Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems

Victor Talpaert; Ibrahim Sobh; B. Ravi Kiran; Patrick Mannion; Senthil Yogamani; Ahmad El-Sallab; Patrick Perez

doi:10.5220/0007520305640572

Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems

Victor Talpaert
, Ibrahim Sobh
, B. Ravi Kiran
, Patrick Mannion
, Senthil Yogamani
, Ahmad El-Sallab
, Patrick Perez

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

24 Citations (Scopus)

Abstract

Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind’s AlphaGo. It has been successfully deployed in commercial vehicles like Mo-bileye’s path planning system. However, a vast majority of work on DRL is focused on toy examples in controlled synthetic car simulator environments such as TORCS and CARLA. In general, DRL is still at its infancy in terms of usability in real-world applications. Our goal in this paper is to encourage real-world deployment of DRL in various autonomous driving (AD) applications. We first provide an overview of the tasks in autonomous driving systems, reinforcement learning algorithms and applications of DRL to AD systems. We then discuss the challenges which must be addressed to enable further progress towards real-world deployment.

Original language	English
Title of host publication	VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Editors	Andreas Kerren, Christophe Hurter, Jose Braz
Publisher	SCITEPRESS
Pages	564-572
Number of pages	9
ISBN (Electronic)	9789897583544
DOIs	https://doi.org/10.5220/0007520305640572
Publication status	Published - 2019
Externally published	Yes
Event	14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 - Prague, Czech Republic Duration: 25 Feb 2019 → 27 Feb 2019

Publication series

Name	VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume	5

Conference

Conference	14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019
Country/Territory	Czech Republic
City	Prague
Period	25/02/19 → 27/02/19

Keywords

Autonomous Driving
Deep Reinforcement Learning
Visual Perception

Access to Document

10.5220/0007520305640572

Cite this

Talpaert, V., Sobh, I., Ravi Kiran, B., Mannion, P., Yogamani, S., El-Sallab, A., & Perez, P. (2019). Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems. In A. Kerren, C. Hurter, & J. Braz (Eds.), VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (pp. 564-572). (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 5). SCITEPRESS. https://doi.org/10.5220/0007520305640572

Talpaert, Victor ; Sobh, Ibrahim ; Ravi Kiran, B. et al. / Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems. VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. editor / Andreas Kerren ; Christophe Hurter ; Jose Braz. SCITEPRESS, 2019. pp. 564-572 (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications).

@inproceedings{5049afc3ade343328513bc59918ee141,

title = "Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems",

abstract = "Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind{\textquoteright}s AlphaGo. It has been successfully deployed in commercial vehicles like Mo-bileye{\textquoteright}s path planning system. However, a vast majority of work on DRL is focused on toy examples in controlled synthetic car simulator environments such as TORCS and CARLA. In general, DRL is still at its infancy in terms of usability in real-world applications. Our goal in this paper is to encourage real-world deployment of DRL in various autonomous driving (AD) applications. We first provide an overview of the tasks in autonomous driving systems, reinforcement learning algorithms and applications of DRL to AD systems. We then discuss the challenges which must be addressed to enable further progress towards real-world deployment.",

keywords = "Autonomous Driving, Deep Reinforcement Learning, Visual Perception",

author = "Victor Talpaert and Ibrahim Sobh and \{Ravi Kiran\}, B. and Patrick Mannion and Senthil Yogamani and Ahmad El-Sallab and Patrick Perez",

note = "Publisher Copyright: Copyright {\textcopyright} 2019 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved; 14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 ; Conference date: 25-02-2019 Through 27-02-2019",

year = "2019",

doi = "10.5220/0007520305640572",

language = "English",

series = "VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

publisher = "SCITEPRESS",

pages = "564--572",

editor = "Andreas Kerren and Christophe Hurter and Jose Braz",

booktitle = "VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

}

Talpaert, V, Sobh, I, Ravi Kiran, B, Mannion, P, Yogamani, S, El-Sallab, A & Perez, P 2019, Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems. in A Kerren, C Hurter & J Braz (eds), VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 5, SCITEPRESS, pp. 564-572, 14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic, 25/02/19. https://doi.org/10.5220/0007520305640572

Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems. / Talpaert, Victor; Sobh, Ibrahim; Ravi Kiran, B. et al.
VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. ed. / Andreas Kerren; Christophe Hurter; Jose Braz. SCITEPRESS, 2019. p. 564-572 (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 5).

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems

AU - Talpaert, Victor

AU - Sobh, Ibrahim

AU - Ravi Kiran, B.

AU - Mannion, Patrick

AU - Yogamani, Senthil

AU - El-Sallab, Ahmad

AU - Perez, Patrick

PY - 2019

Y1 - 2019

N2 - Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind’s AlphaGo. It has been successfully deployed in commercial vehicles like Mo-bileye’s path planning system. However, a vast majority of work on DRL is focused on toy examples in controlled synthetic car simulator environments such as TORCS and CARLA. In general, DRL is still at its infancy in terms of usability in real-world applications. Our goal in this paper is to encourage real-world deployment of DRL in various autonomous driving (AD) applications. We first provide an overview of the tasks in autonomous driving systems, reinforcement learning algorithms and applications of DRL to AD systems. We then discuss the challenges which must be addressed to enable further progress towards real-world deployment.

AB - Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind’s AlphaGo. It has been successfully deployed in commercial vehicles like Mo-bileye’s path planning system. However, a vast majority of work on DRL is focused on toy examples in controlled synthetic car simulator environments such as TORCS and CARLA. In general, DRL is still at its infancy in terms of usability in real-world applications. Our goal in this paper is to encourage real-world deployment of DRL in various autonomous driving (AD) applications. We first provide an overview of the tasks in autonomous driving systems, reinforcement learning algorithms and applications of DRL to AD systems. We then discuss the challenges which must be addressed to enable further progress towards real-world deployment.

KW - Autonomous Driving

KW - Deep Reinforcement Learning

KW - Visual Perception

UR - https://www.scopus.com/pages/publications/85068266702

U2 - 10.5220/0007520305640572

DO - 10.5220/0007520305640572

M3 - Conference Publication

AN - SCOPUS:85068266702

T3 - VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

SP - 564

EP - 572

BT - VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

A2 - Kerren, Andreas

A2 - Hurter, Christophe

A2 - Braz, Jose

PB - SCITEPRESS

T2 - 14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019

Y2 - 25 February 2019 through 27 February 2019

ER -

Talpaert V, Sobh I, Ravi Kiran B, Mannion P, Yogamani S, El-Sallab A et al. Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems. In Kerren A, Hurter C, Braz J, editors, VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SCITEPRESS. 2019. p. 564-572. (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications). doi: 10.5220/0007520305640572

Exploring Applications of Deep Reinforcement Learning for Real-world Autonomous Driving Systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this