End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments

Publikationen: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Konferenzband

Standard

End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments. / Xue, Honghu; Song, Rui; Petzold, Julian et al.
IEEE-RAS International Conference on Humanoid Robots. 2022. (IEEE-RAS International Conference on Humanoid Robots).

Publikationen: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Konferenzband

Harvard

Xue, H, Song, R, Petzold, J, Hein, B, Hamann, H & Rueckert, E 2022, End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments. in IEEE-RAS International Conference on Humanoid Robots. IEEE-RAS International Conference on Humanoid Robots. <https://cloud.cps.unileoben.ac.at/index.php/s/RzMQWqsFarQ6Kw4>

APA

Xue, H., Song, R., Petzold, J., Hein, B., Hamann, H., & Rueckert, E. (2022). End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments. In IEEE-RAS International Conference on Humanoid Robots (IEEE-RAS International Conference on Humanoid Robots). https://cloud.cps.unileoben.ac.at/index.php/s/RzMQWqsFarQ6Kw4

Vancouver

Xue H, Song R, Petzold J, Hein B, Hamann H, Rueckert E. End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments. in IEEE-RAS International Conference on Humanoid Robots. 2022. (IEEE-RAS International Conference on Humanoid Robots).

Author

Xue, Honghu ; Song, Rui ; Petzold, Julian et al. / End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments. IEEE-RAS International Conference on Humanoid Robots. 2022. (IEEE-RAS International Conference on Humanoid Robots).

Bibtex - Download

@inproceedings{3a4d9aa089b749dc8d1ad7bbe15e3b29,
title = "End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments",
abstract = "We solve a visual navigation problem in an urban setting via deep reinforcement learning in an end-to-end manner. A major challenge of a first-person visual navigation problem lies in severe partial observability and sparse positive experiences of reaching the goal. To address partial observability, we propose a novel 3D-temporal convolutional network to encode sequential historical visual observations, its effectiveness is verified by comparing to a commonly-used frame-stacking approach. For sparse positive samples, we propose an improved automatic curriculum learning algorithm NavACL+, which proposes meaningful curricula starting from easy tasks and gradually generalizes to challenging ones. NavACL+ is shown to facilitate the learning process, greatly improve the task success rate on difficult tasks by at least 40% and offer enhanced generalization to different initial poses compared to training from a fixed initial pose and the original NavACL algorithm.",
keywords = "Autonomous Navigation, Deep Learning, mobile navigation",
author = "Honghu Xue and Rui Song and Julian Petzold and Benedikt Hein and Heiko Hamann and Elmar Rueckert",
year = "2022",
month = sep,
day = "26",
language = "English",
series = "IEEE-RAS International Conference on Humanoid Robots",
booktitle = "IEEE-RAS International Conference on Humanoid Robots",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments

AU - Xue, Honghu

AU - Song, Rui

AU - Petzold, Julian

AU - Hein, Benedikt

AU - Hamann, Heiko

AU - Rueckert, Elmar

PY - 2022/9/26

Y1 - 2022/9/26

N2 - We solve a visual navigation problem in an urban setting via deep reinforcement learning in an end-to-end manner. A major challenge of a first-person visual navigation problem lies in severe partial observability and sparse positive experiences of reaching the goal. To address partial observability, we propose a novel 3D-temporal convolutional network to encode sequential historical visual observations, its effectiveness is verified by comparing to a commonly-used frame-stacking approach. For sparse positive samples, we propose an improved automatic curriculum learning algorithm NavACL+, which proposes meaningful curricula starting from easy tasks and gradually generalizes to challenging ones. NavACL+ is shown to facilitate the learning process, greatly improve the task success rate on difficult tasks by at least 40% and offer enhanced generalization to different initial poses compared to training from a fixed initial pose and the original NavACL algorithm.

AB - We solve a visual navigation problem in an urban setting via deep reinforcement learning in an end-to-end manner. A major challenge of a first-person visual navigation problem lies in severe partial observability and sparse positive experiences of reaching the goal. To address partial observability, we propose a novel 3D-temporal convolutional network to encode sequential historical visual observations, its effectiveness is verified by comparing to a commonly-used frame-stacking approach. For sparse positive samples, we propose an improved automatic curriculum learning algorithm NavACL+, which proposes meaningful curricula starting from easy tasks and gradually generalizes to challenging ones. NavACL+ is shown to facilitate the learning process, greatly improve the task success rate on difficult tasks by at least 40% and offer enhanced generalization to different initial poses compared to training from a fixed initial pose and the original NavACL algorithm.

KW - Autonomous Navigation

KW - Deep Learning

KW - mobile navigation

M3 - Conference contribution

T3 - IEEE-RAS International Conference on Humanoid Robots

BT - IEEE-RAS International Conference on Humanoid Robots

ER -