Group items tagged

In case you want to ask him anything

how the us intelligence community forecasts tech development into 2030

Curiosity suffered from BSoD...

very impressive!

Very cool - I like also like the little tumble that the copter does after it launches the pole. It look like it is happy of what it just did :-D

RoboEarth Cloud Engine now complements the RoboEarth knowledge database with computational capabilities and allows web services dedicated to robots

I wanted to post this one, as plant-inspired robotic design and algorithms are a new kid on the block, and then noticed that some ACT-members may already be aware of this special issue...

some of the quotes in there are a bit limit ... :-)

I would well imagine a team at an other space institution, with their own diigo, commenting on that news ... ;p Interesting trend nonetheless. At the NASA Space Apps Challenge, few teams proposed a similar G&C application but for the rover Curiosity... this is certainly a good approach for citizen science.

open source open hardware quadrocopter ! next platform for Astrodrone ?

MSRP suggests it's not designed to survive landing.

In case Guido and Co. want to expand on the scent of science project... ?

Hey Guys, Is one of you has any idea about how it's coded? I mean, is it just a basic database of already-written answers or something more sophisticated? Anyway, have fun! Alex

Hi, thanks for your answer. I had a look to the different versions, that's pretty interesting to see how they have evolved over the years.

I was not at all impressed - stopped after a few questions since getting ridiculous answers or trials to change topic

I got a fever. And the only prescription is more cat faces! ...../\_/\ ...(=^_^) ..\\(___) The article sounds quite interesting, though. I think the idea of a "fake" agent that tries to trick the classifier while both co-evolve is nice as it allows the classifier to first cope with the lower order complexity of the problem. As the fake agent mimics the real agent better and better the classifier has time to add complexity to itself instead of trying to do it all at once. It would be interesting if this is later reflected in the neural nets structure, i.e. having core regions that deal with lower order approximation / classification and peripheral regions (added at a later stage) that deal with nuances as they become apparent. Also this approach will develop not just a classifier for agent behavior but at the same time a model of the same. The later may be useful in itself and might in same cases be the actual goal of the "researcher". I suspect, however, that the problem of producing / evolving the "fake agent" model might in most case be at least as hard as producing a working classifier...

This paper from 2014 seems discribe something pretty similar (except for not using physical robots, etc...): https://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf

Yes, this IS basically adversarial learning. Except the generator part instead of being a neural net is some kind of swarm parametrization. I just love how they rebranded it, though. :))

Spooky cars on the road

yes but they do not drink & drive

Artificial earthworm made from a mesh tube and shape memory alloy muscles.

Autonomous robot driving through a pedestrian zone in Freiburg, recognizing moving obstacles.

He moves with style...

Agency wants to send mini robots into space to recycle and reuse antennas from more than 1,300 dormant satellites in geostationary orbit above the earth.

well done ... why your name does not appear there?

I am a bit surprised by the number of critical comments to this article there ..

But the comments are not critical, it's just bullshitting.

hmmm, I was wondering how many ESA employees do know that ACT does exist....

And my son studying at Stanford (he just sent me the same link !) follows the courses this semester of two of the teachers mentioned in the article, Thrun - very good and Ng - excellent