PX4 team does mindblowing mapping and exploration with optical flow board

The PX4 team at ETH is a finalist for the IROS 2012 Best Paper award for this work, which uses the PX4 and the forthcoming PX4Flow optical flow board (coming soon from 3D Robotics) to do this:

We describe our autonomous vision-based quadrotor MAV system which maps and explores unknown environments. All algorithms necessary for autonomous mapping and exploration run on-board the MAV. Using a front-looking stereo camera as the main exteroceptive sensor, our quadrotor achieves these capabilities with both the Vector Field Histogram+ (VFH+) algorithm for local navigation, and the frontier-based exploration algorithm. In addition, we implement the Bug algorithm for autonomous wall-following which could optionally be selected as the substitute exploration algorithm in sparse environments where the frontier-based exploration under-performs.

We incrementally build a 3D global occupancy map on-board the MAV. The map is used by the VFH+ and frontier-based exploration in dense environments, and the Bug algorithm for wall-following in sparse environments. During the exploration phase, images from the front-looking camera are transmitted over Wi-Fi to the ground station. These images are input to a large-scale visual SLAM process running off-board on the ground station. SLAM is carried out with pose-graph optimization and loop closure detection using a vocabulary tree. We improve the robustness of the pose estimation by fusing optical flow and visual odometry. Optical flow data is provided by a customized downward-looking camera integrated with a microcontroller while visual odometry measurements are derived from the front-looking stereo camera. We verify our approaches with experimental results.

Here's the team and their birds. Huge and well-deserved congratulation!

Views: 5413

Comment by Roberto Navoni on October 5, 2012 at 3:17pm

Great Work Lorentz ... what cpu use for Slam in this project ?

Comment by John Githens on October 5, 2012 at 3:56pm

Nice work, and here is a link to a related paper.

Comment by Ruwan on October 5, 2012 at 6:57pm

Nice work. I wonder the material they used for frame protector. Any ideas?

Comment by W. Joe Taylor on October 5, 2012 at 10:00pm
This is way awesome! Since at least 2004 the outstanding teams at the Swiss federal institute have consistently pushed the technical envelope for quad rotors. I can't wait to see what Sanford, Univ of Penn, MIT, and others publish on this in the next year or so. I also wonder if the team has integrated GPS, because it seems that would be trivial compared to this kind of achievement.
Comment by Jack Crossfire on October 5, 2012 at 10:02pm

It's mindblowing & face melting.

Comment by Kabir on October 6, 2012 at 8:45am

It's mindblowing & face melting.

+1 :)

Comment by Jay Bryon on October 6, 2012 at 4:13pm

Link to paper?  Or competition?  

3D Robotics
Comment by Chris Anderson on October 6, 2012 at 4:22pm

Jay, sorry I missed a link above (it was in the video, but I've now added it above to make it easier to find). The citation to the paper is here:


Comment by Anish on October 8, 2012 at 3:06am

cool , congrats guys :)

Comment by Oliver Sumpton on October 9, 2012 at 12:22am

What?! This is NUTS ! :D


You need to be a member of DIY Drones to add comments!

Join DIY Drones

© 2018   Created by Chris Anderson.   Powered by

Badges  |  Report an Issue  |  Terms of Service