Autonomous DeLorean drives sideways to move forward

They did most of that back in 2015.[1] This is version 2.<p>It&#x27;s interesting what&#x27;s happening as the control theory people get into machine learning. The controls people don&#x27;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 data point within the normal input space. That&#x27;s not OK in control systems.<p>This has all the math of machine learning plus the math of control theory and I don&#x27;t understand it, although I sometimes look at the papers.<p>[1] <a href="https:&#x2F;&#x2F;news.stanford.edu&#x2F;2015&#x2F;10&#x2F;20&#x2F;marty-autonomous-delorean-102015&#x2F;" rel="nofollow">https:&#x2F;&#x2F;news.stanford.edu&#x2F;2015&#x2F;10&#x2F;20&#x2F;marty-autonomous-delore...</a>

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?

Back in the late 70s, my high school driving instructor said &quot;don&#x27;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.&quot; Funny that they are finding that artificial intelligence can use the same method.

This group has done good work, and at talks about their work I was able to come away with an interesting trivia.<p>When they try to compete with the best racers in the world, they do lose by a consistent amount. It turns out the human racers are constantly pushing the vehicle+tires to the limit of control to understand the sharpest possible turns they can make without losing time. As the tires wear, the human is in constant learning mode to compensate turn approaches as the coefficient of friction changes.<p>Work on the DeLorean will hopefully feed into their racing controls and then they might be able to beat the best human racers in the world on arbitrary tracks.

Somewhat reminds the progress airplanes did in the 1970s with fly-by-wire technology. Specifically they way it was utilised in the F-16.<p>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 charge of safety and keeping the aircraft within limits.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Fly-by-wire" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Fly-by-wire</a>

So is the general idea that by removing the automated controls, which normally limit drift so human drivers don&#x27;t lose control, they&#x27;re able to gather data at the extremes of car handling?<p>I&#x27;m curious how this would be applied in the real world. It almost seemed to suggest that a self-driving car would operate with those stability controls turned off, allowing it operate evasive maneuvers that would be impossible in a human-driven car.

Don&#x27;t get me wrong I think this is an impressive feat and I am always impressed to see universities pull off these kinds of complex system and control projects. Yet, there are a few things that I would like to mention.<p>The article says that the car does &quot;doughnuts with inhuman precision&quot; and they want to develop vehicles that can handle &quot;emergency maneuvers or slippery surfaces like ice or snow&quot;. In this context, I feel this demo falls a bit short. The car can drive with superhuman precision, but it also gets superhuman capabilities like inch-precision localization (and an IMU is my guess) or superhuman steering wheel turning speeds. And the vehicle is heavily modified for this specific use-case. Drifting looks stable in the video but I really cannot judge how much easier it is with this car than a normal car. In addition, the asphalt also looks fresh and clean. I would like to see what happens if it suddenly encounters wet surfaces (or ice).<p>edit: typos

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.<p>It will be an interesting time when a $200k production car can whip the pants of a multi-million dollar F1 racecar.

I wonder if it would be feasible to make a fleet of race cars that have self driving technology that has each car communicating with the others and monitoring the human drivers, with the car letting the human drive but able to step in if the human tries to do something that would cause a crash?<p>I bet you could make some pretty good money with such a fleet running open races that members of the public can pay to drive in.<p>The self driving system could keep track of the number and severity of its safety interventions which could be used to give time penalties at the end of the race [1], so that the winner is determined by the skills of the humans.<p>Besides racing, you could also do car chases that recreate scenarios from action movies. Add in something to simulate guns, and you could do scenarios where a car with a driver and a couple armed passengers is trying to escape a couple pursuing cars, each with a driver and armed passenger.<p>[1] Or maybe actually do the time penalties during the race. If the self driving system has to take over from you, it could slow you down for a bit before returning control to you.

Article mentions each tire gets 7,000Nm torque from its electric motor. Is that a typo?

This could be a pay-to-ride-for-thrill startup idea. What a ride!

Doesn&#x27;t this sort of movement cause a lot of wear on the tires, thus making it unsuitable for routine use?

they have gotten this car to do complex and exotic movements via automated manipulations of the car&#x27;s human-oriented interface, that is, a single steering wheel, four wheels that turn in the same direction, and then the brakes &#x2F; accelerator.<p>It seems though that if you are actually trying to design autonomous cars that feature greater maneuverability than what is normally possible you&#x27;d instead ditch the whole assumption of a single steering column and all of that and just consider all the wheels as independent, or maybe add more wheels that engage for some kinds of maneuvers, or probably a whole lot of other things that im sure all the car people here know are possible if you are no longer constrained to controls created for a single human with only four limbs and extremely limited coordination and reaction time.

<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;embed&#x2F;3x3SqeSdrAE?rel=0&amp;autoplay=1&amp;autohide=1" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;embed&#x2F;3x3SqeSdrAE?rel=0&amp;autoplay=1&amp;a...</a><p>Wish theme parks had rides like this.

That&#x27;s incredible footage just on its own :)

Imagine if the car could also do that in the air, where the &quot;ground&quot; is unstable and changes all the time, but autonomy system should still maintain narrow range glissade.<p>Wait, that&#x27;s called landing autopilot.

Can an autonomous car beat the best version of Frank Martin in The Transporter series, let alone any of the Fast &amp; Furious drivers?<p>Now we have the answer. It’s game over people! Even the fictional drivers in the movies have no chance against real world AI today.<p>This means in the future when an autonomous car or robot is chasing you — you may as well give up. You just better hope it doesn’t get cheap enough that someone can simply hire a swarm of robots or autonomous cars to kidnap people or incapacitate them or wreak havoc en masse (eg crashing into 10,000 gas stations at once).

&gt; <i>Besides, MARTY, the driver</i><p>:-D<p>Too many software engineers overlook the fantastic opportunity for cleverness when naming things. It&#x27;s one of the hardest problems in computer science, but one of the most rewarding.

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?

It sounded like it precomputed the route, steering, drift for the whole course first, then executed it.<p>If the friction were variable and unknown it would get completely lost.

&quot;This leads to the physically insightful result that one can use the rotation rate of the vehicle&#x27;s velocity vector to track the path, while simultaneously using the yaw acceleration to stabilize sideslip.&quot;<p>This sounds like what every racer will tell you: When the car is sliding, you control your direction with the throttle and control the angle of the slide with the steering.

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&#x27;t serious about Apple car yet?<p>Does this demo hide something that we should know?

I&#x27;m impressed by how well this complicated page renders without javascript.

Ken Block eat your heart out. He should trademark an enable Block mode.

I seem to recall a video Thrun&#x27;s&#x2F;Stanford&#x27;s DARPA car &quot;Junior&quot; drifting in a parking lot autonomously. Around 2007.<p>Cannot find the video, though.

Response is twofold: I think the cars maneuvering is impressive. How did they get enough power from a a DeLorean to drift? Hail to MrFusion!

Seems like a DeLorean isn&#x27;t necessarily that expensive, prices range from $20,000 to $45,000.

Next step: Controlled flip!

“It almost like as if we did some math for this.” lol, awesome.

Funny, I built a mechanical rig to do figure 8s years ago. It was some rope and a few pulleys, and caster adjustment on the car. This seems like using a laser to peel an apple for internet points.

Soon we will have autonomous f1.

So, in Back to the future : Tokyo drift, did MARTY met Sally when Flash tried to bring back Doc (Hudson)...

You’re telling me that not one Stanford engineering student could come up with a mock Flux Capacitor?!!

I want a longer version of the drifting with some classical music as a backdrop

Thunderhill sighting!

Where we&#x27;re going, we don&#x27;t need roads.

<p><pre><code> echo $NICK | s&#x2F;80mph&#x2F;88mph&#x2F;</code></pre>

I see James Bond plot twists in the future.

&quot;You built an AI... into a <i>DeLorean</i>?&quot;

I guess if you can afford a DeLorean you can afford to keep replacing the tires you burn up by drifting on pavement. I&#x27;d rather have my car programmed for long tire life and high mpg please.