Next Article in Journal
Privacy-Preserving Electrocardiogram Monitoring for Intelligent Arrhythmia Detection
Previous Article in Journal
Development of a Rigid One-Meter-Side and Cooled Coil Sensor at 77 K for Magnetic Resonance Sounding to Detect Subsurface Water Sources
Open AccessArticle

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images

1
School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an 710072, China
2
Highly Automated Driving Team, HERE Technologies Automotive Division, Chicago, IL 60606, USA
*
Author to whom correspondence should be addressed.
This paper is an extended version of our paper published in Ran, L.; Zhang, Y.; Yang, T.; Zhang, P. Autonomous Wheeled Robot Navigation with Uncalibrated Spherical Images. In Chinese Conference on Intelligent Visual Surveillance; Springer: Singapore, 2016; pp. 47–55.
Academic Editor: Vittorio M. N. Passaro
Sensors 2017, 17(6), 1341; https://doi.org/10.3390/s17061341
Received: 23 February 2017 / Revised: 27 May 2017 / Accepted: 6 June 2017 / Published: 12 June 2017
(This article belongs to the Section Physical Sensors)
Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications. View Full-Text
Keywords: convolutional neural networks; vision-based robot navigation; spherical camera; navigation via learning convolutional neural networks; vision-based robot navigation; spherical camera; navigation via learning
Show Figures

Figure 1

MDPI and ACS Style

Ran, L.; Zhang, Y.; Zhang, Q.; Yang, T. Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images. Sensors 2017, 17, 1341. https://doi.org/10.3390/s17061341

AMA Style

Ran L, Zhang Y, Zhang Q, Yang T. Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images. Sensors. 2017; 17(6):1341. https://doi.org/10.3390/s17061341

Chicago/Turabian Style

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao. 2017. "Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images" Sensors 17, no. 6: 1341. https://doi.org/10.3390/s17061341

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

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop