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

Tesla Autopilot Vs Competition

This site may earn commission on affiliate links.

SBenson

Active Member
May 22, 2014
1,871
4,755
Benson
I understand that there are quite a number of threads discussing Tesla's AP both in investor section and else where. But I specifically wanted to discuss Tesla's Autopilot functionality vs competition. I believe it's relevant to investors so creating a thread here.

Many people have said lane keeping and active cruise control are available in many other cars. Mercedes S-Class has collision avoidance which they highlight on their website.

So what is special about Tesla's autopilot? How is it better/different?

I read Model S can change lanes on tap of turn-signal. Does it work? Is this unique to Tesla?

What else?
 
Two words on the above Mercedes system :research car. It's not in production.
Yes, I'm impressed with Tesla but give credit where credit is due. You think any of Tesla's research cars can figure out 4 way stops and adjust to odd behavior. Many impressive things and screens in that video show their level of knowledge.

The main things we've seen from Tesla are what the Mobileye provides to Tesla Mobileye technology

"holistic path prediction" (HPP) is Mobileye's too shown in Mobileye video presentations.

11-May-2015 Mobileye
We [Mobileye] have also a holistic path prediction, the ability to predict the path using a lot of context outside of the main lane detection mechanisms. It is relevant for hands-free driving, of course; you'd like to have a very high availability of lateral control even in situations where you don't see the lanes. But on the other hand, it's very relevant for the existing lane departure warning and lane keeping functionalities.
You can think of traffic light detection as an enabler for automated driving. When you're going into semi-urban areas and there are lots of junctions with traffic lights, you'd like to be able to handle those automatically. But on the other hand, you can think of traffic light detection as a very nice addition to the existing ACC functionality where when you engage ACC, the car would either warn or stop when you reach a red-light junction.
So, all of these new technologies are designed and targeting automated driving, but they also have a secondary use for the existing ADAS function and we see a lot of traction for them. For example, the two major wins that I mentioned at the beginning of my script, they all ask for these functions, regardless of whether it is going to be for automated driving or not. So the traffic light detection, the road profile, the free space, the HPP, all of them are already being sourced since a few months ago.
 
Last edited:
the mobileye chip and algorithm is the Intel inside these systems.
the rest is about integrating with the cars mechanical systems
That sure seems like quite an incorrect/oversimplified analogy since Mobileye analyzes the data as well.
Various Mobileye videos have them explaining how they analyze the information.
Tesla appears to be using the output from Mobileye. Various Mobileye videos show Audi's driving hands off.

Again, I'm very impressed with Tesla's work but most credit goes to Mobileye.
 
That sure seems like quite an incorrect/oversimplified analogy since Mobileye analyzes the data as well.
Various Mobileye videos have them explaining how they analyze the information.
Tesla appears to be using the output from Mobileye. Various Mobileye videos show Audi's driving hands off.

Again, I'm very impressed with Tesla's work but most credit goes to Mobileye.

you misunderstood me, I agree MobileMe is the real deal here.
Their mobileye chip and algorithm are the brains behind computer vision
mobileye sells mostly to auto suppliers, except in Teslas case, where they
sell directly to car manufacturer.
Of course Teslas car integration is unique to tesla

mobileye processes the camera image and selects the cars path
their artificial intelligence algorithms coupled with their chip processor
are the brains in these systems.
 
Honestly, I've been disappointed in how well the Model S perceives the road and objects on it. Cars have to be fairly close and in motion for Mobile Eye to detect it. Coming around curves, up or down a hill will all delay the time it takes to detect the car right in front of you. So the worst is coming around a curve upon a car that is not in motion. My car has to engage emergency braking in that sort of situation, even though with my natural eyes it is quite easy to anticipate the need to come to a stop. Tesla needs to give more attention to street driving, stop sign and red light reading, and reading braking and turning signals of the car ahead. In all, there needs to be better anticipation of the need to stop. Whether Mobile Eye is up for this remains to be seen.

That said, I am very happy to see the progress Tesla has made with AP. I use it as much as possible. I'm just eager to see this technology to evolve, especially as so much advancement can be delivered with OTA upgrades.

Oh yeah, the navigation system needs a major upgrade. It really does a poor job at route selection and does not take any user input on the matter. Google Map is far superior in route selection and user input. Tesla may do well to select a navigation vendor or allow third-party nav apps. Top quality navigation is an absolute requirement for autonomous cars. Even with the autopilot framework, where you could set a destination and allow the car to make turns under driver supervision, I would not trust the current navigation system to make sensible route choices.
 
Honestly, I've been disappointed in how well the Model S perceives the road and objects on it. Cars have to be fairly close and in motion for Mobile Eye to detect it. Coming around curves, up or down a hill will all delay the time it takes to detect the car right in front of you. So the worst is coming around a curve upon a car that is not in motion. My car has to engage emergency braking in that sort of situation, even though with my natural eyes it is quite easy to anticipate the need to come to a stop. Tesla needs to give more attention to street driving, stop sign and red light reading, and reading braking and turning signals of the car ahead. In all, there needs to be better anticipation of the need to stop. Whether Mobile Eye is up for this remains to be seen.

That said, I am very happy to see the progress Tesla has made with AP. I use it as much as possible. I'm just eager to see this technology to evolve, especially as so much advancement can be delivered with OTA upgrades.

Oh yeah, the navigation system needs a major upgrade. It really does a poor job at route selection and does not take any user input on the matter. Google Map is far superior in route selection and user input. Tesla may do well to select a navigation vendor or allow third-party nav apps. Top quality navigation is an absolute requirement for autonomous cars. Even with the autopilot framework, where you could set a destination and allow the car to make turns under driver supervision, I would not trust the current navigation system to make sensible route choices.

I think the biggest advantage of the Tesla AP has not really been seen. Elon mentioned within a week or two they would be noticeably smarter as the Cars learn from each other. Think of the difference of having a few engineering cars and tens of thousands of daily drivers logging miles everyday.

It is technically only for highways right now and still in beta so I think the things you were disappointed on where somewhat unrealistic to expect at this stage but I hope to see them implemented soon.
 
Amnon the lead scientist /engineer at mobileye ,says for proper path recognition a car needs three
Frontal cameras, one to focus nearby, one to focus far away and another for 180 degree vision.
Tesla has only one, this is still the early stage.
 
Honestly, I've been disappointed in how well the Model S perceives the road and objects on it. Cars have to be fairly close and in motion for Mobile Eye to detect it. Coming around curves, up or down a hill will all delay the time it takes to detect the car right in front of you. So the worst is coming around a curve upon a car that is not in motion. My car has to engage emergency braking in that sort of situation, even though with my natural eyes it is quite easy to anticipate the need to come to a stop. Tesla needs to give more attention to street driving, stop sign and red light reading, and reading braking and turning signals of the car ahead. In all, there needs to be better anticipation of the need to stop. Whether Mobile Eye is up for this remains to be seen.

That said, I am very happy to see the progress Tesla has made with AP. I use it as much as possible. I'm just eager to see this technology to evolve, especially as so much advancement can be delivered with OTA upgrades.

Oh yeah, the navigation system needs a major upgrade. It really does a poor job at route selection and does not take any user input on the matter. Google Map is far superior in route selection and user input. Tesla may do well to select a navigation vendor or allow third-party nav apps. Top quality navigation is an absolute requirement for autonomous cars. Even with the autopilot framework, where you could set a destination and allow the car to make turns under driver supervision, I would not trust the current navigation system to make sensible route choices.


Autopilot should not be used on surface streets -- just as you wouldn't use cruise control either. Autopilot is for highway usage.