Traffic3D: A New Traffic Simulation Paradigm

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

Abstract

The field of Deep Reinforcement Learning has evolved significantly over the last few years. However, an important and not yet fully-attained goal is to produce intelligent agents which can be successfully taken out of the laboratory and employed in the real-world. Intelligent agents that are successfully deployable in real-world settings require substantial prior exposure to their intended environments. When this is not practical or possible, the agents benefit from being trained and tested on powerful test-beds, effectively replicating the real-world. To achieve traffic management at an unprecedented level of efficiency, in this work, we demonstrate a significantly richer new traffic simulation environment; Traffic3D, a platform to effectively simulate and evaluate a variety of 3D road traffic scenarios, closely mimicking real-world traffic characteristics, including faithful simulation of individual vehicle behavior, precise physics of movement and photo-realism. In addition to deep reinforcement learning, Traffic3D also facilitates research in several other domains such as imitation learning, learning by interaction, visual question answering, object detection and segmentation, unsupervised representation learning and procedural generation.
Original languageEnglish
Title of host publicationProceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems
PublisherACM
Pages2354-2356
ISBN (Electronic)978-1-4503-6309-9
ISBN (Print)978-1-4503-6309-9
Publication statusPublished - 8 May 2019

Fingerprint

Intelligent agents
Reinforcement learning
Physics
Object detection

Bibliographical note

© 2019 International Foundation for Autonomous Agents and
Multiagent Systems (www.ifaamas.org).

Cite this

Garg, D., Chli, M., & Vogiatzis, G. (2019). Traffic3D: A New Traffic Simulation Paradigm. In Proceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems (pp. 2354-2356). ACM.
Garg, Deepeka ; Chli, Maria ; Vogiatzis, George. / Traffic3D: A New Traffic Simulation Paradigm. Proceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems. ACM, 2019. pp. 2354-2356
@inproceedings{372dd6a834874a63830d79c8db4a8518,
title = "Traffic3D: A New Traffic Simulation Paradigm",
abstract = "The field of Deep Reinforcement Learning has evolved significantly over the last few years. However, an important and not yet fully-attained goal is to produce intelligent agents which can be successfully taken out of the laboratory and employed in the real-world. Intelligent agents that are successfully deployable in real-world settings require substantial prior exposure to their intended environments. When this is not practical or possible, the agents benefit from being trained and tested on powerful test-beds, effectively replicating the real-world. To achieve traffic management at an unprecedented level of efficiency, in this work, we demonstrate a significantly richer new traffic simulation environment; Traffic3D, a platform to effectively simulate and evaluate a variety of 3D road traffic scenarios, closely mimicking real-world traffic characteristics, including faithful simulation of individual vehicle behavior, precise physics of movement and photo-realism. In addition to deep reinforcement learning, Traffic3D also facilitates research in several other domains such as imitation learning, learning by interaction, visual question answering, object detection and segmentation, unsupervised representation learning and procedural generation.",
author = "Deepeka Garg and Maria Chli and George Vogiatzis",
note = "{\circledC} 2019 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org).",
year = "2019",
month = "5",
day = "8",
language = "English",
isbn = "978-1-4503-6309-9",
pages = "2354--2356",
booktitle = "Proceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems",
publisher = "ACM",
address = "United States",

}

Garg, D, Chli, M & Vogiatzis, G 2019, Traffic3D: A New Traffic Simulation Paradigm. in Proceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems. ACM, pp. 2354-2356.

Traffic3D: A New Traffic Simulation Paradigm. / Garg, Deepeka; Chli, Maria; Vogiatzis, George.

Proceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems. ACM, 2019. p. 2354-2356.

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

TY - GEN

T1 - Traffic3D: A New Traffic Simulation Paradigm

AU - Garg, Deepeka

AU - Chli, Maria

AU - Vogiatzis, George

N1 - © 2019 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org).

PY - 2019/5/8

Y1 - 2019/5/8

N2 - The field of Deep Reinforcement Learning has evolved significantly over the last few years. However, an important and not yet fully-attained goal is to produce intelligent agents which can be successfully taken out of the laboratory and employed in the real-world. Intelligent agents that are successfully deployable in real-world settings require substantial prior exposure to their intended environments. When this is not practical or possible, the agents benefit from being trained and tested on powerful test-beds, effectively replicating the real-world. To achieve traffic management at an unprecedented level of efficiency, in this work, we demonstrate a significantly richer new traffic simulation environment; Traffic3D, a platform to effectively simulate and evaluate a variety of 3D road traffic scenarios, closely mimicking real-world traffic characteristics, including faithful simulation of individual vehicle behavior, precise physics of movement and photo-realism. In addition to deep reinforcement learning, Traffic3D also facilitates research in several other domains such as imitation learning, learning by interaction, visual question answering, object detection and segmentation, unsupervised representation learning and procedural generation.

AB - The field of Deep Reinforcement Learning has evolved significantly over the last few years. However, an important and not yet fully-attained goal is to produce intelligent agents which can be successfully taken out of the laboratory and employed in the real-world. Intelligent agents that are successfully deployable in real-world settings require substantial prior exposure to their intended environments. When this is not practical or possible, the agents benefit from being trained and tested on powerful test-beds, effectively replicating the real-world. To achieve traffic management at an unprecedented level of efficiency, in this work, we demonstrate a significantly richer new traffic simulation environment; Traffic3D, a platform to effectively simulate and evaluate a variety of 3D road traffic scenarios, closely mimicking real-world traffic characteristics, including faithful simulation of individual vehicle behavior, precise physics of movement and photo-realism. In addition to deep reinforcement learning, Traffic3D also facilitates research in several other domains such as imitation learning, learning by interaction, visual question answering, object detection and segmentation, unsupervised representation learning and procedural generation.

UR - https://dl.acm.org/citation.cfm?id=3332110

M3 - Conference contribution

SN - 978-1-4503-6309-9

SP - 2354

EP - 2356

BT - Proceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems

PB - ACM

ER -

Garg D, Chli M, Vogiatzis G. Traffic3D: A New Traffic Simulation Paradigm. In Proceedings of the 2019 International Conference on Autonomous Agents and Multi-Agent Systems. ACM. 2019. p. 2354-2356