Slashdot Mirror
Stanley and the Conquest of the DARPA Challenge
geekboy_x writes "Wired has a great in-depth piece on the Stanford team that won the $2 million DARPA prize. If you remember last year's disaster - with most vehicles falling off the road in the first kilometer or so - this victory becomes all the more amazing. The fact that the Stanford team used a 'tailgating' strategy is the best surprise in the article."
Also interesting to note is the fact that the major leaders of the Stanford team came from the Carnegie Mellon AI department 2-3 years ago.
http://www.asti-usa.com
From "Ask Captain Lin":
"On the Boeing 777, the autopilot can be selected on at 200 feet above ground level after take off. Most of the time, the pilot would make use of the autopilot on the climb because it eases the workload of the crew especially during an emergency. Sometimes, a pilot may elect to fly manually during the climb just to get his hands on the control column or to maintain his proficiency because during a flight test, one of the exercise calls for flying without the aid of autopilot. Otherwise, the autopilot is engaged throughout most of the flight. It is smoother, more economical and safer with the autopilot on. In fact, in really bad weather with very limited visibility, the autopilot even lands the aircraft by itself. The pilot only resumes control of the aircraft after it has safely landed on the Runway."
http://www.asti-usa.com
I don't know about turbulence, but planes have been (capable of) landing themselves on autopilot since the 70s. Taking off is harder but I believe autopilots can do that now as well. Autopilots today can also change course and altitude to avoid weather conditions - it's quite a bit more sophisticated than simply following a course. Driving on the ground is a much harder problem, but don't underestimate what autopilots are capable of.
From what I've read, the Nissan system only warns the driver that they are drifting from their lane and doesn't actually steer the car. When the driver drifts from their lane without engaging the turn signals the car emits a warning chime. I think we're still far from an actual automated steering system that is reliable enough (i.e. 99.9% safe) for public use.
basically due to whatever circumstances (width of the road, start order etc) someone has to be in front and someone has to be behind - the fact that the Stanford vehicle was following another entry had nothing to do with how it was successful, in fact one could argue it put the vehicle in some danger if the lead vehicle messed up, rolled, crashed etc. It later passed the said vehicle to go on to the win - The article makes no mention of a "Tailgating Strategy" it does say that it was tailgating another vehicle for a bit before it passed it - not sure how this is any more strategic then when I drive to work in the morning - how about this winning strategy "Don't hit the car in front of you". Don't know why this bugged me so much, its actually a good read, I just don't know why this non-existent "Fact" was so prominent in the lead in. Sorry.. not enough coffee today....
Not ever, for that matter.
The article doesn't say they had a tailgating strategy, it just mentions the raw fact that during the race they'd been tailgating another entry until choosing to pass them. There's no suggestion (let alone assertion) that they could have passed earlier but chose not to, or deliberately delayed attempting to pass until late in the course.
Tailgating would appear to be a pretty poor strategy anyway - it assumes that the one you're tailgating is sensing the road and safe speed better than you are.
The "strategy" employed, per the article, was to learn from a human driver what weights to give to various sensor inputs, as well as to teach itself how to interpret it's video input by comparing it to the same section of road when it got close enough to scan by lidar.
That's actually not true. There was no "tailgating". During the Grand Challenge, no vehicle was allowed to approach another while both vehicles were active. DARPA had the ability to remotely pause any vehicle. When vehicles got anywhere near each other, the trailing vehicle was paused to maintain separation. If the trailing vehicle was clearly faster, a pass was scheduled. All passing took place with one vehicle stationary and at a wide place in the road. Wired has this wrong.
My cousin is a qualified pilot on several of the bigger passenger jets and yes, it is entirely possible for a crew to do nothing but board the plane, taxi to the runway and then let the autopilot handle the entire flight, including the takeoff and landing. The normal mode of operation however is to clear the airport on manual, activate the autopilot until in the approach at the destination and then make a judgement call about letting the autopilot land the plane at the destination based on the conditions at hand. There are also exceptions about if one or more of the autopilots malfunctions (there are apparently three on the bigger jets, I'm not sure about the smaller ones). Technically one functional autopilot is enough to handle the entire flight, but the regulations of my cousin's employer prohibit non-manual landings with just one faulty autopilot, and with two faulty units all flight operations must be fully on manual. They do however have to complete a mandatory amount of manual take-offs, landings and flight hours each year to remain qualified, in addition to the numerous medical, physical and flight examinations you would expect. Other airlines do vary their individual guidelines and proceedures of course, but not by too much.
UNIX? They're not even circumcised! Savages!
Try the Scientific American article on the DARPA challenge: Innovations from a Robot Rally
It covers all the teams a bit and talks about some of the innovations that were used by the competing teams. It is a little light but worth a minute or your time.
Architectural plans are like computer source code with a couple of differences: You only compile once.
Unlikely, as they would be too easy to intercept and destroy. What they really want to use them for is logistics. So much of the military's manpower is concentrated on logistics, that's where the real potential for saving money and saving lives is. What they really want is a convoy of trucks that can be programmed to go from Supply Base A to Tactical Operations Center B, then proceed to Staging Area C, without having to put human drivers in the vehicles.
If you don't know where you are going, you will wind up somewhere else.
In the Grand Challenge, cars didn't race against one another to try to be the first across the line. They raced to try to complete the course in the shortest elapsed time .
According to the Darpa web site, Stanford won the race by finishing with an elapsed time of 6 hours and 53 minutes. They could still have won if they crossed the finish line after the CMU vehicle, as long as their elapsed time was still shorter.
CMU's Sandstorm finished in 7 hours and 4 minutes.
CMU's H1ghlander finished in 7 hours and 14 minutes.
In the states, it varies by state and even then, sometimes by the metro location you're in. In some areas, the "inspection" is just merely a smog check. For instance, my home state does not require an inspection, but in certain metro areas, requires a smog check.
The US inspection system is a joke in most states. Its usually a 100 point inspection, they look at your wheels, windshield, brakes, etc and point out something that should be obvious. The inspections in Europe are much better. Heck, the military POV (personally owned vehicle) inspections that the American soldiers go through in Europe are even more of a joke. So much so that if an American buys a European car, when they clear the car from European Customs - Customs snips the registration to show it was owned by an American.
In Europe, I needed new tires for my car as I was down to the bars in the tires and I was running on the original breaks which needed to be replaced. For grins, I took it in and it passed without them even looking twice. Luckily everything was in the mail already on its way.