Alice Goes Four Wheelin' (Autonomously)
 

Well, today was Team Caltech's first attempt at qualifying for the DARPA Grand Challenge. We couldn't finish the course due to a bug in our GPS code, but we'll have another chance tomorrow. If interesed, the team has posted a short quicktime movie showing Alice (Caltech's entry) autonomously four wheelin' over a bunch of hay bales on the course.

Edit: Here's a link to a story about Alice and the team published today.

-Kevin

Re: Alice Goes Four Wheelin' (Autonomously)
 

That looks cool. Were they able to find the glitch and fix it? Good luck!

Re: Alice Goes Four Wheelin' (Autonomously)
 

Why did it stop?

Re: Alice Goes Four Wheelin' (Autonomously)
 

my guess is that they have problems in their software about reinitializing the system after gps is lost and then picks up again. you would lose gps when you are in the tunnel and when it comes back afterwords your computer needs to be able to handle that.

my team had a similar problem while testing but our vehicle ran into the trees when gps came back and we had to use our ekill

Re: Alice Goes Four Wheelin' (Autonomously)
 

Yes, it'll be fixed by the next attempt.

-Kevin

Re: Alice Goes Four Wheelin' (Autonomously)
 

I don't know all of the details yet. When Alice entered the tunnel, the path planner has to rely on our LN-200 Inertial Measurement Unit and some very sophisticated state estimation code to guess where Alice moves from moment to moment. When the GPS unit started providing navigation solutions again, it looks like the arbiter may have freaked, causing Alice to go into safe mode.

-Kevin

Re: Alice Goes Four Wheelin' (Autonomously)
 

Four wheelin over hay bails is bad? All in all Alice looks very impressive.

Re: Alice Goes Four Wheelin' (Autonomously)
 

Good luck guys! Wish I could be there!

Re: Alice Goes Four Wheelin' (Autonomously)
 

With the last news update I had, CMU's H1ghlander had the best performance so far, turning in a 9:22 run with no errors this morning. They had a planned time of 9:26, and the actual performance was able to improve on that. H1ghlander's elapsed time and driving were improvements beyond its Wednesday qualifier performance. Sensors that were skewed on Wednesday were calibrated overnight, resulting in the improvement. But several other teams were still waiting for their second opportunity at the test course, so we will see if that record holds (Alice had not run yet when I got the H1ghlander update).

-dave

Re: Alice Goes Four Wheelin' (Autonomously)
 

I was working at Stanford this summer, and I got a tour of the 'car' in July.
From what little they let me know, it seems their testing was going pretty well. I've tried to hook up with them in August, but they were pretty much out in the field all summer tweaking.

From what I saw, I think they have a viable contender. I tried to get onto the team, but they were in 'launch lockdown.'

Re: Alice Goes Four Wheelin' (Autonomously)
 

Alice just successfully finished the course in about twelve minutes thirty seconds.

-Kevin

Re: Alice Goes Four Wheelin' (Autonomously)
 

Looking at some of these entries, H1ghlander espescially, blows my mind. I simply cannot fathom the work that went into being able to map terrain to that accuracy in real time, and then do something meaningful with that deluge of data.

Vae Victus (1418) was visited a few weeks ago by two DARPA "referees" who refused to speculate on the outcome, but are probably there right now.

Re: Alice Goes Four Wheelin' (Autonomously)
 

Congrats to you and your team Kevin. I hope to be able to make a similar report about IRV before next Wednesday.

Re: Alice Goes Four Wheelin' (Autonomously)
 

Congrats. Ive been watching this since it started and I'm pretty hopeful that someone will win this year (or at least blow last years record out of the water). I got my picks for the winners and I hope you guys do very well today. Whatever is developed here will herald a new bread of autonomous robots and some of the developments made to that goal are truly amazing. In short, DARPA really knows its shtick. By the way is their a live feed we can watch? I looked but only found footage of last year.

Re: Alice Goes Four Wheelin' (Autonomously)
 

By yesterday morning the Stanford team came through and "Stanley" bettered H1ghlander's time through the course by about 4 seconds. They held the lead for most of the day. But late in the afternoon the other CMU vehicle, Sandstorm, turned in a 8:59 run. I believe that this is the first sub-9-minute performance by any of the vehicles. But any of the vehicles that are able to consistently turn in complete runs over thier set of attempts will likely have a good shot at making it into the race on Saturday.

The fact that about half of the vehicles attempting the course on the first day were able to complete it is a very good sign. As I recall, none of the teams were able to get through the course on the first attempts last year. So this is a significant step forward. The field of finalists next weekend should be quite interesting!

-dave

Re: Alice Goes Four Wheelin' (Autonomously)
 

Actually Stanford uses a really cool programming ideas. Their robot takes data and then figures out the probability that that data isn't false. apparently they reran last years coarse and made it most of the way (they had to stop because the human driven car got a flat.).

Re: Alice Goes Four Wheelin' (Autonomously)
 

These are the twenty-three teams going to the DGC festivities this weekend:

Axion Racing (Westlake Village, CA)
Team Cajunbot (Lafayette, LA)
Team Caltech (Pasadena, CA)
CIMAR (Gainesville, FL)
Team Cornell (Ithaca, NY)
Team DAD (Morgan Hill, CA)
Desert Buckeyes (Ohio State University, Columbus, OH)
Team ENSCO (Springfield, VA)
The Golem Group/UCLA (Los Angeles, CA)
The Gray Team (Metairie, LA)
Insight Racing (Cary, NC)
Intelligent Vehicle Safety Systems I (Littleton, CO)
Mitre Meteorites (McLean, VA)
MonsterMoto (Cedar Park, TX)
Mojavaton (Grand Junction, CO),
Princeton University (Princeton, NJ)
Red Team (Carnegie-Mellon University, Pittsburgh, PA)
Red Team Too (Carnegie-Mellon University, Pittsburgh, PA)
SciAutonics/Auburn Engineering (Thousand Oaks, CA)
Stanford Racing Team (Palo Alto, CA)
Team Terra Max (Oshkosh, WI)
Virginia Tech Team Rocky (Blacksburg, VA)
Virginia Tech Grand Challenge Team (Blacksburg, VA)

-Kevin

Edit: Here's the official press release.

Re: Alice Goes Four Wheelin' (Autonomously)
 

Woah, VT qualified TWO teams. That's impressive.

Re: Alice Goes Four Wheelin' (Autonomously)
 

here's a recent article on GC including the pictures! http://www.robots.net/article/1662.html enjoy!

Re: Alice Goes Four Wheelin' (Autonomously)
 

Alice is looking good, im rooting for Team CalTech!

Re: Alice Goes Four Wheelin' (Autonomously)
 

I had the chance to look around in Alice last year when I visited my cousin (Joe, he's a sophmore and one of the programmers) and I have to say it was ridiculously cool. My favorite part was the dynamic pneumatic braking system, using something like four or five pneumatics of increasing strength for differnent ammounts of pressure.

I talked to Joe on Saturday, he said Alice only made it eight miles before running into a concrete wall. He said there wasn't that much damage, just to the power steering. He said that the one of the LADAR's was miscalibrated or got disconnected or something, and since their code requires both to be active, they lost both. After that, I guess they lost their GPS signal underneath some powerlines and when they got their signal back, they were angeled differently then they thought. Hopefully thats something close to what happend, maybe Kevin can clarify.

PS: Hey Kevin, if you know Joe, tell him I said hi :)

Re: Alice Goes Four Wheelin' (Autonomously)
 

I'll know more later today.

I'm sure Joe (Donovan, right?) is still sleeping after months of writing code 24/7 <grin>.

-Kevin

Re: Alice Goes Four Wheelin' (Autonomously)
 

A bunch of us trekked out from Caltech to see the show as spectators. I thought it was a really incredible experience, and definitely worth the drive. It was wonderful to see car after car after car make its way from the starting line off to the horizon. It was even more exciting to watch Alice's dust cloud make its way back toward us for the photo-opp pass near the 8-mile mark. I don't think anyone in the stands would have imagined Alice suddenly turning off road right there in front of us-- it was a tragic thing to watch. The crash story as related above jives with what the speculation was at the time of the incident, but we didn't hang around to get anything in the way of a debriefing from the team after their inspection of the vehicle.

Re: Alice Goes Four Wheelin' (Autonomously)
 

One of the grad students on Team Caltech assembled a movie using imagery from one of Alice's cameras. Here's the link: http://robotics.caltech.edu/~klk/alice.html. To those that don't know what happened, Alice malfunctioned and easily drove over the top of a K-rail and headed up an embankment towards the press, who scattered muy rapido.

-Kevin

Re: Alice Goes Four Wheelin' (Autonomously)
 

Yah I saw the crash on Daily Planet, Alice took quiet a beating. Any word if they will be holding the event again next year? But all in all good job to all teams.

Re: Alice Goes Four Wheelin' (Autonomously)
 

Actually, Alice was/is just fine and was driven back to Caltech from Primm. Sportsmobile, who did the 4x4 conversion, did a remarkable job of beefing-up the suspension to take such abuse.


No, they won't be doing it again.

-Kevin

Re: Alice Goes Four Wheelin' (Autonomously)
 

Kevin,

i was wondering what kind of resolution of accuracy you had on your steering. i noticed while watching the video Alice seems to move back and forth during in the lane. The team i was on had the same problem and it was due to the variation in the steering column vs the encoder trying to keep it at a specific angle. actually i was really wondering if this was a problem for you or it was intentional (you system was plotting the "best" path)