Watch Tesla Full Self-Driving Beta v12 autonomously look for a parking spot
A Tesla driver using the new Full Self-Driving (FSD) Beta v12 software managed to showcase a new behavior: FSD Beta autonomously looking for a parking spot.
The Tesla v12 software update is expected to introduce what CEO Elon Musk has been calling “end-to-end neural nets”. The biggest difference with previous FSD updates is that the vehicle’s controls would now be handled by neural nets rather than being coded by programmers.
It is being touted as the difference maker.
Tesla was supposed to release v12 last year, but it was delayed. The automaker started to push the update last month, but only to a few customers.
The company has yet to do a wide release of FSD Beta v12 software update, but a new version of the system was pushed to a few more owners this week.
Arthur on X was one of them and he posted an interesting video of a test drive on FSD Beta v12:
He entered a location in an alley in Sacramento, and generally, a Tesla vehicle on FSD Beta would drive to the location and stop in the street or, in this case, an alley.
But in this case, with v12, it looks like the car is autonomously looking for a parking spot.
In fact, Tesla FSD Beta appears to drive slowly through the alley in order to get to the end of the alley, where the pin was located. Once there, there was nowhere to park and instead of stopping, the vehicle updated the navigation to do another drive around the block.
As the vehicle drove back into the alley, this time it stopped earlier than the pin to pull into a parking spot.
Electrek’s Take
This is impressive behavior, especially if it’s the vehicle actually thinking. However, it’s still an anecdotal experience. What Tesla really needs with FSD Beta is data.
We have been saying for a long time, but Tesla has been completely opaque with its vehicle data and we have no evidence whatsoever that the system is getting better. Zero.
In fact, the data we have from self-reported FSD Beta testers is pretty bad.
If Tesla wants FSD to be taken seriously, it needs to start releasing disengagement data over time so that we can see the system improve… or not.
FTC: We use income earning auto affiliate links. More.
A Tesla driver using the new Full Self-Driving (FSD) Beta v12 software managed to showcase a new behavior: FSD Beta autonomously looking for a parking spot.
The Tesla v12 software update is expected to introduce what CEO Elon Musk has been calling “end-to-end neural nets”. The biggest difference with previous FSD updates is that the vehicle’s controls would now be handled by neural nets rather than being coded by programmers.
It is being touted as the difference maker.
Tesla was supposed to release v12 last year, but it was delayed. The automaker started to push the update last month, but only to a few customers.
The company has yet to do a wide release of FSD Beta v12 software update, but a new version of the system was pushed to a few more owners this week.
Arthur on X was one of them and he posted an interesting video of a test drive on FSD Beta v12:
He entered a location in an alley in Sacramento, and generally, a Tesla vehicle on FSD Beta would drive to the location and stop in the street or, in this case, an alley.
But in this case, with v12, it looks like the car is autonomously looking for a parking spot.
In fact, Tesla FSD Beta appears to drive slowly through the alley in order to get to the end of the alley, where the pin was located. Once there, there was nowhere to park and instead of stopping, the vehicle updated the navigation to do another drive around the block.
As the vehicle drove back into the alley, this time it stopped earlier than the pin to pull into a parking spot.
Electrek’s Take
This is impressive behavior, especially if it’s the vehicle actually thinking. However, it’s still an anecdotal experience. What Tesla really needs with FSD Beta is data.
We have been saying for a long time, but Tesla has been completely opaque with its vehicle data and we have no evidence whatsoever that the system is getting better. Zero.
In fact, the data we have from self-reported FSD Beta testers is pretty bad.
If Tesla wants FSD to be taken seriously, it needs to start releasing disengagement data over time so that we can see the system improve… or not.
FTC: We use income earning auto affiliate links. More.
Denial of responsibility! Techno Blender is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.