A Gaze Model Improves Autonomous Driving

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)

2 Scopus Citations
View graph of relations

Author(s)

  • Congcong Liu
  • Yuying Chen
  • Lei Tai
  • Haoyang Ye
  • Ming Liu
  • And 1 others
  • Bertram E. Shi

Detail(s)

Original languageEnglish
Title of host publicationETRA'19 Proceedings of the 11th ACM Symposium on Eye Tracking Research and Applications
PublisherAssociation for Computing Machinery
ISBN (Print)9781450367097
Publication statusPublished - Jun 2019
Externally publishedYes

Publication series

NameEye Tracking Research and Applications Symposium (ETRA)

Conference

Title11th ACM Symposium on Eye Tracking Research and Applications (ETRA 2019)
PlaceUnited States
CityDenver
Period25 - 28 June 2019

Abstract

End-to-end behavioral cloning trained by human demonstration is now a popular approach for vision-based autonomous driving. A deep neural network maps drive-view images directly to steering commands. However, the images contain much task-irrelevant data. Humans attend to behaviorally relevant information using saccades that direct gaze towards important areas. We demonstrate that behavioral cloning also benefits from active control of gaze. We trained a conditional generative adversarial network (GAN) that accurately predicts human gaze maps while driving in both familiar and unseen environments. We incorporated the predicted gaze maps into end-to-end networks for two behaviors: following and overtaking. Incorporating gaze information significantly improves generalization to unseen environments. We hypothesize that incorporating gaze information enables the network to focus on task critical objects, which vary little between environments, and ignore irrelevant elements in the background, which vary greatly.

Research Area(s)

  • Eye Tracking, Imitation Learning, Autonomous Driving

Citation Format(s)

A Gaze Model Improves Autonomous Driving. / Liu, Congcong; Chen, Yuying; Tai, Lei; Ye, Haoyang; Liu, Ming; Shi, Bertram E.

ETRA'19 Proceedings of the 11th ACM Symposium on Eye Tracking Research and Applications. Association for Computing Machinery, 2019. 33 (Eye Tracking Research and Applications Symposium (ETRA)).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)