Driver prediction to improve interaction with in-vehicle HMI

Bret Harsham, Shinji Watanabe, Alan Esenther, John Hershey, Jonathan Le Roux, Yi Luan, Daniel Nikovski, Vamsi Potluru

研究成果: Conference contribution

3 引用 (Scopus)

抄録

Recently there has been a trend toward increasing the capability of the in-vehicle interface in terms of access to information and complex controls. This has been accompanied by an increase in the complexity of the car Human Machine Interface [HMI], At the same time, studies have shown that driver distraction can contribute to accidents. This paper provides some possible ways to reduce driver cognitive load by augmenting the interface. We use prediction of the driver's next action or intention in order to provide UI affordances for more quickly selecting actions. Two examples of this are presented: prediction of driver interaction with the car HMI based on the driving history, and prediction of driver intention from the driver speech. In the first example, we used signal processing techniques to extract meaningful features from vehicle CAN and history data, and then we used machine learning techniques to predict the driver's next action. In the second example, we used ASR and natural language processing to extract text features from driver speech, and predict user intention using a neural network and word embedding. The proposed prediction methods for user actions and intentions can be used to improve in-vehicle task performance.

元の言語English
ホスト出版物のタイトル7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015
出版者University of Texas at Dallas
ページ1-8
ページ数8
ISBN(電子版)9781510827844
出版物ステータスPublished - 2015
外部発表Yes
イベント7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015 - Berkeley, United States
継続期間: 2015 10 142015 10 16

Other

Other7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015
United States
Berkeley
期間15/10/1415/10/16

Fingerprint

Railroad cars
Time and motion study
Vehicle performance
Learning systems
Accidents
Signal processing
Neural networks
Processing

ASJC Scopus subject areas

  • Signal Processing
  • Automotive Engineering
  • Control and Systems Engineering

これを引用

Harsham, B., Watanabe, S., Esenther, A., Hershey, J., Le Roux, J., Luan, Y., ... Potluru, V. (2015). Driver prediction to improve interaction with in-vehicle HMI. : 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015 (pp. 1-8). University of Texas at Dallas.

Driver prediction to improve interaction with in-vehicle HMI. / Harsham, Bret; Watanabe, Shinji; Esenther, Alan; Hershey, John; Le Roux, Jonathan; Luan, Yi; Nikovski, Daniel; Potluru, Vamsi.

7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015. University of Texas at Dallas, 2015. p. 1-8.

研究成果: Conference contribution

Harsham, B, Watanabe, S, Esenther, A, Hershey, J, Le Roux, J, Luan, Y, Nikovski, D & Potluru, V 2015, Driver prediction to improve interaction with in-vehicle HMI. : 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015. University of Texas at Dallas, pp. 1-8, 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015, Berkeley, United States, 15/10/14.
Harsham B, Watanabe S, Esenther A, Hershey J, Le Roux J, Luan Y その他. Driver prediction to improve interaction with in-vehicle HMI. : 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015. University of Texas at Dallas. 2015. p. 1-8
Harsham, Bret ; Watanabe, Shinji ; Esenther, Alan ; Hershey, John ; Le Roux, Jonathan ; Luan, Yi ; Nikovski, Daniel ; Potluru, Vamsi. / Driver prediction to improve interaction with in-vehicle HMI. 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015. University of Texas at Dallas, 2015. pp. 1-8
@inproceedings{22ccc874646949e48c4b740679a6adef,
title = "Driver prediction to improve interaction with in-vehicle HMI",
abstract = "Recently there has been a trend toward increasing the capability of the in-vehicle interface in terms of access to information and complex controls. This has been accompanied by an increase in the complexity of the car Human Machine Interface [HMI], At the same time, studies have shown that driver distraction can contribute to accidents. This paper provides some possible ways to reduce driver cognitive load by augmenting the interface. We use prediction of the driver's next action or intention in order to provide UI affordances for more quickly selecting actions. Two examples of this are presented: prediction of driver interaction with the car HMI based on the driving history, and prediction of driver intention from the driver speech. In the first example, we used signal processing techniques to extract meaningful features from vehicle CAN and history data, and then we used machine learning techniques to predict the driver's next action. In the second example, we used ASR and natural language processing to extract text features from driver speech, and predict user intention using a neural network and word embedding. The proposed prediction methods for user actions and intentions can be used to improve in-vehicle task performance.",
keywords = "Car HMI, Machine learning, Prediction of driver intention, Prediction of driver interaction, Spoken language understanding",
author = "Bret Harsham and Shinji Watanabe and Alan Esenther and John Hershey and {Le Roux}, Jonathan and Yi Luan and Daniel Nikovski and Vamsi Potluru",
year = "2015",
language = "English",
pages = "1--8",
booktitle = "7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015",
publisher = "University of Texas at Dallas",
address = "United States",

}

TY - GEN

T1 - Driver prediction to improve interaction with in-vehicle HMI

AU - Harsham, Bret

AU - Watanabe, Shinji

AU - Esenther, Alan

AU - Hershey, John

AU - Le Roux, Jonathan

AU - Luan, Yi

AU - Nikovski, Daniel

AU - Potluru, Vamsi

PY - 2015

Y1 - 2015

N2 - Recently there has been a trend toward increasing the capability of the in-vehicle interface in terms of access to information and complex controls. This has been accompanied by an increase in the complexity of the car Human Machine Interface [HMI], At the same time, studies have shown that driver distraction can contribute to accidents. This paper provides some possible ways to reduce driver cognitive load by augmenting the interface. We use prediction of the driver's next action or intention in order to provide UI affordances for more quickly selecting actions. Two examples of this are presented: prediction of driver interaction with the car HMI based on the driving history, and prediction of driver intention from the driver speech. In the first example, we used signal processing techniques to extract meaningful features from vehicle CAN and history data, and then we used machine learning techniques to predict the driver's next action. In the second example, we used ASR and natural language processing to extract text features from driver speech, and predict user intention using a neural network and word embedding. The proposed prediction methods for user actions and intentions can be used to improve in-vehicle task performance.

AB - Recently there has been a trend toward increasing the capability of the in-vehicle interface in terms of access to information and complex controls. This has been accompanied by an increase in the complexity of the car Human Machine Interface [HMI], At the same time, studies have shown that driver distraction can contribute to accidents. This paper provides some possible ways to reduce driver cognitive load by augmenting the interface. We use prediction of the driver's next action or intention in order to provide UI affordances for more quickly selecting actions. Two examples of this are presented: prediction of driver interaction with the car HMI based on the driving history, and prediction of driver intention from the driver speech. In the first example, we used signal processing techniques to extract meaningful features from vehicle CAN and history data, and then we used machine learning techniques to predict the driver's next action. In the second example, we used ASR and natural language processing to extract text features from driver speech, and predict user intention using a neural network and word embedding. The proposed prediction methods for user actions and intentions can be used to improve in-vehicle task performance.

KW - Car HMI

KW - Machine learning

KW - Prediction of driver intention

KW - Prediction of driver interaction

KW - Spoken language understanding

UR - http://www.scopus.com/inward/record.url?scp=85016982607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016982607&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85016982607

SP - 1

EP - 8

BT - 7th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems and Safety 2015

PB - University of Texas at Dallas

ER -