sensors-logo

Journal Browser

Journal Browser

Deep Learning Techniques for the Mapping and Localization of Mobile Robotics

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Remote Sensors".

Deadline for manuscript submissions: closed (31 December 2021) | Viewed by 13888

Special Issue Editors


E-Mail Website
Guest Editor
Department of Systems and Automation Engineering, Universidad Miguel Hernández, Avinguda de la Universitat d'Elx, s/n, 03202 Elche, Alicante, Spain
Interests: computer vision; robotics; cooperative robotics
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
System Engineering and Automation Department, Miguel Hernandez University, 03202 Elche, Spain
Interests: computer vision; omnidirectional imaging; appearance descriptors; image processing; mobile robotics; environment modeling; visual localization
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear colleagues,

Over the past few years, deep learning techniques have permitted tackling a number of problems in regard to the recognition of scenes or of classification from visual information and other sensors, with promising results. More recently, their ability to analyze and detect patterns from large amounts of data has broadened their applications, and they can be used to solve a variety of problems in robotics, such as mapping and localization. Deep learning techniques may constitute a powerful alternative, either when the main sensorial system is a vision system that provides enormous amounts of information, or when this visual information is merged with data provided by other types of sensors, such as range sensors.

In this sense, different techniques have recently emerged, either supervised or unsupervised, such as convolutional neural networks (CNNs), autoencoders, recurrent neural networks, generative adversarial networks, and siamese networks. These techniques have shown excellent performance in a variety of tasks, usually related to classification. However, the use of deep learning techniques to address the problem of mapping and/or the localization of mobile robots, undoubtedly offers great possibilities for any type of robot (drones, ground vehicles, or submarine robots, etc.). Recognizing, identifying, and modeling scenarios from the information provided by multiple sensory systems is essential in order to carry out tasks related to autonomous navigation in mobile robots. In this field, deep learning techniques provide a novel alternative to describe the environments in which the robot operates.

The aim of this Special Issue is to present different alternatives or applications to resolve the problem of the mapping and/or localization of a mobile robots using deep learning techniques. Additionally, state-of-the-art reviews of a specific problem in this field, and how it has been addressed through the use of deep learning, would also be welcomed.

This Special Issue invites contributions related to—but not limited to—the following topics:

  • place recognition and/or image retrieval by means of deep learning techniques;
  • metric, topological, or hybrid mapping through deep learning techniques;
  • modeling environments through long-short term memories;
  • long-term mapping and localization;
  • computer vision and deep learning in mapping and localization;
  • fusion of information in multi-sensor systems;
  • movement estimation using deep learning techniques;
  • human–robot interaction in mapping and localization;
  • navigation in social and/or crowded environments;
  • path following in challenging environments;
  • simultaneous localization and mapping (SLAM);
  • visual odometry and trajectory estimation;
  • loop closure detection;
  • deep learning and autonomous driving;

Prof. Dr. Oscar Reinoso Garcia
Prof. Dr. Luis Payá
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

16 pages, 4870 KiB  
Article
An End-to-End Trainable Multi-Column CNN for Scene Recognition in Extremely Changing Environment
by Zhenyu Li, Aiguo Zhou and Yong Shen
Sensors 2020, 20(6), 1556; https://doi.org/10.3390/s20061556 - 11 Mar 2020
Cited by 6 | Viewed by 2936
Abstract
Scene recognition is an essential part in the vision-based robot navigation domain. The successful application of deep learning technology has triggered more extensive preliminary studies on scene recognition, which all use extracted features from networks that are trained for recognition tasks. In the [...] Read more.
Scene recognition is an essential part in the vision-based robot navigation domain. The successful application of deep learning technology has triggered more extensive preliminary studies on scene recognition, which all use extracted features from networks that are trained for recognition tasks. In the paper, we interpret scene recognition as a region-based image retrieval problem and present a novel approach for scene recognition with an end-to-end trainable Multi-column convolutional neural network (MCNN) architecture. The proposed MCNN utilizes filters with receptive fields of different sizes to have Multi-level and Multi-layer image perception, and consists of three components: front-end, middle-end and back-end. The first seven layers VGG16 are taken as front-end for two-dimensional feature extraction, Inception-A is taken as the middle-end for deeper learning feature representation, and Large-Margin Softmax Loss (L-Softmax) is taken as the back-end for enhancing intra-class compactness and inter-class-separability. Extensive experiments have been conducted to evaluate the performance according to compare our proposed network to existing state-of-the-art methods. Experimental results on three popular datasets demonstrate the robustness and accuracy of our approach. To the best of our knowledge, the presented approach has not been applied for the scene recognition in literature. Full article
Show Figures

Figure 1

Review

Jump to: Research

17 pages, 4751 KiB  
Review
Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey
by Saba Arshad and Gon-Woo Kim
Sensors 2021, 21(4), 1243; https://doi.org/10.3390/s21041243 - 10 Feb 2021
Cited by 78 | Viewed by 9901
Abstract
Loop closure detection is of vital importance in the process of simultaneous localization and mapping (SLAM), as it helps to reduce the cumulative error of the robot’s estimated pose and generate a consistent global map. Many variations of this problem have been considered [...] Read more.
Loop closure detection is of vital importance in the process of simultaneous localization and mapping (SLAM), as it helps to reduce the cumulative error of the robot’s estimated pose and generate a consistent global map. Many variations of this problem have been considered in the past and the existing methods differ in the acquisition approach of query and reference views, the choice of scene representation, and associated matching strategy. Contributions of this survey are many-fold. It provides a thorough study of existing literature on loop closure detection algorithms for visual and Lidar SLAM and discusses their insight along with their limitations. It presents a taxonomy of state-of-the-art deep learning-based loop detection algorithms with detailed comparison metrics. Also, the major challenges of conventional approaches are identified. Based on those challenges, deep learning-based methods were reviewed where the identified challenges are tackled focusing on the methods providing long-term autonomy in various conditions such as changing weather, light, seasons, viewpoint, and occlusion due to the presence of mobile objects. Furthermore, open challenges and future directions were also discussed. Full article
Show Figures

Figure 1

Back to TopTop