Yes, you can learn a lot of robotics without actual hardware. I develop software for self-driving vehicles, and spend 95% of my time away from the hardware!

ROS + Gazebo will let you assemble a robotics software stack and explore different planning and control algorithms in simulation: http://gazebosim.org/ and http://www.ros.org/

If you want to explore perception and computer vision, take a look at OpenCV ( http://opencv.org/ ) and the tutorials there. The great thing about computer vision is you can run your software against the standard research sets or images you pull off Flickr.

Point Cloud Library is a nice package for looking at 3D laser data (but has some numerical quirks): http://pointclouds.org/

I would definitely take a look at some MOOCs, Andrew Ng's Machine Learning at Coursea (https://www.coursera.org/learn/machine-learning) or the MIT Courseware ( http://ocw.mit.edu/courses/ele... )

I think you're missing the brilliance of the phone doing the gameplay part. They're building an AI stack for one of the most ubiquitous portable computing devices of our time. One that can be had for $200.

Anki Drive performs real-time planning and control of multiple vehicles. It contends with dynamic obstacles (human drivers don't "stay in their lane") and relatively high speeds. These are non-trivial problems to solve, especially for objects with inertia and latency, and it's a first-step for more sophisticated platforms.

Once you have planning and control, you can start thinking about adding sensors for obstacle detection. And since the customer supplies the computing, it's a relatively cheap upgrade.

So I'm interested in seeing what they do next, and whether they can move beyond toys and entertainment.

Everybody else must continue this comment.

This was the case when I was an Engineering student at the University of Michigan in '03 and continues to be the case now.

http://ro.umich.edu/tuition/full.php#Lower_Eng

Your first two years as Engineering student will cost you about $100/$400 (out-of-state/in-state) more per semester versus general undergraduate. Those numbers shoot up to $1000/$1500 more your second two years (when courses are typically more lab intensive).

pdfLaTeX!

Here's a tutorial: http://www.ctan.org/tex-archive/info/pdf-forms-tutorial
or
http://tex.stackexchange.com/questions/14842/creating-fillable-pdfs

LIDARs (laser scanners) are pulsed, both for eye-safety and to measure the time of flight. These pulses are on the order of a few microseconds in duration. So it's not as simple as putting on some IR glasses or using a cheap web-cam. You need to time your shutter precisely. Long-exposures won't work because you'll accumulate too much ambient.

Some people loosely connected to the Lunar X Prize want to place a Christian cross on the moon.

http://crossonthemoon.com/

Religious Zeal-sourcing?

I don't have it on any of my machines and haven't really had to use it.

I guess you haven't seen XMMS2, it's a fucking trainwreck...

A quick search on youtube revealed this video which seems to be of the software in question.

The summary mentions prior work by Hoiem at CMU (slashdotted here), a video of which can be also seen on Youtube.

I'm not sure I'm very impressed by the Stanford videos. In the few examples of non-vertical surfaces, you can see quite a few artifacts.