Deep predictive models for collision risk assessment in autonomous driving

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we investigate a predictive approach for collision risk assessment in autonomous and assisted driving. A deep predictive model is trained to anticipate imminent accidents from traditional video streams. In particular, the model learns to identify cues in RGB images that are predictive of hazardous upcoming situations. In contrast to previous work, our approach incorporates (a) temporal information during decision making, (b) multi-modal information about the environment, as well as the proprioceptive state and steering actions of the controlled vehicle, and (c) information about the uncertainty inherent to the task. To this end, we discuss Deep Predictive Models and present an implementation using a Bayesian Convolutional LSTM. Experiments in a simple simulation environment show that the approach can learn to predict impending accidents with reasonable accuracy, especially when multiple cameras are used as input sources.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Robotics and Automation, ICRA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4685-4692
Number of pages8
ISBN (Electronic)9781538630815
DOIs
StatePublished - Sep 10 2018
Event2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia
Duration: May 21 2018May 25 2018

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Conference2018 IEEE International Conference on Robotics and Automation, ICRA 2018
CountryAustralia
CityBrisbane
Period5/21/185/25/18

Fingerprint

Risk assessment
Accidents
Decision making
Cameras
Experiments
Uncertainty

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Strickland, M., Fainekos, G., & Ben Amor, H. (2018). Deep predictive models for collision risk assessment in autonomous driving. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 (pp. 4685-4692). [8461160] (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2018.8461160

Deep predictive models for collision risk assessment in autonomous driving. / Strickland, Mark; Fainekos, Georgios; Ben Amor, Hani.

2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 4685-4692 8461160 (Proceedings - IEEE International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Strickland, M, Fainekos, G & Ben Amor, H 2018, Deep predictive models for collision risk assessment in autonomous driving. in 2018 IEEE International Conference on Robotics and Automation, ICRA 2018., 8461160, Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 4685-4692, 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 5/21/18. https://doi.org/10.1109/ICRA.2018.8461160
Strickland M, Fainekos G, Ben Amor H. Deep predictive models for collision risk assessment in autonomous driving. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 4685-4692. 8461160. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2018.8461160
Strickland, Mark ; Fainekos, Georgios ; Ben Amor, Hani. / Deep predictive models for collision risk assessment in autonomous driving. 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 4685-4692 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{e6ae43f632954da1ab26d6a27e66b100,
title = "Deep predictive models for collision risk assessment in autonomous driving",
abstract = "In this paper, we investigate a predictive approach for collision risk assessment in autonomous and assisted driving. A deep predictive model is trained to anticipate imminent accidents from traditional video streams. In particular, the model learns to identify cues in RGB images that are predictive of hazardous upcoming situations. In contrast to previous work, our approach incorporates (a) temporal information during decision making, (b) multi-modal information about the environment, as well as the proprioceptive state and steering actions of the controlled vehicle, and (c) information about the uncertainty inherent to the task. To this end, we discuss Deep Predictive Models and present an implementation using a Bayesian Convolutional LSTM. Experiments in a simple simulation environment show that the approach can learn to predict impending accidents with reasonable accuracy, especially when multiple cameras are used as input sources.",
author = "Mark Strickland and Georgios Fainekos and {Ben Amor}, Hani",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/ICRA.2018.8461160",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4685--4692",
booktitle = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018",

}

TY - GEN

T1 - Deep predictive models for collision risk assessment in autonomous driving

AU - Strickland, Mark

AU - Fainekos, Georgios

AU - Ben Amor, Hani

PY - 2018/9/10

Y1 - 2018/9/10

N2 - In this paper, we investigate a predictive approach for collision risk assessment in autonomous and assisted driving. A deep predictive model is trained to anticipate imminent accidents from traditional video streams. In particular, the model learns to identify cues in RGB images that are predictive of hazardous upcoming situations. In contrast to previous work, our approach incorporates (a) temporal information during decision making, (b) multi-modal information about the environment, as well as the proprioceptive state and steering actions of the controlled vehicle, and (c) information about the uncertainty inherent to the task. To this end, we discuss Deep Predictive Models and present an implementation using a Bayesian Convolutional LSTM. Experiments in a simple simulation environment show that the approach can learn to predict impending accidents with reasonable accuracy, especially when multiple cameras are used as input sources.

AB - In this paper, we investigate a predictive approach for collision risk assessment in autonomous and assisted driving. A deep predictive model is trained to anticipate imminent accidents from traditional video streams. In particular, the model learns to identify cues in RGB images that are predictive of hazardous upcoming situations. In contrast to previous work, our approach incorporates (a) temporal information during decision making, (b) multi-modal information about the environment, as well as the proprioceptive state and steering actions of the controlled vehicle, and (c) information about the uncertainty inherent to the task. To this end, we discuss Deep Predictive Models and present an implementation using a Bayesian Convolutional LSTM. Experiments in a simple simulation environment show that the approach can learn to predict impending accidents with reasonable accuracy, especially when multiple cameras are used as input sources.

UR - http://www.scopus.com/inward/record.url?scp=85059237317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059237317&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2018.8461160

DO - 10.1109/ICRA.2018.8461160

M3 - Conference contribution

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 4685

EP - 4692

BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -