RESUMO
This paper proposes a novel hybrid car-following model: the physics-informed conditional generative adversarial network (PICGAN), designed to enhance multi-step car-following modeling in mixed traffic flow scenarios. This hybrid model leverages the strengths of both physics-based and deep-learning-based models. By taking advantage of the inherent structure of GAN, the PICGAN eliminates the need for an explicit weighting parameter typically used in the combination of traditional physics-based and data-driven models. The effectiveness of the proposed model is substantiated through case studies using the NGSIM I-80 dataset. These studies demonstrate the model's superior trajectory reproduction, suggesting its potential as a strong contender to replace conventional models in trajectory prediction tasks. Furthermore, the deployment of PICGAN significantly enhances the stability and efficiency in mixed traffic flow environments. Given its reliable and stable results, the PICGAN framework contributes substantially to the development of efficient longitudinal control strategies for connected autonomous vehicles (CAVs) in real-world mixed traffic conditions.
RESUMO
Car-following modeling is essential in the longitudinal control for connected and autonomous vehicles (CAVs). Considering the advantage of the generative adversarial network (GAN) in capturing realistic data distribution, this paper applies conditional GAN (CGAN) to car-following modeling. The generator is elaborately designed with a sequence-to-sequence structure to reflect the decision-making process of human driving behavior. The proposed model is trained and tested based on the empirical dataset, and it is compared with a supervised learning model and a mathematical model. Numerical simulations are conducted to verify the model's performance, especially in the condition of mixed traffic flow. The comparison result shows that the CGAN model outperforms others in trajectory reproduction, indicating it can effectively imitate human driving behavior. The simulation results suggest that the introduction of CGAN-based CAVs improves the stability and efficiency of the mixed traffic flow.
RESUMO
The introduction of connected autonomous vehicles (CAVs) gives rise to mixed traffic flow on the roadway, and the coexistence of human-driven vehicles (HVs) and CAVs may last for several decades. CAVs are expected to improve the efficiency of mixed traffic flow. In this paper, the car-following behavior of HVs is modeled by the intelligent driver model (IDM) based on actual trajectory data. The cooperative adaptive cruise control (CACC) model from the PATH laboratory is adopted for the car-following model of CAVs. The string stability of mixed traffic flow is analyzed for different market penetration rates of CAVs, showing that CAVs can effectively prevent stop-and-go waves from forming and propagating. In addition, the fundamental diagram is obtained from the equilibrium state, and the flow-density chart indicates that CAVs can improve the capacity of mixed traffic flow. Furthermore, the periodic boundary condition is designed for numerical simulation according to the infinite length platoon assumption in the analytical approach. The simulation results are consistent with the analytical solutions, suggesting the validity of the string stability and fundamental diagram analysis of mixed traffic flow.
RESUMO
A prevalent family of fully convolutional networks are capable of learning discriminative representations and producing structural prediction in semantic segmentation tasks. However, such supervised learning methods require a large amount of labeled data and show inability of learning cross-domain invariant representations, giving rise to overfitting performance on the source dataset. Domain adaptation, a transfer learning technique that demonstrates strength on aligning feature distributions, can improve the performance of learning methods by providing inter-domain discrepancy alleviation. Recently introduced output-space based adaptation methods provide significant advances on cross-domain semantic segmentation tasks, however, a lack of consideration for intra-domain divergence of domain discrepancy remains prone to over-adaptation results on the target domain. To address the problem, we first leverage prototypical knowledge on the target domain to relax its hard domain label to a continuous domain space, where pixel-wise domain adaptation is developed upon a soft adversarial loss. The development of prototypical knowledge allows to elaborate specific adaptation strategies on under-aligned regions and well-aligned regions of the target domain. Furthermore, aiming to achieve better adaptation performance, we employ a unilateral discriminator to alleviate implicit uncertainty on prototypical knowledge. At last, we theoretically and experimentally demonstrate that the proposed prototypical knowledge oriented adaptation approach provides effective guidance on distribution alignment and alleviation on over-adaptation. The proposed approach shows competitive performance with state-of-the-art methods on two cross-domain segmentation tasks.
RESUMO
Considering that the road short-term traffic flow has strong time series correlation characteristics, a new long-term and short-term memory neural network (LSTM)-based prediction model optimized by the improved genetic algorithm (IGA) is proposed to improve the prediction accuracy of road traffic flow. Firstly, an improved genetic algorithm (IGA) is proposed by dynamically adjusting the mutation rate and crossover rate of standard GA. Secondly, the parameters of the LSTM, such as the number of hidden units, training times, gradient threshold and learning rate, are optimized by the IGA. Therefore, the optimal parameters are obtained. In the analysis stage, 5-min short-term traffic flow data are used to demonstrate the superiority of the proposed method over the existing neural network algorithms. Finally, the results show that the Root Mean Square Error achieved by the proposed algorithm is lower than that achieved by the other neural network methods in both the weekday and weekend data sets. This verifies that the algorithm can adapt well to different kinds of data and achieve higher prediction accuracy.
RESUMO
In order to resolve the imbalance of demand-capacity and airspace congestion, improve the performance of the en route air traffic management, promote the development of air traffic control automation system in the future, this paper proposes an En route air traffic control process model from the perspective of operation requirements. Taking the minimization of operation time, instantaneous density, maximum lateral displacement and air traffic controllers' workload as the optimization objectives, the commonly used air traffic control instructions such as climb and descent and speed restriction are set as constraints, the algorithm is designed based on the air traffic control scheme, and a complete air traffic control process are modeled which outputs instructions for each aircraft. Finally, the model is applied to a case study in the northwest region of China. The simulation results show that compared with the actual operation process, the total operation time is reduced by 18.6%, the variance of the lateral displacement and the vertical separation are efficiently reduced, and the en route air traffic capacity is improved. The proposed model envisages the following two innovations: (â °) the whole process of air traffic controllers' command is considered in the model, especially the control scheme and different types of instructions, and (â ±) the en route historical trajectory data of aircraft is used to as the key parameters of the input data to efficiently yield the acceptable results of the model. By quantifying the operation requirements of air traffic control, this model can also balance the distribution of traffic flow density, reduce the utilization rate of horizontal airspace, alleviate flight conflicts on air routes, and lessen the workload of controllers.
Assuntos
Aviação , Aeronaves , Automação , Aviação/métodos , Simulação por Computador , Humanos , Carga de TrabalhoRESUMO
Object tracking based on sparse representation has given promising tracking results in recent years. However, the trackers under the framework of sparse representation always overemphasize the sparse representation and ignore the correlation of visual information. In addition, the sparse coding methods only encode the local region independently and ignore the spatial neighborhood information of the image. In this paper, we propose a robust tracking algorithm. Firstly, multiple complementary features are used to describe the object appearance; the appearance model of the tracked target is modeled by instantaneous and stable appearance features simultaneously. A two-stage sparse-coded method which takes the spatial neighborhood information of the image patch and the computation burden into consideration is used to compute the reconstructed object appearance. Then, the reliability of each tracker is measured by the tracking likelihood function of transient and reconstructed appearance models. Finally, the most reliable tracker is obtained by a well established particle filter framework; the training set and the template library are incrementally updated based on the current tracking results. Experiment results on different challenging video sequences show that the proposed algorithm performs well with superior tracking accuracy and robustness.
Assuntos
Modelos Teóricos , Sistemas On-Line , Inteligência Artificial , Humanos , Interpretação de Imagem Assistida por Computador , Processamento de Imagem Assistida por Computador , Reconhecimento Visual de Modelos/fisiologia , Valor Preditivo dos Testes , Gravação em VídeoRESUMO
Traffic flow is widely recognized as an important parameter for road traffic state forecasting. Fuzzy state transform and Kalman filter (KF) have been applied in this field separately. But the studies show that the former method has good performance on the trend forecasting of traffic state variation but always involves several numerical errors. The latter model is good at numerical forecasting but is deficient in the expression of time hysteretically. This paper proposed an approach that combining fuzzy state transform and KF forecasting model. In considering the advantage of the two models, a weight combination model is proposed. The minimum of the sum forecasting error squared is regarded as a goal in optimizing the combined weight dynamically. Real detection data are used to test the efficiency. Results indicate that the method has a good performance in terms of short-term traffic forecasting.