27 October 2022 in IEEE Transactions on Intelligent Transportation Systems
Traffic congestion at signalized intersections often leads to serious impacts on adjacent intersections on a corridor. To enhance intersections’ throughput efficiency, traffic signals are commonly coordinated across intersections. Traditional signal coordination methods control the adjacent intersections by setting a fixed phase offset. However, these traditional coordination methods may have poor adaptability to dynamic traffic conditions, which can cause additional congestion. To reduce arterial traffic delays, this paper develops an adaptive coordination control method based on multi-agent reinforcement learning (MARL). Most existing MARL-based methods rely on impractical assumptions to improve their performance in complex and dynamic traffic scenarios. To overcome these assumptions, this paper proposes a fully scalable MARL algorithm for arterial traffic signal coordination based on the proximal policy optimization algorithm. We apply a parameter-sharing training protocol to mitigate the slow convergence due to nonstationarity and to reduce computational requirements. In addition, a new action setting is designed by using the lead-lag phase sequence to simultaneously improve the implementation and coordination flexibility of the method. Extensive simulation experiments and comparisons with existing methods demonstrate that the proposed method performed stably in both simulated and real-world arterial corridors. Hence, the proposed signal coordination method can alleviate traffic congestion more effectively than existing traditional and MARL-based methods.
1 January 2021 in Transportation Research Part C: Emerging Technologies
1 December 2020 in Transportation Research Part D: Transport and Environment
29 May 2022 in Journal of Intelligent Transportation Systems
Accurate turning movement counts (TMCs) data collected from regional-wide signalized intersections is critical to regional transportation planning and simulation modeling. A variety of existing traffic sensors, configured at intersections for traffic detection and signal control, can generate a large amount of real-time high-resolution event-based data from traffic controllers but few of these sensors are configured to collect TMC. This paper proposes a methodology for estimating network-level TMC using existing traffic controller event-based data without installing additional sensors. First, relevant features that can indicate traffic arrival are extracted from existing event-based data, including detector occupancy time, detector-triggered count, and green time duration. With these features, a multi-output multilayer neural network model is developed to estimate TMC. To further improve network-level TMC estimation accuracy, intersection infrastructure data and point-of-interest (POI) data are included as exogenous variables for the proposed model. Ninety-three signalized intersections are chosen from the Pima County region, Arizona, to calibrate and verify the developed model. The validation results show that the proposed model can accurately estimate TMC, as indicated by a median Root Mean Square Error (RMSE) of 41 veh/15 min, 11 veh/15 min, and 12 veh/15 min for through movement, left-turn movement, and right-turn movement volume estimation, respectively. This research provides a new possibility of utilizing existing data sources to obtain network-level TMC data without additional infrastructure and labor costs for transportation agencies.
1 July 2024 in Journal of Transportation Engineering, Part A: Systems
Vehicular flow rate is an essential measure commonly collected by inductive-loop detectors for transportation agencies to evaluate freeways and highways. Loop detectors are typically locate...
26 January 2023 in IEEE Transactions on Intelligent Transportation Systems
Accurate transit arrival time prediction is a critical factor for improving the quality of transit services. A significant factor that can affect transit arrival times is the other vehicles traveling on transit routes, as transit arrival time is significantly affected by traffic conditions. However, few previous studies considered traffic condition impacts in transit arrival time prediction due to a lack of real-time traffic data, reducing the accuracy in predictions under varying traffic conditions. To fill this research gap, crowdsourced speed data with wide coverage is utilized to indicate traffic conditions and to predict transit arrival time in conjunction with General Transit Feed Specification (GTFS) data. Interaction Networks (INs) are employed to model the interactions between transit speed, dwell time, and traffic speed for arrival time prediction. The proposed method only uses limited historical data and can predict arrival time at stops along a transit route. Ten days of data were collected from bus route #4 in Tucson, Arizona to evaluate the performance of the proposed method. The evaluation results show the average mean absolute percentage error (MAPE) of predicted arrival time on weekdays and weekends is 13.5% and 14%, respectively, indicating that the proposed method is promising for predicting transit arrival time while considering real-time traffic conditions. Furthermore, six traditional methods are compared with the proposed method, and the comparison results show the proposed method outperforms the other six methods.