This is *exactly* why machine learning is the most popular of the Stanford
online classes. Gizmodo goes into the ML a bit more:
http://gizmodo.com/quadrotor
Most of the optimizations are based on spacial partial derivatives being
fed into a gradient descent optimizer. In the ping-ball catch, the
optimization is a bit more complex: it has to create a good model of the
ping ball parabola and intercept it. It may be doing continuous tracking,
however, simply because its own blades creates turbulence.
-- Owen
On Sat, Feb 25, 2012 at 2:14 PM, Tom Johnson <[email protected]> wrote:
> For our "fly by night" colleagues.
>
> A "swarm" of nanodrones flying in formation and navigating through
> obstacles.
>
> http://www.youtube.com/watch?v=FubP0KzeS4w
>
> -tj
>
>
> ============================================================
> FRIAM Applied Complexity Group listserv
> Meets Fridays 9a-11:30 at cafe at St. John's College
> lectures, archives, unsubscribe, maps at http://www.friam.org
>
============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
lectures, archives, unsubscribe, maps at http://www.friam.org
