Become a MacRumors Supporter for $25/year with no ads, private forums, and more!

MacRumors

macrumors bot
Original poster
Apr 12, 2001
55,464
17,802



Apple's preliminary disengagement data for its self-driving car project surfaced yesterday pointing towards a high number of disengagements, and today, the DMV has shared the full disengagement reports from the company, providing more insight into Apple's autonomous car testing.

A disengagement report tracks the number of times an autonomous vehicle disengages and gives control back to a safety driver or the number of times the safety driver in the vehicle interferes.

lexussuvselfdriving2-800x511.jpg

Yesterday's information suggested Apple had the worst rank when it came to disengagements, but Apple has now provided details [PDF] explaining its disengagement reporting procedures and some changes that were made mid-year.

For the period between April 2017 and June 2018, Apple vehicles drove 24,604 miles autonomously and experienced 40,198 manual takeovers and 36,359 software disengagements, a number that is comparatively high based on disengagement reports from other companies.

As of July 2018, however, Apple stopped reporting its total number of disengagements and instead began focusing on "Important Disengagements," aka disengagements that might have resulted in a safety-related event (aka accident) or a violation of the rules of the road.

Using this metric, Apple vehicles have driven 56,135 miles since July 2018, with only 28 "Important Disengagements" reported. Two of these "Important Disengagements" were indeed minor collisions that weren't the fault of Apple's vehicles. One accident took place in August 2018 and the other was in October 2018.

Under Apple's revised reporting threshold, the company's cars experienced only one important disengagement every 2005 miles, compared to every 1.1 miles if the full data is counted. If other companies use similar thresholds to Apple's new standard, Apple would rank much better.

Making direct comparisons between Apple's disengagement report and the results from other companies is difficult because there is no standard for reporting disengagements. It's up to each individual company to decide what constitutes a disengagement and what disengagements need to be reported.

It is clear, though, that Apple's vehicles are in the early stages of testing, as the company says itself in a DMV cover letter.

According to Apple, safety is its "highest priority" and its approach to disengagements is "conservative" because its system is not yet able to operate in "all conditions and situations."

Apple's testing parameters require drivers to proactively take manual control of a vehicle any time the system encounters a scenario beyond its current capabilities. The vehicle itself also self-monitors and returns control back to the driver when errors or issues are encountered.

Situations where drivers take over include the appearance of emergency vehicles, construction zones, or unexpected objects in the road, as Apple's vehicles cannot self-navigate these obstacles.

The autonomous software hands over control when it can't sufficiently track an object, is unable to generate a motion plan using the path planning system, when the vehicle systems don't respond as expected, and when there are communication issues.

Apple now has more than 62 vehicles out on the road, a number that will likely ramp up in 2019 as autonomous software testing continues. Apple is required to provide annual disengagement reports to the DMV, so we'll see the company's 2019 performance in early 2020, and will be able to look for improvements.

Article Link: Apple's Self-Driving Car Performance May Not Be So Bad After All
 
  • Like
Reactions: JTBing

macduke

macrumors G4
Jun 27, 2007
11,828
16,758
Central U.S.
Good to know. Leave it up to the government to mandate something and not standardize it so the data is essentially useless. Bureaucracy at it's finest.

The autonomous software hands over control when it can't sufficiently track an object, is unable to generate a motion plan using the path planning system, when the vehicle systems don't respond as expected, and when there are communication issues.

What I want to know is when will this tech make video games better? I think this sort of path finding and response system would be great for NPCs and boss battles, or even things like horses that shouldn't stupidly run into a tree while you ride them.
 

trifid

macrumors 68020
May 10, 2011
2,046
4,885
Apple Maps is not industry leader.

Siri is not industry leader.

If Apple can't lead on these, trying to twist the disengagement stats and trying to put Apple in a better light is not going to help anyone.

Stop dismissing the signs, Apple needs a huge wake up call, switch up management, bring in new blood that has the tenacity and drive that Steve Jobs had, make Apple great again.
 
Last edited:

Amacfa

macrumors 68000
May 22, 2009
1,923
4,170
D.C.
Apple Maps is not industry leader.

Siri is not industry leader.

If Apple can't lead on these, trying to twist the disengagement stats and trying to put Apple in a better light is not going to help anyone.

Stop dismissing the signs, Apple needs a huge wakeup call, switch up management, bring in new blood that has the tenacity and drive that Steve Jobs had, make Apple great again.

Somebody needs a wake up call and it isn’t Apple
 

julesme

macrumors 6502
Oct 14, 2016
465
1,644
San Jose
The iCar is somewhere in the middle on an apples to apples basis (obviously behind Waymo, for example).

But no way they are dead last amid a field of tech also-rans, as the previous figures suggested!
 

thasan

macrumors 65816
Oct 19, 2007
1,097
1,027
Germany
Apple Maps is not industry leader.

Siri is not industry leader.

If Apple can't lead on these, trying to twist the disengagement stats and trying to put Apple in a better light is not going to help anyone.

Stop dismissing the signs, Apple needs a huge wakeup call, switch up management, bring in new blood that has the tenacity and drive that Steve Jobs had, make Apple great again.

Question: How do you know Apples disengagement is worse than Googles?
 

Doctor Q

Administrator
Staff member
The statistic I'd be most interested in is the number of accidents or near-accidents for a self-driving car versus the number for a comparable number of miles driven in a regular car by an average driver.

I don't expect that self-driving cars will ever be absolute perfect, but I'd like to know when they're better, on average, than we humans are.
 

Hanson Eigilson

macrumors regular
Sep 19, 2016
222
217
For the period between April 2017 and June 2018, Apple vehicles drove 24,604 miles autonomously and experienced 40,198 manual takeovers and 36,359 software disengagements, a number that is comparatively high based on disengagement reports from other companies.
hmm, the real eye-opener here seems to me that they only drove 24604 "autonomous" miles in the 61 days between April 2017 and June 2018, that's 403 miles a day, or at an average of 40mph Apple's autonomous car program has an average of 10 hours a day of autonomous car time a day. For the entire program.
Wonder if this is another program with 20 efficiency experts, 30 media experts, 40 HR consultants 100 bosses, 5 actual engineers and 2 "unskilled technicians" from Apple.

EDIT:
actually it's 2 different years, so my math is wrong and the average hours a day an apple selfdriving car is on the road for autonomous tests is down to 57 miles a day, or just 1.5 hours of testing a day on average, insane.
 
Last edited:

brofkand

macrumors 6502a
Jun 11, 2006
689
1,348
hmm, the real eye-opener here seems to me that they only drove 24604 "autonomous" miles in the 61 days between April 2017 and June 2018, that's 403 miles a day, or at an average of 40mph Apple's autonomous car program has an average of 10 hours a day of autonomous car time a day. For the entire program.
Wonder if this is another program with 20 efficiency experts, 30 media experts, 40 HR consultants 100 bosses, 5 actual engineers and 2 "unskilled technicians" from Apple.

check your math - there are way more than 61 days between April 2017 and June 2018.
 
  • Like
Reactions: Hanson Eigilson

Chrjy

macrumors 6502a
May 19, 2010
952
1,523
UK
I presume the reversing cameras on the top of the vehicle in the photo will be an optional extra!!
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.