicles may stop multiple times before completely cross. This situation cannot be effectively reflected with the standard cumulative vehicle counting curves. The phasing sequence is also challenging due to the limited space within the interchange. To address these issues, we proposed a new adaptive traffic control framework based on a linear traffic control model, referred to as a phase-time network. The objective of this framework was to dynamically fine-tune control splits and optimize the phasing sequence according to the vehicle arrival counts (from infrastructure sensors) and turning movement ratios (from CAV technologies). The optimization problem was first formulated into a mixed-integer linear programming (MILP) formulation and validated through offline examples. Then, an online search algorithm was presented and evaluated within a microscopic traffic simulation environment. The proposed MILP formulation and algorithm were assessed in both offline and online experiments. The results of all numerical experiments validated the formulation and show promise for real-world implementations. [ABSTRACT FROM AUTHOR]

This paper evaluated the congestion reduction benefits over a 6-year period from the implementation of an adaptive traffic control system (ATCS) in a congested area of Manhattan, New York, bounded by 2nd and 6th Avenues and 42nd and 57th Streets—known as the Midtown-in-Motion (MIM) area. A methodology using taxi Global Positioning System (GPS) sensors was used to measure traffic speed. Traffic speeds were calculated for May weekdays before the ATCS was installed (May 2011) and for each subsequent year (May 2012 to May 2016). Within 1 to 2 years after the implementation of the ATCS, the area’s traffic speed increased on avenues and cross streets. This gain, however, could not be sustained in subsequent years because of intervening changes in key factors impacting traffic congestion. These factors included reduction in roadway space/capacity for motor vehicles, lack of effective traffic enforcement to maintain/protect available roadway capacity, increased vehicle miles traveled (VMT) from transportation network company vehicles, and increasing volume of bicycle trips sharing street space with vehicles/pedestrians. This paper’s two key findings are, first, traffic speed gains initially seen in the MIM area after 1 year of ATCS implementation could not be sustained because intervening external factors reduced capacity and increased VMT. However, during the same analysis period, the rest of the Midtown Core area (without ATCS deployment) experienced a greater speed loss than the MIM area, indicating the effectiveness of ATCS deployment in minimizing losses in traffic speed. Second, to protect street network capacity and to minimize VMT growth, midtown Manhattan requires adopting proactive, collaborative, and coordinated strategies by the three key agencies involved with traffic management in New York City (NYC): the NYC Department of Transportation (traffic control system technology), the NYC Police Department (traffic enforcement), and the Mayor’s office (traffic demand mitigation policies). [ABSTRACT FROM AUTHOR]