It gets worse than that or perhaps better than that.

So the interplanetary system is on its way, but there's a last project, which the Defense Advanced Research Projects Agency, which funded the original ARPANET, funded the Internet, funded the interplanetary architecture, is now funding a project to design a spacecraft to get to the nearest star in 100 years' time.

This vehicle will eventually be able to drive in a different direction and reach the goal point behind the blockage.

let me briefly tell you about another project that I worked on called the DARPA Urban Challenge.

That's fantastic. All the high school students out there you guys rock.

Those are fascinating by their own rights.

So here we go.

I get this sort of unrequested by me anyway visit, and sitting in my conference room is a very senior surgeon from the military and the guy that runs DARPA.

And we can now use this as what I think will be a major medical breakthrough.

Jason started at DARPA on March 18th, 2010.

We have a fully autonomous vehicle that can drive into urban environments.

This is a very typical stereo vision result.

This work led to the Urban Challenge, in which we built another robot called Junior that eventually took second place.

There, they're just looking for a sticker that says Boardwalk, but it can also be used to find real things.

I think what this is all about, this whole movement which is growing from the margins, remains quite small.

What you see here is a robot my students and I built at Stanford called Stanley, and it won the DARPA Grand Challenge.

A star planning, and dynamic programming planning that all address slightly different use cases.

And more so than most, he saw the highs and the lows, the celebrations and the disappointments.

let me show you some videos.

The environment may be stochastic, yes or no, and it may be adversarial, yes or no?

And we are flying it, or trying to.

It takes less than a tenth of a second to build this entire search tree, and the robot is able to navigate this parking lot really, really efficiently.

Now these two ideas are connected more than you may realize, because when you remove the fear of failure, impossible things suddenly become possible.

I saw the concept first in the DARPA Grand Challenges where the U.S. government issued a prize to build a self driving car that could navigate a desert.

And the unimaginable happened it became the first car to ever return from a DARPA Grand Challenge, winning Stanford 2 million dollars.

So if you want to build a self driving car you now understand to make a really complex, nice search algorithm to find a path to a goal.

Two letters, an L and an O, now a worldwide force.

Lots of teams competed from various universities, car companies, and also lots of hobbiests that were new to the field competed, and built this huge set of different cars.

This implimentation is so fast that it can plan these paths in less than 10 msec for any location in this maze.

Let me just discuss it for this one example and show you what we've done to solve this problem in the DARPA Urban Challenge.

Now the Minotaur IV has too much impulse, so we have to bleed it off by flying the rocket at an 89 degree angle of attack for portions of the trajectory.

I'd like to tell you about a magical place called DARPA where scientists and engineers defy the impossible and refuse to fear failure.

They challenge existing perspectives at the edges of science and under the most demanding of conditions.

Now Chuck is doing something quite extraordinary, at least for my limited physical skill.

low cost commercial production of these kinds of materials, or for that matter, ultra light steels that are a good backup technology, the military can do the trick it did in turning DARPAnet into the Internet.

Here is a laser map being produced in this case, Stanford's car, and we used particles to localize this robot by matching momentary measurements with the previously acquired map.

A few years ago I was visited by the guy that runs DARPA, the people that fund all the advanced technologies that businesses and universities probably wouldn't take the risk of doing.

I have often suspected that this whole place might just be a front for some type of DARPA funded breeding project.

Speaking of imperatives, geoengineering is taboo now, especially in government circles, though I think there was a DARPA meeting on it a couple of weeks ago, but it will be on your plate not this year but pretty soon, because some harsh realizations are coming along.

You can see it here close before the finishing line, and after just about 7 hours it managed to do what no robot had every done before.

But they're getting better quite quickly and DARPA, which is the investment arm of the Defense Department, is trying to accelerate their trajectory.

Today, I'd like to tell you about those, and also show you some of the basic techniques so you can in principle program your own self driving car.

Stanley has been here for a couple of years now in exhibits our robot that won the DARPA Grand Challenge, and it was really fascinating to see the thing that we've built and visited in its own little room in the Smithsonian museum.

So, what I've been teaching you last class about the common fater really had a major role to play in making Stanley the robot win the DARPA Grand Challenge.

The vehicle was based on a Volkswagen Touareg that was equipped with all kinds of sensors like GPS and laser, and it was able to make its own decisions without any human input whatsoever.