Bio-Inspired and Probabilistic Algorithms for Odor Source Localization

This project aims at exploring algorithms to localize sources that release airborne molecules or particles. Special attention is given to multi-agent algorithms, and a main goal is to find out how and in which circumstances multi-agent algorithms are preferred over single-agent algorithms.

Experiments are carried out both in simulation and with real robots. For the latter purpose, a Khepera III robot has been equipped with a VOC (volatile organic compound) sensor and an anemometer (wind sensor). Real-robot experiments are carried out in the EPFL wind tunnel.

Experiments with single-robot algorithms so far have shown that pure zig-zagging is not a very effective strategy. The spiral-surge algorithm and the newly proposed crosswind-surge algorithm are faster and more robust.

Motivation of the project

While the olfactory sense is of crucial importance for many animals (e.g. for mating, kin recognition, scavenging), odor recognition, localization and discrimination has many current applications in industry as well. Among the most visible applications are search and rescue operations, customs inspection, police operations, or humanitarian demining.

Nowadays, different types of animals (notably dogs and rats, but also bees, …) are employed for such applications. However, training and using these animals is non-trivial and expensive. The ultimate goal of odor localization research therefore is to develop mobile robots to replace the animals in such applications

Additional information here and here.

Team and Collaborators

Sponsors and Research Period

NCCR MICS, a project of the Swiss National Science Foundation

Videos

Video of wind tunnel experiments

Publications

2013

A Plume Tracking Algorithm Based on Crosswind Formations

T. Lochmatter; E. A. Goel; I. Navarro; A. Martinoli 

2013. Distributed Autonomous Robotic Systems, Lausanne, Switzerland, November 2010. p. 91-102. DOI : 10.1007/978-3-642-32723-0_7.

2010

A Plume Tracking Algorithm based on Crosswind Formations

T. Lochmatter; E. Aydin; I. Navarro Oiza; A. Martinoli 

2010. Int. Symp. on Distributed Autonomous Robotic Systems, Lausanne, Switzerland, November, 2010.

Bio-inspired and probabilistic algorithms for distributed odor source localization using mobile robots

T. Lochmatter / A. Martinoli (Dir.)  

Lausanne, EPFL, 2010. 

2009

Theoretical Analysis of Three Bio-Inspired Plume Tracking Algorithms

T. Lochmatter; A. Martinoli 

2009. 2009 IEEE International Conference on Robotics and Automation (ICRA 2009), Kobe, Japan, May 12-17, 2009. DOI : 10.1109/ROBOT.2009.5152686.

Localizing an Odor Source and Avoiding Obstacles: Experiments in a Wind Tunnel using Real Robots

T. Lochmatter; N. Heiniger; A. Martinoli 

2009. 13th International Symposium on Olfaction and Electronic Nose, Brescia, Italy, April 15-17, 2009. p. 69-72. DOI : 10.1063/1.3156629.

Tracking Odor Plumes in a Laminar Wind Field with Bio-Inspired Algorithms

T. Lochmatter; A. Martinoli 

2009. 11th International Symposium on Experimental Robotics 2008 (ISER 2008), Athens, Greece, July 14-17, 2008. p. 473-482. DOI : 10.1007/978-3-642-00196-3_54.

2008

Tracking an Odor Plume in a Laminar Wind Field with the Crosswind-Surge Algorithm

T. Lochmatter; A. Martinoli 

2008. Int. Symp. Experimental Robotics, Athens, Greece, July, 2008. p. 473-482.

Understanding the Potential Impact of Multiple Robots in Odor Source Localization

T. Lochmatter; A. Martinoli 

2008. 9th Symposium on Distributed Autonomous Robotic Systems (DARS 2008), Tsukuba, Japan, November 17-19, 2008. p. 239-250. DOI : 10.1007/978-3-642-00644-9_21.

Simulation Experiments with Bio-Inspired Algorithms for Odor Source Localization in Laminar Wind Flow

T. Lochmatter; A. Martinoli 

2008. Seventh International Conference on Machine Learning and Applications (ICMLA 2008), San Diego, CA, USA, December 11-13, 2008. DOI : 10.1109/ICMLA.2008.128.

SwisTrack – A Flexible Open Source Tracking Software for Multi-Agent Systems

T. Lochmatter; P. Roduit; C. Cianci; N. Correll; J. Jacot et al. 

2008. IEEE/RSJ 2008 International Conference on Intelligent Robots and Systems (IROS 2008), Nice, France, September 22-26, 2008. p. 4004-4010. DOI : 10.1109/IROS.2008.4650937.

A Comparison of Casting and Spiraling Algorithms for Odor Source Localization in Laminar Flow

T. Lochmatter; X. Raemy; L. Matthey; S. Indra; A. Martinoli 

2008. 2008 IEEE International Conference on Robotics and Automation, Pasadena, California, May 19-23, 2008. p. 1138-1143. DOI : 10.1109/ROBOT.2008.4543357.

2007

Toward Multi-Level Modeling of Robotic Sensor Networks: A Case Study in Acoustic Event Monitoring

C. M. Cianci; T. Lochmatter; J. Pugh; A. Martinoli 

2007. International Conference on Robot Communication and Coordination (ROBOCOMM), Athens, Greece, October 15-17, 2007. p. 1-8. DOI : 10.4108/ICST.ROBOCOMM2007.2275.

Geruchslokalisation mit mobilen Robotern

T. Lochmatter; X. Raemy; A. Martinoli 

IT Business. 2007. num. 1, p. 40-41.

Odor Source Localization with Mobile Robots

T. Lochmatter; X. Raemy; A. Martinoli 

Bulletin of the Swiss Society for Automatic Control. 2007. num. 46, p. 11-14.