We are applying principles of distributed intelligence and model-based methods of distributed control and analysis to (potentially mobile) sensor networks, particularly for event-driven monitoring scenarios (where the quantity being measured or affected is spatially and temporally unpredictable) and deployments requiring relatively high sampling rates (where simply enforcing a < 1% duty cycle is insufficient or ineffectual). Areas of special interest include acoustic monitoring, power management, collective attention, dynamic re-configuration, and collaborative signal processing using adaptation and learning at the level of the individual.
Leveraging the Swarm-Intelligent Systems Group’s accumulated expertise in system design and systematic experimentation with mobile robotic swarms, this project attempts to bring the rigor of reproducible experiments and multi-level modeling to the domain of sensor and actuator networks.
Team and Collaborators
In collaboration with:
Sponsors and Research Period
SNSF
Publications
Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.
2008
Exploration of an Incremental Suite of Microscopic Models for Acoustic Event Monitoring Using a Robotic Sensor Network
2008. IEEE International Conference on Robotics and Automation, Pasadena, CA, US, May 19-23, 2008. p. 3290-3295. DOI : 10.1109/ROBOT.2008.4543712.2007
Toward Multi-Level Modeling of Robotic Sensor Networks: A Case Study in Acoustic Event Monitoring
2007. International Conference on Robot Communication and Coordination (ROBOCOMM), Athens, Greece, October 15-17, 2007. p. 1-8. DOI : 10.4108/ICST.ROBOCOMM2007.2275.Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.