Stanford and Volkswagen Create Autonomous Vehicle

nght2000 writes "Stanford University has created an autonomous driving robot to compete in the 2005 DARPA Grand Challenge Race. The race will be held on October 8, 2005 in the desert Southwest. The team that develops an autonomous ground vehicle that finishes the designated route most quickly within 10 hours will receive $2 million. The route will be no more than 175 miles over desert terrain featuring natural and man-made obstacles. The Stanford Racing Team's vehicle is a Volkswagen R5 turbo diesel Touareg that was donated by Volkswagen of America. The Stanford Team has been working with the Volkswagen Electronics Research Laboratory on the project."

Comments

The people's car...

[FlameboyC11]

...without people! Gotta love that.

Re:The people's car...

[Penguinoflight]

Kinda adds new meaning to their slogan "Drivers Wanted" huh?

Re:The people's car...

[netsphinx]

God, yes.

I live in Atlanta. I work on one side of town, I room on the other. I go 25 miles each way. Average speed of 25mph. That's 2 hours a day I spend in the car.

If I could get into my car, type in a destination, and read, have breakfast, catch the last 10 winks, or write the great American novel while the car did the work, I would jump at it like a shot.

I realize that what I want out of an autonomous car is available, mostly, as public transportation. Unfortunately, public transportation in Atlanta is a joke. To do the 25 miles from my house to the office takes 2 hours, on 2 different systems, with three transfers. That's 4 hours a day in transit, provided nothing breaks down and the buses aren't late. I tried it, and I had just enough time left over in the day to sleep. Not eat, just sleep.

I saw a test car and strip of highway (somewhere in California, IIRC) that worked together as an autopilot. Drivers could enter the freeway, tell the computer what exit they wanted to get off at, and let the car drive itself. Little pips in the tarmac told the car where the lanes were, the on-board did the steering, and the central controller managed congestion by telling the cars what speed was best for the volume of traffic, when to change lanes, and when to wake (pardon me, alert) the driver that the exit was near.

Anyone out there remember this? Is it still under development?

Anyone care to speculate how soon I can get a robot chaffeur or auto-highway?

And does anyone remember...Sally? Asimov fans will know what I mean.

I worked on this project for a few hours

[CrazyJim1]

I only did some roadmapping for CMU. Outside of creating true artificial intelligence, only luck can win this goal. You map a route then calibrate your GPS, and hope the vehicle can stay on the road you drew, and hope it doesn't hit any obsticles in the way.

Re:I worked on this project for a few hours

[Anonymous Coward]

No one has come even come close to the finish line on this race, so it would be very significant if a team was able to finish it. In 2004 "The furthest any of the teams had gotten was the Red Team's 7.4 miles" in a 150 mile course. http://en.wikipedia.org/wiki/DARPA_Grand_Challenge

Re:Red Team

[dangerz]

Yes it is as far as I remember. Actually, one of my friends was telling me they're writing software to give the car the ability to powerslide.

this specifically won't work

[Anonymous Coward]

The course is specifically designed to defeat the gps+road map method of solving the puzzle.

It is guaranted that the vehicle has to pass through a tunnel or other type of obstruction that disables GPS.

Also, it is guaranteed that all roads will have obsticles at random locations that must be avoided. I understand that there are points where the vehicle must do an obstacle course and avoiding it or jumping over it is banned.

Re:this specifically won't work

[Anonymous Coward]

I'm working on the project for a different team. This can work. The competition is aimed towards making military vehicles that can drive autonomous. The military will look at satellite photos and choose a path for the vehicle to follow. The vehicle is then given these GPS points and must go. There will be cases where GPS may not be available for a short period of time; this problem is solved by an inertial navigation system, which uses gyroscopic sensors and accelerometers to give location based on the last known GPS location. There will also be situations where there will be obstacles and the vehicle must navigate through them using lasers and cameras. They are creating a real environment to test these machines in.

Re:this specifically won't work

[Nefarious Wheel]

GPS isn't the only positioning system in existence -- GPS plus intertial navigation could do it. Inav sums micro changes in direction along a path to give you a resultant vector.

Re:this specifically won't work

[john_anderson_ii]

It's true that GPS and "turn here", "turn there" technologies won't work, if that was all it took the U.S. Military could have done it themselves.

I do recall reading in Leatherneck magazine about a project the USN was undertaking involving unmanned subs that were to be used as long range sonar platforms and possibly very long range torpedos.

While operating underwater GPS is useless, but dead reckoning (Speed * Time = distance, distance @ bearing = position relative to start position) is still useful. The subs they were working on used a combination of surfacing for GPS, dead reckoning, and sonar navigation to avoid obstacles to reach their goal. I haven't read Leatherneck since I retired from the USMC, so I don't know what became of this project.

I think the point of this exercise is to use a mix of technolgies to accomplish the task. The most efficient mix, in theory, will win.

market potential?

[moviepig.com]

The...autonomous ground vehicle that finishes...most quickly...will receive $2 million. The route will be...175 miles...featuring...man-made obstacles.

Bulk purchases of these robots, modified for high-speed runs of less than 30 minutes, is under consideration by Domino's Pizza.

They're a bit optimistic..

[ElScorcho]

The team that develops an autonomous ground vehicle that finishes the designated route most quickly within 10 hours will receive $2 million.

Considering no vehicle has made it more than a couple miles in these races before, I find it pretty funny that they include the "finished most quickly" bit. If anyone could finish at all it would be a huge leap forward. Some of the footage last year was pretty amusing. One in particular I remember was a big SUV looking vehicle that was really moving, made it about 2 miles before it got stuck. Seems to me they'd be better served if they laid off the emphasis on speed for the time being and just got to the point where a sharp turn can be safely negotiated.

Re:They're a bit optimistic..

[sturat]

Seems to me they'd be better served if they laid off the emphasis on speed for the time being and just got to the point where a sharp turn can be safely negotiated.

This is the same advice I give to my mother and it's yet to have an effect.

But how many humans can do the job?

[tftp]

Driving a 4WD in a desert, with obstacles and detours, arriving at a destination within a time limit... I dare say not every human driver is up to the task. And they want to achieve this with a computer?

Re:But how many humans can do the job?

[Eivind]

Actually, the course is by no means that hard. It's no longer than 170 miles, and you've got 10 hours, that means an average speed of 17 will do it.

Parts of that is paved roads, parts unpaved roads and parts "offroad". This means you can do like walking-speed on the offroad-parts and still manage it fine.

Infact I'd take a bet that 9 out of 10 got-drivers-license-yesterday humans would be able to do this in less than half the time allocated to the robots, probably a good driver would do it in a quarter the time the robots get. That'd require him to average 68mph.

Re:But how many humans can do the job?

[zero_offset]

You've clearly never driven off-road. Indeed, with your statement that somebody could average 68 MPH in terrain like this demosntrates that you've probably never raced in your life, either.

Even in relatively benign terrain, a speed of about 15 MPH is actually moving pretty quickly. These aren't $2M one-time-use lightweight 500HP Paris-Dakar desert racers with a navigator, an 8-ton supply-laden chase truck. These are extremely heavy fully autonomous machines. If you read the rules, they're even supposed to refuel themselves without human intervention should it become necessary. It's really, really easy to break stuff at only 15 MPH, particularly when you consider how heavy these robots are.

Also, the paved sections are very short -- I haven't looked at the 2004 course in quite awhile and I'm not sure if the 05 proposed courses are up yet, but it was something like only 10% of the entire route -- and then you're not permitted to exceed the speed limit, which I think was pretty low -- 50 MPH or thereabouts.

It's very, very hard.

Re:CMU did this year ago

[__aaclcg7560]

And anyway, wouldn't a robotic vehicle be more likely to run into pedestrians like school kids?

Only if Grand Theft Auto was pre-installed.

Google / Stanford team too?

[chachacha]

I was driving through campus near the Stanford Golf Course the other day and saw a robotic solar vehicle emblazoned with the Google and Stanford logos. There was a large van outfitted with all sorts of sensors and gadgets on the roof and hood. Has anyone heard of Stanford attempting to build a robotic solar-powered car too?

Good thing, too...

[interactive_civilian]

I'm glad they made it autonomous because I heard that the back of a Volkswagen is a very uncomfortable place.

;p

Re:Good thing, too...

[fbform]

I heard that the back of a Volkswagen is a very uncomfortable place.

Only on Slashdot would that statement be qualified by "I heard that". :-P

Herbie!

[rossdee]

Didn't VW do an autonomous vehicle back about 1970 (in association with Disney)

"On the road of life...

[samkass]

"There are passengers and there are drivers. Drivers not wanted."

As someone who went to CMU, I'm of course rooting for the home team, but it is fun to read about the other guys. For the on-road stuff, they had those trucks zipping driver-less, pretty fast, through Schenley Park back in the 90's, so it'll be interesting to see if they can keep on the trail this time for the off-road challenge.

Re:YAY!!!

[NanoGator]

"Herbie Rides Again"

I can't believe that Herbie is taking precedence over KITT here. I know it's a VW and all, but yeesh, KITT's got der bliken lights!

I Cried

[LordMyren]

I cried when I saw how the DARPA desert race was done. I was thinking vehicles actually had to do pathfinding, you know, like, interesting stuff.

Thats simply not the case. DARPA hands out the final destination a day before launch and the teams madly scramble to find a route to send their vehicle down (on nice sat photos). Then they send the vehicle off on its own. What sort of fun is that?

Knowing this, I'm ashamed how poor last years competition was. The winning team was pretty sweet, but I certainly expect a lot more competitive entries this year. Hand most any college worth its salt $25,000 and let the CS & ME's go to. In a year they should build something which could at least contend with the DARPA incumbent.

As it stands the whole thing requires almost no intelligence. The whole point, from a computer engineers' biased persepctive, was to get people building robots aware of their surroundings. The Berkeley city auto-mapper robot is a perfect example; couple that with Sandstorm and then maybe I'm interested. But so many teams can make a robot which FAILS to track a GPS path while staying moderately on the road is just beyond me.

I understand the whole point is that the terrain is supposedly "hostile"... But when you're driving an `86 Hummer, its quite apparent that any area full of enough dangerous terrain to give you a problem will likely be seen on the sat-maps.

Myren

Re:I Cried

[daniel_mcl]

Actually, several teams (including my school's) did use pathfinding, and did a pretty decent job of it as well. The CMU team was one that preprogrammed the entire path, and they got one of the best scores, largely because it's really, really hard to develop an autonomous robot in your spare time while attending classes all day. It also doesn't help not to be able to run very many tests on site.

For instance, my school's robot was doing well until it hit a chain link fence. As it turned out, the chain-link fence was almost invisible to the car's vision system -- think about it, it's a bunch of air with these little tiny lines which are pretty hard to distinguish from debris in the air and such. You try writing a computer program that can accurately determine the presence of chain link fencing in a photograph and then see what you think.

As for GPS, again it doesn't tell you whether there's a fence, cow, brick wall, etc. standing in the way, and GPS was blocked for large sections of the course. If you're suggesting dead reckoning instead, note that that's really, really hard even under ideal conditions and essentially impossible outdoors. If a car gets one degree off course and travels 60 miles, it'll end up a mile off of the road, perhaps gleefully crashing through houses / oncoming traffic.

My school is in this competition

[Antilles]

I dont understand why their team is getting this much press, other than the fact that Volkswagen's PR dept is probably hyping stanford to get some marketing exposure for their company, as this year almost 200 teams applied to get site visits.

In terms of technology, well, outside of the Turing test, this is sorta like the Super Bowl of AI. My team/part of the project dealt with Machine Vision, which has proven to be quite difficult for a lot of people (including me!). Real time scene analysis is *very* computationally expensive, and you have to make guesses and inferences as optical signal data fluxes around constantly, a lot of the time completely rendering your approach useless.

Even though from life experiences I know that Life Isnt Fair, and the playing field is never level, some of these teams get insane advantages. I wont even go into CMU (ok, I will: they have basically Defense Contractor backing, parts, and consultants, and like 7 million dollars to spend on the project), and here stanford has sponsorship with volkswagen. I was suprised Cal Tech didnt get more major sponsors, but they might have for round 2 of the challenge. No one has near the advantage of CMU though, their main LIDAR cost more than a lot of people's whole car/setup.

Aside from that, for me this project has been a blast. The work, needless to say, is very unique and its almost like a mini-1960's space race, "first one to the finish line!". Its funny how some people try different angles, spend millions of dollars, and then get foiled by a rut in the road that hangs their car up (I'm tellin ya, if the sun shifts even slightly all vision input outside of lidar can basically go to sh!t if you arent careful, and if your lidar doesnt pick it up, well...)

Regardless of whoever makes it to the top 30, it will be interesting to see if anyone finishes this year. Darpa3, maybe?

Re:Uhhhh... No...

[Efinel]

Just when you thought it was safe to cross the street...

Don't be a chicken.

---------
Remember, drive defensively! And of course, the best defense is a good offense!

Re:Hey, VW, how about making diesel cars

[Gulthek]

What the deuce? I've been driving around in a Jetta Wagon TDI for two years. The only reason we got a Jetta TDI instead of a Passat is that the Passat isn't available with a manual transmission.

Golf, Beetle, Jetta, Passat, Toureg are all available with TDI engines. Try em out, but the waiting list is pretty lengthy because they are selling like freakin' hot cakes.

My wife and I keep our TDI pumped with biodiesel too. Less emissions, less smell, and our gas was living plant material mere years (or months) ago. Staying in the current carbon cycle is better than releasing carbon stored millions of years ago.