The Driver Time Memory Car-Following Model Simulating in Apollo Platform with GRU and Real Road Traffic Data

Fei, Rong; Li, Shasha; Hei, Xinhong; Xu, Qingzheng; Liu, Fang; Hu, Bo

doi:10.1155/2020/4726763

Cited by 7 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other data-driven models, which outperformed mathematical methods, have been put forward (21)(22)(23)(24)(25). Data-driven car-following models that consider the effect of driver memory have also been proposed (26)(27)(28)(29)(30)(31). These models utilize recurrent neural networks (RNNs), gated recurrent units, or LSTM models to replicate human driving styles, and have demonstrated promising results in capturing complex car-following behaviors.…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Car-Following Behavior of Autonomous Vehicle and Human-Driven Vehicle Based on Drivers’ Memory and Cooperation With Lead Vehicle

Adewale,

Lee

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Autonomous vehicles (AVs) have moved from hype to reality as the penetration and acceptance rate continues to increase. As they are slowly integrated into traffic with human-driven vehicles (HDVs), it is necessary to predict the car-following behaviors of AVs and HDVs for better control of AV–HDV mixed traffic. This study extends a data-driven car-following model to incorporate drivers’ memory, and cooperation with the lead vehicle. The model predicts the following vehicle’s speed in AV–HDV mixed traffic. The effect of drivers’ cooperation on car-following behavior was modeled using prospect theory (PT), whereas the driver’s memory was incorporated using the memory cell of a long short-term memory (LSTM) neural network. This extended car-following model is called the “PT-LSTM model.” Real-world vehicle trajectories of HDVs and AVs in the Waymo AV Open Dataset were used to calibrate and validate the PT-LSTM model. The PT-LSTM model demonstrated higher accuracy compared with the LSTM model that did not consider drivers’ cooperation, the multiple layer perceptron model, Gipps’ model, and the intelligent driver model that incorporated PT. The importance of variables in different time steps in the PT-LSTM model was also evaluated using SHapley Additive exPlanations (SHAP). The SHAP results showed that AV followers were more likely to cooperate with the lead HDV, whereas HDV followers were more likely to cooperate with the lead AV than the lead HDV. Thus, this study underscores the importance of considering drivers’ memory and cooperation with the lead vehicle for the prediction of car-following behaviors in AV–HDV mixed traffic.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Car-Following Behavior of Autonomous Vehicle and Human-Driven Vehicle Based on Drivers’ Memory and Cooperation With Lead Vehicle

Adewale,

Lee

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…It was introduced as a simpler alternative to the more complex Long Short-Term Memory (LSTM) networks, which were originally developed to address the vanishing gradient problem in traditional RNNs [20]. GRU was proposed by Cho, Kyunghyun; van Merrienboer, Bart; Bahdanau, DZmitry; Bougares, Fethi; Schwenk, Holger; and Bengio, Yoshua as a way to maintain similar modelling capabilities to LSTMs while simplifying the architecture and are known for their efficiency and practicality [21,22]. In the context of understanding GRUs, it's important to highlight key differentiators from LSTMs, including the reduction in the number of parameters, simplified training processes, and the role of specific gates like the update gate 𝑧 𝑡 , and the reset gate 𝑟 𝑡 .…”

Section: Gated Recurrent Unitmentioning

confidence: 99%

Analyzing Election Sentiments in Tweets with Gated Recurrent Units (GRU)

Agu Edward O.,

Zevini,

Abiola

2023

AJRCoS

View full text Add to dashboard Cite

Sentiment analysis, a key task in natural language processing, is important for detecting the emotional tone portrayed in text. In this study, we focus on implementing a Gated Recurrent Unit (GRU) model to analyze attitudes within the 2020 Donald Trump Election tweets dataset. By setting the GRU model with carefully selected parameters, the aim of the study is to unveil the inherent sentiment patterns in the dataset. To develop the sentiment analysis model, the study devised a three phase methodology which that include data preprocessing, feature selection using correlation matrix, and lastly the implementation of GRU. Futhermore, we provided the outcomes of our experiment, evaluating the model's performance through important measures such as accuracy, precision, and recall. Notably, our data exhibit an exceptional accuracy rate of 93%, verifying the model's power to appropriately categorize attitudes. Additionally, both recall and precision receive outstanding ratings of 94% and 96%, indicating the model's skill in distinguishing both positive and negative attitudes. This inquiry emphases the effective usage of the GRU model in sentiment analysis, shedding light on the emotional nuances within the 2020 Donald Trump dataset and enriching our understanding of sentiments during the election period.

show abstract

“…Jafaripournimchahi et al developed a new CF model to investigate the effects of driver anticipation and driver memory on traffic flow [13]. Fei et al developed a CF model with driver time memory based on real-world traffic data, which is effective and robust, thereby improving simulation accuracy [14]. Chen et al believed that data-driven CF models could be a promising research direction [15,16].…”

Section: Introductionmentioning

confidence: 99%

Car-Following Model with Automatic Reaction Delay Estimation: An Attention-Based Ensemble Learning Methodology

Liao

Lin

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

Car-following behavior is a vital traffic phenomenon in the process of vehicle driving. For modeling the car-following behavior, it is crucial to capture the reaction delay for balancing with safety and comfort, but it is generally ignored in existing works. This work proposes a car-following model based on attention-based ensemble learning to automatically capture the reaction delay from driving data and better depict the traffic flow characteristics. The model integrates a data-driven model and a theory-driven model, and a weight computation method is proposed to combine the advantage of these two different models. In detail, an encoder-decoder model and attention mechanism are employed to capture the reaction delay from driving data. Extensive experiments show that the proposed model could balance safety with comfort and help avoid unsafe driving behavior.

show abstract

The Driver Time Memory Car-Following Model Simulating in Apollo Platform with GRU and Real Road Traffic Data

Cited by 7 publications

References 31 publications

Prediction of Car-Following Behavior of Autonomous Vehicle and Human-Driven Vehicle Based on Drivers’ Memory and Cooperation With Lead Vehicle

Prediction of Car-Following Behavior of Autonomous Vehicle and Human-Driven Vehicle Based on Drivers’ Memory and Cooperation With Lead Vehicle

Analyzing Election Sentiments in Tweets with Gated Recurrent Units (GRU)

Car-Following Model with Automatic Reaction Delay Estimation: An Attention-Based Ensemble Learning Methodology

Contact Info

Product

Resources

About