Capturing Car-Following Behaviors by Deep Learning

@article{Wang2018CapturingCB,
  title={Capturing Car-Following Behaviors by Deep Learning},
  author={Xiao Wang and R. Jiang and L. Li and Yilun Lin and Xinhu Zheng and F. Wang},
  journal={IEEE Transactions on Intelligent Transportation Systems},
  year={2018},
  volume={19},
  pages={910-920}
}
  • Xiao Wang, R. Jiang, +3 authors F. Wang
  • Published 2018
  • Engineering, Computer Science
  • IEEE Transactions on Intelligent Transportation Systems
In this paper, we propose a deep neural network-based car-following model that has two distinctive properties. First, unlike most existing car-following models that take only the instantaneous velocity, velocity difference, and position difference as inputs, this new model takes the velocities, velocity differences, and position differences that were observed in the last few time intervals as inputs. That is, we assume that drivers’ actions are temporally dependent in this model and try to… Expand
Simultaneous modeling of car-following and lane-changing behaviors using deep learning
TLDR
A deep learning model, long short-term memory (LSTM) neural networks, is adopted to model the two basic behaviors simultaneously of car-following and lane-changing, and the results show that HRC LSTM model can accurately estimate CF and LC behaviors simultaneously with low longitudinal trajectories error and high LC prediction accuracy compared with the classical models. Expand
Memory, attention and prediction: a deep learning architecture for car-following
TLDR
By combining numerous deep neural network structures to mimic the memory, attention and prediction mechanisms of real drivers, a deep learning-based car following model named MAP is built and can produce space-time diagrams similar to real traffic. Expand
Modeling Car-Following Behaviors and Driving Styles with Generative Adversarial Imitation Learning
TLDR
The results show that the proposed model can reproduce drivers’ car-following trajectories and driving styles more accurately than the intelligent driver model and the recurrent neural network-based model, with the lowest average spacing error and speed validation error. Expand
Human-Like Autonomous Car-Following Model with Deep Reinforcement Learning
TLDR
A deep deterministic policy gradient car-following model that uses disparity between simulated and observed speed as the reward function and considers a reaction delay of 1s, denoted as DDPGvRT, can reproduce human-like car- following behavior with higher accuracy than traditional and recent data-driven car- followeding models. Expand
Modeling Car Following with Feed-Forward and Long-Short Term Memory Neural Networks
TLDR
Experimental results confirm the reliability of the assumption that the reaction is not instantaneous and highlight that the deep recurrent neural network outperforms the simpler feed-forward neural network. Expand
A Car-Following Model Using Online Sequential Extreme Learning Machine
TLDR
The research results show that the car-following model proposed in this article is reasonable and feasible and can fully meet the real-time requirements of the online traffic simulation system. Expand
A sequence to sequence learning based car-following model for multi-step predictions considering reaction delay
TLDR
The seq2seq model is further extended with spatial anticipation, which improves platoon simulation accuracy and traffic flow stability and the evaluation results indicate that the proposed model outperforms others for reproducing trajectory and capturing heterogeneous driving behaviors. Expand
Fusion Modeling Method of Car-Following Characteristics
TLDR
Test results of real driving data from a single driver prove that the fusion car-following model has higher accuracy than a single model, while at the same time highlighting the driver’s personality compared to the IDM model. Expand
A data-driven lane-changing model based on deep learning
TLDR
This may be the first work that comprehensively models LC using deep learning approaches and the results indicate that the proposed data-driven model is able to accurately predict the LC process of a vehicle. Expand
Backpropagation through Simulation: A Training Method for Neural Network-based Car-following
TLDR
A training method to reduce the long-term error of neural network-based car-following models, with multiple experimental validations, using a recurrent framework with simulation to generate long- term predictions for generic car- following models, and use gradient backpropagation to reduce accumulative error. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 68 REFERENCES
Neural Agent Car-Following Models
  • S. Panwai, H. Dia
  • Computer Science, Engineering
  • IEEE Transactions on Intelligent Transportation Systems
  • 2007
TLDR
A car-following model that was developed using a neural network approach for mapping perceptions to actions and showed very close agreement between field data and model outputs, demonstrating the robustness of the model under mild and severe traffic disturbances. Expand
A rule-based neural network approach to model driver naturalistic behavior in traffic
Abstract This paper proposes a rule-based neural network model to simulate driver behavior in terms of longitudinal and lateral actions in two driving situations, namely car-following situation andExpand
End-to-End Learning of Driving Models from Large-Scale Video Datasets
TLDR
This work advocates learning a generic vehicle motion model from large scale crowd-sourced video data, and develops an end-to-end trainable architecture for learning to predict a distribution over future vehicle egomotion from instantaneous monocular camera observations and previous vehicle state. Expand
DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
TLDR
This paper proposes to map an input image to a small number of key perception indicators that directly relate to the affordance of a road/traffic state for driving and argues that the direct perception representation provides the right level of abstraction. Expand
A Neural-Fuzzy Framework for Modeling Car-following Behavior
  • Xiaoliang Ma
  • Computer Science
  • 2006 IEEE International Conference on Systems, Man and Cybernetics
  • 2006
TLDR
A multi-regime framework based on the statistical property in each regime and mathematical models adopted in those regimes is proposed, an extension of TSK fuzzy inference system and can be expressed by a neural-fuzzy system. Expand
End to End Learning for Self-Driving Cars
TLDR
A convolutional neural network is trained to map raw pixels from a single front-facing camera directly to steering commands and it is argued that this will eventually lead to better performance and smaller systems. Expand
Thirty Years of Gipps’ Car-Following Model
TLDR
The structure of the acceleration component of the Gipps’ model is analytically investigated for what concerns the meaning of some parameters that in common practice are usually kept to some empirically derived fixed values and the results show the necessity for these parameters to be calibrated to improve the model's predictive capabilities. Expand
Car-following behavior with instantaneous driver–vehicle reaction delay: A neural-network-based methodology
Reaction delay of the driver–vehicle unit varies greatly according to driver–vehicle characteristics and traffic conditions, and is an indispensable factor for modeling vehicle movements. In thisExpand
A global optimization algorithm for trajectory data based car-following model calibration
Abstract How to calibrate the parameters of car-following models based on observed traffic data is a vital problem in traffic simulation. Usually, the core of calibration is cast into an optimizationExpand
Artificial Neural Network Models for Car Following: Experimental Analysis and Calibration Issues
TLDR
Validation tests show that artificial neural networks (ANNs) provide a good approximation of driving patterns and can be suitably implemented in microsimulation models, and a new experimental calibration method for microsimulating software might consist of training one specific ANN for each representative individual of the driver population through systematic observations in the field or in virtual environment trials. Expand
...
1
2
3
4
5
...