Live data from Hacker News

The first person to hack the iPhone is building a self-driving car

bloomberg.com

151–160 of 462 posts

Re: The first person to hack the iPhone is building a self-driving car

#151

Earlier quoted context omitted.

The steering is massively torque limited by the car's EPS module(5x lower limit than Tesla). It can't turn hard right, it can lazily list to the right, giving you tons of time to react. I actually have put a lot of thought into safety :)

How do you train it for emergency situations (i.e. a car suddenly turning left in front of you)? I'd imagine it would be hard to get many of those in the training data set.

Easy, you drive in a simulator! (ie: backfeed/simulate LIDAR and camera data using a video game (GTA5 for example)). Then try to simulate lots of near-crashes, reactions to traffic lights, signs, etc. Hotz's code just reacts to inputs. Simulate the inputs and you can run any training case you want.

Re: The first person to hack the iPhone is building a self-driving car

#152

"His self-funded experiment could end with Hotz humbly going back to knock on Google’s door for a job." The biggest thing here IMO is this is self-funded. Any startup trying to do what he is doing in this environment would have raised $50 Million, hired 100's of engineers from top notch schools, become accepted in YC, and have Marc Andreessen, Paul Graham, Sam Altman and all singing their praises. Kudos to him for be…

While I understand where you're coming from, and even feel emotionally invested in the idea of bootstrapping, objectively speaking, it's a bad decision to stay self-funded. It is, after all, a business, and if you can accelerate your business' growth 100x by taking on some very smart outside investors and hire very smart people, why wouldn't you?

A typical woodhead's thought. "Accelerate your business's growth". Hahaha. Hard things have to be done solo because explaining to others is slowwwwwwww.

Re: The first person to hack the iPhone is building a self-driving car

#154
post #37

Prototypical case of the 80/20 rule. He has implemented the happy case. But that system is nothing people realistically would want to drive their cars. What he did is impressive. But the results are not that outlandish for a talented person. 1) Hook up a computer to the CAN-Bus network of the car [1] and attach a bunch of sensor peripherals. 2) Drive around for some time and record everything to disk. 3) Implement so…

>He has implemented the happy case.

I could probably do this using ROS, opencv, and pcl. At least on a level where the car could recognize the road well enough to drive on it, but I imagine both my car and his car are nothing that any sane human would want to sit in. That last 20% focusing on safety and edge cases is going to be 100x the work/innovation/testing/staff/code/talent/smarts here.

As a side note, I am intrigued by the idea of a FOSS self-driving car. Its a little worrysome we'll never see the code Tesla, Mercedes, etc are using.

Re: The first person to hack the iPhone is building a self-driving car

#155
post #69
post #4

> “I understand the state-of-the-art papers,” he says. “The math is simple. For the first time in my life, I’m like, ‘I know everything there is to know.’ ” Yep, he's still in his twenties.

I cringed. Saying "the math is simple" -- ouch. The writer must have been barely able to suppress his glee when that one popped out.

I don't doubt it at all. Keep in mind that "simple" is relative, we have to ask "simple compared to what?" For lots of people, I be that the math involved in these neural nets is the most complicated math they've ever done. They would never say it is simple, because they themselves barely grasp it. But in my experience, topics in mathematics have a funny way of becoming very simple the moment you "graduate" to thinking about a slightly more general mathematical framework.

Someone who has digested enough of the AI literature to think about the methods in aggregate is very likely to be in a position to see any particular method as a "simple" implementation of some more general set of principles.

Re: The first person to hack the iPhone is building a self-driving car

#156
post #21

Sorry, but how can this be legal? With his homemade solution, he is not only endangering himself but all the other people in the cars around him. Usually before you are allowed to use something like this on a public road your stuff has to be tested and approved by the state. At least this is how it is in Europe, does this not matter in the states?

Maybe this is another reason he isn't joining a corporate entity for his project. The insurance and legal liability will prevent him from testing and gathering "in-the-wild" data. Very risky and dangerous process that, i think in his mind will give him a faster improvement curve, compared to indoors and confined testing.

Re: The first person to hack the iPhone is building a self-driving car

#157

He thinks machines will take care of much of the work tied to producing food and other necessities. Humans will then be free to plug into their computers and get lost in virtual reality. Well, that's an astronomically depressing future.

Said a person who probably spends 10 hours a day staring at a computer

Re: The first person to hack the iPhone is building a self-driving car

#158
post #33

Earlier quoted context omitted.

Sure. But that belief is a genuine worry when you are talking about creating something that'll move a hulk of metal down a road at 70mph.

if we don't have laws currently, we sure as hell need them. i can't imagine letting everybody try their own self-driving software.

we already have enough laws. responsibility doesn't change because a computer does some thinking for you. Besides, how many people are actually writing their own self-driving software?

Re: The first person to hack the iPhone is building a self-driving car

#159
post #37

Prototypical case of the 80/20 rule. He has implemented the happy case. But that system is nothing people realistically would want to drive their cars. What he did is impressive. But the results are not that outlandish for a talented person. 1) Hook up a computer to the CAN-Bus network of the car [1] and attach a bunch of sensor peripherals. 2) Drive around for some time and record everything to disk. 3) Implement so…

Can you use the Canbus to actuate?
Post reply on HN