A Framework for Estimating Driver Decisions Near Intersections

Gadepally, Vijay; Krishnamurthy, Ashok; Özgüner, Ü.

doi:10.1109/tits.2013.2285159

Cited by 106 publications

(72 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…

γ_{t} false(i false) = P false(q_{t} = S_{i} | O, λ false) \begin{matrix} = & true \sum_{j = 1}^{N} ξ_{t} false(i, j false) \end{matrix}

where

γ_{i} false(t false)

defines the probability of being in state S i at time t given the observation sequence O and the model parameters λ . And then, parameters can be updated as follows [34,40]:

{\bar{π}}_{i} = γ_{1} false(i false)

where

γ_{1} false(i false)

represents the expected frequency in state S i at time t ( t = 1).

{\bar{a}}_{i j} = \frac{true \sum_{t = 1}^{T - 1} ξ_{t} false(i, j false)}{true \sum_{t = 1}^{T - 1} γ_{t} false(i false)}

where T is the number of observations in the sequence.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Driver Behavior near Intersections in Hidden Markov Model

Zhou

et al. 2016

IJERPH

View full text Add to dashboard Cite

Intersections are one of the major locations where safety is a big concern to drivers. Inappropriate driver behaviors in response to frequent changes when approaching intersections often lead to intersection-related crashes or collisions. Thus to better understand driver behaviors at intersections, especially in the dilemma zone, a Hidden Markov Model (HMM) is utilized in this study. With the discrete data processing, the observed dynamic data of vehicles are used for the inference of the Hidden Markov Model. The Baum-Welch (B-W) estimation algorithm is applied to calculate the vehicle state transition probability matrix and the observation probability matrix. When combined with the Forward algorithm, the most likely state of the driver can be obtained. Thus the model can be used to measure the stability and risk of driver behavior. It is found that drivers’ behaviors in the dilemma zone are of lower stability and higher risk compared with those in other regions around intersections. In addition to the B-W estimation algorithm, the Viterbi Algorithm is utilized to predict the potential dangers of vehicles. The results can be applied to driving assistance systems to warn drivers to avoid possible accidents.

show abstract

“…

γ_{t} false(i false) = P false(q_{t} = S_{i} | O, λ false) \begin{matrix} = & true \sum_{j = 1}^{N} ξ_{t} false(i, j false) \end{matrix}

where

γ_{i} false(t false)

defines the probability of being in state S i at time t given the observation sequence O and the model parameters λ . And then, parameters can be updated as follows [34,40]:

{\bar{π}}_{i} = γ_{1} false(i false)

where

γ_{1} false(i false)

represents the expected frequency in state S i at time t ( t = 1).

{\bar{a}}_{i j} = \frac{true \sum_{t = 1}^{T - 1} ξ_{t} false(i, j false)}{true \sum_{t = 1}^{T - 1} γ_{t} false(i false)}

where T is the number of observations in the sequence.…”

Section: Methodsmentioning

confidence: 99%

“…In HMMs, each driver’s driving process is described as a continuous trajectory which involves a set of discrete decisions made by the driver [34]. The discrete decisions which represent drivers’ decision-making behaviors are then estimated and predicted.…”

Section: Introductionmentioning

confidence: 99%

Modeling Driver Behavior near Intersections in Hidden Markov Model

Zhou

et al. 2016

IJERPH

View full text Add to dashboard Cite

show abstract

“…The IDM [19] [20] is a crash-free microscopic carfollowing model which estimates longitudinal dynamic speed controls. It is configured by several parameters which reflect potential factors of the following vehicle's driving behavior as shown in equation (1), (2), and (3).…”

Section: B Intelligent Driver Model(idm) and Minimize Overall Brakinmentioning

confidence: 99%

Driving Intention Recognition and Lane Change Prediction on the Highway

Han

Jing

Özgüner

2019

2019 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

This paper proposes a framework to recognize driving intentions and to predict driving behaviors of lane changing on the highway by using externally sensable traffic data from the host-vehicle. The framework consists of a driving characteristic estimator and a driving behavior predictor. A driver's implicit driving characteristic information is uniquely determined and detected by proposed the online-estimator. Neural-network based behavior predictor is developed and validated by testing with the real naturalistic traffic data from Next Generation Simulation (NGSIM), which demonstrates the effectiveness in identifying the driving characteristics and transforming into accurate behavior prediction in real-world traffic situations.

show abstract

“…In [22], a single HMM was used to identify the vehicles in conflict with other vehicles in a limited intersection road with appropriate measurements of the ego-vehicle and surrounding vehicle dynamics. The authors in [5] aimed also to estimate the driving behavior (Left or Right turn, straight or Stop) at intersection from HMM using on the filtered vehicle data.…”

Section: Related Workmentioning

confidence: 99%

Recognizing Driver Awareness of Pedestrian

Phan

Frémont

Thouvenin

et al. 2014

17th International IEEE Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

In this paper, we propose a novel approach to recognize the awareness or the unawareness that a driver has of a pedestrian appearing on the road in front of the vehicle. Based on the theory of situation awareness and the collected driving data from the on board sensors, a suitable Hidden Markov Model (HMM) is used to model the "Driver Awareness of Pedestrian" and the "Driver Unawareness of Pedestrian". These behaviors are then recognized by using a maximumlikelihood decision method. A real-time validation taken on a driving simulator shows that the model and the output decisions are accurate and efficient.

show abstract

A Framework for Estimating Driver Decisions Near Intersections

Cited by 106 publications

References 17 publications

Modeling Driver Behavior near Intersections in Hidden Markov Model

Modeling Driver Behavior near Intersections in Hidden Markov Model

Driving Intention Recognition and Lane Change Prediction on the Highway

Recognizing Driver Awareness of Pedestrian

Contact Info

Product

Resources

About