Next Article in Journal
Resource Allocation in the Cognitive Radio Network-Aided Internet of Things for the Cyber-Physical-Social System: An Efficient Jaya Algorithm
Previous Article in Journal
Non-Adaptive Methods for Fetal ECG Signal Processing: A Review and Appraisal
Article Menu
Issue 11 (November) cover image

Export Article

Open AccessArticle

Learn to Steer through Deep Reinforcement Learning

School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
*
Author to whom correspondence should be addressed.
Sensors 2018, 18(11), 3650; https://doi.org/10.3390/s18113650
Received: 12 October 2018 / Revised: 24 October 2018 / Accepted: 25 October 2018 / Published: 27 October 2018
(This article belongs to the Section Physical Sensors)
  |  
PDF [4097 KB, uploaded 5 November 2018]
  |  

Abstract

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. View Full-Text
Keywords: deep reinforcement learning; autonomous steering; depth image deep reinforcement learning; autonomous steering; depth image
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Wu, K.; Abolfazli Esfahani, M.; Yuan, S.; Wang, H. Learn to Steer through Deep Reinforcement Learning. Sensors 2018, 18, 3650.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top