NIO NOP/NAD and Xpeng NGP/XNGP have limitations
$NIO Inc (NIO.US)$ $XPeng (XPEV.US)$ $Tesla (TSLA.US)$ The 2 articles revealed some limitations about NIO NAD ( Navigation Assisted and Intelligent Driving)/NOP (Navigation on Autopilot) and Xpeng NGP (Navigation Guided Pilot)/ XNGP (last step before full autonomous driving is realized). For easy reference, the article referred them as NOA (Navigation on Autopilot):
1) Still Level 2 Self Drive System
NOA system, exemplified by Tesla’s FSD or XPeng’s XNGP are only Level 2, meaning human drivers still need to monitor most tasks.
2) Misleading and Meaningless names
It’s easy to believe that commercially available vehicles are closer to fully autonomous than they actually are, because Chinese car companies have given their NOA products all kinds of misleading or meaningless names:
NIO calls it NOP (Navigate on Pilot) and NAD (NIO Assisted and Intelligent Driving)
XPeng calls it NGP (Navigation Guided Pilot) and more recently XNGP (the “last step before full autonomous driving is realized,” the company says)
3) Lack of consistent standards
Apart from just being hard to remember, the different names also mean a lack of consistent standards. There’s no guarantee that these companies are promising the same things with their similar-sounding products. Some might only cover the major beltways in a city, while others go into smaller streets; some use LiDAR (a laser-based sensor) to help improve accuracy, while others only use cameras. And there’s no standard on how safe the tech needs to be before it is sold to consumers.
4) Lack of qualifications
“Many such concepts are invented by Chinese companies themselves with no reference or background,” says Zhang Xiang, an auto industry analyst and visiting professor at Huanghe Science and Technology College. “What are the standards for achieving NOA? How many qualifications are there? No one can explain.”
5) NOA is limited to only some cities
But to have a car merely capable of providing city NOA is not enough. You also need to actually live in one of the few first-tier cities where the function has been made available, like Beijing, Shanghai, Shenzhen, or Guangzhou.
6) NOA offers limited functionality due to complexity of road conditions
Haomo’s Cai echoes this: “The real urban environment is far more complicated than what is imagined. The planning, policies, driving styles are different in each city,” she said. “For example, the traffic lights we usually see have three signs—red, yellow, and green. But some cities have five-sign lights, Chinese characters as signs, or triangle- shaped lights.” But even within these pilot places, city NOA products still only offer limited functionalities.
7) Problems with using LiDAR-based system
Both NIO NOP and Xpeng NGP used LiDAR sensors. Tesla dumped LiDAR sensor and used camera-based system also known as Tesla Vision. According Datahunt, the biggest problem with LIDAR is its lack of adaptability. Most are implemented in a way that relies heavily on maps, and very few have been tested on real-world roads - and even if they have, it's only on large, highly mapped roads. But the average person doesn't drive on those roads every day, so they're not very practical.
1) Still Level 2 Self Drive System
NOA system, exemplified by Tesla’s FSD or XPeng’s XNGP are only Level 2, meaning human drivers still need to monitor most tasks.
2) Misleading and Meaningless names
It’s easy to believe that commercially available vehicles are closer to fully autonomous than they actually are, because Chinese car companies have given their NOA products all kinds of misleading or meaningless names:
NIO calls it NOP (Navigate on Pilot) and NAD (NIO Assisted and Intelligent Driving)
XPeng calls it NGP (Navigation Guided Pilot) and more recently XNGP (the “last step before full autonomous driving is realized,” the company says)
3) Lack of consistent standards
Apart from just being hard to remember, the different names also mean a lack of consistent standards. There’s no guarantee that these companies are promising the same things with their similar-sounding products. Some might only cover the major beltways in a city, while others go into smaller streets; some use LiDAR (a laser-based sensor) to help improve accuracy, while others only use cameras. And there’s no standard on how safe the tech needs to be before it is sold to consumers.
4) Lack of qualifications
“Many such concepts are invented by Chinese companies themselves with no reference or background,” says Zhang Xiang, an auto industry analyst and visiting professor at Huanghe Science and Technology College. “What are the standards for achieving NOA? How many qualifications are there? No one can explain.”
5) NOA is limited to only some cities
But to have a car merely capable of providing city NOA is not enough. You also need to actually live in one of the few first-tier cities where the function has been made available, like Beijing, Shanghai, Shenzhen, or Guangzhou.
6) NOA offers limited functionality due to complexity of road conditions
Haomo’s Cai echoes this: “The real urban environment is far more complicated than what is imagined. The planning, policies, driving styles are different in each city,” she said. “For example, the traffic lights we usually see have three signs—red, yellow, and green. But some cities have five-sign lights, Chinese characters as signs, or triangle- shaped lights.” But even within these pilot places, city NOA products still only offer limited functionalities.
7) Problems with using LiDAR-based system
Both NIO NOP and Xpeng NGP used LiDAR sensors. Tesla dumped LiDAR sensor and used camera-based system also known as Tesla Vision. According Datahunt, the biggest problem with LIDAR is its lack of adaptability. Most are implemented in a way that relies heavily on maps, and very few have been tested on real-world roads - and even if they have, it's only on large, highly mapped roads. But the average person doesn't drive on those roads every day, so they're not very practical.
Because people have driven more than a billion miles in Tesla cars, we've accumulated a huge amount of unpredictable road data. Because Tesla Vision is a way to learn and improve from this data, we knew it would be much more meaningful than LIDAR. Other disadvantages of LiDAR based systems can be found in the article.
Conclusion
This post is about limitations of NOA. Although some articles claimed their autonomous driving technology is better (as compared to Tesla FSD), there are also many that said otherwise. Hence it's important to read both sides of the story.
Conclusion
This post is about limitations of NOA. Although some articles claimed their autonomous driving technology is better (as compared to Tesla FSD), there are also many that said otherwise. Hence it's important to read both sides of the story.
$BYD COMPANY (01211.HK)$ $BYD Co. (BYDDF.US)$ $S&P 500 Index (.SPX.US)$ $Nasdaq Composite Index (.IXIC.US)$ $Tesla (TSLA.US)$ $VOLKSWAGEN A G (VWAGY.US)$ $NIO Inc (NIO.US)$ $Li Auto (LI.US)$ $XPeng (XPEV.US)$ $General Motors (GM.US)$ $Ford Motor (F.US)$ $Rivian Automotive (RIVN.US)$ $MERCEDES-BENZ GROUP AG (MBGAF.US)$ $TOYOTA MOTOR CORP (TOYOF.US)$ $GEELY AUTO (00175.HK)$ $Lucid Group (LCID.US)$ $Stellantis NV (STLA.US)$
Disclaimer: Community is offered by Moomoo Technologies Inc. and is for educational purposes only.
Read more
Comment
Sign in to post a comment
I reflected trading experiences by writing journals. My comments are for educational purposes not financial advice.
3070Followers
95Following
12KVisitors
Follow
Revelation 6 : Thanks for putting in the effort and taking the time, day in and day out, to write so I have the opportunity to read. It’s thought provoking you know!
ZnWC OP Revelation 6 : You're welcome. Hope you find the post useful.
MonkeyGee : at least NIO and Xpeng has an Autonomous drive mode. What do Tesla have? Tesla auto drive will never work.
ZnWC OP MonkeyGee : Thanks for contributing "comment".
ZnWC OP : Based on the article shared, NIO NOP/NAD and Xpeng NGP/XNGP are only providing L2 self-drive limited features for customers. The so-called autonomous driving which lack standardisation and qualification is still at testing stage. On the other hand, many customers have driven and clocked more than a billion miles in Tesla cars accumulated a huge amount of unpredictable road data.
bullrider_21 ZnWC OP : Tesla's Autopilot/ Full Self-Driving is also L2 autonomy. Full Self-Driving is misleading as it is not fully autonomous. Ford, GM and Tesla have their own ADAS. Each call their ADAS by different names which is confusing. They also have no standardisation and qualification. A billion miles driven in Tesla cars with a driver inside is useless. You can't even compare with 100 million miles driven without a driver.
MonkeyGee bullrider_21 : I have been in both cars with auto drive activated. With the Tesla I could not leave it running for more than 5 minutes before I had to turn it off or it will kill me. it does the dumbest things. Tesla automation feels like a child is driving or a grandpa. in contrast, I could leave xpeng on in Shanghai for the full trip and of course you have to intervene once in awhile like when a bike drops in front of you from nowhere. I truely think if Tesla buys xpeng it would make them king in china.
bullrider_21 MonkeyGee : Hear that? Listen to people who have actually driven the 2 brands. And people think that Tesla is the best. This article is one-sided and has many inaccuracies.
bullrider_21 Revelation 6 : This article is one-sided and has many inaccuracies.
Tesla's Autopilot/ Full Self-Driving is also still L2 autonomy. Full Self-Driving is misleading as it is not fully autonomous. Ford, GM and Tesla have their own ADAS. Each call their ADAS by different names which is confusing. They also have no standardisation and qualification. A billion miles driven in Tesla cars with a driver inside is useless. You can't even compare with 100 million miles driven without a driver.
Xpeng and Nio don't rely on high-precision maps. They are using neural networks. Which means that they are using AI to train for different city and rural settings.
Tesla dropped the Lidar and radar systems because of costs reason. It's because of this that they have not been able to achieve L4 autonomy. They have been saying they will achieve full autonomy since 2016 and have not been able to do so. All robotaxis use the Lidar and radar systems and there have been no life-threatening injuries or deaths. Tesla cars have recorded at least 93 deaths from FSD.
Read the article below for an accurate picture:
https://www.moomoo.com/community/feed/111013669765126?global_content=%7B%22invite%22%3A%22102079252%22%2C%22promote_content%22%3A%22mm%3Afeed%3A111013669765126%22%7D&data_ticket=8d79554dc8b17a0ea10adf128b61190d&futusource=nnq_search_search-result
ZnWC OP bullrider_21 : Thanks for contributing "comment".
View more comments...