Autopilot: an open source driving agent

Post by oh_sigh » Thu, Dec 01, 2016, 4:55 AM UTC

skuhn wrote: post #28

jws wrote: post #23

Earlier quoted context omitted.

Not to nitpick your dilemma, there will always be a dilemma, but at any speed where children in the road are likely ( (Ok, I used a "head on collision" number because I couldn't find a wall number, but the physics are probably pretty close. Numbers from a New Zealand Ministry of Transport PDF from 2012: http://www.transport.govt.nz/assets/Import/Documents/_versio... )

What if behind that wall are a ton more babies? Now we'll have to put x-ray machines in self-driving cars too.

Post by JoshTriplett » Thu, Dec 01, 2016, 5:27 AM UTC

MichaelBurge wrote: post #85

ryaneager wrote: post #10

Earlier quoted context omitted.

Why wouldn't you do the research on a platform that could actually be deployed? Build the core using the proper tools and techniques. Any bug in a system like this could be life threatening at worst. Wouldn't you want to use the research phase to help eliminate such bugs? Unless you're not planning on ever releasing then a platform like this makes sense for strictly research, but Comma AI did plan on releasing their…

As an example of some requirements, any recursion is banned unless accompanied by a termination proof that keeps track of stack size. No calls to malloc() or free() are allowed, and so any library you might use that allocates memory is banned. It's far easier to get the code working in something like Python, and then rewrite it in safety-critical C later. And the kinds of people who can write self-driving cars in Pyt…

Post by tptacek » Thu, Dec 01, 2016, 6:10 AM UTC

KKKKkkkk1 wrote: post #88

Matthias247 wrote: post #7

Really, a safety critical hard realtime system with control loops on top of Python, a general purpose OS and a CAN-USB adapter? There are reasons why we have realtime operating systems, deterministic bus systems and dedicated CPUs for these kinds of applications. That might be an interesting research, prototyping or simulation platform. But nothing you want to have on a real public road.

Human drivers don't run an RTOS and a deterministic bus system either. In fact, I would argue that very rarely do human drivers fail because of jitter or nondeterminism.

Post by Animats » Thu, Dec 01, 2016, 6:33 AM UTC

ma2rten wrote: post #92

Matthias247 wrote: post #7

Really, a safety critical hard realtime system with control loops on top of Python, a general purpose OS and a CAN-USB adapter? There are reasons why we have realtime operating systems, deterministic bus systems and dedicated CPUs for these kinds of applications. That might be an interesting research, prototyping or simulation platform. But nothing you want to have on a real public road.

The Python control loop is probably the safest part of this system. The reason that comma.ai was able to get a working prototype quickly (unlike much bigger and well-funded companies) is that they use an end-to-end deep learning model. The model directly learns to issue commands to the car based on raw image data. The problem with this approach is that neural network models are a blackbox. They can behave in complete…

Post by nightski » Thu, Dec 01, 2016, 6:56 AM UTC

throwaway729 wrote: post #32

hasbroslasher wrote: post #27

Earlier quoted context omitted.

I'm not really following. If it works then why not use a control loop on top of Python? We are engineers, after all.

Because by "works" you mean "I tried it out a bunch of times and nothing bad happened, so must be production ready", because that's what you do when you build websites and desktop CRUD apps and nobody ever died cause the web server choked under load or the web page rendered a bit funny or the request took a full quarter second because the GC kicked off as a wave of requests came in. And then one day a one-in-ten-mill…