31–40 of 462 posts
So how does his technology/software react on dangers? The video only shows how he keeps his lane...
>The smartest people I knew were in high school, and I was so let down by the people in college. He seems like a good person to get into business with. He's so non-judgmental. Reminds me of myself and all the stupid things I said to VCs in my 20s.
> “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.
But that belief is enough to attempt something that more experienced people would hesitate to start. Naivety is a very good thing at times. I've seen average people achieve incredible things, and not because what they did was incredible... but just because they started work on things that no-one else thought they could complete. Some way into it, when enough progress has been made, people have rushed to give support…
> “Frankly, I think you should just work at Tesla,” Musk wrote to Hotz in an e-mail. “I’m happy to work out a multimillion-dollar bonus with a longer time horizon that pays out as soon as we discontinue Mobileye.” > “I appreciate the offer,” Hotz replied, “but like I’ve said, I’m not looking for a job. I’ll ping you when I crush Mobileye.” > Musk simply answered, “OK.” I have to agree with Elon here, Hotz is such a g…
Earlier quoted context omitted.
There are laws[1] allowing public road testing of such cars in a few US states and EU countries. [1] https://en.wikipedia.org/wiki/Autonomous_car#Legislation
I doubt this is meant for single individuals instead of a company. I also doubt it is allowed without prior notice.
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 some of the recent ideas from deep reinforcement learing [2,3]. For training, feed the system with the oberservations from test drives and reward actions that mimick the reactions of actual drivers.
In 2k lines of code he probably does not have a car model that can be used for path planning [4] (with tire slippage, etc.). So his system will make errors in emergency situations. Especially since the neural net has never experienced most emergencies and could not learn the appropriate reactions.
And guess what, emergency situations are the hard part. Driving on a freeway with visible lane markings is easy. German research projects autonomously drove on the Autobahn since the 80s [5]. Neural networks were used for the task since about the same time [6].
[1] http://www.instructables.com/id/Hack-your-vehicle-CAN-BUS-wi...
[2] http://arxiv.org/abs/1509.02971
[3] http://arxiv.org/abs/1504.00702
[4] http://www.rem2030.de/rem2030-wAssets/docs/downloads/07_Konf...
[5] https://en.wikipedia.org/wiki/Eureka_Prometheus_Project
[6] http://repository.cmu.edu/cgi/viewcontent.cgi?article=2874&c...
> “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 also realize this kid probably won't end up making a huge dent in the universe.... but.... statistically speaking, there should be several "Leonardo da Vinci"- level humans alive right now. Why not this kid?
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…