Search

In this paper, we study the shortest path problem (SPP) with multiple source-destination pairs (MSD), namely MSD-SPP, to minimize average travel time of all shortest paths. The inherent traffic capacity limits within a road network contributes to the competition among vehicles. Multi-agent reinforcement learning (MARL) model cannot offer effective and efficient path planning cooperation due to the asynchronous decision making setting in MSD-SPP, where vehicles (a.k.a agents) cannot simultaneously complete routing actions in the previous time step. To tackle the efficiency issue, we propose to divide an entire road network into multiple sub-graphs and subsequently execute a two-stage process of inter-region and intra-region route planning. To address the asynchronous issue, in the proposed asyn-MARL framework, we first design a global state, which exploits a low-dimensional vector to implicitly represent the joint observations and actions of multi-agents. Then we develop a novel trajectory collection mechanism to decrease the redundancy in training trajectories. Additionally, we design a novel actor network to facilitate the cooperation among vehicles towards the same or close destinations and a reachability graph aimed at preventing infinite loops in routing paths. On both synthetic and real road networks, our evaluation result demonstrates that our approach outperforms state-of-the-art planning approaches.

Multi-section license plate recognition (LPR) data provides input-output information and sampled travel times of the investigated link, serving as an ideal data source for lane-based queue length estimation in recent studies. However, most of these studies assumed the strict FIFO rule or a specific arrival process, thus ignoring the potential impact of overtaking and the variation of traffic flows, especially in multi-lane scenarios. To address this issue, we propose a probabilistic approach to derive the stochastic queue length by constructing a conditional probability model of no-delay arrival time (NAT), i.e., the arrival time of vehicles without experiencing any delay, based on multi-section LPR data. First, the NAT conditions for all vehicles are established based on upstream and downstream vehicle departure times and sequences. To reduce the computational dimensionality and complexity, a DP-based algorithm is developed for vehicle group partitioning based on potential interactions between vehicles. Then, the conditional probability of NATs of each vehicle group is derived and an MCMC sampling method is employed for calculation. Subsequently, the stochastic queue profile and maximum queue length for each cycle can be derived based on the NATs of vehicles. Eventually, to leverage the LPR data sufficiently, we extend our approach to multi-lane scenarios, where the problem can be converted to a weighted general exact coverage problem and solved by a backtracking algorithm with heuristics. Empirical and simulation experiments have shown that the proposed approach outperforms the state-of-the-art method, demonstrating significant improvements in accuracy and robustness across various traffic conditions, including different V/C ratios, matching rates, and FIFO violation rates. In addition, the performance of the proposed approach can be further improved by utilizing multi-lane LPR data., Comment: 30 pages, 20 figures

Recent advancements in Connected Vehicle (CV) technology have prompted research on leveraging CV data for more effective traffic management. Despite the low penetration rate, such detailed CV data has demonstrated great potential in improving traffic signal performance. However, existing studies share a common shortcoming in that they all ignore traffic flow estimation errors in their modeling process, which is inevitable due to the sampling observation nature of CVs. This study proposes a CV data-driven robust optimization framework for traffic signal timing accounting for both traffic flow variability and estimation errors. First, we propose a general CV data-driven optimization model that can be widely applied to various signalized intersection scenarios including under-/over-saturated and fixed-/real-time. Then, we propose a novel data-driven uncertainty set of arrival rates based on the bounds information derived from CVs, which circumvents the error-prone arrival rate estimation process. Finally, a CV data-driven robust optimization model (CV-RO) is formulated to explicitly handle arrival rate uncertainties. By means of the robust counterpart approach, this robust optimization problem can be equalized to a deterministic mixed-integer linear programming problem with an exact solution. The evaluation results highlight the superior performance of the CV-RO model compared to the deterministic model and traditional methods across various scenarios: different penetration rates, traffic demands, and control types. Notably, the CV-RO model demonstrates its excellence at lower CV penetration rates and in the presence of different traffic flow fluctuation levels, affirming its effectiveness and robustness., Comment: Accepted for podium session of the Conference in Emerging Technologies in Transportation Systems (TRC-30)

Accurate traffic demand estimation is critical for the dynamic evaluation and optimization of signalized intersections. Existing studies based on connected vehicle (CV) data are designed for a single phase only and have not sufficiently studied the real-time traffic demand estimation for oversaturated traffic conditions. Therefore, this study proposes a cycle-by-cycle multi-phase traffic demand joint estimation method at signalized intersections based on CV data that considers both undersaturated and oversaturated traffic conditions. First, a joint weighted likelihood function of traffic demands for multiple phases is derived given real-time observed CV trajectories, which considers the initial queue and relaxes the first-in-first-out assumption by treating each queued CV as an independent observation. Then, the sample size of the historical CVs is used to derive a joint prior distribution of traffic demands. Ultimately, a joint estimation method based on the maximum a posteriori (i.e., the JO-MAP method) is developed for cycle-based multi-phase traffic demand estimation. The proposed method is evaluated using both simulation and empirical data. Simulation results indicate that the proposed method can produce reliable estimates under different penetration rates, arrival patterns, and traffic demands. The feature of joint estimation makes our method less demanding for the penetration rate of CVs and the consideration of prior distribution can significantly improve the estimation accuracy. Empirical results show that the proposed method achieves accurate cycle-based traffic demand estimation with a MAPE of 12.73%, outperforming the other four methods., Comment: 30 pages, 11 figures

Time-dependent fixed-time control is a cost-effective control method that is widely employed at signalized intersections in numerous countries. Existing optimization models rely on traditional delay models with specific assumptions regarding vehicle arrivals. Recent advancements in intelligent mobility have led to development of high-resolution trajectory data of connected vehicles (CVs), thereby providing opportunities for improving fixed-time signal control. Taking advantage of CV trajectories, this study proposes a cumulative flow diagram (CFD)-based signal timing optimization method for fixed-time signal control at isolated intersections, which includes a CFD model and a multi-objective optimization model. The CFD model is formulated to profile the time-dependent vehicle arrival and departure processes under varying signal timing plans, where the intersection demand is estimated based on a weighted maximum likelihood estimation method. Then, a CFD-based multi-objective optimization model is proposed for both undersaturated and oversaturated traffic conditions. The primary objective is to minimize the exceeded queue dissipation time, whereas the secondary objective is to minimize the average delay at the intersection. Considering the data-driven property of the CFD model, a bi-level particle swarm optimization-based algorithm is then specially designed to solve the optimal cycle length (and the reference point if it is considered) and green ratios separately. The proposed method is evaluated based on simulation data and compared with Synchro. The results indicate that the proposed method outperforms Synchro under various traffic conditions in terms of average delay and queue since the time-dependent vehicle arrivals during the cycle are considered in a CV trajectory data-driven way., Comment: 15 pages, 20 figures