This paper presents a mathematical model to determine the optimal routes for a heterogeneous fleet comprising autonomous and human-driven vehicles operating in freight distribution. The model is formulated as a mixed-integer programming problem with multiple objectives: minimize total emissions, energy consumption, and operational costs, while maximizing the reliability associated with autonomous vehicle deployment. A dedicated parameter models the probability that an autonomous vehicle can successfully traverse a given arc, enforcing a minimum reliability threshold. The proposed optimization framework is embedded within a higher-level decision support system that enables route adjustments based on discrete-time monitoring of network reliability conditions. Since the multi-objective model is solved by means of scalarization, a specific algorithm is designed to adjust the weights of the objectives. A case study is provided to demonstrate the effectiveness of the model and its practical applicability. To further enhance the performance of the proposed model in solving larger instances, three families of valid inequalities are presented, and a computational comparison between the basic model and the improved model is shown in a single-objective environment (operational cost minimization). We also implement a constructive heuristic and an Adaptive Large Neighborhood Search metaheuristic to further appreciate the reduced duality gaps achieved by the enhanced model.
With the gradual digitization of highways, traffic data is reshaping the role of related fields. Establishing comprehensive data acquisition networks enables the analysis of operational strategies for transportation-associated projects, which provides robust support for the development of smart highways. This study investigates strategic deployment issues at the intersection of highway transportation systems and photovoltaic (PV) energy system allocation. By leveraging efficient networks to transmit data to processing centers, this approach facilitates the synergistic development of intelligent transportation and smart energy systems. This study focuses on the coordinated deployment of highway transportation and photovoltaic energy systems, aiming at transmitting data to data processing centers through efficient networks to promote the integration of smart transportation and smart energy. The proposed photovoltaic energy intelligent allocation mechanism has information traceability and can be associated with the traffic flow statistical model for analysis. The Particle Swarm Optimization-Conditional Kernel Density Estimation (PSO-CKDE) model can effectively infer the traffic flow of the whole network, and introduce the adversarial analysis framework with the operation information entropy of the photovoltaic energy allocation model. The validation work for this study was conducted over a three-month period from April to June 2024, during which a single expressway section in Jiangsu Province was selected for the scenario test. Simulation results verify that the proposed method reduces the prediction error (measured by RMSE) by 32
Road segmentation is a fundamental task in transportation-oriented road network extraction, yet its performance is often limited by scarce pixel-wise annotations and the difficulty of exploiting unlabeled imagery. To address this issue, this paper proposes Multi-Constraint Consistency Learning (MCCL), a semi-supervised framework that improves road extraction through complementary constraints at the feature, perturbation, and representation levels. Specifically, Cross-Augmentation Feature Alignment (CAFA) reduces semantic drift between weakly and strongly augmented views by enforcing pixel-level feature consistency and prototype-level intra-class compactness, while Similarity-Adaptive Feature Perturbation (SAFP) improves decoder robustness by applying adaptive feature masking and noise injection guided by cross-view similarity. In addition, a dual-branch backbone combines convolutional local-detail modeling with Transformer-based global-context modeling, and a Feature Fusion Module (FFM) integrates the two streams to obtain more structurally coherent road representations. Extensive experiments on the DeepGlobe and Massachusetts road datasets demonstrate that the proposed method consistently outperforms representative fully supervised and semi-supervised methods under different labeling ratios. In particular, under the 1/64 labeling ratio, the proposed method achieves 73.58
The connected vehicles have shown great potential in improving traffic efficiency, but their influence on mixed traffic has not been fully understood. This study proposed and evaluated a simple cooperative control method at unsignalized intersections. All vehicles in this study were assumed to be connected, including connected autonomous vehicles and connected manual vehicles. Both of them could receive real-time information and instructions from control center. Vehicles without conflict relationships were allowed to enter an intersection simultaneously by following the suggested order. Moreover, overtaking was allowed based on the predicted probability of success, which leaded to a high level of vehicle cooperation. A microsimulation was developed and implemented based on cellular automata to validate the proposed method. By comparing with priority control and signal control, the proposed method was demonstrated efficient under traffic flow rates that did not cause congestion, and resulted in better efficiency when the penetration of automated vehicles exceeds 75
Urban corridors in large Indian cities continue to face severe congestion as traffic demand grows faster than available roadway capacity. The Fateh Nagar Railway Flyover in Hyderabad is one such location, routinely carrying flows well above 3,200 PCU/hr, far beyond the Indo-HCM guideline for a single lane. Under these conditions, vehicles crawl at 6–12 km/h and experience delays of more than 200 s, indicating a failing level of service. To examine these conditions and assess possible remedies, this study brings together three commonly used but rarely integrated tools: the BPR speed–flow model, PTV VISSIM microsimulation, and an Artificial Neural Network-based delay estimator. The workflow involved calibrating the BPR parameters, tuning driver-behaviour settings in VISSIM to reflect the observed mixed-traffic environment, and validating the predictions using both regression models and the neural network. Model performance was evaluated with standard statistical measures. Improvement scenarios primarily involved widening the Balkampet–Fateh Nagar section and introducing a parallel Railway Over Bridge (ROB), which were then tested. The calibrated BPR model reproduced field delays with errors under four seconds, while VISSIM reflected actual speeds and flows within a 10
