Learn to steer through deep reinforcement learning
It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/103342 http://hdl.handle.net/10220/47293 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-103342 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1033422020-03-07T14:00:36Z Learn to steer through deep reinforcement learning Wu, Keyu Esfahani, Mahdi Abolfazli Yuan, Shenghai Wang, Han School of Electrical and Electronic Engineering Autonomous Steering DRNTU::Engineering::Electrical and electronic engineering Deep Reinforcement Learning It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with unseen circumstances. Therefore, we propose an end-to-end deep reinforcement learning algorithm in this paper to improve the performance of autonomous steering in complex environments. By embedding a branching noisy dueling architecture, the proposed model is capable of deriving steering commands directly from raw depth images with high efficiency. Specifically, our learning-based approach extracts the feature representation from depth inputs through convolutional neural networks and maps it to both linear and angular velocity commands simultaneously through different streams of the network. Moreover, the training framework is also meticulously designed to improve the learning efficiency and effectiveness. It is worth noting that the developed system is readily transferable from virtual training scenarios to real-world deployment without any fine-tuning by utilizing depth images. The proposed method is evaluated and compared with a series of baseline methods in various virtual environments. Experimental results demonstrate the superiority of the proposed model in terms of average reward, learning efficiency, success rate as well as computational time. Moreover, a variety of real-world experiments are also conducted which reveal the high adaptability of our model to both static and dynamic obstacle-cluttered environments. Published version 2019-01-02T03:35:17Z 2019-12-06T21:10:30Z 2019-01-02T03:35:17Z 2019-12-06T21:10:30Z 2018 Journal Article Wu, K., Esfahani, M. A., Yuan, S., & Wang, H. (2018). Learn to Steer through Deep Reinforcement Learning. Sensors, 18(11), 3650-. doi:10.3390/s18113650 1424-8220 https://hdl.handle.net/10356/103342 http://hdl.handle.net/10220/47293 10.3390/s18113650 en Sensors © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). 19 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Autonomous Steering DRNTU::Engineering::Electrical and electronic engineering Deep Reinforcement Learning |
spellingShingle |
Autonomous Steering DRNTU::Engineering::Electrical and electronic engineering Deep Reinforcement Learning Wu, Keyu Esfahani, Mahdi Abolfazli Yuan, Shenghai Wang, Han Learn to steer through deep reinforcement learning |
description |
It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with unseen circumstances. Therefore, we propose an end-to-end deep reinforcement learning algorithm in this paper to improve the performance of autonomous steering in complex environments. By embedding a branching noisy dueling architecture, the proposed model is capable of deriving steering commands directly from raw depth images with high efficiency. Specifically, our learning-based approach extracts the feature representation from depth inputs through convolutional neural networks and maps it to both linear and angular velocity commands simultaneously through different streams of the network. Moreover, the training framework is also meticulously designed to improve the learning efficiency and effectiveness. It is worth noting that the developed system is readily transferable from virtual training scenarios to real-world deployment without any fine-tuning by utilizing depth images. The proposed method is evaluated and compared with a series of baseline methods in various virtual environments. Experimental results demonstrate the superiority of the proposed model in terms of average reward, learning efficiency, success rate as well as computational time. Moreover, a variety of real-world experiments are also conducted which reveal the high adaptability of our model to both static and dynamic obstacle-cluttered environments. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Wu, Keyu Esfahani, Mahdi Abolfazli Yuan, Shenghai Wang, Han |
format |
Article |
author |
Wu, Keyu Esfahani, Mahdi Abolfazli Yuan, Shenghai Wang, Han |
author_sort |
Wu, Keyu |
title |
Learn to steer through deep reinforcement learning |
title_short |
Learn to steer through deep reinforcement learning |
title_full |
Learn to steer through deep reinforcement learning |
title_fullStr |
Learn to steer through deep reinforcement learning |
title_full_unstemmed |
Learn to steer through deep reinforcement learning |
title_sort |
learn to steer through deep reinforcement learning |
publishDate |
2019 |
url |
https://hdl.handle.net/10356/103342 http://hdl.handle.net/10220/47293 |
_version_ |
1681034436016078848 |