Accurate real-time traffic forecasting is a core technological problem against the implementation of the intelligent transportation system. However, it remains challenging considering the complex spatial and temporal dependencies among traffic flows. In the spatial dimension, due to the connectivity of the road network, the traffic flows between linked roads are closely related. In the temporal dimension, although there exists a tendency among adjacent time points, the importance of distant time points is not necessarily less than that of recent ones, since traffic flows are also affected by external factors. In this study, an attention temporal graph convolutional network (A3T-GCN) was proposed to simultaneously capture global temporal dynamics and spatial correlations in traffic flows. The A3T-GCN model learns the short-term trend by using the gated recurrent units and learns the spatial dependence based on the topology of the road network through the graph convolutional network. Moreover, the attention mechanism was introduced to adjust the importance of different time points and assemble global temporal information to improve prediction accuracy. Experimental results in real-world datasets demonstrate the effectiveness and robustness of the proposed A3T-GCN. We observe the improvements in RMSE of 2.51–46.15% and 2.45–49.32% over baselines for the SZ-taxi and Los-loop, respectively. Meanwhile, the Accuracies are 0.95–89.91% and 0.26–10.37% higher than the baselines for the SZ-taxi and Los-loop, respectively.
A coordinated torque distribution method (CTDM) combined with balanced torque vectoring distribution method (BTVDM) and differential braking distribution method (DBDM) is proposed to enhance vehicle lateral stability and improve ride comfort. The phase plane of sideslip angle and its angular velocity with three regions are used to evaluate vehicle lateral stability. The models of region boundary parameters considering vehicle velocity, steering angle, and road adhesion coefficient are established on the basis of the nonlinear partial least squares regression model (NLPLSRM). Vehicle lateral stability is dynamically evaluated on the basis of the vehicle state position in the phase plane. The distribution ratio of direct yaw moment (DYM) realised by DBDM and BTVDM is determined in accordance with the instability risk of vehicle lateral stability. Compared with BTVDM and DBDM, the proposed CTDM can correctly realise the accuracy of DYM and reduce vehicle velocity, which is beneficial to improving vehicle lateral stability. Numerical simulation results show that the proposed CTDM substantially improves vehicle lateral stability and reduces control intervention for ride comfort.
20 September 2016 in Transportation Planning and Technology
Based on the increasing demands of transportation development, the concept of an Intelligent Transportation System (ITS) has received increasing attention in both academic and industry arenas. It integrates information, communications, computers and other technologies, and applies them in the field of transportation to build an integrated system of people, roads and vehicles by utilizing advanced data communication technologies. It can establish a large, fully functioning, real-time, accurate and efficient transportation management system. Intelligent transportation systems shift the focus from road managers to road users. In order to achieve this purpose, intelligent transportation systems use advanced technology to provide drivers with convenient information to help reduce traffic congestion and to increase available road capacity. This special issue is dedicated to exploring the most recent advances in intelligent transportation systems and big data based on intelligent technology.
1 September 2019 in Journal of Central South University
Traffic flow forecasting is an important function of intelligent transportation systems. With the rise of deep learning, building traffic flow prediction models based on deep neural networks has become a current research hotspot. Most of the current traffic flow prediction methods are designed from the perspective of model architectures, using only the traffic features of future moments as supervision signals to guide the models to learn the spatiotemporal dependence in traffic flow. However, traffic flow data themselves contain rich spatiotemporal features, and it is feasible to obtain additional self-supervised signals from the data to assist the model to further explore the underlying spatiotemporal dependence. Therefore, we propose a self-supervised traffic flow prediction method based on a spatiotemporal masking strategy. A framework consisting of symmetric backbone models with asymmetric task heads were applied to learn both prediction and spatiotemporal context features. Specifically, a spatiotemporal context mask reconstruction task was designed to force the model to reconstruct the masked features via spatiotemporal context information, so as to assist the model to better understand the spatiotemporal contextual associations in the data. In order to avoid the model simply making inferences based on the local smoothness in the data without truly learning the spatiotemporal dependence, we performed a temporal shift operation on the features to be reconstructed. The experimental results showed that the model based on the spatiotemporal context masking strategy achieved an average prediction performance improvement of 1.56% and a maximum of 7.72% for longer prediction horizons of more than 30 min compared with the backbone models.
In 2008, an Intelligent Vehicle Infrastructure Experiment System (IVIES) based on Wi-Fi technology was built at Tongji University to test the solutions for traffic safety and environmental problems. TongJi Cooperative Traffic System (TJ-CTS) is the updated version testbed of IVIES; it has lower data communication latency and can support higher-speed test vehicles. In this paper, we present an overview of TJ-CTS. First, we present the overall system architecture of TJ-CTS. Three layers are expounded from the viewpoint of structure. Then, based on the analysis of the requirements for latency of safety applications, we present the related devices used in TJ-CTS in detail, such as the Processing Unit, GPS Receiver and Software Development Environment. Compared with IVIES, TJ-CTS have better performance and can satisfy the requirements of traffic safety researches in urban roads and expressways.