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

Why I am losing faith in Tesla’s Autopilot (Autosteer)

This site may earn commission on affiliate links.
VideoCapture_20221104-012354.jpg



I absolutely love my Model 3. I have had it for just over 3 years now and enjoyed driving every mile of the 42,000 miles that I have clocked till today. Most of the mileage has been on the highway and the remainder was miles that I racked up while commuting for work before the pandemic. When I bought it in 2019, I was primarily using it for the daily 60-mile round trip commute for work during the week. I had started using autopilot right away and loved the fact that I could relax a bit during my daily commute to work. My Model 3 was a replacement for my 2005 Toyota Prius and the difference between the two is significant. This summer, I drove over 8,000 miles across 14 states in my Model 3 - I’m as familiar with it and its autopilot system as anyone else.

Using autopilot for my commute became a ritual and I became very accustomed to it – understanding its weaknesses as well as its strengths. I became so accustomed to it, that whenever I was traveling away from home without my Model 3, I would find it strange to drive any other car, especially on highways. Autopilot allowed me to relax a bit more while driving and take more of a managerial role of the car's systems rather than actively driving it. It helped to reduce my overall fatigue during most drives. This was helpful especially in places like the Bay Area where there is heavy traffic, and you have to constantly be aware of changes in speed and lane changes of vehicles around you.

I experienced the real impact of autopilot when I took my first long road trip with my partner from San Jose to Seattle. This was in early 2020 when work from home had just taken off due to the pandemic and flying to places was out of the question. Several weeks later, we decided to spend some time in Colorado to take advantage of the remote work situation, so we drove to Boulder from Seattle via Yellowstone National Park. As we headed back to San Jose later that year, we had driven over 5,000 miles and had primarily used Tesla’s massive supercharging network. We wouldn’t have been able to do the trip without it. But the real game changer for us was autopilot. I had driven other vehicles with ‘lane-assist’ systems such as those in Toyota and other manufacturers, but nothing came close to Tesla’s autopilot. The ability of the car to stay within the lanes on a highway was impeccable even in times of inclement weather such as heavy rain or snow. We were very impressed with the overall system. There were times when autopilot got confused with lanes or times when we experienced phantom braking – instances when the car would engage the brakes even when there was no need to do so. These were a small fraction of instances and very soon I could predict when I would need to take over from autopilot when there was any complexity in the lane markings. But overall, it was a fantastic system that I found hard to drive without on any road trip or long commute thereafter.

Fast forward to 2022 to a couple of months ago in October. My father flew in from overseas to take a 26-day road trip with me across 7 states starting from California and ending in Wyoming. I was excited to take him in my Model 3 – for him to experience an electric vehicle, seamless supercharging across Tesla’s vast network, and of course autopilot. My dad being a man of precision is not easy to impress and I was eager to know his impression of a Tesla. When he finally decided to take over the wheel from me in Nevada, he was thrilled by the torque and power delivered by the Model 3. I watched him enjoy overtaking slower vehicles as I took videos of him from the passenger seat. I did 90% of the driving of the 3,500+ miles that we covered over 26 days. But I also relied on a key system for half the trip – autopilot. I say half because sometime in late September and early October, I updated the software for the vehicle to the latest version. I initially thought of waiting to complete our trip, but the software update notification popup became annoying, and I finally decided to just complete the update. Later I realized that I had made a big mistake.

On one of our drives, we experienced 4 phantom braking events within 30 minutes. Not only was I embarrassed, but I was also concerned about our safety. A vehicle behind us could have easily slammed into us when our vehicle braked suddenly without any reason to the outside observer. I had to switch off autopilot and drive the vehicle myself. This was such a shame since we could not have been on a straighter road, and it was so monotonous to have to steer as well as press the accelerator pedal. During the remainder of the drive, I kept wondering why this was happening. Was it the road? It had not happened at this frequency for most of our trip so why was this happening now. Then it hit me – it was the most recent software update. Tesla has started transitioning vehicles from its radar + Tesla Vision based autopilot to Tesla Vision only. I felt so silly for choosing to update my vehicle’s software. Even though I knew I had no way of knowing.

This was not the end though. For the remainder of the trip, I experienced multiple phantom braking events. The last straw was when I was driving back home to California from Salt Lake City and experienced such harsh phantom braking that my vehicle dropped in speed by 20 miles per hour within seconds. That was it. I decided to stop using autopilot and stuck to traffic-aware cruise control only. Little did I realize that traffic-aware cruise control is also using Tesla vision. So, I experienced the same exact harsh braking again while just using cruise control! I was so disappointed and so frustrated. I just decided to drive manually altogether. I realized that my 2005 Prius’ (or even my 98 Civic) classic cruise control would have been better than today’s updated version of autopilot.

To state the obvious - In software production, every update should either make a system safer or retain its current level of safety, and then not regress in overall functionality. Unfortunately, I felt less safe with today’s version of autopilot and have decided to not use it until Tesla has addressed this issue thoroughly. It feels very strange to not use autopilot on drives and I definitely feel its absence. The Model 3 has been one of the best purchases I have ever made in my life – I just hope that Tesla will remedy this soon (re-enable radar) and continue to deliver state-of-the-art systems going forward. The competition in the electric vehicle space as well as driver assist systems is about to get fierce.
 
For almost all mfgs, OTA updates only apply to the infotainment systems. I've never heard of any other mfg improving their ADAS through OTA updates
Now you have.

over-the-air-updates-how-does-each-ev-automaker-compare.

Note, this is EV only.

  • Audi - maps only
  • BMW - partial but for existing features including ADAS
  • Ford - yes
  • GM - yes
  • Honda - partial
  • Hyundai - partial
  • Jaguar/Land Rover - yes
  • Lucid - yes
  • Mercedes - partial
  • Nissan - partial
  • Polestar - yes
  • Porsche - partial
  • Rivian - yes
  • Stellantis Fiat Chrysler - partial
  • Tesla - yes
  • Toyota - partial
  • VW - yes
  • Volvo - yes
 
  • Like
Reactions: powertoold
Thanks for the list, but I think that's an aspirational list. For almost all mfgs, OTA updates only apply to the infotainment systems. I've never heard of any other mfg improving their ADAS through OTA updates (not saying they won't do it in the future).

Then there's also this article, 2023 for full GM OTA:

wishful thinking is strong with this one
 
wishful thinking is strong with this one

How so? Where is the evidence that other mfgs are constantly improving their ADAS through OTA updates?

See my original comment about constant improvement:

As for your video of PB 5 months ago, the difference between AP and other mfgs is that Tesla is constantly improving, whereas other mfgs don't have OTA updates..........
 
Last edited:
  • Funny
Reactions: COS Blue
How so? Where is the evidence that other mfgs are constantly improving their ADAS through OTA updates?

See my original comment about constant improvement:

As for your video of PB 5 months ago, the difference between AP and other mfgs is that Tesla is constantly improving, whereas other mfgs don't have OTA updates..........
Yes, imagine, others also update ADAS
Literally first google result
Screenshot_20221220-024045.png


Kia for example pushed the battery charging improvements fir EV6 owners in October..

Again, others provide OTA updates and these updates come in various packages... Like teslas..

P.s. PB is less but happens still. In 1 year I had maybe 20 instances of PB (one - couple weeks ago). In bmw had 0. No it yeah, go figure
 
Last edited:
Yes, imagine, others also update ADAS
Literally first google result

Let's stay on topic (although we're kinda hijacking this thread lol). This is about ADAS (lane keeping and TACC).

Your post has nothing to do with performance improvements in the lane keeping logic or TACC. Your example is related to user-experience.

I know it's difficult to stay on topic, but your prior example of getting Android Auto has nothing to do with what we're talking about. Also posting a list of other mfgs aspirational or limited capabilities doesn't help either. (like why did you bring up KIA improving their charging? we're talking about Autopilot / ADAS, thanks for the info though)

Once again, Tesla is constantly improving Autopilot through OTA updates. Other mfgs don't do this. What we complain about Autopilot this month could be solved 3 months from now. It has happened this way regarding many complaints (although I agree some issues still persist).
 
Let's stay on topic (although we're kinda hijacking this thread lol). This is about ADAS (lane keeping and TACC).

Your post has nothing to do with performance improvements in the lane keeping logic or TACC. Your example is related to user-experience.

I know it's difficult to stay on topic, but your prior example of getting Android Auto has nothing to do with what we're talking about. Also posting a list of other mfgs aspirational or limited capabilities doesn't help either. (like why did you bring up KIA improving their charging? we're talking about Autopilot / ADAS, thanks for the info though)

Once again, Tesla is constantly improving Autopilot through OTA updates. Other mfgs don't do this. What we complain about Autopilot this month could be solved 3 months from now. It has happened this way regarding many complaints (although I agree some issues still persist).
well, I could not be arsed to trawl through each and every update release notes.

but firstly you talk about AP being superior to anything else on the market, while my experience is opposite.
Then you talk that other manufacturers do not have OTA updates, but I point that they do, even for the other stuff (adding functionality, like android auto) and for the ADAS (lane departure assistant (it is part of ADAS) improvement for example).

Another example is polestar - OTA update improved lane keeping aid (read AP auto steer)

1671527918253.png


I mean, whatever, dude, you can keep your head in the sand if you like this. but the fact is - others are here and doing stuff, they have OTA and they push improvements via OTA - just like Tesla, you know.

Glorified AP - in essence is the standard one, is just lane keeping assistant and TACC. which is not the best implementation. that's all.

About constant improvements - I agree and disagree at the same time. While auto high beam improved, it took tesla 5+ years since release of model 3 to make it usable. This feature just works on other manufacturers, but it takes tesla 5 years. and still - it could be improved to be on par (it switches on too late, imho). However auto wipers are crap. really bad - it's algorythm is just unsolvable mystery to Tesla Devs. Or since they are based in California they do not know how this thing works.

there are few other niggles which could be fixed/updated, but at least these small improvements which should be OK straight out of the box if normal sensor, like in all other cars, is used. but since we insisting on the vision, we have to be patient.
 
Last edited:
  • Like
Reactions: COS Blue
This is a discussion thread that is designed from the start, through its title, to turn people away from Tesla. Every posting, no matter the content, supports that aim. Therefore this will be my last posting here.
but it should not - it should be reasonable discussion.

I, for the matter, really wanted the self parking option, as I really loved it in my Mondeo/Fusion, but I could not justify to pay premium on the EAP. seeing how badly it behaves puts my mind at ease.
 
  • Like
Reactions: Ts91
Another example is polestar - OTA update improved lane keeping aid (read AP auto steer)

1671527918253.png


I mean, whatever, dude, you can keep your head in the sand if you like this. but the fact is - others are here and doing stuff, they have OTA and they push improvements via OTA - just like Tesla, you know.

I'm actually not the one with my head in the sand here.

It's becoming clear that you post stuff that superficially supports what you're saying, but when you spend a few minutes to analyze it, it's unrelated to Autosteer and TACC.

First example was your post about bmw improving their ADAS through OTA updates. It turns out the improvements listed for that update had nothing to do with improving an Autopilot-like feature. It was related to steering wheel resistance for user intervention.

Now you post about a Polestar update that has little to do with an Autopilot-like feature. Lane Keeping Aid is not "Autosteer." It is a warning system that alerts the driver when they drift out of a lane. See here:

Lane Keeping Aid can provide steering assistance and/or a warning to the driver when the vehicle is about to leave its lane unintentionally. The function is active between 65-200 km/h (40-125 mph) on roads with clearly visible side markings.


Now, I'm not saying mfgs NEVER update their ADAS. You might find one case of it, ever, from one mfg, but that doesn't refute my point that Tesla is constantly improving Autopilot through OTA updates (and for free).
 
firstly, actually you do not believe that others ADAS can be better than AP. Although objectively, due to the reasons I mentioned, it actually is better than AP. Marginally, but IMHO (and IME) it is. It's up to you to believe what ever you want, really.

I'm actually not the one with my head in the sand here.

It's becoming clear that you post stuff that superficially supports what you're saying, but when you spend a few minutes to analyze it, it's unrelated to Autosteer and TACC.

First example was your post about bmw improving their ADAS through OTA updates. It turns out the improvements listed for that update had nothing to do with improving an Autopilot-like feature. It was related to steering wheel resistance for user intervention.
It still is part of ADAS improvement. Your message was that others "do not provide OTA Improvements to ADAS".
to quote your message in #32:
the difference between AP and other mfgs is that Tesla is constantly improving, whereas other mfgs don't have OTA updates..........
By the way, the above could be read that others do not have OTA updates at all.. whatever.
Now you post about a Polestar update that has little to do with an Autopilot-like feature. Lane Keeping Aid is not "Autosteer." It is a warning system that alerts the driver when they drift out of a lane. See here:

Lane Keeping Aid can provide steering assistance and/or a warning to the driver when the vehicle is about to leave its lane unintentionally. The function is active between 65-200 km/h (40-125 mph) on roads with clearly visible side markings.


Now, I'm not saying mfgs NEVER update their ADAS. You might find one case of it, ever, from one mfg, but that doesn't refute my point that Tesla is constantly improving Autopilot through OTA updates (and for free).
no matter how you call it - Lane keeping aid - is part of ADAS. The AP equivalent in Polestar is called as:

Pilot Assist​

Pilot Assist supplements Adaptive Cruise Control, supporting the driver in keeping the Polestar 2 centered in the driving lane. The camera and radar units that control the speed also monitor the car’s position, making light steering adjustments if it moves too close to the lane markings."
It had one of the updates at 1.9 update. If you want to go deeper to the woods - please - follow the path Pure progressive performance | Polestar

I did not even trawl through other manufacturers and their updates and their release notes, as I cannot be arsed to spend time on the internet to argue stupid things, as for whatever reason, I am not that ignorant to assume that Tesla is the only one which this magical feature that is super duper better than others, called AP and that it is the only one which has OTA updates to their software. this is just stupid
 
It still is part of ADAS improvement.

You're right: AEB, lane departure warning / correction, and forward collision warning are part of the ADAS system.

But they're totally unrelated to the topic here, which is Autopilot.

Look, if it's so difficult to find a single example of other mfgs improving their Autopilot-equivalent through OTA or any updates whatsoever, then aren't I right about what I said?
 
You're right: AEB, lane departure warning / correction, and forward collision warning are part of the ADAS system.

But they're totally unrelated to the topic here, which is Autopilot.

Look, if it's so difficult to find a single example of other mfgs improving their Autopilot-equivalent through OTA or any updates whatsoever, then aren't I right about what I said?
I just posted you a bloody link, it is not my problem that your head is in sand.
1671574213176.png


And if you follow the discussion, you would see that you are delusional. you can stop responding to me, as I feel like I am writing to a wall.
 
  • Like
Reactions: Just a Reader
I just posted you a bloody link, it is not my problem that your head is in sand.
View attachment 887259

And if you follow the discussion, you would see that you are delusional. you can stop responding to me, as I feel like I am writing to a wall.

It's odd that I feel the same way (a wall).

You posted about Autopilot's poor driving performance. You gave an example of phantom braking. The original poster's point was also about driving performance, nothing about bugs or stability of the system.

So I said that AP is constantly improving through OTA updates. You basically said that all other decent mfgs are also improving their AP-equivalent driving performance through OTA updates.

So I asked for examples, and you posted 3 examples of updates, most of which had nothing to do with an Autopilot-like feature.

And then you point out some vague radar stability in a Polestar update without any explanation of how that improves driving *performance*. It sounds more like a bug fix than anything (prevents the radar-related systems from crashing).
 
Last edited:
Not sure if it's worth the risk of interjecting here!

If other manufacturers can update OTA, especially steering system or braking related, then clearly they have some capability. If they are treading cautiously, I'm OK with that. TBH, I'm fine using USB to update none critical stuff and in some ways I prefer knowing that stuff can't change if I don't want it to.

Regarding TACC and a degree of lane positioning, my Hyundai behaves impeccably. Not one random slow down and certainly no sudden heavy braking. The MS in comparison throws some random caper most journeys.

I get no satisfaction from pointing this out and would be so happy if the Tesla did not have these issues.

Also remember that UK road layouts, conventions and also software behavior are likely different from US.

Most posters here are invested one way or another in Tesla's success regardless of how we feel they are doing so far.
 
Last edited:
Not sure if it's worth the risk of interjecting here!

If other manufacturers can update OTA, especially steering system or braking related, then clearly they have some capability. If they are treading cautiously, I'm OK with that. TBH, I'm fine using USB to update none critical stuff and in some ways I prefer knowing that stuff can't change if I don't want it to.

Regarding TACC and a degree of lane positioning, my Hyundai behaves impeccably. Not one random slow down and certainly no sudden heavy braking. The MS in comparison throws some random caper most journeys.

I get no satisfaction from pointing this out and would be so happy if the Tesla did not have these issues.

Also remember that UK road layouts, conventions and also software behavior are likely different from US.

Most posters here are invested one way or another in Tesla's success regardless of how we feel they are doing so far.
same for me - I want this to be succesful. but I am interested to see the degree of blindness from some people here
 
Regarding TACC and a degree of lane positioning, my Hyundai behaves impeccably. Not one random slow down and certainly no sudden heavy braking. The MS in comparison throws some random caper most journeys.

All systems have pros and cons, but AP is the best overall (in my limited opinion).

The problem with assessing other mfgs is there are no videos showing a variety of real-world scenarios for us to assess. Almost all other mfg videos are from dealerships...

 
All systems have pros and cons, but AP is the best overall (in my limited opinion).

The problem with assessing other mfgs is there are no videos showing a variety of real-world scenarios for us to assess. Almost all other mfg videos are from dealerships...


I agree totally about lack of extensive evidence, and sadly the very public nature of much of Tesla's testing makes it all to easy to focus on the negative.

I keep coming back to a feeling though that Tesla is often somewhat more than a little disingenuous with its representations, and may be niave with its messaging.

I would actually agree that my Hyundai's lane keeping is 'vague' and drifty in comparison to the MS. From that view point it is inferior. What makes it a 'better' experience for me is that the Hyundai didn't promise half what the Tesla did, but it delivered more than it promised on most fronts. And its behavior is consistent.

I find it hard to see how Tesla is demonstrating that they are leading the field as far as stability and useabilty go, especially outside of FSD Beta. (since FSD Beta is clearly work in progress)
 
Last edited:
Totally wish there were more comprehensive reviews of adas systems. Right now, the only way to really know is to try them out yourself which is expensive and time consuming.

Out-of spec review tries with their hogback challenge but fails with a weird scoring system and testing all adas in the same overly favorable conditions. For me, adas performance is most critical on rural imperfect windy, hilly unmapped roads. I think we have interstate and highway driving mostly solved as it's more or less just driving in-between the lines. I want to know how adas systems fail, and how badly they fail rather than how they perform in ideal scenarios. Here's a bmw adas drive. It fails by silently doing an unannounced 3 lane lane change. That's pretty bad imo. You can see the fail at 23 minutes in.


But I do like that he posts uninterrupted footage at least. Wish there were more adas reviews like this.
 
  • Like
Reactions: Battpower
on rural imperfect windy, hilly unmapped roads.

.... yes, plenty of those near me. To drive them in any way like I do would go well beyond 'staying between the lines'. (to get better visibility on bends). Other than map based speed changes for certain locations (which I believe also cause some incorrect changes with stacked roads) I haven't seen any evidence that Tesla attempts preemptive lane positioning and speed reduction ahead of dangerous road junctions, obscured bends etc.

Appropriate driving speeds on rural roads are pretty much unrelated to posted limits. Around us there are many single lane tracks or narrow windy roads that are the regular routes for local traffic. You get horses, cyclists, farm animals, hikers with dogs mixed in with regular oversized farm machinery - not as some extreme edge case, but pretty much any time. While I don't particularly expect ap to handle these situations any time soon, neither does it make sense that a car should be ready to attempt to drive at the posted speed of 60 mph. At the very least there should be a fall back mode where ap (or equivalent) max speed drops to say 30 mph and other control functions default to an extra conservative mode in certain situations.

doing an unannounced 3 lane lane change.

I get the impression that the underlying control systems must be verging on instability in order to get the required responsiveness. If things get out of the envelope I can imagine they can really get badly out of shape without warning. Probably not what's going on with the lane change that kinda remains in control..... may be just based on flawed interpretation.

uninterrupted footage

Yes. We have been subject to spliced footage presented as evidence for too long and it is misleading!

try them out yourself

I think it's pretty much impossible to try these systems out for long enough to become familiar and relaxed to the extent that you really have a confidence in their behavior. A few years ago I drove a VW with lane departure warning that vibrated the steering wheel. The idea didn't sound quite as bad as the actual experience of using it! My Kona beeps and gives a tug on the steering wheel which is OK on larger main roads but not so good on rural roads where you have little room to move within the lanes.
 
Last edited: