[robotics-worldwide] [Journals] CFP Special Issue on Omnidirectional Vision Sensors for Mapping, Localization, and Navigation of Mobile Robots - Journal of Sensors

Miguel Juliá miguel.julia at q-bot.co
Mon Oct 24 02:15:09 PDT 2016


Journal of Sensors 

Special Issue on Omnidirectional Vision Sensors for Mapping,
Localization, and Navigation of Mobile Robots 

Impact Factor 0.712 

Call for Papers 

In order to be truly autonomous, a mobile robot should be capable of
navigating through any kind of environment while carrying out a task. To
achieve this goal, the robot must be able to create a model of its
workspace, estimate its position within it, and navigate to the target
points. Map building and navigation are currently very active research
areas where a large number of researchers have focused on. As a result,
very different approaches have emerged, considering different kinds of
sensorial information. Vision sensors have gained popularity in such
applications due to the richness of the information they provide.
However, the limited field of view of monocular cameras causes the
necessity of employing several images of the environment in order to
acquire complete information from it. In contrast, omnidirectional
vision systems have the ability to capture a more complete description
of the environment in only one scene. 

Using these scenes, a model of the environment can be built. In general,
these models can be defined as metric, topological, or hybrid maps. A
metric map usually defines the position of some landmarks with respect
to a coordinate system and permits localization and navigation with
geometric accuracy. Second, topological maps tend to represent the
environment as a graph where the nodes are some distinctive
localizations and links are the connectivity relations between them.
They usually permit a rough robot localization and navigation with a
reasonable computational cost. At last, hybrid maps are hierarchical
models that combine the features of metric and topological methods to
try to retain the advantages of both approaches. In all cases, to build
a functional map it is necessary to extract some relevant information
from the scenes. Researchers have studied both methods that extract and
describe some interesting points or local features from the scenes and
methods that describe each image as a whole, building a unique
descriptor per scene that describes its global appearance. 

The purpose of this special issue is to invite researchers to present
original papers as well as review articles that address the use of
omnidirectional vision systems to solve the problems of mapping,
localization, SLAM, and/or navigation of mobile robots. 

Potential topics include but are not limited to the following: 

Visual mapping
Metric maps
Topological maps
Hybrid maps
Visual localization using a model previously built
Local features (landmarks) extraction and description
Global appearance descriptors
Local and global features matching
Visual navigation
Visual SLAM
Omnidirectional visual scan matching
Appearance based localization
Visual topological slam
Topological localization 

Authors can submit their manuscripts through the Manuscript Tracking
System at https://urldefense.proofpoint.com/v2/url?u=http-3A__mts.hindawi.com_submit_journals_js_ovs_&d=DQIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=Ft1NRpmB2O1DLdUjsgWCsRS--OhaeNtaTlWBsbg2Xn0&s=z33knPspX78BvMXSgV-MCVMkyWkmYkPCK3KX-D87850&e=   

Manuscript Due Friday, 9 December 2016
First Round of Reviews Friday, 3 March 2017
Publication Date Friday, 28 April 2017 

Lead Guest Editor 

Oscar Reinoso, Miguel Hernández University, Elche, Spain 

Guest Editors 

Luis Paya, Miguel Hernández University, Elche, Spain
Miguel Juliá, Q-Bot Limited, London, UK
Jaime Valls-Miro, University of Technology Sydney, Sydney, Australia

-- 
Miguel Juliá Cristóbal, PhD.
Senior Robotics and Automation Researcher
Q-Bot Limited, Block G, Riverside Business Centre, Bendon Valley,
Wandsworth, SW18 4UQ


More information about the robotics-worldwide mailing list