(SPS #02-Tracking) Recent advances in Bayesian inference for localization and tracking


Error message

Deprecated function: The each() function is deprecated. This message will be suppressed on further calls in menu_set_active_trail() (line 2405 of /homepages/18/d697803754/htdocs/conferences/2017/icuwb/includes/menu.inc).

The Special Session on Recent advances in Bayesian inference for localization and tracking will be held in conjunction with the 17th edition of the IEEE International Conference on Ubiquitous Wireless Broadband ICUWB’2017 in Salamanca, Spain, from September 12th to 15th, 2017.


The localization and tracking of objects, e.g., by using a distributed wireless sensor network, is a relevant problem within the Internet of Things, Intelligent Robotics/Vehicles and Signal Processing communities. The Bayesian methodology that allows to properly quantify the uncertainty in the inference problem is widely used in machine learning, information fusion, statistics and signal processing. Under the Bayesian framework, these problems are addressed by constructing posterior probability distributions of the unknown parameters conditioned to the available data. The posteriors combine optimally all the information about the parameters in the observations with the information that is present in the prior of the parameters. Using that posterior distribution, one often wants to make inference about the parameters, e.g., finding the value that maximizes the posterior (namely maximum a posteriori estimation), or the value that minimizes a cost function given the uncertainty of the parameters. Unfortunately, obtaining closed-form solutions to these types of problems is only possible in few simplistic models (e.g. linear Gaussian model) and in most practical applications the posterior cannot be exactly computed. Therefore, developing approximate inference techniques is of utmost interest.  In this session, we will focus on localization and tracking theory, algorithm and applications and more in particular in the recent advances of approximate Bayesian methods.

Potential topics include but are not limited to the following:

  • Parametric/non-parametric (approximate) Bayes Filters/Smoothers
  • Indoor Localization/Positioning/Fingerprinting
  • Mobile Robot/Unmanned Vehicle-based Positioning and Navigation
  • Distributed/WSN-based Tracking/Localization
  • UWB (Ultra-wideband) Based Positioning, Localization and Tracking
  • (Multiple) Target Detection/Tracking
  • Sensor Network Communication for Positioning and Tracking
  • Location Based Applications and Services

Special session chair:

Víctor Elvira (IMT Lille Douai)

Tiancheng Li (Universidad de Salamanca)

Luca Martino (Universidad de Valencia)

Pau Closas (Northeastern University)

Submission & Publication:

More information: www.icuwb2017.org/participants/paper-submission