News for hackers. Stuff that matters.
Re:Openpilot – Operating system for robotics by bks on Friday September 20, 2024 @07:09AM (#41600792)
I chose the Hyundai Ioniq 5 as my current car specifically because it’s compatible with OpenPilot. It’s been a total game-changer for my driving experience. Just like their tagline says, “make driving chill,” and for me, it truly delivers on that promise.
Re:Openpilot – Operating system for robotics by zrt1019 on Friday September 20, 2024 @07:23AM (#41600867)
I'm confused:

"THIS IS ALPHA QUALITY SOFTWARE FOR RESEARCH PURPOSES ONLY. THIS IS NOT A PRODUCT. YOU ARE RESPONSIBLE FOR COMPLYING WITH LOCAL LAWS AND REGULATIONS. NO WARRANTY EXPRESSED OR IMPLIED."

Where can this be used? In a private parking lot?

Re:Openpilot – Operating system for robotics by SkyPuncher on Friday September 20, 2024 @08:19AM (#41601262)
They’re just trying to scare away people who thing they can chuck this on their car and suddenly have a self-driving robot that they don’t have to pay attention to.
Re:Openpilot – Operating system for robotics by rogerrogerr on Friday September 20, 2024 @07:29AM (#41600912)
The driver takes liability, of course, and this can be used wherever the driver deems it safe and useful.
Re:Openpilot – Operating system for robotics by diggan on Friday September 20, 2024 @08:42AM (#41601437)
> this can be used wherever the driver deems it safe and useful

With the disclaimer that this depends on the location of course. For example, I think in Spain (and probably EU wide?) modifications that affect steering and throttle control would need to undergo local homologation before you're legally allowed to drive with that on public roads at all.

Which, to be honest, makes a lot of sense. I don't think anyone would be happy if cars start using software MVPs automatically controlling throttle and steering while in real traffic.

Re:Openpilot – Operating system for robotics by edude03 on Friday September 20, 2024 @01:19PM (#41603926)
I mean let’s be frank here. The sort of people who are enthusiastic about this also aren’t going to be stopped by the law especially with the low risk of getting caught.
Re:Openpilot – Operating system for robotics by targetx on Friday September 20, 2024 @03:09PM (#41604760)
While the chances of getting caught are low, I wouldn't want to risk this for insurance. If you are involved in a crash for any reason I don't think they are going to cover it if you modified this stuff on purpose.
Re:Openpilot – Operating system for robotics by diggan on Friday September 20, 2024 @02:24PM (#41604361)
If I were to personally install this and use it anyways, my biggest worry would be the additional punishment if I cause an accident. Not sure exactly what the punishment is for driving a vehicle you know isn't road worthy, but I bet it aint pretty.
Re:Openpilot – Operating system for robotics by moffkalast on Friday September 20, 2024 @01:05PM (#41603808)
Aka, this will drive your car into a ditch and it will be your fault.
Re:Openpilot – Operating system for robotics by rogerrogerr on Friday September 20, 2024 @01:57PM (#41604202)
It really bothers me when people make statements like this. I propose a bet:

If you’re so confident this will drive my car into a ditch, then front the money for me to buy a compatible car & this kit. If it drives my car into a ditch, I’ll pay you back double that money.

That’s an easy bet for you, right?

Re:Openpilot – Operating system for robotics by moffkalast on Friday September 20, 2024 @02:34PM (#41604426)
If a piece of software that has the capacity to kill people is provided without any kind of assurances or warranty with the sole responsibility placed solely on the user, then that already tells me all I need to know, no bet needed to settle it.

Would you buy an angle grinder that's specifically been designed to not have a guard so it can be more useful, made by random contributors on the internet without any official certification? I'll stick with the ones that needed to pass the CE mark and you can sue the company responsible if it chops your arm off thank you very much. They at least have a required level of anxiety needed to patch anything serious knowing the level of responsibility they carry and what's coming if they mess up.

Re:Openpilot – Operating system for robotics by xipix on Saturday September 21, 2024 @03:00AM (#41608063)
Two thoughts.

Suppose I deem it safe and useful for my 6yo to drive for a while, using his Xbox controller from the passenger seat.

It is illegal in many countries for a device (or anything else) to obscure any part of the driver's forward view (area swept by wipers). So even without actually controlling the car, we have an unlawful vehicle.

Re:Openpilot – Operating system for robotics by torlok on Friday September 20, 2024 @09:23AM (#41601773)
You pay a thousand bones for a device you have to babysit. What's confusing about that?
Re:Openpilot – Operating system for robotics by thatgerhard on Friday September 20, 2024 @07:35AM (#41600946)
Is it like an app you install on the car or is it a custom integration?
Re:Openpilot – Operating system for robotics by rvnx on Friday September 20, 2024 @07:36AM (#41600957)
It's a dashcam that you put on the windshield with 2 cameras pointing forward and one inward (filming the driver).

It has no blind spot view, so if someone comes on your side, it's your luck.

Re:Openpilot – Operating system for robotics by ozzyphantom on Friday September 20, 2024 @07:43AM (#41601022)
It’s my understanding that in addition to the cameras it also uses the sensors already built in to the car which would include blind-spot detection, no?
Re:Openpilot – Operating system for robotics by diggan on Friday September 20, 2024 @08:44AM (#41601449)
It says my car is supported and my car doesn't have any blind-spot detection, nor does the requirements list that as needed, so maybe it's optional but not required?
Re:Openpilot – Operating system for robotics by ranon on Friday September 20, 2024 @08:48PM (#41606657)
Some cars that have BSD it will work with. My car uses it, but don't forget the lane changes are not automated by default. A user must turn on the blinker and nudge the wheel by default. Positive BSD sensors read on CAN-BUS will be read by OP and it will not perform the rest of the lane change. This is how it works on my car (albeit, I don't run default so I just need the blinker).
Re:Openpilot – Operating system for robotics by falcor84 on Friday September 20, 2024 @07:59AM (#41601130)
What is filming the driver used for? Can you disable that?
Re:Openpilot – Operating system for robotics by world2vec on Friday September 20, 2024 @08:50AM (#41601489)
To ensure the driver has eyes on the road all time. It detects if you're not paying attention and beeps at you. I don't think it can be disabled.
Re:Openpilot – Operating system for robotics by falcor84 on Friday September 20, 2024 @09:44AM (#41601973)
Ah, thanks, I just found more detail here - https://github.com/commaai/openpilot/blob/master/docs%2FSAFE...

They say it's required for ISO compliance with Level 2 autonomous driving

Re:Openpilot – Operating system for robotics by sofixa on Friday September 20, 2024 @08:42AM (#41601434)
This reminds me of Waymo's approach to self-driving cars. Paraphrasing, but basically they found that progressively adding self-driving to help human drivers is bad, because it leads to the humans becoming complacent and not paying enough attention. Therefore they decided on an all or nothing approach, where their cars would be only and entirely self-driven.
Re:Openpilot – Operating system for robotics by typewithrhythm on Friday September 20, 2024 @09:14AM (#41601692)
This always seemed like a bit of bull from waymo. It's not an easy problem to work with existing manufacturers to give a better and or cheaper solution... Especially when there are established competitors with efficient verification and validation processes (that every manufacturer requires).

They decided it wasn't worth explaining that their techniques don't generalise to a driver assist. It would not be good or cheap enough to be worth developing the compliance and integration frameworks.

Re:Openpilot – Operating system for robotics by jowday on Friday September 20, 2024 @09:33AM (#41601870)
The first thing Waymo tried building (way back when, circa 2010 or so) was highway based driver assist in the style of Autopilot. They did a ton of testing with it and didn’t like how quickly their testers stopped paying attention despite a ton of instruction not to. I’ve seen clips from these tests.

It’s also possible they shifted direction because the long term vision of robotaxis is much more lucrative.

Re:Openpilot – Operating system for robotics by warble on Friday September 20, 2024 @10:42AM (#41602484)
Maybe I'm being ignorant about something here but isn't paying less attention the whole point?
Re:Openpilot – Operating system for robotics by sofixa on Friday September 20, 2024 @11:59AM (#41603230)
Unless you assume that self-driving software is perfect, no, it really isn't. That's the whole problem - the drivers would get complacent, so when there's an issue, they'd be caught by surprise and wouldn't be able to react.
Re:Openpilot – Operating system for robotics by mook on Friday September 20, 2024 @11:26AM (#41602891)
Isn't the point to pay _no_ attention? The difference is when an accident occurs, was the person in the car at fault for not vigilantly watching everything.
Re:Openpilot – Operating system for robotics by Veserv on Friday September 20, 2024 @02:04PM (#41604237)
You can already do that by just closing your eyes and letting Jesus take the wheel. No, the point is doing so while maintaining safety.

It is materially less safe to operate a ADAS while distracted than driving manually. Humans are exceptionally good drivers on average, only encountering minor crashes on timeframes measured in years to decades. As such, if safety critical ADAS errors occur more frequently than every ~100,000 miles and you are attentive in less than 100% of all such occurrences, you are operating your vehicle multiple times more dangerously than the average driver (which is a number that includes drunks and distracted drivers).

That is why it is critical to deliberately downplay the capabilities, to avoid wishful over-reliance, and enforce strict driver awareness (through techniques such as driver monitoring) to avoid operating multi-ton killing machines in ways that are multiple times more dangerous to the occupants, other drivers, and pedestrians. Without that, people are prone to over-generalization of safety capabilities, extrapolating that a single success means robust, continued success thousands to tens of thousands of times in a row.

Re:Openpilot – Operating system for robotics by renewiltord on Friday September 20, 2024 @03:05PM (#41604727)
You want the curve of total attention to be always above a baseline human in an unassisted car. The car can do some attention and the human can do some. But if the sum of the two falls below the threshold, you’re in trouble.
Re:Openpilot – Operating system for robotics by typewithrhythm on Saturday September 21, 2024 @08:54AM (#41609658)
The thing is, you can tune driver assist to whatever form you like; but then you have a true comparison of function with established competitors.

I just don't believe the approaches for high autonomy (especially at the time) actually could make a cost effective assist system.

And for whatever reason they decided to push the we didn't like the driver behaviour message, rather than actually talking about what was actually plausible to achieve in the driver assist space.

Re:Openpilot – Operating system for robotics by simondotau on Friday September 20, 2024 @09:58PM (#41606895)
That statement from Waymo always struck me as deeply uninsightful because it was really just a more complicated way of saying “self driving systems need to be good enough to drive the car on their own” which isn’t just obvious, but tautological.