UCL logo
skip to navigation. skip to content.

Gatsby Computational Neuroscience Unit




UCL Home
  • UCL Home
  • UCL Gatsby Computational Neuroscience Unit
UCL Gatsby Unit
  • introduction
  • people
  • research
  • publications
  • courses
  • phd programme
  • events
  • directions
  • greater gatsby
  • vacancies
  • Internal
  • ucl

 

 

  • Home
  • Staff & Students
  • Vacancies

 

Martin D. Adams

(INTERNAL TALK)

 

http://www.cec.uchile.cl/~martin/

 

Friday 23rd November 2012

Time: 2.30pm

 

4th FloorSeminar Room

Alexandra House, 17 Queen Square, London, WC1N 3AR

 

 

Circumventing the Feature Association Problem in SLAM

 

In autonomous applications, a vehicle requires reliable estimates of its location and information about the world around it. To capture prior knowledge of the uncertainties in a vehicle’s motion response to input commands and sensor measurements, this fundamental task has been cast as probabilistic Simultaneous Localisation and Map building (SLAM). SLAM has been investigated as a stochastic filtering problem in which sensor data is compressed into features, which are consequently stacked in a vector, referred to as the map.

Inspired by developments in the tracking literature, recent research in SLAM has recast the map as a Random Finite Set (RFS) instead of a random vector, with huge mathematical consequences. With the application of recently formulated Finite Set Statistics (FISST), such a representation eliminates the need for fragile feature management and association routines, which are often the weakest component in vector based SLAM algorithms.

This presentation demonstrates that true sensing uncertainty lies not only in the spatial estimates of features, but also in their very existence. This gives rise to sensor probabilities of detection and false alarm, as well as spatial uncertainty values. By re-addressing the fundamentals of SLAM under an RFS framework, it will be shown that it is possible to estimate the map in terms of true feature number, as well location. The concepts are demonstrated with short range radar, which detects multiple features, but yields many false measurements.
Comparison of vector, and RFS SLAM algorithms shows the superior robustness of RFS based SLAM to such realistic sensing  defects.

Martin D. Adams

Martin Adams is Professor  of Electrical Engineering at  the Dept. of Electrical Engineering, University of Chile. He is also a co-member of the industrially sponsored Advanced Mining Technology Centre (AMTC).  He obtained his first degree in Engineering Science at the University of Oxford, U.K, in 1988 and continued to study for a D.Phil. at the Robotics Research Group, University of Oxford, which he received in 1992. He continued his research in autonomous robot navigation as a project leader and part time lecturer at the  Institute of Robotics, Swiss Federal Institute of Technology (ETH), Zurich, Switzerland. He was employed as a Guest Professor and taught control theory in St.
Gallen (Switzerland) from 1994 to 1995. From 1996 to 2000, he served as a senior research scientist in robotics and control, in the field of semiconductor assembly automation, at the European Semiconductor Equipment Centre (ESEC),  Switzerland. From 2000 to 2010, he was Associate Professor at the School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore.  His research work focuses on autonomous robot navigation, sensing, sensor data interpretation and control, and he has published many technical papers in these fields. He has been  the  principle investigator  and leader  of many robotics projects, coordinating researchers from local industries and local and overseas universities and has served as associate editor on various journal and conference editorial boards.

 

 

 

 

 

 

 

  • Disclaimer
  • Freedom of Information
  • Accessibility
  • Privacy
  • Advanced Search
  • Contact Us
Gatsby Computational Neuroscience Unit - Alexandra House - 17 Queen Square - London - WC1N 3AR - Telephone: +44 (0)20 7679 1176

© UCL 1999–20112011