Stop-and-go traffic poses significant challenges to the efficiency and safety of traffic operations, and its impacts and working mechanism have attracted much attention. Recent studies have shown that Connected and Automated Vehicles (CAVs) with carefully designed longitudinal control have the potential to dampen the stop-and-go wave based on simulated vehicle trajectories. In this study, Deep Reinforcement Learning (DRL) is adopted to control the longitudinal behavior of CAVs and real-world vehicle trajectory data is utilized to train the DRL controller. It considers a Human-Driven (HD) vehicle tailed by a CAV, which are then followed by a platoon of HD vehicles. Such an experimental design is to test how the CAV can help to dampen the stop-and-go wave generated by the lead HD vehicle and contribute to smoothing the following HD vehicles’ speed profiles. The DRL control is trained using real-world vehicle trajectories, and eventually evaluated using SUMO simulation. The results show that the DRL control decreases the speed oscillation of the CAV by 54% and 8%-28% for those following HD vehicles. Significant fuel consumption savings are also observed. Additionally, the results suggest that CAVs may act as a traffic stabilizer if they choose to behave slightly altruistically.
more »
« less
Full Vehicle Trajectory Planning Model for Urban Traffic Control Based on Imitation Learning
Connected and automated vehicles (CAVs) extend urban traffic control from temporal to spatiotemporal by enabling the control of CAV trajectories. Most of the existing studies on CAV trajectory planning only consider longitudinal behaviors (i.e., in-lane driving), or assume that the lane changing can be done instantaneously. The resultant CAV trajectories are not realistic and cannot be executed at the vehicle level. The aim of this paper is to propose a full trajectory planning model that considers both in-lane driving and lane changing maneuvers. The trajectory generation problem is modeled as an optimization problem and the cost function considers multiple driving features including safety, efficiency, and comfort. Ten features are selected in the cost function to capture both in-lane driving and lane changing behaviors. One major challenge in generating a trajectory that reflects certain driving policies is to balance the weights of different features in the cost function. To address this challenge, it is proposed to optimize the weights of the cost function by imitation learning. Maximum entropy inverse reinforcement learning is applied to obtain the optimal weight for each feature and then CAV trajectories are generated with the learned weights. Experiments using the Next Generation Simulation (NGSIM) dataset show that the generated trajectory is very close to the original trajectory with regard to the Euclidean distance displacement, with a mean average error of less than 1 m. Meanwhile, the generated trajectories can maintain safety gaps with surrounding vehicles and have comparable fuel consumption.
more » « less- NSF-PAR ID:
- 10379496
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- Transportation Research Record: Journal of the Transportation Research Board
- Volume:
- 2676
- Issue:
- 7
- ISSN:
- 0361-1981
- Page Range / eLocation ID:
- p. 186-198
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Stop-and-go traffic poses significant challenges to the efficiency and safety of traffic operations, and its impacts and working mechanism have attracted much attention. Recent studies have shown that Connected and Automated Vehicles (CAVs) with carefully designed longitudinal control have the potential to dampen the stop-and-go wave based on simulated vehicle trajectories. In this study, Deep Reinforcement Learning (DRL) is adopted to control the longitudinal behavior of CAVs and real-world vehicle trajectory data is utilized to train the DRL controller. It considers a Human-Driven (HD) vehicle tailed by a CAV, which are then followed by a platoon of HD vehicles. Such an experimental design is to test how the CAV can help to dampen the stop-and-go wave generated by the lead HD vehicle and contribute to smoothing the following HD vehicles’ speed profiles. The DRL control is trained using realworld vehicle trajectories, and eventually evaluated using SUMO simulation. The results show that the DRL control decreases the speed oscillation of the CAV by 54% and 8%-28% for those following HD vehicles. Significant fuel consumption savings are also observed. Additionally, the results suggest that CAVs may act as a traffic stabilizer if they choose to behave slightly altruistically.more » « less
-
null (Ed.)Connected and automated vehicles (CAVs) will undoubtedly transform many aspects of transportation systems in the future. In the meantime, transportation agencies must make investment and policy decisions to address the future needs of the transportation system. This research provides much-needed guidance for agencies about planning-level capacities in a CAV future and quantify Highway Capacity Manual (HCM) capacities as a function of CAV penetration rates and vehicle behaviors such as car-following, lane change, and merge. As a result of numerous uncertainties on CAV implementation policies, the study considers many scenarios including variations in parameters (including CAV gap/headway settings), roadway geometry, and traffic characteristics. More specifically, this study considers basic freeway, freeway merge, and freeway weaving segments in which various simulation scenarios are evaluated using two major CAV applications: cooperative adaptive cruise control and advanced merging. Data from microscopic traffic simulation are collected to develop capacity adjustment factors for CAVs. Results show that the existence of CAVs in the traffic stream can significantly enhance the roadway capacity (by as much as 35% to 40% under certain cases), not only on basic freeways but also on merge and weaving segments, as the CAV market penetration rate increases. The human driver behavior of baseline traffic also affects the capacity benefits, particularly at lower CAV market penetration rates. Finally, tables of capacity adjustment factors and corresponding regression models are developed for HCM implementation of the results of this study.more » « less
-
more » « less
Abstract This article focuses on the development of distributed robust model predictive control (MPC) methods for multiple connected and automated vehicles (CAVs) to ensure their safe operation in the presence of uncertainty. The proposed layered control framework includes reference trajectory generation, distributionally robust obstacle occupancy set computation, distributed state constraint set evaluation, data-driven linear model representation, and robust tube-based MPC design. To enable distributed operation among the CAVs, we present a method, which exploits sampling-based reference trajectory generation and distributed constraint set evaluation methods, that decouples the coupled collision avoidance constraint among the CAVs. This is followed by data-driven linear model representation of the nonlinear system to evaluate the convex equivalent of the nonlinear control problem. Finally, to ensure safe operation in the presence of uncertainty, this article employs a robust tube-based MPC method. For a multiple CAV lane change problem, simulation results show the efficacy of the proposed controller in terms of computational efficiency and the ability to generate safe and smooth CAV trajectories in a distributed fashion.
-
null (Ed.)For energy-efficient Connected and Automated Vehicle (CAV) Eco-driving control on signalized arterials under uncertain traffic conditions, this paper explicitly considers traffic control devices (e.g., road markings, traffic signs, and traffic signals) and road geometry (e.g., road shapes, road boundaries, and road grades) constraints in a data-driven optimization-based Model Predictive Control (MPC) modeling framework. This modeling framework uses real-time vehicle driving and traffic signal data via Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communications. In the MPC-based control model, this paper mathematically formulates location-based traffic control devices and road geometry constraints using the geographic information from High-Definition (HD) maps. The location-based traffic control devices and road geometry constraints have the potential to improve the safety, energy, efficiency, driving comfort, and robustness of connected and automated driving on real roads by considering interrupted flow facility locations and road geometry in the formulation. We predict a set of uncertain driving states for the preceding vehicles through an online learning-based driving dynamics prediction model. We then solve a constrained finite-horizon optimal control problem with the predicted driving states to obtain a set of Eco-driving references for the controlled vehicle. To obtain the optimal acceleration or deceleration commands for the controlled vehicle with the set of Eco-driving references, we formulate a Distributionally Robust Stochastic Optimization (DRSO) model (i.e., a special case of data-driven optimization models under moment bounds) with Distributionally Robust Chance Constraints (DRCC) with location-based traffic control devices and road geometry constraints. We design experiments to demonstrate the proposed model under different traffic conditions using real-world connected vehicle trajectory data and Signal Phasing and Timing (SPaT) data on a coordinated arterial with six actuated intersections on Fuller Road in Ann Arbor, Michigan from the Safety Pilot Model Deployment (SPMD) project.more » « less
