Are Tesla's Data-Gathering Cars Secretly Improving Autopilot's Algorithms?


IT Security Nachrichten vom | Direktlink: tech.slashdot.org

"When the history of autonomous cars is written, the winner will be Tesla," speculates long-time technology pundit Robert Cringely. "Heck, I think they've already won." But his article includes a disclaimer that it's "based pretty much on logic, not knowledge, which is to say I might again be too frigging stupid to read, much less write." Tesla has more than a million data-gathering devices on the roads. We call them cars. Tesla cars have no LIDAR but they have eight cameras and RADAR. Every night all those cars wirelessly report their driving data back to Tesla. I would love to know how Tesla decided what to put in those reports. Given the limited bandwidth LTE connection involved, it can't be a complete data dump. They have to pick and choose what to report. And what does Tesla do with the reports? I think it comes down to algorithms, mapping, and exceptions. They are logically trying to improve their algorithms, improve their maps, but mainly — after having already parsed billions of miles of driving data — they are looking for exceptional events that are testing their algorithms in ways never seen before... Tesla has a dual processor system in their cars — two completely distinct computers. Why...? Because every night is an A-B test for Tesla — a test that is running on your car. One processor is driving the car (or following the driver's actions if Autopilot isn't being used, which is most of the time) with production software while the second processor is running beta software, simulating the drive, and noting discrepancies between the two software versions. Multiply this times a million cars per night. Whether Autopilot is used or not doesn't matter: the evolution of the software continues. And it's finished when the beta software stops improving and the outcome shows the only difference between human and Autopilot driving is that Autopilot does it better. Continue for another month or year or decade just to confirm your results, then announce that full autonomous mode is available. That is exactly where I believe Tesla has been heading for as long as those two-processor cars have been on the road. Tesla's autonomous driving software could be ready right now for all we know. Elon certainly hints at this from time to time in his tweets. And THAT's why I believe Tesla has already won the autonomous driving war, because they have real cars facing real exceptions that you won't find in a simulation, and their dual processor system knows what it knows. Yes, I reached out to Tesla about this last week. They still haven't replied. Again, Cringely wants that this is "based pretty much on logic, not knowledge, which is to say I might again be too frigging stupid to read, much less write."

Read more of this story at Slashdot.

...

Externe Quelle mit kompletten Artikel anzeigen

https://tech.slashdot.org/story/20/09/20/1810218/are-teslas-data-gathering-cars-secretly-improving-autopilots-algorithms?utm_source=rss1.0mainlinkanon&utm_medium=feed
Zur Startseite

➤ Weitere Beiträge von Team Security | IT Sicherheit

Are Tesla's Data-Gathering Cars Secretly Improving Autopilot's Algorithms?

vom 406.1 Punkte ic_school_black_18dp
"When the history of autonomous cars is written, the winner will be Tesla," speculates long-time technology pundit Robert Cringely. "Heck, I think they've already won." But his article includes a disclaimer that it's "based pretty much on logic, not

Diving Deep Into a Pwn2Own Winning WebKit Bug

vom 373.63 Punkte ic_school_black_18dp
Pwn2Own Tokyo just completed, and it got me thinking about a WebKit bug used by the team of Fluoroacetate (Amat Cama and Richard Zhu) at this year’s Pwn2Own in Vancouver. It was a part of the chain that earned them $55,000 and was a nifty piece of

CVE-2020-0932: Remote Code Execution on Microsoft SharePoint Using TypeConverters

vom 294.56 Punkte ic_school_black_18dp
In April 2020, Microsoft released four Critical and two Important-rated patches to fix remote code execution bugs in Microsoft SharePoint. All these are deserialization bugs. Two came through the ZDI program from an anonymous researcher: CVE-2020-0931

Tesla Autopilot Crisis Deepens With Loss of Third Autopilot Boss In 18 Months

vom 275.57 Punkte ic_school_black_18dp
An anonymous reader quotes a report from Ars Technica: It is no secret that Tesla's Autopilot project is struggling. Last summer, we covered a report that Tesla was bleeding talent from its Autopilot division. Tesla Autopilot head Sterling Anderson quit

There's Growing Evidence Tesla's Autopilot Handles Lane Dividers Poorly

vom 271.29 Punkte ic_school_black_18dp
An anonymous reader writes: Within the past week, two Tesla crashes have been reported while Autopilot was engaged, and both involved a Tesla vehicle slamming into a highway divider. One of the crashes resulted in the death of Walter Huang, a Tesla customer

CVE-2020-0729: Remote Code Execution Through .LNK Files

vom 244.83 Punkte ic_school_black_18dp
In this excerpt of a Trend Micro Vulnerability Research Service vulnerability report, John Simpson and Pengsu Cheng of the Trend Micro Research Team detail a recent remote code execution bug in Microsoft Windows .LNK files. The following is a portion of

Report That Tesla Autopilot Cuts Crashes By 40% Called 'Bogus'

vom 243.93 Punkte ic_school_black_18dp
Remember when America's National Highway Traffic Safety Administration reported Tesla's Autopilot reduced crashes by 40%? Two years later the small research and consulting firm Quality Control Systems (QCS) finally obtained the underlying data -- and

ConstraintLayout 2.0.0 beta 7

vom 225.71 Punkte ic_school_black_18dp
We are happy to announce the release of ConstraintLayout 2.0 beta 7. It’s available from the google maven repository:dependencies {    implementation 'androidx.constraintlayout:constraintlayout:2.0.0-beta7'}or if using the android.support packages:dependencies {    implementation 'com.android.support.constraint:constraint

Deobfuscating/REversing Remcos - AutoIt, Shellcode, and RunPE

vom 204.03 Punkte ic_school_black_18dp
Remcos is a robust RAT actively being used in the wild. This multi-staged/evasive RAT provides powerful functionality to an attacker. Each stage is written in a different language: AutoIt -> Shellcode -> C++. I wanted to explore both the evasiven

ConstraintLayout 2.0.0 beta 2

vom 201.48 Punkte ic_school_black_18dp
We are happy to announce the release of ConstraintLayout 2.0 beta 2. It’s available from the google maven repository: dependencies {    implementation 'com.android.support.constraint:constraint-layout:2.0.0-beta2'} or if using the AndroidX packages: dependencies {    implementation 'androidx.con

Pwn2Own Returns to Vancouver for 2020

vom 196.4 Punkte ic_school_black_18dp
Jump to the contest rules As each new year starts, we at the Zero Day Initiative begin to think of spring and the Vancouver edition of the Pwn2Own contest. It was in Vancouver where the contest began back in 2007 and continues to be where we push the

ConstraintLayout 2.0.0 beta 5

vom 191.28 Punkte ic_school_black_18dp
We are happy to announce the release of ConstraintLayout 2.0 beta 5. It’s available from the google maven repository:dependencies {    implementation 'androidx.constraintlayout:constraintlayout:2.0.0-beta5'}or if using the android.support packages:dependencies {    implementation 'com.android.support.constraint:constraint

Team Security Diskussion über Are Tesla's Data-Gathering Cars Secretly Improving Autopilot's Algorithms?