Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Autonomous DeLorean drives sideways to move forward

news.stanford.edu

Post reply on HN
Print view View original

151–160 of 197 posts

Re: Autonomous DeLorean drives sideways to move forward

#151

Post by aeternum »

RandomBacon wrote: post #122
charliepark wrote: post #39

Earlier quoted context omitted.

> "The trouble with pure neural net controllers is that they sometimes do something totally bogus for some data point within the normal input space." A friend's theory on Google Maps is that it sometimes intentionally sends you down a non-optimal path in order to gather data on alternate routes. This friend isn't in the ML space, so this is just their anecdotal observation. Are they right, then?

That is my theory as well. It sometimes suggests a route I don't normally take, then when I continue on the route I normally take , the ETA updates to say I will now arrive sooner. Google Maps intentionally suggests to take longer routes.

It could be that Google Maps is saving everyone time by doing this. The Braess Paradox is really interesting, and this could be an attempt to prevent it: http://vcp.med.harvard.edu/braess-paradox.html

Re: Autonomous DeLorean drives sideways to move forward

#152

Post by chkaloon »

perl4ever wrote: post #150
chkaloon wrote: post #125

Back in the late 70s, my high school driving instructor said "don't tell your parents, but the best way to learn how to control a car is to go out to the school parking lot on a snowy night and spin donuts." Funny that they are finding that artificial intelligence can use the same method.

I've never tried it with a RWD car, but as a teenager, I thought the behavior of FWD in the snow was really fun. Go around a turn as fast as possible, and push on the gas pedal, it slides towards the outside, front first. Let off on the gas, and the front snaps back to the inside of the turn. I also buried my car in a snowbank more than once and had to dig it out.

I always thought RWD was more intuitive, and in this video the car appears to be RWD. It probably depends on what you grew up with.

Re: Autonomous DeLorean drives sideways to move forward

#153

Post by perl4ever »

Neil44 wrote: post #64
ohadron wrote: post #32

Somewhat reminds the progress airplanes did in the 1970s with fly-by-wire technology. Specifically they way it was utilised in the F-16. Moving from directly piloted controlled surfaces (rudder, elevator, flaps, ailerons etc) to using a computer to convert the pilot command input to servo actuators. Flight surfaces had much more authority, much better performance could be achieved, but the flight computer was in char…

Steer and brake by wire is a safety thing, all manufacturers so far have kept a mechanical link in place despite electric assistance because of the potential for lawsuits. Infinity has gone the closest to full steer by wire so far that I’m aware of.

https://www.motor1.com/news/64033/infiniti-q50-steer-by-wire...

Re: Autonomous DeLorean drives sideways to move forward

#154

Post by tachyonbeam »

YeGoblynQueenne wrote: post #117
asdfman123 wrote: post #105

Can we just stop for a minute and admire the fact that there are people out there who have found a way to get paid to program a DeLorean to drift?

More like, if you can program a DeLorean to drift, someone will pay you for it.

That's definitely not true. Making something cool and useful doesn't necessarily translate into making money. In this case, these people are getting funding because they convinced someone that this was useful research, probably through a grant application of some kind.

Re: Autonomous DeLorean drives sideways to move forward

#155

Post by tachyonbeam »

sap9433 wrote: post #135

If self-driving tech has become so advanced, I wonder why Waymo is not delivering anything? I wonder why is Tesla taking forever to deliver self-driving, why Uber discontinued its self-driving program, Why Apple ain't serious about Apple car yet? Does this demo hide something that we should know?

Because this has not much to do with what Waymo or Tesla are doing. What they've developed here is a control system, a way to make the car move in a certain way, follow a certain course. The problem that autonomous driving needs to solve is to have a car that can reliably perceive and understand what's happening around it, navigate any complex situation involving pedestrians, intersections, road work, parking, etc. The drifting DeLorean doesn't have to worry about any of those things, it only has to work in an empty parking lot. There might not even be safety measures to prevent it from hitting people. They use precise GPS to track the car's position (where it is on the course), so it's possible the car doesn't have cameras or LIDAR to perceive its surroundings.

Re: Autonomous DeLorean drives sideways to move forward

#157

Post by Hamuko »

zzzeek wrote: post #130
toss1 wrote: post #124

Earlier quoted context omitted.

Yes, but. Yes #1 is that this is mostly Drifting techniques, which are mostly for show/style competition. The tyre slip angles mentioned are around 40deg, far past the optimal level of grip. Yes #2 Racing techniques are more explicitly seeking to optimize for maximum grip, often found around 3 to 6 degree slip angles (depending on tyres, tyre pressure, tread & road temps, road cleanliness, dryness, etc.). Both still…

> BUT, all that said, it is absolutely critical to have thise techniques in your bag of tricks, available to use when something exceptional happens. In those rare-ish events, being able to use the full performance envelope of the vehicle is a real life saver, both for you and the others nearby. are you referring to during a road race, or ordinary driving on ordinary streets? It would be great if you could try to prov…

>I've never heard of accidents being avoided on highways because someone knew how to do racecar drifting.

Knowing how to control oversteer is a crucial skill when driving on snow and ice.

Re: Autonomous DeLorean drives sideways to move forward

#158

Post by Hamuko »

ForHackernews wrote: post #95
grecy wrote: post #55

I genuinely hope Tesla get a 2020 Roadster to lap the Nurburgring on autopiliot with nobody inside. If it lives up to promises, it will easily set the all time lap record as the fastest vehicle ever. It will be an interesting time when a $200k production car can whip the pants of a multi-million dollar F1 racecar.

Tesla cars historically are pretty terrible on the track. They're too heavy, and they wind up overheating. The torque from the electric motors means they do really well in a straight line drag race, but they're fairly pathetic at any race that involves manoeuvring over a longer course.

They've apparently made improvements to the cooling since the Model S, which could not complete a lap of Nordschleife without overheating.

Re: Autonomous DeLorean drives sideways to move forward

#159

Post by Hamuko »

saagarjha wrote: post #7

I was half expecting a Toyota Sprinter Trueno and Eurobeat. Pop references aside, though, what is this useful for? I thought cars were designed to not skid normally due to ABS?

ABS is a system to prevent you from locking your wheels when you step on the brake. It doesn't prevent your car from breaking traction.

Re: Autonomous DeLorean drives sideways to move forward

#160

Post by octoboto »

Animats wrote: post #6

They did most of that back in 2015.[1] This is version 2. It's interesting what's happening as the control theory people get into machine learning. The controls people don't typically run a neural net as a controller. They use the trained net as a tool for building a controller with known continuity properties. The trouble with pure neural net controllers is that they sometimes do something totally bogus for some dat…

What papers are you talking about? Can you please link to them? I don't see anything about neural networks in the papers about this experiment.
Post reply on HN