Search Results

With the development of vehicle-road coordination technology, driving modes of the vehicle are in the process of development from manual driving, assisted driving, autonomous driving, mixed driving between people and vehicles to advanced unmanned driving. Heterogeneous traffic flows are essential for the development of vehicle-road coordination systems. However, in real life, it is necessary to intelligently monitor heterogeneous traffic flow because they involve many types of vehicles, complex scenarios, complex hidden factors in traffic conditions, and different operating characteristics of vehicles at different times and places.

In order to solve the problem that the existing customized bus can only select transfer points on the static line, and cannot dynamically plan the route according to the user's real-time demand, this paper establishes a route planning model of unmanned customized bus with the total cost minimization as the optimization goal. The model comprehensively considers the operating cost, passenger satisfaction and charging demand of driverless public transport to ensure efficient transportation and excellent user experience. Dijkstra algorithm is applied to solve the shortest path selection problem involved in the model, and genetic algorithm is used to solve the model. The route selection schemes of vehicle transportation plan, driving route and charging plan are obtained to achieve the goal of minimizing the total cost. The validity and practicability of the model and method are verified by the example of Sioux Falls network.

At present, prediction values of accurate traffic data by highway traffic control departments are not accurate enough. To provide better traffic guidance for pedestrians, new methods must be used to estimate traffic speed data with less error. This paper proposes an attention-convolution-bidirectional long short-term memory model that considers both temporal and spatial factors, combining a convolutional neural network with spatial local feature extraction capabilities and a bidirectional long short-term memory that can simultaneously consider long-term information in the forward and backward directions. Then add a layer of attention mechanism at the top to make the network architecture pay more attention to the temporal and spatial factors that contribute more weight to the final prediction, we use it to predict traffic speed that can better reflect the fluctuations of time and space.

The increasing number of vehicles has been causing many problems during the past years such as traffic congestion, environmental pollution and traffic accidents, etc. Recently, the impact of Connected and Autonomous Vehicle (CAV) on traffic system has received extensive interests, which is regarded as a promising driving pattern to significantly improve traffic safety and efficiency. Due to the developing technologies, more information flow topologies may appear in the future, which brings more challenges in the study on CAV. Thus, it is necessary to classify the topologies systematically to address the problem. Currently, some studies have provided certain insights on the influence of information flow topologies from several aspects including the internal stability, scalability, asymptotic stability and robustness etc. However, to the best of our knowledge, the influence of communication topologies on string stability is still unsatisfied and unclear.