ETH Fully Vision Based Autonomous Helicopter in Unstructured Environments: VTOL

Developed at the ETH Zurich. Only a single camera is used to control the helicopter. The blob is used to initialize the map and the scale factor at the beginning. Take-off is automatic. Feature points are tracked and used in a visual SLAM framework to build the map of the environment. The helicopter then follows autonomously the via-points created in this map and land automatically onto the second blob, which is used to show the precision of landing. The distance between the start and end position is about 3 meters.
With this helicopter, we will partecipate in the EMAV (European Micro Aerial Vehicle) competition in September 2009 in Delft. This work is supported by the European research project sFly (www.sfly.org).
This work was developed at the ETH Zurich, in the Autonomous Systems Lab.

Category:

Science & Technology

Tags:

• vtol
• flyiing robot
• autonomous helicopter
• helikopter
• visual slam
• mav
• computer vision
• image processing
• navigation
• mapping
• feature tracking
• blob

[davidescaramuzza]

no, for the moment this is done offboard by streaming the image to an external laptop.

[potpie921]

amazing

[mishrasubhransu]

@davidescaramuzza: What transmitter are you using for streaming the images to the computer. I had something similar but the speed of transmission was very low with the xbee modules which made it impossible to use for realtime processing of the images

[pmukherj87]

Props to the man in green. That is confidence right there! We usually sit behind a glass window!

[chevron7locked]

what typer of camera and "Visual" interface system did you use for the robot?

[realfaronel]

the music is from gabyx :)

[FrullyBully]

The music is cool too! :) what is that?

[WVUDesignBuildFly]

This awesome. Great ideas :D

[arminask]

is the image processing done onboard the heli?