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

Text Messages Between Travis Kalanick and Anthony Levandowski

spectrum.ieee.org

Post reply on HN
Print view View original

81–90 of 124 posts

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#81

Post by erikpukinskis »

ariwilson wrote: post #61
tim333 wrote: post #47

Earlier quoted context omitted.

Incidentally, Musk's take: "The whole road system is meant to be navigated with passive optical or cameras and so once you solve camera vision then autonomy is solved if you don't solve vision it's not solved so that that's why our focus is so heavily on having a vision neural net that's very effective for road conditions." https://www.youtube.com/watch?v=gv7qL1mcxcw&feature=youtu.be...

Why would you want to limit yourself to passive cameras and make your life harder? This is like limiting yourself to flapping bird wings to make airplanes.

No, it's like limiting yourself to using skis to move down a ski slope. He's right: the roads are design to be navigated using vision. Signage, regulations, paint, curbs, etc. There's no proof that you could safely navigate the roads with LIDAR, but we prove every time we drive that you can do it with vision.

And sure, there might be a better way to get down a ski slope, but skis would be a pretty good starting point. And they guarantee you don't end up in an impossible situation because you're doing things a fundamentally different way than the system expects.

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#82

Post by paul6987 »

furioussloth wrote: post #41
paul6987 wrote: post #35

Earlier quoted context omitted.

Don't forget illegally running autonomous tractor trailers in Palo Alto and on the roads of Nevada. These guys are criminals... total disregard for human life (but their own) in every shape and way there is. From potentially killing people, too treating everyone is who not their BRO like trash; drivers, employees, customers, business partners, etc, etc, etc... GROSS!

Your comments come off as if you are more bitter about some company you can just choose to ignore than benchamark is about Travis.

I am very bitter after Uber pretty much laughed at my Uber account being hacked and thus $1k stolen from me. These hacks were happening about a dozen or more a day for months and years and did they respond properly by alerting users that they should change their password? No, their PR blamed it on the users saying those getting hacked should have used a stronger password or something to that extent.

Further, thousand of us aspire to reach Kalanick's heights and to see all lack of graciousness and humility for his position is disgusting! His persona is one of a greedy BRO who thinks he's king one who needs to be kicked off his horse and learn humility! Thankfully it looks like this is slowly happening!!!

Give it up Travis and save Uber or continue being your greedy BRO king self and in turn burn Uber to the ground.

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#83

Post by swang »

furioussloth wrote: post #40
swang wrote: post #34

> A source close to Uber’s operations says its engineers watched the intersection where Uber’s cars were said to have run the red light, and that this text refers to them recording a number of normal, human-operated vehicles also breaking the law. Uber has never officially admitted that its software was to blame. is the implication here that that intersection has a lot of red light runners? if so, are they so dense i…

weren't they suspended? Also i doubt they coded it in their software to break the signal , can't believe you just implied that. It surely was a bug in software and I hope they got fined for it and took steps to fix it. Testing self-driving cars is not trivial, pretty much everyone who is testing them have screwed up here and there. That's the reason the person behind the wheel should be vigilant.

i'm not sure why you reached that conclusion but i didn't say they coded anything into their software.

also they weren't suspended insomuch as the vehicle registration of the cars they were using were revoked. at that point i'm assuming at that point uber stopped messing around with the ca dmv.

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#84

Post by ramdomize »

studentrob wrote: post #79
ramdomize wrote: post #68

Earlier quoted context omitted.

Part of the fix was to use radar: https://www.tesla.com/blog/upgrading-autopilot-seeing-world-...

Oh interesting. That's a pretty detailed report. One thing jumps out at me, > This is where fleet learning comes in handy. Initially, the vehicle fleet will take no action except to note the position of road signs, bridges and other stationary objects, mapping the world according to radar. The car computer will then silently compare when it would have braked to the driver action and upload that to the Tesla database.…

> Relying on whitelists seems like a hack. Then again, I'm not building it =)

Agree that it feels hacky at first, but once the whitelist dataset gets huge, it becomes unique training data for Tesla (and hopefully their machine learning will be able to generalize from it).

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#85

Post by canoebuilder »

tim333 wrote: post #47
sanguy wrote: post #24

Earlier quoted context omitted.

Multiple images can be used to compute a 3D point cloud. This is computer vision stuff around for many years. The challenge is this is a passive sensor in that the cameras count on light illuminating the scene. So at night; in bright light (that causes images to blow out); shadows; etc; you can have voids. If a person is in that void bad things can happen. But cameras now cost under a $1 each in volume (thanks smartp…

Incidentally, Musk's take: "The whole road system is meant to be navigated with passive optical or cameras and so once you solve camera vision then autonomy is solved if you don't solve vision it's not solved so that that's why our focus is so heavily on having a vision neural net that's very effective for road conditions." https://www.youtube.com/watch?v=gv7qL1mcxcw&feature=youtu.be...

So just from reading the pulled quote, is he saying current road users, i.e. humans, navigate using a passive optical system, i.e. our eyes take in photons, they don't emit lasers, but our eyes are also components of a general intelligence, does "solving vision" entail development of a general intelligence?

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#86

Post by overcast »

josh2600 wrote: post #45
Afforess wrote: post #42

Earlier quoted context omitted.

Normal humans also run red lights when the yellow-to-red light time is too short. Transit guidelines generally state that yellow lights should stay lit 1 second for every 10mph of the speed limit. When the yellow light is shorter than this, it's easy to get caught in the middle of a red.

Have you seen the video? It's way more jacked up than what you're implying: https://m.youtube.com/watch?v=pzzQ42D9Srw Watch that and tell me that it's reasonable or caused by a short yellow...

Honestly I thought it was the vehicle just before it, until that one came out of nowhere on the right. That was WAAAAAY after. I nearly closed the browser tab before it came through.

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#87

Post by boomboomsubban »

aeontech wrote: post #77
boomboomsubban wrote: post #58

Earlier quoted context omitted.

>If the intersection is poorly designed/timed, why would it be implausible to happen to catch human drivers make the same mistake? Unless they had already pulled the self driving cars, which the timeline presented suggests they haven't, why would that data be important enough to text back without the corresponding number of Uber violations?

I'm saying there's not enough context in the released messages to declare this unambiguously bullshit, and provided a reason why they would record the intersection, as parent comment asked "why in the world would they be taping it". The number of Uber's violations could have been communicated previously, or could have been implicit in the context of the conversation (at least 1 violation, causing the investigation) -…

>The number of Uber's violations could have been communicated previously, or could have been implicit in the context of the conversation (at least 1 violation, causing the investigation) - either of these 3 explanations seems equally likely.

The implicit one doesn't make sence, if an event caused the investigation surely how well Uber did would be the primary focus. Which leaves he knew already, meaning they already had a meeting or something to discuss the results and they were significant enough that he wanted a comparison.

>Uber's management and engineers may be irresponsible, but I don't think they're that evil, and I would hope no self-respecting engineer or human being would go along with that. "Oh, that's funny, let's try that again" works for software development, it's emphatically not how real world testing involving danger to life and limb works.

This was their illegal self driving car test on the streets of San Fransisco. They were unwilling to follow the legal safety rules, and unwilling to provide the deposit in the event they did cause someone serious harm. That they left on the road while they tested if the light was to blame.

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#88

Post by studentrob »

ramdomize wrote: post #84
studentrob wrote: post #79

Earlier quoted context omitted.

Oh interesting. That's a pretty detailed report. One thing jumps out at me, > This is where fleet learning comes in handy. Initially, the vehicle fleet will take no action except to note the position of road signs, bridges and other stationary objects, mapping the world according to radar. The car computer will then silently compare when it would have braked to the driver action and upload that to the Tesla database.…

> Relying on whitelists seems like a hack. Then again, I'm not building it =) Agree that it feels hacky at first, but once the whitelist dataset gets huge, it becomes unique training data for Tesla (and hopefully their machine learning will be able to generalize from it).

> Agree that it feels hacky at first, but once the whitelist dataset gets huge, it becomes unique training data for Tesla (and hopefully their machine learning will be able to generalize from it).

I guess. But then you still have to deal with rollout in other countries. And maintenance of sign locations which can change over time, get removed, etc. Still hacky IMHO.

How would machine learning make use of white-listed data? I doubt they could use that data to predict the GPS location of unknown signs.

If you mean image recognition, I assume if machine learning could properly identify the signs with accuracy, then they wouldn't need the whitelist. Then again, maybe they truly haven't collected a full overhead-sign dataset yet. I'd be shocked though if they don't by now. Anyway, you could be right. It would be fun to learn more about these setups.

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#89

Post by yorwba »

jfim wrote: post #70
sanguy wrote: post #24

Earlier quoted context omitted.

Multiple images can be used to compute a 3D point cloud. This is computer vision stuff around for many years. The challenge is this is a passive sensor in that the cameras count on light illuminating the scene. So at night; in bright light (that causes images to blow out); shadows; etc; you can have voids. If a person is in that void bad things can happen. But cameras now cost under a $1 each in volume (thanks smartp…

> Multiple images can be used to compute a 3D point cloud. [...] Add a GPU enabled system to process (it's quite compute heavy) and you are set. It requires enough information ("features") in the images to compute a stereo pair. Flat patches of color have no features and as such, cannot be correlated between cameras. In such a case, you have a spot with no depth information. This is exactly why you want to have other…

> Flat patches of color have no features and as such, cannot be correlated between cameras.

Flat patches of color are also flat, which makes it possible to fill in the missing depth information.

I took a course in computer vision where one of the projects [1] involved monocular vision, and assuming that flat patches are flat, vertical lines are vertical, all others are horizontal and the background is flat, it was possible to get a pretty good reconstruction.

[1] http://groups.csail.mit.edu/vision/courses/6.869/notes/chapt...

Re: Text Messages Between Travis Kalanick and Anthony Levandowski

#90

Post by stickfigure »

swang wrote: post #34

> A source close to Uber’s operations says its engineers watched the intersection where Uber’s cars were said to have run the red light, and that this text refers to them recording a number of normal, human-operated vehicles also breaking the law. Uber has never officially admitted that its software was to blame. is the implication here that that intersection has a lot of red light runners? if so, are they so dense i…

This is a cartoonishly uncharitable interpretation of "Quick update on that special intersection in SF, we taped 6 red car violations within 2 hours".

A more reasonable interpretation is: A techie pointing out that this is a really confusing intersection, and trying to ease his boss' concerns that the software isn't going to work. Surprise surprise, people have trouble with it too.

Post reply on HN