Drone learns from humans how to navigate a forest

From the ROS blog:

The Robotics Institute at CMU has been developing systems to learn from humans. Using a Machine Learning class of techniques called Imitation Learning the group has developed AI software for a small commercially available off-the-shelf ARdrone to autonomously fly through the dense trees for over 3.4 km in experimental runs. They are also developing methods to do longer range planning with such purely vision-guided UAVs. Such technology has a lot of potential impact for surveillance, search and rescue and allowing UAVs to safely share airspace with manned airspace. 
Watch the flight in unstructured environments below.

 

Views: 958

Comment by W. Joe Taylor on December 12, 2012 at 2:15pm
Chris,
This is amazing for several reasons. 1st they only used a camera as the main sensor. 2nd the optical flow routine & vision based learning algorithm looks simple. 3rd the payload capacity of the Ardrone is very limited. I assume the autopilot was based on the px4 fmu like the one that 3dr has & the px4ioar. CMU article at

http://www.ri.cmu.edu/pub_files/2012/11/1211.1690v1.pdf

Thanks Chris & CMU team.

Comment

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

Join DIY Drones

© 2014   Created by Chris Anderson.

Badges  |  Report an Issue  |  Terms of Service