First Jerry rig everything, now mark rober 🧐

[PungoteagueDave]

Vision alone can only go so far. Aka in ideal conditions. The reason why us humans slow down or don’t drive in certain conditions, ie blizzards or sand storms.

I can’t wrap my brain around why a manufacturer would choose only one sensing technology instead of a network of different types for different weather/road conditions.

Fact: I’m not an engineer.

Why? Cost. Elon's first principles - fewer parts, use software instead of hardware (eg no switches). My FSD supervised is brilliant. After the first few FSD cars I had, I never thought it would get this far, expected the edge cases to be too difficult. Now I'm pretty confident it will be there soon.

Sponsored

 

[cybercricket]

According to the comments on the video he was using regular autopilot. I'm not watching all of it but maybe he should try with FSD.

As far as I can tell he ran the tests as follows :

1) Emergency Braking against a "pedestrian"
2) Autopilot against a "pedestrian"
3) Autopilot against a "pedestrian" in the "fog"
4) unclear against a "pedestrian" in the "rain"
5) unclear against a "pedestrian" when blinded
6) Autopilot against the "wall"

I would add it's a significant issue that Tesla's safety features behave significantly differently between AEB, Autopilot and FSD.

 

[CyberNC]

Looking at the stock chart, it seems like Luminar stock is going to be delisted.

This viral video might just be their last desperate attempt, don't you think?

 

[CyberZephyr]

I'm very surprised Mark has succumbed to this.

 

[cybercricket]

I'm very surprised Mark has succumbed to this.

I didn't find anything negative in his presentation.

 

[woodersonowl]

from what I could gather watching the demonstration, Rober used autopilot not FSD

 

[CyberZephyr]

I didn't find anything negative in his presentation.

It sounded like he was being negative from OP's post.

 

[tingmo13]

these days I watched FSD in China-released Feb 25-Tesla called it 'City Street Autopilot'-I lived in India for so long and definitely believe FSD will work in India as well-very excited!
Glad I don't watch these Snake Oil sales men!

 

[mongo]

I didn't find anything negative in his presentation.

Wall test didn't have AP on
Rain test likely didn't either
First impact was AEB, not even AP (which he did call out afterwards, but made no mention of FSD nor his car's hardware version)

 

[cybercricket]

It sounded like he was being negative from OP's post.

He demonstrated the fundamental limitations of the vision-based systems specifically in the context of forward collision prevention. Technically Tesla doesn't even deny any of it, with FSD kicking out if it decides that condition are too severe for it to work. LIDAR works better for that narrow application, but it of course doesn't solve any of the bigger problems with FSD which Tesla is tackling.

Then separately he demonstrated some odd behavior of Tesla's emergency braking (obstacle detected, but brakes not engaged).

 

[cybercricket]

Wall test didn't have AP on
Rain test likely didn't either
First impact was AEB, not even AP (which he did call out afterwards, but made no mention of FSD nor his car's hardware version)

His display was showing the "rainbow road" during the "wall test", which is suggests he had the AP on. It didn't even matter, as none of the Tesla's vision based systems (AEB, AP, FSD) are capable passing that test.

 

[freyguy]

Looking at the stock chart, it seems like Luminar stock is going to be delisted.

This viral video might just be their last desperate attempt, don't you think?

Either way still completely ashamed that mark the fun enjoy fun content creator making a maze in his backyard for fat Gus, would reach these levels. The test is not valid in my opinion and was definitely an attempt to slander the company

 

[sybertruck]

Mark has a 2020 Model Y on Old Hardware 3 and it was not in FSD. So testing a Tesla at a handicap against a sponsored Luminar custom configured Lexus vehicle at it's max it not a scientific test at all.

Lexus, the luxury division of Toyota, has been exploring the integration of Luminar’s lidar technology into its vehicles. In 2017, the Toyota Research Institute (TRI) collaborated with Luminar to equip a fleet of self-driving Lexus sedans with Luminar’s lidar sensors for autonomous vehicle testing.

As of now Lexus has not integrated Luminar’s lidar technology into its production vehicles. While Luminar has partnerships with several automakers, including Volvo and Mercedes-Benz, for integrating its lidar systems into production models, there is no official announcement regarding such integration with Lexus vehicles.

Matt was a NASA engineer and he knows the scientific method which must be done to have a level playing field of variables. No question a Youtube hit building video and is the first video of his where it is disappointing and highly inaccurate due to sponsorhip leanings.

 

[Deleted member 22486]

TLDR:
Jerry rig everything and Mark Rober have both criticized Tesla's technology, with Rober downplaying its camera vision compared to LiDAR, leading to disappointment over their behavior and possible intentional oversight in testing.


In case you missed it Jerry rig everything put the trailer hitch through hell of the cybertruck trying to really throw dirt on the Tesla name. He’s a relatively big channel, but now mark rober who has way many followers 65m and decides to try and make Tesla camera vision less superior than LiDAR. I can’t believe there is so much going on with these platforms downplaying the amount of tech and engineering that Tesla has developed over the years. I’m actually ashamed of both channels for this behavior, whether it be for clicks or views it’s complete bs. Additionally during his testing he was only using autopilot and not FSD. I do t wanna say this was intentional but he’s a nasa engineer so something like that would never be an oversight.

Jerry is full of crap- there is a difference between rated tongue weight and towing capacity. The CT actually out performed its rating. Mark’s test, however, was a valid scientific test and spot on- the reliance on cameras alone is and always will be a issue when it comes to anything beyond supervised self driving.

 

[cybercricket]

Mark has a 2020 Model Y on Old Hardware 3 and it was not in FSD. So testing a Tesla at a handicap against a sponsored Luminar custom configured Lexus vehicle at it's max it not a scientific test at all.

Matt was a NASA engineer and he knows the scientific method which must be done to have level playing field of variables. No question a Youtube hit building video and is the first video of his where it is disappointing and highly inaccurate due to sponsorhip leanings.

Again, I call bullshit. The test was a very basic forward collision avoidance. Automatic Emergency Braking is included with the base vehicle. None of this should be tied to FSD.

Sponsored