Modeling Eye-Gaze Behavior of Electric Wheelchair Drivers via Inverse Reinforcement Learning

被引：0

作者：

Maekawa, Yamato ^{[1
]}

Akai, Naoki ^{[1
]}

Hirayama, Takatsugu ^{[2
]}

Morales, Luis Yoichi ^{[2
]}

Deguchi, Daisuke ^{[1
]}

Kawanishi, Yasutomo ^{[1
]}

Ide, Ichiro ^{[3
]}

Murase, Hiroshi ^{[1
]}

机构：

[1] Nagoya Univ, Grad Sch Informat, Nagoya, Aichi 4648601, Japan

[2] Nagoya Univ, Inst Innovat Future Soc MIRAI, Nagoya, Aichi 4648601, Japan

[3] Nagoya Univ, Math & Data Sci Ctr, Nagoya, Aichi 4648601, Japan

来源：

2020 IEEE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC) | 2020年

关键词：

ATTENTION;

D O I：

10.1109/itsc45102.2020.9294255

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

It is intuitively obvious that eye-gaze behaviors of experienced drivers are different from those of novice drivers. However, it is not easy to understand the difference in their behavior quantitatively. In this work, we present an explainable eye-gaze behavior modeling method for electric wheelchair drivers based on Inverse Reinforcement Learning (IRL). We first create feature maps that represent risk factors during driving. These feature maps are able to represent not only to what but also from where drivers pay attention. IRL uses the feature maps to learn the reward representing the eye-gaze behaviors and allows us to see important features via the automatic acquisition of the reward. Through analysis of the learned model, we show quantitative evidence that eye-gaze behaviors of experienced drivers are better-balanced by paying attention to multiple risks.

引用

页数：7

共 26 条

[1]

Akai N., 2019, P 2019 IEEE INT VEH, P828

[2]

Akai N, 2019, IEEE INT C INTELL TR, P2367, DOI 10.1109/ITSC.2019.8917163

[3]

Akai N, 2018, IEEE INT C INT ROBOT, P3159, DOI 10.1109/IROS.2018.8594146

[4]

Dellaert F, 1999, ICRA '99: IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-4, PROCEEDINGS, P1322, DOI 10.1109/ROBOT.1999.772544

[5]

DUBUISSON MP, 1994, INT C PATT RECOG, P566, DOI 10.1109/ICPR.1994.576361

[6] Attention Branch Network: Learning of Attention Mechanism for Visual Explanation [J].

Fukui, Hiroshi ;

Hirakawa, Tsubasa ;

Yamashita, Takayoshi ;

Fujiyoshi, Hironobu .

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :10697-10706

[7] Improved techniques for grid mapping with Rao-Blackwellized particle filters [J].

Grisetti, Giorgio ;

Stachniss, Cyrill ;

Burgard, Wolfram .

IEEE TRANSACTIONS ON ROBOTICS, 2007, 23 (01) :34-46

[8]

Hartman E., 1970, TECHNICAL PAPER SERI, P629

[9] Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning [J].

Hirakawa, Tsubasa ;

Yamashita, Takayoshi ;

Tamaki, Toru ;

Fujiyoshi, Hironobu ;

Umezu, Yuta ;

Takeuchi, Ichiro ;

Matsumoto, Sakiko ;

Yoda, Ken .

ECOSPHERE, 2018, 9 (10)

[10]

Kitani KM, 2012, LECT NOTES COMPUT SC, V7575, P201, DOI 10.1007/978-3-642-33765-9_15

← 1 2 3 →