Evaluating Efficiency and Safety of Mixed Traffic with Connected and Autonomous Vehicles in Adverse Weather

Hou, Guangyang

doi:10.3390/su15043138

Cited by 16 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the existing research results, in the future, we plan to enrich and expand the traffic flow prediction framework by integrating multi-source external data, such as weather 37 , holidays 38 , and regional POI features 39 , to enhance the capture ability of geospatial semantic information of the model. At the same time, new arriving data are processed in real-time, and a more effective prediction system is explored in the field of dynamic training 40 , to further optimize the design of the traffic flow prediction model and improve its generalization ability.…”

Section: Discussionmentioning

confidence: 99%

Road traffic flow prediction based on dynamic spatiotemporal graph attention network

Chen,

Huang,

et al. 2023

Sci Rep

View full text Add to dashboard Cite

To improve the prediction accuracy of traffic flow under the influence of nearby time traffic flow disturbance, a dynamic spatiotemporal graph attention network traffic flow prediction model based on the attention mechanism was proposed. Considering the macroscopic periodic characteristics of traffic flow, the spatiotemporal features are extracted by constructing spatiotemporal blocks with an adjacent period, daily period, and weekly period respectively. The spatiotemporal block is mainly composed of a two-layer graph attention network and a gated recurrent unit to capture the hidden features of space and time. In space, based on considering adjacent road segments, the Pearson correlation coefficient is used to capture the hidden correlation characteristics between non-adjacent road segments according to a certain time step. In terms of time, due to the random disturbance of traffic flow at the micro level, the attention mechanism is introduced to use the adjacent time as the query matrix to weight the output characteristics of daily cycle and weekly cycle, and the three are connected in series to output the prediction results through the linear layer. Finally, the experimental results on the public data sets show that the proposed model is superior to the six baseline models.

show abstract

Section: Discussionmentioning

confidence: 99%

Road traffic flow prediction based on dynamic spatiotemporal graph attention network

Chen,

Huang,

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In future research, we hope to construct more accurate models by considering factors that have an impact on traffic flow, such as weather [45], epidemic [46], or driver's driving style [47]. In addition, we will further consider the impact of cyclical vacations on traffic and try to research using techniques such as continual learning [48].…”

Section: Discussionmentioning

confidence: 99%

Gated Recurrent Graph Convolutional Attention Network for Traffic Flow Prediction

Feng

Chen

et al. 2023

Sustainability

View full text Add to dashboard Cite

Traffic flow prediction is an important function of intelligent transportation systems. Accurate prediction results facilitate traffic management to issue early congestion warnings so that drivers can avoid congested roads, thus directly reducing the average driving time of vehicles, which means less greenhouse gas emissions. However, traffic flow data has complex spatial and temporal correlations, which makes it challenging to predict traffic flow accurately. A Gated Recurrent Graph Convolutional Attention Network (GRGCAN) for traffic flow prediction is proposed to solve this problem. The model consists of three components with the same structure, each of which contains one temporal feature extractor and one spatial feature extractor. The temporal feature extractor first introduces a gated recurrent unit (GRU) and uses the hidden states of the GRU combined with an attention mechanism to adaptively assign weights to each time step. In the spatial feature extractor, a node attention mechanism is constructed to dynamically assigns weights to each sensor node, and it is fused with the graph convolution operation. In addition, a residual connection is introduced into the network to reduce the loss of features in the deep network. Experimental results of 1-h traffic flow prediction on two real-world datasets (PeMSD4 and PeMSD8) show that the mean absolute percentage error (MAPE) of the GRGCAN model is as low as 15.97% and 12.13%, and the prediction accuracy and computational efficiency are better than the baselines.

show abstract

“…For instance, Li et al [23] assessed the effects of three CAV driving strategies-adaptive cruise control, follower-stopper, and jam-absorption driving-on both ring roads and freeways in mixed traffic conditions. Hou [24] explored the impact of CAVs on traffic efficiency and safety in mixed traffic under varying weather conditions. Liang et al [25] created a multi-agent system-based hierarchical architecture for CAV platoon control, enhancing efficiency and safety through coordinated decision-making and actions.…”

Section: Related Workmentioning

confidence: 99%

Simulating and Modelling the Safety Impact of Connected and Autonomous Vehicles in Mixed Traffic: Platoon Size, Sensor Error, and Path Choice

Papadoulis,

Imprialou,

Feng

et al. 2024

Machines

View full text Add to dashboard Cite

The lack of real-world data on Connected and Autonomous Vehicles (CAVs) has prompted researchers to rely on simulations to assess their societal impacts. However, few studies address the operational and technological challenges of integrating CAVs into existing transport systems. This paper introduces a new CAV driving model featuring a constant time gap longitudinal control algorithm that accounts for sensor errors and platoon formations of varying sizes. Additionally, it develops a high-level route-based decision-making algorithm for CAV path choice. These algorithms were tested in a calibrated motorway corridor simulation, examining different market penetration rates, platoon sizes, and sensor error scenarios. Traffic conflicts were used as a primary safety performance indicator. The findings indicate that CAV sensors are generally adequate, but optimal platoon sizes vary with market penetration rates. To further explore factors influencing traffic conflicts, a hierarchical Bayesian negative binomial regression model was used. This model revealed that in addition to unobserved heterogeneity and spatial autocorrelation, the standard deviation of speeds between lanes and the CAV market penetration rate significantly affect conflict occurrences. These results corroborate the simulation outcomes, enhancing our understanding of CAV deployment impacts on traffic safety.

show abstract

Evaluating Efficiency and Safety of Mixed Traffic with Connected and Autonomous Vehicles in Adverse Weather

Cited by 16 publications

References 42 publications

Road traffic flow prediction based on dynamic spatiotemporal graph attention network

Road traffic flow prediction based on dynamic spatiotemporal graph attention network

Gated Recurrent Graph Convolutional Attention Network for Traffic Flow Prediction

Simulating and Modelling the Safety Impact of Connected and Autonomous Vehicles in Mixed Traffic: Platoon Size, Sensor Error, and Path Choice

Contact Info

Product

Resources

About