DIADEM

     

ICRA Workshop on Networked and Mobile Robot Olfaction in Natural, Dynamic Environments



The 2010 IEEE International Conference on Robotics and Automation (ICRA2010) was held in Anchorage, Alaska, May 3 - 8, 2010. The theme of the conference was ”50 Years of Robotics,” reflecting on the amazing achievements of the field and the broad impact of robotics and automation research, development and education. The conference was attended by over 1575 attendees and featured 857 papers, 8 keynotes celebrating 50 Years of Robotics, 3 plenary lectures and 42 workshops.

The ICRA Workshop on Networked and Mobile Robot Olfaction in Natural, Dynamic Environments was held in Anchorage, Alaska, on May 7, 2010 as a workshop in ICRA 2010. This workshop was organized by Achim Lilienthal and Amy Loutfi from AASS centre, Örebro University. This workshop aimed to bring together researchers from sensor networks and mobile robotics who face the same challenges in developing artificial olfaction solutions for real world applications.

In this workshop, Achim Lilienthal presented an invited talk entitled
“The EU project Diadem: Towards Gas Detection and Gas Distribution Monitoring on a Large Scale “ where Diadem project was introduced and the challenges and the research on gas detection and gas distribution monitoring in Diadem project were presented.





Asadi, S., Reggente, M., Stachniss, C., Plagemann, C., and Lilienthal, A. J. (2010). Statistical Gas Distribution Modelling Using Kernel Methods. In E. Hines & M. Leeson (Ed.), Intelligent Systems for Machine Olfaction: Tools and Methodologies. IGI Global. Submitted full chapter.

The book chapter “Statistical Gas Distribution Modelling Using Kernel Methods” has been submitted to be published in the Intelligent Systems for Machine Olfaction: Tools and Methodologies. This chapter reviews kernel methods that statistically model gas distribution. Gas measurements are treated as random variables and the gas distribution is predicted at unseen locations either using a kernel density estimation or a kernel regression approach. The resulting statistical models do not make strong assumptions about the functional form of the gas distribution, such as the number or locations of gas sources, for example. The major focus of this chapter is on two-dimensional models that provide estimates for the means and predictive variances of the distribution. Furthermore, three extensions to the presented kernel density estimation algorithm are described, which allow to include wind information; to extend the model to three dimensions; and to reflect time-dependent changes of the random process that generates the gas distribution measurements. All methods are discussed based on experimental validation using real sensor data.

The book “Intelligent Systems for Machine Olfaction: Tools and Methodologies” will introduce new and state-of-the art applications of intelligent systems to researchers and developers in the area of machine olfaction who may benefit from the use of these intelligent systems techniques. The material will be presented in a series of chapters that support the reader via the introduction of theoretical material and application examples. The book will also reach potential readers in other research areas such as chemistry, biology, medicine and other related areas where intelligent systems have a great potential that has only barely been explored.