sFly project (Swarm of Micro Flying Robots), European Community's Seventh Framework Programme (FP7/2007-2013)

[Airicist]

Project Coordinator - Davide Scaramuzza (https://pr.ai/showthread.php?9278)

youtube.com/sFlyTeam (https://www.youtube.com/sFlyTeam)

[Airicist]

https://youtu.be/AdmTGAo1Jvg

Uploaded on Dec 28, 2011


Demo proposal of the sFly European Project (2009-2011).
The demo simulates a search and rescue operation in an outdoor GPS-denied disaster scenario. No laser, no GPS, and Vicon or other external cameras are used for navigation and mapping, but just onboard cameras and IMUs. All the processing runs onboard, on a Core2Duo processing unit. This video gives an overview of the existing modules being used for the final demonstration. The mission consists of first collecting images for creating a common global map of the working area with 3 helicopters, then engaging positions for an optimal surveillance coverage of the area, and finally detecting the transmitter positions

[Airicist]

https://youtu.be/_-p08o_oTO4

SFly: Swarm of Micro Flying Robots (Finalist best video paper award IROS 2012)

Published on May 2, 2012


The scope of the sFly project (2009-2011) was to develop a system of multiple vision-controlled micro aerial vehicles that are capable of autonomous navigation in GPS-denied environments, 3D mapping, and radio-beacons localization. The Sfly MAV's are fully autonomous. Flight control is done by computer vision and runs entirely onboard. No laser rangefinder or GPS are used, but just onboard cameras running at 30 Hz. An on-board monocular visual slam computes local camera poses and sparse features. These estimated poses are fused with the IMU measurements in a filter. "An additional stereo system captures image data while the MAVs explore the environment. These image data are used to compute a detailed dense 3D model of the environment. An off-board visual SLAM module computes a global map by utilizing loop detection and bundle adjustment optimization. The individual maps from the MAVs are merged into a single global map. A 3D occupancy grid map is generated by depthmap fusion in the final step of the mapping process. A cognitive adaptive optimization algorithm is used to compute the optimal surveillance positions for the MAVs based on the generated 3D map of the environment. The MAVs reach the optimal surveillance positions autonomously by waypoint navigation. The MAVs locate the radio beacon by measuring the power of the received radio signal (RSSI value). We envisage that in the near future our sFly MAVs will play a major role in tasks such as search and rescue, inspection, and environment monitoring.