it is interesting just how involved the contestants are. This contest is their life. They mentioned several times in the show how many months of long workdays they spent to build and program these cars. And, then, who owns the work? Do they at least get patent recognition on some of the innovations? Some of the software they talked about was truly seriously cool stuff.

Sidenote: One hour of Nova or Frontline is like watching 5 days worth of "learning" and "discovery" shows elsewhere. It's amazing how good some of these shows are.

After watching Why We Fight [imdb.com], I'm not so keen on something like this anymore.

'Coverage' and 'Darpa' in the same paragraph.

Another interesting point is that it seems to me that this is the development arena for the military's new autonomously roving gun platform.

The Red team (CMU) basically preprogrammed their robots before the race by looking at satellite maps of the race course. I thought in essence this was cheating but I suppose it was not against the rules. The Blue Team (Stanford) had a better software solution where their robot would essentialy drive and learn on the fly. I'm glad to see Stanley won because this is the technology needed for automated driving, imagine using the Red team's solution and have to preprogram you car? What's the point?

The human eye and visual cortex are an amazingly complex and complicated system. Interestingly enough, I remember about reading about the a while back in December. According to the wired article, IIRC, Stanley used a combination of lasers (short range) and cameras (long range). It then took what it learned about the short range view of the landscape and it applied that knowledge against what it was seeing on the long range from the cameras. [slashdot.org]

This is actually not too far different from how human vision works -- we sort of guess about the landscape in front of us based on knowledge of other landscapes and the current landscape around us that we can see close-up. We just don't have lasers. ;)

It was a good show. One nifty bit of engineering from the Stanford team was to overlay a video camera image over laser-generated map, use a color-matching system to determine what colors of the video were level and safe to drive on, and then extrapolate what areas of the video image were safe.

The main difficulty that I see, going forward, is that the laser-rangefinder systems that these robots all relied on all function by looking for obstacles and attempting to avoid them. They can spot vertical anomalies, such as hay bales, other cars, poles, etc., but that's about it. None of these systems can actually determine road conditions. A rangefinder can't tell if the smooth road up ahead is actually a ginormous pothole filled with water, or if the road ahead is covered with a thick layer of ice. All it knows is that the area ahead is flat and clear... accelerate at will. Under such circumstances, any of these robots would run into serious difficulty, even if the course were relatively flat and straight.

As impressive as driving a windy road autonomously is, there's a long way to go before these things see commercial, or even military, use.

There were several points made in the program that I hadn't heard elsewhere (and I've been paying attention to the Grand Challenge since the initial press release).

  -- The teams get the GPS waypoints a few hours before the race. The waypoints are purposefully vague, so the robots have the choice of driving off a cliff (or into one) while still being within GPS parameters. This is supposed to prevent the race from reducing to "Who can follow GPS the best?" The Red Team had a group of what looked like 20 or 30 people who immediately sat down with the waypoints mapped out on satellite imagery, going through and adding waypoints of their own and adding speed commands for their robots. This seems to me to be a big violation of the spirit of the competition.
  -- The Red Team had two entries, which they programmed differently: one more aggressive, the other more conservative (on speed). The faster robot, Highlander, was pulling away from Stanley for the first part of the race, until some unknown issue starting causing problems. Nova didn't say what was wrong, but it looked literally like Highlander was slipping out of gear and rolling back down hills. It _might_ have been doing it on purpose, i.e. a software glitch, but it didn't look that way.
  -- One of the Red Team's entries completed the last portion (the hardest portion) of the course with its main sensor non-functional -- it was stuck pointed 90 degrees to the side. This argues even more strongly that the Red Team's vehicles weren't doing much route-finding and were pretty much just following GPS waypoints.

The conclusion I draw from this is that we are still a long way from the DOD's goal of autonomous transport vehicles. In a combat situation, transports need to be able to avoid obstacles put in their way _by the enemy_. The only time during this challenge that the vehicles did anything like this was during the initial trials before the race, and that was very limited. The actual race course was hard -- off-road, dirt, narrow, slippery -- but it didn't have tank traps painted the same color as the dirt they rest on. It didn't have razor-wire barricades, forcing the cars to figure out a route through the bushes around them.

I'm confident that if I had been on the course fifteen minutes before the cars showed up, I could have stalled or disabled all of them. Pile a bunch of bushes across the road and all of them would have stopped. During the trials and race, none of them demonstrated the ability to work around such a very limited obstacle.

All of this is not to minimize what was accomplished. But we're a long way from sitting back sipping champagne while robots do the dirty work of war.

As a student at Carnegie Mellon who has discovered the extent of his school's ties to development (had I known prior... and no, CMU is not unique in this regard, the problem is everywhere) of military products and has since spoken out against them a few times, thank you for realizing that this DARPA stuff isn't all it's cracked up to be.

I'm perhaps one of four people (an exaggeration, I hope) on my campus that isn't gung-ho about helping the DOD build driverless vehicles, and it's lonely at times.

Whatever moderator marked this down as off-topic was clearly just trying to limit the scope of discussion in the same way that DARPA and military contractors are trying to limit the scope of their moral and ethical liability.

True. There was so much hype surroung "Red Storm" and how it would p0wn the rest of the field before GC-1. Then during the trials, their Hummer tipped over because it took a curve too fast (d'oh!! where's the linkage between the wheel turning system and the speed system?). And in the race, it almost caught fire because 1 wheel got stuck and the other spun freely; the system controlling the engine just kept increasing the RPM, with the eventual result that the tires melted and flew off, and the controllers had to hit the emergency stop.

It was clear then that the CMU team was loaded with tech, but lacked smarts. They were trying to bruteforce the course (they sent teams to navigate every possible path in the race area with a GPS, so they could map out obstacles beforehand. Geez! talk aboout spare no expense!).

The most impressive, of course, was DAD. With almost nothing but a pair of cameras for stereo vision, they were able to achieve so much in their garage.