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

Rivian's gambit for full autonomy

spectrum.ieee.org

Post reply on HN
Print view View original

71–80 of 126 posts

Re: Rivian's gambit for full autonomy

#71

Post by LoganDark »

k310 wrote: post #2

Dear humans at Rivian. If your vehicle didn't look like a cartoon, I might consider one. It's not conformity, or even ego. It's the same reason I don't wear a clown outfit in public. I don't own a lot of things, but they all look nice. Until then, I enjoy the tech story.

Google Maps, the lack of CarPlay, and the lack of amber turn signals turned me away from Rivian but otherwise I would love them. I particularly like how their brake pedals feel, although I'm not a fan of the accelerator being so far off the floor.

Re: Rivian's gambit for full autonomy

#72

Post by MisterKent »

ShinyLeftPad wrote: post #69
jayd16 wrote: post #68

Earlier quoted context omitted.

They're talking about verification. Was there a collision or not compared to is this story good.

I can think of scenarios that avoid collision in probably 95% of the cases while being bad choices - Driving through an empty prairie - Driving slowly through a crowded square, giving people enough time to jump out of the way

There's less gray area with driving wss the point. Legal or illegal, efficient or inefficient. And whatever gray area remains is generally "good enough" compared to human drivers on the road.

Re: Rivian's gambit for full autonomy

#73

Post by digitalPhonix »

margalabargala wrote: post #65
tescreal wrote: post #47

I see a lot of Self-driving cars hitting people vs. reckless drivers hitting people. What I want is simple: accountability. If a human hits a human, we throw the book at them in the case of a modality of negligence. If a robot screws up, how do we remedy and discourage?

Hold the manufacturer equally liable. Easy.

The shenanigans AI companies have been up to recently (including boasting about criminal behaviour hacking other companies) without repercussions is pretty good proof that it isn't "easy".

Re: Rivian's gambit for full autonomy

#74

Post by ShinyLeftPad »

MisterKent wrote: post #72
ShinyLeftPad wrote: post #69

Earlier quoted context omitted.

I can think of scenarios that avoid collision in probably 95% of the cases while being bad choices - Driving through an empty prairie - Driving slowly through a crowded square, giving people enough time to jump out of the way

There's less gray area with driving wss the point. Legal or illegal, efficient or inefficient. And whatever gray area remains is generally "good enough" compared to human drivers on the road.

It's easy evaluate if there's no victims. Stats say there's more than 6000 injuries per day and more than 16000 deaths per year on the road.

If you choose between hitting a pedestrian and swerving potentially injuring the driver and totaling the car, what would you like the car to pick? Or any given trolley problem variation, etc

Re: Rivian's gambit for full autonomy

#75

Post by SecretDreams »

GoToRO wrote: post #42

"You are right, that was a red light!" At first I was skeptical, but reading the article, they do track object across video frames which for me it's the minimum a system like this should do. All previous FSD systems are just Fake self-driving. "That proprietary AI driver identifies features in images and point clouds, groups them into objects, and tracks them across frames, time-stamped to the millisecond to account…

> slamming the brakes due to a camera blip on a single frame

Ironically, I'm sure most humans have done the eyeball equivalent a handful of times, despite our knowledge of object permeance.

Re: Rivian's gambit for full autonomy

#76

Post by Onavo »

GoToRO wrote: post #42

"You are right, that was a red light!" At first I was skeptical, but reading the article, they do track object across video frames which for me it's the minimum a system like this should do. All previous FSD systems are just Fake self-driving. "That proprietary AI driver identifies features in images and point clouds, groups them into objects, and tracks them across frames, time-stamped to the millisecond to account…

> The AI thus builds confidence over time, acting on object detections that persist across several frames, rather than, say, slamming the brakes due to a camera blip on a single frame.

Nice in theory but in practice they still need a ton of training data. The bitter lesson is very bitter. Tesla's end to end FSD uses occupancy networks and brake stabbing still hasn't been fully solved.

Re: Rivian's gambit for full autonomy

#77

Post by sbstp »

jdross wrote: post #62
SoftTalker wrote: post #4

> Rivian says it will charge $49.99 a month, or $2,500 up front, versus Tesla’s $99 per month for its rival system, which is somewhat misleadingly called Full Self-Driving (Supervised), or FSD. Mercedes, meanwhile, plans to charge $3,950 for a three-year subscription for the forthcoming MB.Drive Assist Pro If and when FSD systems become a reality and are safer than human drivers, I would expect that regulators will r…

My 2025 model 3 has driven me over 95% of my last thousand miles. I'm frankly surprised it isn't more, but I'm not the only driver of the car. It's very obvious to me that FSD is a reality already, usually from parking spot to parking spot. And it at least feels much safer than I am driving, especially since I can get tired, etc

Out of curiosity, do you live in a place that gets heavy snow? I've always felt that FSD would struggle to handle heavy snow fall, roads with snow banks on the sides and difficult driving/braking conditions in the snow and on ice patches.

Re: Rivian's gambit for full autonomy

#78

Post by qwerpy »

Rohansi wrote: post #70
jdross wrote: post #62

Earlier quoted context omitted.

My 2025 model 3 has driven me over 95% of my last thousand miles. I'm frankly surprised it isn't more, but I'm not the only driver of the car. It's very obvious to me that FSD is a reality already, usually from parking spot to parking spot. And it at least feels much safer than I am driving, especially since I can get tired, etc

For any doubters: using a 2025 model is a key detail here. It's the latest hardware version of the self driving computer. The older cars on the road are stuck with significantly worse FSD software because the hardware is far too weak.

FSD 14 lite, which is now available for the HW3 (~2019-2023) Teslas, is surprisingly good. I have a HW3 and HW4, and while HW3 isn't as confident and competent as HW4, it's good enough that I don't mind it anymore. My wife was planning on trading in the HW3 for a new Model Y next year, and now she might just wait a few more years.

Re: Rivian's gambit for full autonomy

#79

Post by GMoromisato »

Rohansi wrote: post #70
jdross wrote: post #62

Earlier quoted context omitted.

My 2025 model 3 has driven me over 95% of my last thousand miles. I'm frankly surprised it isn't more, but I'm not the only driver of the car. It's very obvious to me that FSD is a reality already, usually from parking spot to parking spot. And it at least feels much safer than I am driving, especially since I can get tired, etc

For any doubters: using a 2025 model is a key detail here. It's the latest hardware version of the self driving computer. The older cars on the road are stuck with significantly worse FSD software because the hardware is far too weak.

I have a 2020 M3 on HW3 with v14 lite and it's very good. But even v12 was pretty good. I drove an HW4 as a loaner and did not notice a significant difference. I think the big difference would be on the long-tail of edge conditions, but I'm not sure.

Re: Rivian's gambit for full autonomy

#80

Post by GMoromisato »

I think this article is underestimating Tesla and very much underestimating how hard Level 4 autonomy is. The long-tail of edge conditions to handle is really long, and Rivian is only at the beginning.

What Rivian is going to release at the end of 2026 is what Tesla had 3 years ago. All that time has gone to dealing with edge conditions: bike lanes, emergency vehicles, construction zones, and all the crazy one-off situations that their fleet has seen.

Tesla's fleet is an order of magnitude larger, so events that Rivian has seen only once, Tesla already has ten examples of. And rare events that Tesla has trained on, Rivian has never yet seen.

I will say this, though: Rivian is the closest competitor to Tesla (not counting Chinese cars). Waymo FSD is obviously more advanced than Tesla, but they will lose out to both Tesla and Rivian when it comes to manufacturing. And the robotaxi game is going to be all about manufacturing.

Post reply on HN