Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior

Morton, Jeremy; Wheeler, Tim A.; Kochenderfer, Mykel J.

doi:10.1109/tits.2016.2603007

Cited by 220 publications

(117 citation statements)

References 30 publications

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…The total acceleration is the sum of both the free road and the interaction acceleration. Since the IDM only outputs a longitudinal acceleration, we assume no lateral motion when using the IDM We take the IDM parameters for the NGSIM dataset from Morton et al [5]. For the HighD dataset, we tune the IDM's parameters using guided random search with a total of 20 000 samples.…”

Section: B Baselinesmentioning

confidence: 99%

See 1 more Smart Citation

Graph Neural Networks for Modelling Traffic Participant Interaction

Diehl

Brunner

et al. 2019

2019 IEEE Intelligent Vehicles Symposium (IV)

107

View full text Add to dashboard Cite

By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffic prediction. These naturally take interaction between traffic participants into account while being computationally efficient and providing large model capacity. We evaluate two state-of-the art GNN architectures and introduce several adaptations for our specific scenario. We show that prediction error in scenarios with much interaction decreases by 30% compared to a model that does not take interactions into account. This suggests that interaction is important, and shows that we can model it using graphs. This makes GNNs a worthwhile addition to traffic prediction systems. †

show abstract

Section: B Baselinesmentioning

confidence: 99%

“…At the same time, it has been shown [3]- [5] that machine learning models and particularly (deep) neural networks perform well on this problem. Yet most available deep learning models operate on data of a fixed size and with a fixed spatial organization such as single data points, time series, or images.…”

Section: Introductionmentioning

confidence: 99%

Graph Neural Networks for Modelling Traffic Participant Interaction

Diehl

Brunner

et al. 2019

2019 IEEE Intelligent Vehicles Symposium (IV)

107

View full text Add to dashboard Cite

show abstract

“…The success of deep learning in many real-life applications motivates research on its use for motion prediction and related methods include Mixture Density Networks (MDN) [8], Recurrent Neural Networks (RNN) [9], and Convolutional Neural Networks (CNN) [10]. Deep learning models can achieve high accuracy but at the expense of high abstraction which cannot be trusted.…”

Section: Interpretable Modelsmentioning

confidence: 99%

“…There exists a number of studies addressing the problem of modeling multi-modality. Feedforward network with Gaussian Mixture [8] [9] is usually applied to solve multi-modal regression tasks but it is often difficult to train in practice due to numerical instabilities when operating in high-dimensional spaces such as predicting future sequences.…”

Section: Multi-modalitymentioning

confidence: 99%

Multi-modal Probabilistic Prediction of Interactive Behavior via an Interpretable Model

Zhan

Sun

et al. 2019

2019 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

For autonomous agents to successfully operate in real world, the ability to anticipate future motions of surrounding entities in the scene can greatly enhance their safety levels since potentially dangerous situations could be avoided in advance. While impressive results have been shown on predicting each agent's behavior independently, we argue that it is not valid to consider road entities individually since transitions of vehicle states are highly coupled. Moreover, as the predicted horizon becomes longer, modeling prediction uncertainties and multi-modal distributions over future sequences will turn into a more challenging task. In this paper, we address this challenge by presenting a multi-modal probabilistic prediction approach. The proposed method is based on a generative model and is capable of jointly predicting sequential motions of each pair of interacting agents. Most importantly, our model is interpretable, which can explain the underneath logic as well as obtain more reliability to use in real applications. A complicate real-world roundabout scenario is utilized to implement and examine the proposed method.

show abstract

“…To describe the driving behavior in various traffic situations, some new methods have been proposed that use mathematical models and neural networks like Bayesian filtering, Recurrent Neural Network to predict a driver's intended actions across traffic situations [59], [60]. Artificial neural network (ANN) and radial basis function neural network (RBF-NN) showed great benefits to predict the vehicle second-by-second trajectory in congested traffic condition in terms of accuracy and efficiency [61], [62].…”

Section: Driving Behavior Modelingmentioning

confidence: 99%

The State-of-the-Art of Coordinated Ramp Control with Mixed Traffic Conditions

Zhao

Wang

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Ramp metering, a traditional traffic control strategy for conventional vehicles, has been widely deployed around the world since the 1960s. On the other hand, the last decade has witnessed significant advances in connected and automated vehicle (CAV) technology and its great potential for improving safety, mobility and environmental sustainability. Therefore, a large amount of research has been conducted on cooperative ramp merging for CAVs only. However, it is expected that the phase of mixed traffic, namely the coexistence of both humandriven vehicles and CAVs, would last for a long time. Since there is little research on the system-wide ramp control with mixed traffic conditions, the paper aims to close this gap by proposing an innovative system architecture and reviewing the state-of-the-art studies on the key components of the proposed system. These components include traffic state estimation, ramp metering, driving behavior modeling, and coordination of CAVs. All reviewed literature plot an extensive landscape for the proposed system-wide coordinated ramp control with mixed traffic conditions.

show abstract

Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior

Cited by 220 publications

References 30 publications

Graph Neural Networks for Modelling Traffic Participant Interaction

Graph Neural Networks for Modelling Traffic Participant Interaction

Multi-modal Probabilistic Prediction of Interactive Behavior via an Interpretable Model

The State-of-the-Art of Coordinated Ramp Control with Mixed Traffic Conditions

Contact Info

Product

Resources

About