Buses are recognized as a highly efficient mode of transportation, and therefore the reservation of lanes for them is considered to increase the attractiveness of the public transportation system. However, the routes of social vehicles often change due to the choice of dedicated lanes, which leads to dynamic changes in the state of the road network. Therefore, the main focus of this study is on the reservation of dedicated lanes for bus considering user equilibrium. Under the strict control of cost budget, the objective of this paper is to maximize network connectivity and minimize the negative impact on normal traffic due to the reduction of available lanes for social vehicles. We initially introduce a novel bi-objective bi-level programming model. Then, an NSGA-II algorithm is proposed to solve it. The effectiveness of the proposed model and method is verified by conducting a case study.
Traffic signs contain important traffic information. Timely and accurate perception and understanding of traffic sign could be significant for driving safety for intelligent autonomous vehicles. In this study, we prioritize the complex problem of cross country road sign understanding with limited data from only one country. Our proposal consists of unsupervised domain adaptation and attention module for Cross-country Traffic Sign Recognition. Most prevalent methods require large quantity of traffic sign data from different countries and states for cross-country traffic sign understanding which could be nearly infeasible due to difficulties in data acquisition, collection and data privacy policies. By applying Squeeze-and-Excitation attention module enhanced unsupervised domain adaptation (UDA), our work demonstrated quality performance in cross-country traffic sign understanding with only source domain data (Traffic sign samples in China). Experimental results suggest that our model can make accurate inferences on the understanding of cross-country traffic signs. We evaluated its performance using data from different countries, including China, Germany, Iran, etc.
With the continuous advancement of urbanization, traffic congestion becomes a major challenge for social development. Intelligent driving technology can ease the traffic pressure at intersections, which is the trend of future traffic development. Cooperative Adaptive Cruise Control (CACC) is a specific application of intelligent driving technology and a necessary step toward autonomous driving. This paper proposes a signal control method for CACC homogeneous traffic flow at single intersections based on deep reinforcement learning, which considers the operation characteristics of CACC vehicles at intersections and uses a grid-based state space input to improve the model prediction accuracy. On this basis, this paper proposes a variable phase duration strategy to enhance the phase control flexibility and a platoon clearance time to reduce the vehicle travel delay. Simulation experiments show that the signal control method based on deep reinforcement learning has a significant advantage over traditional signal control methods in the CACC homogeneous traffic flow environment and is more suitable for intersections with high traffic volume. The research results of this paper not only contribute to enriching the related research field but also offer a valuable reference for improving traffic safety and efficiency at intersections.
Most existing the mixed traffic flow with connected automated vehicles (CAVs) and human-driven vehicles (HDVs) on expressway off-ramp areas literature focuses on the possible impacts of CAVs with various penetration rates on the macroscopic traffic flow but neglects the platooning intensity of CAVs and comprehensive evaluation of Safety and Efficiency on expressway off-ramp areas. In this article, we proposed a novel model to detect the characteristics of mixed traffic flow on expressway off-ramp areas via not only taking into account the penetration rate of CAVs but also the platooning intensity of CAVs in the mixed traffic flow. Four car-following pairs of vehicles with different time headway are considered, including CAV-CAV, CAV-HDV, HDV-CAV, HDV-HDV respectively. To evaluate the impacts of the mixed traffic flow for both the safety and efficiency on expressway off-ramp areas, we adopted the TOPSIS (the technique for order performance by similarity to ideal solution) -Entropy method. The results showed that the penetration rates of CAVs have a positive influence both on the traffic Efficiency and safety on expressway off-ramp areas when the traffic demands level is free flow or saturated flow. Furthermore, the traffic efficiency could be improved significantly only if the penetration rate of CAVs reaches over 0.4 in the congested flow. By contrast, the intensity of platoons of CAVs lead to a negative effect in the traffic efficiency and safety on expressway off-ramp areas as the traffic demands increase on the road.
In context of modal shift and the reform of rail freight system, it is important to construct a competitive rail container pricing strategy. This paper regards the shippers on the freight line as bounded rational economic men, analyzes their transport mode choice behaviors on the basis of prospect theory and stochastic utility theory. In addition, an optimization model of rail container pricing is constructed with goals of maximizing the revenues of rail transport and volume of modal shift from road to rail, as well as minimizing the generalized costs of shippers. Finally, the freight data on a main freight lines in western China are used to evaluate the performance of the proposed pricing model. The experimental results show that compared with current rail container transport situation, the application of optimized pricing strategy and subsidy can increase the market share of rail container by 94.87%, and the profit by 68.18%. It also results in a reduction in shippers' expense by 5.73%. All of these prove that our proposed approach has practical and theoretical significance.
