Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

Autonomous Car Progress

This site may earn commission on affiliate links.
Cross-posting from another thread because, to me, this is a fascinating and entertaining example of a company’s claims about the autonomy software they’ve developed looking pretty dubious. The employee reviews paint a picture of the biggest “sugar” show at a big “tech” company I’ve ever heard of, with the exceptions of Nikola and Theranos.



What did Xpeng actually develop?

There is little visibility into Xpeng's software. I'm unsure how much of Xpeng's ADAS software they actually own, control, or developed in-house.
Not particularly surprised if they outsourced a lot of things. Even many major OEMs are outsourcing their ADAS (just rebranding them). Mobileye is a big supplier.
“This is for the most part not a real company”

I'm reading Glassdoor reviews for "Xmotors.ai", Xpeng's R&D subsidiary in Mountain View. The reviews are dismal.

w6comYe.jpg

"This is for the most part not a real company. Probably of 75% of the people here are not working on real projects. As others have mentioned, most of the people here spending time appropriating or copying demos from academic research or other companies and then passing it off as their own work. Only a quarter of the people are doing anything actually related to technology that will be deployed or used in production, the rest are a glorified marketing team. Investors have paid enormous sums of money to fund a US marketing campaign who's only goal is to attract more investment through PPTs. Real shareholder value. The admin is also horrendous. Never have I seen such unprofessionalism in the admin they have hired. Benefits promised at hiring are not delivered. Promised stock options never was real."​


"A lot of engineering time is spent on preparing unnecessary demos. This can often be a nuisance because it can distract you from your current project and bring down your productivity. This problem is more serious than it seems."​


"They talked about the company’s goal of making the world better, solving challenges and being the next Tesla to lure you to accept the offer. Once you come to work, you find people here are busy with producing demos used to show to the headquarter. And as mentioned by others “There are lots of talk,lots of planning,lots of meetings, but no actual action”. Senior managers in China crazy about demos, they have no direction and vision."​


"Poor management, poor (or non-existing, i.e fake) stock option policy, poor technology execution."​


"Many decisions that are made seem to be strange and beyond understanding of the people. An example is sometimes projects will start in the US office and then without much explanation we are asked to provide all results to the China team and stop working on projects. And then for some reason certain weeks after that, the project will be transferred back with the US team. And then later the entire project is outsourced to a contractor. And then the contract is cancelled."​


"* The stock options were too good to be true. They aren't granted, basically a broken promise​
* Press releases about Apple IP theft means you won't have any career prospects after working here​
* Senior management does not have technical credentials -- resulting mediocre or low quality middle management being hired -- naturally resulting in low quality talent being hired generally.​
* No technical questions asked during interviews. Speaks to quality of hiring practices. I was asked something along the lines of "how many binaries have I compiled in the last month"."​


"Lots of talk,lots of planning,but no actual action. Company talks like it is the next Tesla but actually have produced nothing of value. They have an electric car but otherwise it is all marketing. Investors and employees were tricked into thinking this is a technology company. It is not. It is a marketing company. No technical questions during interview and all the fancy presentations given to investors and management were copied from unrelated academic presentations."​



"you will lose your skills here because there no actual development. stock options are fake. no one wants to hire someone from a company with all the public news about FBI investigation. leaders have no experience."​


And it goes on. I'm not cherry picking these examples. Go see for yourself.
Wow, didn't realize there was such a mess at XPeng. To be fair to them however, what happens in their US subsidiary may not necessarily be representative of what is going on at their China HQ. Of course we are unlikely to get as good a picture of the internal workings of their China HQ.
 
Oh look. The guy who told us Tesla will be at ~150k miles per safety disengagement in 6-9 months, 7 months ago.

The guy who said Tesla would have level 5 by end of 2021 acouple months after his 6-9 months statement were evident to have failed. The same guy is now telling us, wait another year. Then the next year he will say just wait another year.

Care to revisit your track record?


New Audi A8 due by end of 2017.
Complete autonomous driving for a single lane on the highway while under 35mph. It is based on their jack prototype and uses mobileye eyeq3 chip on a board called zFAS. Its latest sensors include 12 Ultrasonics, 8 Radars, 4 Top View Camera, 1 Wide View Front Camera and 2 Lidars (Forward & Rear)

Technical Details

Jack Prototype in Action

Nissan in 2018
"Complete autonomous driving for all driving situation on the highway."
Propilot 2.0 (multi-lane) Based on their Nissan Intelligent Driving platform, uses 5 Radars, 4 Lidars and 8 (12 now) surround cameras. It uses the mobileye eyeq4 chip including REM map of every highway in partnership with Zenrin.


Technical Details & Timeline

Propilot 2.0 in Action

Volvo in 2019
Based on their L4 Drive Me prototype using mobileye eyeQ4. Sensors include 7 radars, 7 cameras, 12 ultrasonics and 1 forward lidar.

Technical Details

Prototype Car
Volvo Drive Me - Public Autonomous Driving Experiment - XC90 SUV

Autopilot
Introducing Volvo Interface for Self-Driving Cars

Honda in 2019
uses mobileye eyeq4


Source
26 mins
Prof. Amnon Shashua delivers Mobileye press conference at CES 2017 autonomous cars
 
Care to revisit your track record?


That not my track record. Unlike you I rarely give my opinion.
I spend tens of thousands of hours researching every single auto, av company and ml industry at large and compile everything they are doing, saying and post them. The same way I compile everything Tesla is doing and what Elon has had about Level 5.
None of this is my prediction.
 
Not particularly surprised if they outsourced a lot of things. Even many major OEMs are outsourcing their ADAS (just rebranding them). Mobileye is a big supplier.

Wow, didn't realize there was such a mess at XPeng. To be fair to them however, what happens in their US subsidiary may not necessarily be representative of what is going on at their China HQ. Of course we are unlikely to get as good a picture of the internal workings of their China HQ.

You will find similar reviews at any company. For example look at Cruise 3.5 Glassdoor reviews.

When Xpeng assembled their team in SF, they didn't have a production car to develop on, so there weren't any production development.
They were scheduled to get their car in 2019. So the development team spent time researching SOTA DL Algorithms and creating demos with the prototype cars they had for investor to show what they are capable of doing.

Its funny shrine puts an emphasize on that, yet This is exactly what Tesla did, created a fake demo in 2016 using Nvidia software to impress customers and investor and to sell a product and passed it off as their own work. Even then early on, their AP software was based on Academic GoogleNet from 2015 (Inception net) for several years (2016-2018/2019 I believe).

This is perfect example of the pot calling the kettle black.

The reviews are from 2018 which is 3 years ago (an eternity in the AV industry) and you can see other reviews saying their team is research and developing algorithms and demos till they receive the cars in 2019.

@shrineofchance like always tries to distract from actually addressing why their model and prediction that supposedly based on fact or data but isn't at all.

In Xpeng's 2021 Q1 Investor conference they said: "we’re able to collect highly valuable rate cases with our customers using NGP. We’re now able to achieve fast iterations of our algorithm on a weekly basis, based on our advanced closed-loop data capabilities. With the growing number of P7s on the road, I believe Xpeng will have the largest and fast growing Smart EV fleet close-loop data capabilities on China’s road network."

Shrine can't imagine another company other than Tesla collecting data from production cars, this is how strong thier bias is and how much Tesla has clouded their logic and reason.

They do OTA/FOTA updates which shrine was not aware of. Their recent update was for Navigation Guided Pilot, An navigate on autopilot equivalent.

They use a multi domain controller, which replaces the hundreds of ECU found in cars with a single computer unit. It facilitates the communication between the main chip (Nvidia..whatever) and the car's actuators. You either design and create your own hardware or work with tier 1s to create one based on the chip of your choice. With Xpeng they used Nvidia's Xavier.

This has nothing to do with the AV software that Xpeng is actually creating/created.

"Desay SV argues that: tier-1 suppliers and OEMs will collaborate in the following two ways in the area of autonomous driving domain controller:

First, tier-1 suppliers are devoted to making middleware and hardware, and OEMs develop autonomous driving software. As tier-1 suppliers enjoy edges in producing products at reasonable cost and accelerating commercialization, automakers are bound to partner with them: OEMs assume software design while tier-1 suppliers take on the production of hardware and integration of middleware and chip solutions.

Second, tier-1 suppliers choose to work with chip vendors in solution design and research and development of central domain controllers and then sell their products to OEMs. Examples include Continental ADCU, ZF ProAI and Magna MAX4."


QNX is the most popular OS for providing functional safety, security and real time operation and is a standard in the auto industry. Its in over 150 million cars. SDC companies either use QNX or Linux. But to disparage Xpeng because they use QNX secure OS is like disparaging a company because they run their software on Linux or Windows.


Alot of SDC companies uses Nvidia Drive OS including Zoox because it has embedded RTOS, hypervisor, NVIDIA CUDA libraries, NVIDIA Tensor RT and other components optimized to provide direct access to DRIVE AGX hardware acceleration engines. which is needed for the acceleration of deep learning models that Xpeng will be developing.

Nvidia DRIVE OS is NOT Nvidia DRIVE AV or Nvidia DRIVE IX.
This has nothing to do with the AV software that Xpeng is actually creating/created.
Again what you are doing is equivalent to disparaging companies for using windows/android/linux and drivers that come with it.

NVIDIA DRIVE® OS is a foundational software stack consisting of an embedded real-time operating system (RTOS), NVIDIA Hypervisor, NVIDIA® CUDA® libraries, NVIDIA TensorRT™ and other modules that provide you access to the hardware engines. DRIVE OS offers a safe and secure execution environment for applications such as secure boot, security services, firewall and over-the-air (OTA) updates.

Details:
  • Multiple guest operating systems
  • 64-bit user space and runtime libraries
  • NvMedia APIs for hardware-accelerated multimedia and camera input processing
  • CUDA parallel computing platform
  • Graphics APIs: OpenGL, OpenGL ES, EGL with EGLStream extensions
  • Deep learning libraries: TensorRT, cuDNN

NVIDIA DRIVE - Software


For anyone wondering what QNX OS (which is integrated into Nvidia Drive OS by Nvidia) is and what it isn't. Take a look at the link below.

QNX OS for Safety​

Streamline your products’ functional safety certifications with a microkernel operating system pre-certified specifically for safety-critical embedded systems, and toolchains pre-qualified for building these systems. Ideal for building complex safe systems, the QNX OS for Safety is a full-featured, deterministic OS designed for use in every sector where functionally safe, reliable embedded software is critical: medical devices, industrial controls, aerospace, automotive, power generation, robotics and rail transportation.

QNX OS for Safety – Pre-Certified Embedded OS and Toolchains | BlackBerry QNX | BlackBerry QNX


For anyone wondering what a multi domain controller like IPU-03 is. Take a look at the link below.

Multi Domain Controllers​

Today, every electronic control system in the car, such as Instrument Cluster, Infotainment, Anti-lock braking system, Engine Management System, Transmission Control Unit, and Body Control Management is a self-sufficient unit with its own sources like ROM, RAM memory, microprocessor or microcontroller, I/O and power supply. The idea of automotive domain controller is to replace multiple distributed ECUs with a single powerful central computer with multi-core. Multi-core processing technologies integrate multiple ECUs into one single chip. In a multi-core solution, these individual ECUs retain separated and independent processing space. However, a lot of redundant components like housing, drivers, wire and harnesses, and power supplies can be eliminated. These not only largely save cost but also the component's weight and space. Moreover, communication between ECUs is within the processor itself instead of communicating over an external network like CAN or LIN, this will reduce the data latency and system complexity considerably.

 
  • Funny
Reactions: shrineofchance
1 year =
8 765.8 hours

A self driving engineer spends 2920 hours doing that a year. If they worked from 2015 that’s 17,520 hours. I have been actively researching ML, AV and the auto industry for over 7 years.

And I’m not talking about just watching Tesla Autonomy day video which for most here is the closet thing to a technical talk, research paper that they have heard.

I’m a software engineer, I love tech and knowing precisely how bleeding edge technology works.

I take pleasure in researching AV and passionate about innovative technology and creating them. I can’t wait to go to Phoenix and SF and ride in Waymo and eventually Cruise when they launch in SF. I’m also planning a trip to China to take a ride in huawei and Zeekr door to door systems. I’m making a move to full remote and might move to China if that works out (difficult because almost every thing is blocked there and you need good VPN)

If I do that I will be making videos in my Zeekr 001 and doing comparison videos with huawei autopilot and whatever FSD Tesla manages to release in China
 
A self driving engineer spends 2920 hours doing that a year. If they worked from 2015 that’s 17,520 hours. I have been actively researching ML, AV and the auto industry for over 7 years.

Wow! Your own math discredits your absurd claim! 😅

And I’m not talking about just watching Tesla Autonomy day video which for most here is the closet thing to a technical talk, research paper that they have heard.

Of course, real technologists watch "Amon" Shashua videos, which are totally different and much more technical.

I’m also planning a trip to China to take a ride in huawei and Zeekr door to door systems.

So, is this a prediction that the advertised functionality will actually materialize on schedule, or are you merely neutrally reporting the news about Geely's claims?
 
  • Like
Reactions: mikes_fsd
That not my track record. Unlike you I rarely give my opinion.
I spend tens of thousands of hours researching every single auto, av company and ml industry at large and compile everything they are doing, saying and post them. The same way I compile everything Tesla is doing and what Elon has had about Level 5.
None of this is my prediction.
Funny you say that now, but then you got on my case for years about me "vowing" Tesla FSD would be released in 2018 (which never existed BTW, and you never found the supposed post where I said that after all these years) as opposed to what I actually did: which is just analyzed what Elon said about expected FSD timeline.

Hopefully you kind of understand now what I was feeling when you did numerous accusations against me (in an obvious attempt to say "I told you so"), even though I made my position clear many times in response. I could have gotten on your case many times on Audi's broken L3 promises, but I didn't.
 
Minimum number that is "tens of thousands of hours": 20,000

7 years * 365 days per year = 2,555 days

20,000 hours / 2,555 days = 7.8 hours per day

The typical Western working adult's weekday schedule:
  • 8 hours work (work 9am to 5pm, which is 8 hours, minus 1 hour for a lunch break, plus 1 hour for a commute)
  • 8 hours sleep (ideally)
  • 8 hours everything else
8 hours + 8 hours + 8 hours = 24 hours

If you devote the full 32 hours you get on weekends for "everything else" solely to learning about AVs, ML, etc., then that's still 4.5 hours every weekday.

But average American works 47 weeks out of the 52 in the year, which is roughly 90% of the weeks in the year. So, we can subtract 10% — assuming you use all vacations and holidays to study — and it comes to about 4 hours per weekday.

This would still require you devote half of your waking, non-working hours to study on weekdays and all of your waking hours on weekends, holidays, and vacations.

BS.
 
Last edited:
Funny you say that now, but then you got on my case for years about me "vowing" Tesla FSD would be released in 2018 (which never existed BTW, and you never found the supposed post where I said that after all these years) as opposed to what I actually did: which is just analyzed what Elon said about expected FSD timeline.

Hopefully you kind of understand now what I was feeling when you did numerous accusations against me (in an obvious attempt to say "I told you so"), even though I made my position clear many times in response. I could have gotten on your case many times on Audi's broken L3 promises, but I didn't.

lol I was the first one who called out Audi for not having L3 and resorting to marketing.

I also called out BMW years before they came out and said their iNext won’t be L3 based on my research.


Many other companies I have also called out.
None of those things were my prediction. That’s why I can call it out.

I also called out BMW when their ceo said they could have L5 if they wanted
 
Last edited:
  • Funny
Reactions: shrineofchance
The colour white, according to bladerskb:

View attachment 667415

“Some consider white to be a color, because white light comprises all hues on the visible light spectrum. And many do consider black to be a color, because you combine other pigments to create it on paper. But in a technical sense, black and white are not colors, they’re shades. They augment colors.”

Source
 
  • Disagree
Reactions: Demonofelru