Autonomous DeLorean drives sideways to move forward • Hacker News Board

Re: Autonomous DeLorean drives sideways to move forward

#81

Post by elfexec » Sun, Dec 22, 2019, 11:42 AM UTC

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…

> They did most of that back in 2015.[1]

Just in time for the 30th anniversary of back to the future. Nice.

Re: Autonomous DeLorean drives sideways to move forward

#82

Post by mdiesel » Sun, Dec 22, 2019, 12:01 PM UTC

spockz wrote: post #51

Animats wrote: post #41

Earlier quoted context omitted.

One approach is that you have a semi-traditional control system, which has integrators, filters, adders, etc. All these components have tuning parameters, and tuning complex controllers is hard. But once you get them tuned, they behave in a reasonably predictable way. The machine learning part is used to get a predictor. You operate the thing and train a model of what will happen for various inputs. The machine learn…

So what is the difference of using this approach with exploring the set of inputs to find the optimal one using a search algorithm like A* or the many different ones? I’ve been struggling to find where machine learning starts and what is just good old statistics (used in data mining for ages) and search algorithms like A*.

They serve the same purpose (optimisation). The advantage of ML is that you don't need to be able to define an objective function instead you just have a data set.

Re: Autonomous DeLorean drives sideways to move forward

#83

Post by taneq » Sun, Dec 22, 2019, 12:01 PM UTC

wongarsu wrote: post #77

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?

"Alternate routes" are still normal roads people travel on. Since the travel time of a path is just the sum of the travel time of all path segments you only need people traveling every road to estimate the total time of any path. Path finding is well understood with many algorithmic solutions, so there is no reason to use machine learning. Google's implementation is impressive, but I see no reason why it would benefi…

It doesn't have to be doing gradient descent on a neural network to be machine learning. You could easily generate small perturbations to generated routes if they didn't add much time and took the driver down an under-monitored road.

Re: Autonomous DeLorean drives sideways to move forward

#84

Post by taneq » Sun, Dec 22, 2019, 12:04 PM UTC

"This leads to the physically insightful result that one can use the rotation rate of the vehicle's velocity vector to track the path, while simultaneously using the yaw acceleration to stabilize sideslip."

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.

Re: Autonomous DeLorean drives sideways to move forward

#85

Post by taneq » Sun, Dec 22, 2019, 12:06 PM UTC

sudhirj wrote: post #31

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 very human-centric system the tries to keep the car controllable under low traction, often by sacrificing something aspect of movement. The neural nets here throw all that out of the window, and control the car with direct physics, without being once or twice removed from reality. The video also has some very interesting points about how the AI should be able to control the acceleration and braking on each w…

This was what finally killed my long-held attitude of "we don't need no stinkin' ABS". No matter how good I am, I will never be able to independently limit-brake each wheel of my car.

Re: Autonomous DeLorean drives sideways to move forward

#86

Post by bborud » Sun, Dec 22, 2019, 12:09 PM UTC

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.

Well, a very key factor of steering is that it connects your fingers to the interface between tyres and road surface and imparts critical information about what’s going on there. If you decouple the steering completely from the mechanical bits you have to recreate that channel of information. Which isn’t necessarily easy to get right.

Even servo assisted steering systems can easily become a bit numb. If you have ever driven a tractor it is very different from a light sports car without power steering for instance.

Re: Autonomous DeLorean drives sideways to move forward

#87

Post by mootzville » Sun, Dec 22, 2019, 12:23 PM UTC

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

Re: Autonomous DeLorean drives sideways to move forward

#88

Post by bborud » Sun, Dec 22, 2019, 12:25 PM UTC

jamestimmins wrote: post #9

So is the general idea that by removing the automated controls, which normally limit drift so human drivers don't lose control, they're able to gather data at the extremes of car handling? I'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…

I drive a lot on slippery surfaces. My car has stability control from 7-8 years ago. I’m sure a lot has improved in that time, but it is very obvious that the stability control in my car is more about trying to “rescue” me than assist me. Meaning, it will interrupt normal flow to “correct” more than it will assist.

If you extend the envelope for what driving dynamics you can handle I would imagine you could make a much more smooth and safe experience.

That being said: I’ve driven somewhat newer cars on wet race tracks, at speed, and I have to say I’m a bit impressed with how well they behave under stress. Still meddlesome, but not as dangerous as they used to be.

(But track use in slippery conditions are outside the envelope for a road car, so you’re better off with the assists turned down or off to avoid surprises)

Re: Autonomous DeLorean drives sideways to move forward

#89

Post by psim1 » Sun, Dec 22, 2019, 12:27 PM UTC

fouc wrote: post #34

Seems like a DeLorean isn't necessarily that expensive, prices range from $20,000 to $45,000.

Are you telling me they built an automated drift car... out of a DeLorean?

The way I see it, if you’re going to build an automated drift car, why not do it with some style?

Re: Autonomous DeLorean drives sideways to move forward

#90

Post by bborud » Sun, Dec 22, 2019, 12:32 PM UTC

OnlineGladiator wrote: post #62

tempestn wrote: post #53

Earlier quoted context omitted.

Another exception of a sort, and I believe the one this research is meant to address, is when the drift is initiated unintentionally. Say you hit a patch of black ice mid-corner, for example. This kind of work can expand the envelop of the control system to encompass these scenarios.

I don't think this is true. If you hit black ice and the tire skids, the problem is you just have no friction. Modern traction control systems already account for this as best they can - I don't see how this model would help any more except for trying to go faster through patches of black ice. And even then, drifting inherently requires traction in order to modulate the throttle and control the vehicle. If you can't…

If you hit black ice you are screwed anyway. The most useful thing your car could do is to detect black ice before you hit it.

I’ve seen some technologies for doing just that. Black ice isn’t very easy to distinguish from other surface conditions cheaply, but the technology exists. (It just has to reach volume production).