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

Tesla Live Stream – Autonomy Day [video]

livestream.tesla.com

Post reply on HN
Print view View original

341–350 of 550 posts

Re: Tesla Live Stream – Autonomy Day [video]

#341

Post by justapassenger »

localhost wrote: post #192

At the tail end of Karpathy's presentation, he said something that reminded me of why Peter Norvig decided to join Google: because that's where the data is. In Tesla's case, they have a unique and likely accelerating advantage in having the best source of data up on which to train their models. I think this forms the basis of an enduring moat relative to their other competitors, none of which are collecting data at t…

Is Tesla collecting that data? I've looked at their earnings and didn't see any big expenses related to datacenters. Amount of data they would need to store and process is massive, that would for sure show up in earnings, as one of the biggest costs.

Re: Tesla Live Stream – Autonomy Day [video]

#342

Post by tomComb »

willio58 wrote: post #244
tomComb wrote: post #135

Earlier quoted context omitted.

I'm a fan of Tesla, but not Musk. You really can't believe much that comes out of his mouth. If you look at his past claims it becomes clear that he should just be ignored.

Being the fan of a company while completely ignoring the ceo of said company is questionable to me.

Tesla has great products, created and supported by thousands of people who appear to go above and beyond. Kudos to them. And kudos to Musk for the vision and the early execution, but that doesn't mean I have to like him or believe that he is the right person for this phase of the companies growth.

Re: Tesla Live Stream – Autonomy Day [video]

#343

Post by zaroth »

VikingCoder wrote: post #51

Q: "What's the primary design objective of the next-gen chip?" Mumbled Answer: "Safety." ...doesn't that mean the current-gen chip... isn't as safe as you want?

No, it just means the next-gen design had safety as a primary design objective. Secondary objectives could be additional modes of self driving like traffic light detection and managing intersections.

Volvo leadership states the exact same thing about their car designs. The primary motivation “in everything they do” is safety.

The statement can be made entirely distinct from the current safety level.

Re: Tesla Live Stream – Autonomy Day [video]

#344

Post by derpherp »

cromwellian wrote: post #275

Seems to me that relying too much on Machine Learning for this is actually the real risk, not LIDAR. Tesla's competitors are using ML, but combining it with sensor fused data from LIDAR, Radar, accurate maps, and visual data. In other words, they're starting from a view of the world with super-human sensing. Starting from a purely visual domain likely dooms your system to making the same types of mistakes that humans…

I agree with all your points. However, Musk did mention that his team at SpaceX built their own LIDAR for docking with ISS. I think Tesla can custom make their own LIDAR too.

And I would secretly look forward to. I was part of a self-driving team at university and we had to raise funds especially to be able to afford a Velodyne HDL-32.

Re: Tesla Live Stream – Autonomy Day [video]

#345

Post by reitzensteinm »

mlindner wrote: post #309
RivieraKid wrote: post #255

Earlier quoted context omitted.

It's so frustrating to see that people eat Elon's BS. Even after: - the Unsworth lie - the "zero concern and I mean zero about 10k Model 3s per week in Dec 2018" lie - the "funding secured" and "only uncertainty is shareholder approval" lies - the "short burn of the century" lies I mean, they were even wrong about Nvidia's chip today, Nvidia had to issue a statement: https://www.marketwatch.com/story/nvidia-says-tesl…

There was no "Unsworth lie". There was Elon saying some very unkind things after Unsworth personally attacked him. Neither thing is appropriate, but let's not pretend this wasn't a tit-for-tat.

When plotted on a logarithmic scale.

Re: Tesla Live Stream – Autonomy Day [video]

#346

Post by tomComb »

davej wrote: post #254
tomComb wrote: post #135

Earlier quoted context omitted.

I'm a fan of Tesla, but not Musk. You really can't believe much that comes out of his mouth. If you look at his past claims it becomes clear that he should just be ignored.

> If you look at his past claims it becomes clear that he should just be ignored. What's an example of this? His timelines are often much too aggressive for reality but he repeatedly delivers (eventually).

The main example, of course, is in self-driving where he has most certainly not delivered. And he wasn't just a little off.

But also his claims about being able to automate the manufacture of Model 3 turned out to be very wrong and to do terrific damage to the company - they are/were way ahead with their technology and should have taken a less risky approach to getting that tech onto the market and taking advantage of that lead. And how did he not learn from the model X experience?

Re: Tesla Live Stream – Autonomy Day [video]

#347

Post by ajross »

threeseed wrote: post #285
bogomipz wrote: post #265

Earlier quoted context omitted.

>"People drive vision only." Can you elaborate on what you mean here? Do you mean that Tesla will only be using Computer Vision for autonomy? Doesn't or wouldn't Lidar compliment CV? Or is there a practical design consideration that makes them mutual exclusive?

That people drive vision is so idiotic. Humans have far higher resolution sensors and the most advanced computer ever seen behind them. And even that fails at a far higher rate than we want self driving cars to be.

> Humans have far higher resolution sensors

This is really not true. The phone in your pocket is just plain better. More total pixels per unit area, much greater dynamic range, able to sample over time periods an order of magnitude faster.

The reason your vision seems better is because your brain is amazingly good at synthesizing a picture of the world around you. But all that data (the sphere around you is something like 150 MP at eye resolution) is an illusion. You're only looking at a million pixel(-equivalents) at once, thereabouts.

[1] Your eyes come close only in the middle half a degree of your fovea. Everywhere else your brain gets a blurry mess and has to extrapolate.

Re: Tesla Live Stream – Autonomy Day [video]

#348

Post by zaroth »

krzkaczor wrote: post #234
sairahul82 wrote: post #114

Karpathy's presentation is really good. Watch it later if you get some time. The key points are - Telsa is using fleet for learning (Fleet learning). This has 3 components, a. Trigger infrasture that collects the kind of data telsa is looking for training. The rational here is we don't need massive amounts of same kind of data but needs right kind of data for training neural networks correctly. b. Data Engine which l…

What I found interesting as well is that they (him and Elon) hated the idea of using high definition maps, saying that if you need them you don't do self-driving cars really. For example, when driving condition change (roadblock or anything) you're done.

That is very interesting. High definition maps perhaps not, but I do hope maps of some kind are an integral part of the logic.

For example on a country road near my house, the road veers left while a side street continues perfectly straight. The current auto-pilot has a very hard time staying on the main road and almost always disengages before putting enough left-steer to stay in lane.

A human who didn’t know about the road (no knowledge of the left bend ahead), and who missed the big yellow “left curved arrow” sign, would likewise probably end up going straight onto the side street.

This is a hierarchy of stateful awareness which I believe is essential for successful self-driving — the only way to increase NN weighting to the point where the car will convincingly execute the left bend to stay on the main road is some awareness that a left bend is upcoming. This is a case where you can’t drive the road by staring at the lines. And there are many, many others.

Re: Tesla Live Stream – Autonomy Day [video]

#349

Post by 6d6b73 »

Animats wrote: post #35

So far, half an hour from the head of IC design. Nice special purpose IC and board. Dual everything for redundancy. Wide special purpose neural net evaluation. 100 watts for the compute system. Code signing. Shipping in new Model 3 cars since last 10 days. "All we need to do is improve the software" - Musk [12:07 PDT] LIDAR "unnecessary" - Musk [12:13 PDT] Computer vision guy is now speaking. Recognizes "driveable sp…

Having two GPUs on one board is not redundancy.

Re: Tesla Live Stream – Autonomy Day [video]

#350

Post by asteli »

ubercow13 wrote: post #96
vasilipupkin wrote: post #86

Earlier quoted context omitted.

it snowed a few weekends ago in Chicago, my autopilot turned off because snow covered up the cameras. So I am not buying all this "self driving with no lidar" brouhaha

Can snow cover lidars?

Depends on the unit. On some designs (e.g. Velodyne HDL-64) the unit is split into two sections. The whole upper section, along with all the optics and some of the electronics, spins at 10-15 Hz, which naturally tends to shed precipitation and other crud.

Sensors with non-moving optical windows can use other strategies, such as air knives or wipers.

Post reply on HN