New cars can stay in their lane—but might not stop for parked cars

TheSteelRider

Well-Known Member
Joined
Dec 31, 2019
Threads
56
Messages
1,135
Reaction score
2,007
Location
United States
Vehicles
'21 Premium RWD
Country flag
This is an interesting research study conducted by AAA about the ability (or lack thereof) of driver assistance technology to avoid certain non-moving hazards. I thought the article and paper were interesting because they seem to indicate Cadillac's Super Cruise was one of the better performing systems with respect to having to intervene when highway cruising, and I am of the understanding that Ford's Co-Pilot Assist is said to be most similar to Super Cruise.

Article: https://arstechnica.com/cars/2020/0...heir-lane-but-might-not-stop-for-parked-cars/
AAA Research Paper: http://media.acg.aaa.com//content/1...eport - Evaluating ADA (FINAL 7-13-20)(1).pdf


New cars can stay in their lane—but might not stop for parked cars
Drivers complain of need for “constant monitoring and intervention.”
TIMOTHY B. LEE - Friday at undefined

AAA_testing-800x557.jpg

Enlarge / A test vehicle collides with a dummy car at a AAA test track in California.

In recent years, a number of car companies have—like Tesla—begun offering driver assistance systems that offer lane-keeping as well as adaptive cruise control. This might seem like a big step toward a "self-driving car," since a system like this can travel down the freeway for miles without human intervention. But a new report from AAA underscores the limitations of these systems.
Its most dramatic finding: the advanced driver-assistance systems (ADAS) on the latest cars still struggle to avoid collisions with parked vehicles. They tested cars from BMW, Kia, and Subaru; none consistently avoided running into a fake car partially blocking the travel lane.
The researchers also examined the ADAS in the Cadillac CT6 and the Ford Edge, but these cars' systems weren't included in the parked-vehicle test because their driver assistance systems wouldn't engage on AAA's closed course. They were included in other tests conducted on public highways.
"All test drivers reached a general consensus that combining adaptive cruise and lane-keeping functionalities in a single system did not consistently enhance the driving experience," the report said. The vehicles made mistakes often enough that drivers often found the experience nerve-wracking rather than relaxing.
Greg Brannon, a co-author of the AAA report, argues that a fundamental challenge with this kind of system is the need to maintain alertness. Human beings are terrible at paying continued attention behind the wheel of a car that mostly drives itself. So when (not if) these vehicles make a mistake, there's a heightened risk that the driver won't be paying close enough attention to recover safely.
Why ADAS systems keep hitting parked cars
aaa2-640x450.jpg
Enlarge


You might think that cars with adaptive cruise control or emergency braking capabilities would be able to stop for parked cars and other obstacles in the roadway. But often they fail to do so. To see why, it's helpful to understand a bit about how these systems work.
Most of the early adaptive cruise control systems sold 10 to 20 years ago were based on radar. And as we explained two years ago, radar has some important limitations:
Radar has low angular resolution, so it had only a crude idea of the environment around the vehicle. What radar is quite good at, however, is figuring out how fast objects are moving. And so a key strategy for making the technology work was to ignore anything that wasn't moving. A car's radar will detect a lot of stationary objects located somewhere ahead of the car: these might be trees, parked cars, bridges, overhead signs, and so forth.
These systems were designed to work on controlled-access freeways, and, in the vast majority of cases, stationary objects near a freeway would be on the side of the road (or suspended above it) rather than directly in the car's path. Early adaptive cruise control systems simply didn't have the capability to distinguish the vast majority of objects that were near the road from the tiny minority that were on the road.
So cars were programmed to focus on maintaining a safe distance from other moving objects—cars—and to ignore stationary objects. Designers assumed it would still be the job of the human driver to pay attention to the road and intervene if there was an obstacle directly in the roadway.
Today's driver assistance systems are more sophisticated than early systems that came on the market 10 or 20 years ago. They're no longer just radar-based; most have cameras, and, presumably, they try to use both radar and cameras to identify potential objects in the road ahead.
FURTHER READING
Why emergency braking systems sometimes hit parked cars and lane dividers
And indeed, the newest cars do seem to do better on this score than past systems. The best system AAA tested in this respect was a 2020 Subaru Outback. AAA performed three test runs on the Outback with a starting speed of 30 miles per hour. The vehicle stopped in two out of three test runs. In the third run, the vehicle at least slowed down before striking the dummy car.
On the same test, a 2019 BMW X7 stopped in one out of three runs, while a 2020 Kia Telluride hit the dummy vehicle in all three 30mph runs. Both cars decelerated somewhat prior to impact in the other runs.
In other words, all three vehicles have some capacity to detect imminent collisions and at least mitigate them—which represents an improvement over early radar-based systems. But none of them was sophisticated enough to consistently prevent crashes with parked cars.
Tesla Autopilot isn’t the only system struggling with parked vehicles
GettyImages-1182783513-640x427.jpg
Enlarge
/ A Tesla Model S driving on the freeway in Silicon Valley.
Andrei Stanescu / Getty

This provides a bit of vindication for fans of Tesla, which has gotten the most media attention for this kind of ADAS failure. At least three Tesla owners have died when Autopilot crashed into a concrete lane divider (in one case) or a semi crossing the road (in two others). Several other Tesla cars have had non-fatal crashes into parked police cars or fire trucks. AAA's tests make it clear that this isn't a problem that's limited only to Tesla vehicles.
FURTHER READING
“I was just shaking”—new documents reveal details of fatal Tesla crash
I asked AAA's Greg Brannon if he knew of ADAS-related crashes involving other car brands; he said he didn't. It's not clear why. Perhaps Autopilot has simply been on the market longer. Or maybe Tesla crashes get more media coverage, and crashes involving other automakers have flown under the radar. Brannon noted that the National Transportation Safety Board has investigated several fatal crashes involving Tesla vehicles using Autopilot. The agency doesn't seem to have conducted any investigations involving other carmakers' ADAS technology.
That may change in the coming years as other companies sell more and more cars with Autopilot-like capabilities—since other car models seem to have the same basic limitation as Tesla's Autopilot.
Highway performance
Dash-View-from-Inside-Test-Vehicle-640x360.png
Enlarge


The parked car test was the most clear-cut failure of these ADAS systems. But AAA's testing went far beyond that scenario. On its closed course, AAA tested whether the Subaru, BMW, and Kia vehicles could stay in their lanes and respond when a vehicle ahead hit the brakes. All three cars handled these situations with little difficulty. (Again, cars from GM and Ford had geofences that prevented the ADAS from engaging.)
The researchers also performed qualitative testing of the five cars' performance on public highways. Over 800 miles of testing, drivers in the BMW, Ford, Kia, and Subaru cars intervened dozens of times—most often because the vehicle seemed to be drifting out of its lane.
FURTHER READING
The Cadillac CT6 review: Super Cruise is a game-changer
Cadillac's Super Cruise was different. Its drivers intervened only eight times in 800 miles of driving over concerns that the vehicle wasn't staying in its lane properly. However, the system seemed overly conservative about proactive disengagement. There were 37 times when Super Cruise had "unexpected or erroneous system disengagements."
"Test drivers were sometimes taken by surprise and were required to retake full control in the middle of critical situations with little to no advance notice," the AAA report says.
Super Cruise is different from most other driver assistance systems because it uses a user-facing camera to ensure drivers are paying attention. (Subaru has a similar system called DriverFocus, but Brannon said drivers saw little indication the camera was being used.) The Cadillac's camera monitored the driver's eyes and tried to estimate whether the driver was paying attention to the road. AAA found that this system was far from perfect; on a number of occasions, Super Cruise forced the driver to take over because it wrongly thought the driver wasn't paying attention.
All that said, there's a lot to be said for Cadillac's approach, which we've praised before. Super Cruise is conservative about its own capabilities, handing back control to the driver at the first sign of trouble. This not only minimizes the chances that the system itself will make a mistake, it may also prompt drivers to pay closer attention to what the vehicle is doing.
“Constant monitoring and intervention”
Dash-View-of-System-Alert-640x360.png
Enlarge


By contrast, AAA found the Kia Telluride allowed users to go as long as two minutes without touching the steering wheel. Even worse, dashboard indicators were "easy to miss due to inconspicuous icons," creating the risk that drivers could become confused about whether the ADAS was active.
The Subaru Outback would "frequently issue a lane departure warning while disengaging simultaneously." This would sometimes occur on a sharp curve, creating a heightened risk of a crash if the driver didn't take control quickly.
Ultimately, none of these systems earned rave reviews from AAA's drivers. Drivers reported that the systems "could sometimes increase perceived driver workload because constant monitoring and intervention in many cases was required."
This may be a fundamental problem with this approach to driver assistance technology. The ADAS is supposed to do most of the driving, but the human driver is supposed to still monitor the system and make sure it doesn't make mistakes. But our brains aren't wired for this level of monotony. Monitoring a system that works correctly 99 percent of the time is in some ways harder—not easier—than just driving the car yourself. And monitoring a system that works correctly 99.9 percent of the time is even harder, because it's that much easier for our brains to get distracted by something else.
 

portlandg

Well-Known Member
First Name
grahame
Joined
Mar 17, 2020
Threads
7
Messages
2,913
Reaction score
3,660
Location
Dorset UK
Vehicles
Black RWD ER and loving it
Occupation
Cabinet maker
Country flag
The clue is in the name of the system. They are driver ASSISTANCE systems. They DON'T take over control of the car. The driver should always be attentive and in control and be ready to overide the system when needed.
 

KAustin

Well-Known Member
Joined
Apr 14, 2020
Threads
24
Messages
1,254
Reaction score
1,555
Location
WDC
Vehicles
Kia Telluride
Country flag
I have a Telluride and love it, but I would trust it to "drive" for me. I use the the ADAS system on long trips. It works well. Yes, you have to pay attention. Automation doesn't absolve you of responsibility.
 

macchiaz-o

Well-Known Member
First Name
Jonathan
Joined
Nov 25, 2019
Threads
168
Messages
8,157
Reaction score
15,299
Location
🔑 ]not/A/gr8'Place.2.store-mEyePassword[ 👀
Vehicles
MY21 J1 Premium RWD SR
Country flag
The clue is in the name of the system. They are driver ASSISTANCE systems. They DON'T take over control of the car. The driver should always be attentive and in control and be ready to overide the system when needed.
Yep.

It's disappointing that AAA fails to notice the naming distinction between "autopilot/FSD" and "assist" systems. Inappropriately named systems can lead the public to believe that the ADAS is capable of driving without human supervision. And this increases risks of accidents, potentially including hurting or killing people outside of the errant vehicle.

Consumer Reports gets it.

We like that Ford doesn’t seem to be overselling the system’s capabilities to customers, because the word "assist" is part of its name; it doesn't imply it can take care of the entire task of driving for you.
IIHS, representing auto insurance companies, also gets it.

The IIHS study released Thursday questioned more than 2,000 people about the names used by five automobile companies to market systems intended to relieve driver stress and improve safety, and its results indicated that names such as Tesla’s Autopilot create consumer confusion about how much attention a driver really has to pay. The other technologies covered in the study are Audi and Acura Traffic Jam Assist, Cadillac Super Cruise, BMW Driving Assistant Plus and Nissan ProPilot Assist. (The automakers’ names were not mentioned in the study.)

Autopilot created the most confusion among study respondents. Nearly half — 48% — thought it would be safe to take hands off the steering wheel when using the system. The Tesla manual says the driver should hold the wheel at all times, and — when used as intended — Autopilot warns drivers if they do not. Only 21% to 33% of study respondents thought (incorrectly) that it would be safe for a driver to take hands off the wheel when using the other driver-assist systems.
 

Kamuelaflyer

Well-Known Member
Joined
Feb 18, 2020
Threads
9
Messages
7,924
Reaction score
15,846
Location
Hawaii
Vehicles
2021 Premium Infinite Blue. ER AWD. 2020 Raptor
Country flag
In the airline business, we had some wonderfully capable autopilots. They could take a 500,000 lbs aircraft from altitude to a stop in zero visibility with little to no input from the pilots once it was setup. We still had to actively monitor the system and maintain situational awareness throughout. Sort of the same thing should be done in a car.
 


macchiaz-o

Well-Known Member
First Name
Jonathan
Joined
Nov 25, 2019
Threads
168
Messages
8,157
Reaction score
15,299
Location
🔑 ]not/A/gr8'Place.2.store-mEyePassword[ 👀
Vehicles
MY21 J1 Premium RWD SR
Country flag
In the airline business, we had some wonderfully capable autopilots. They could take a 500,000 lbs aircraft from altitude to a stop in zero visibility with little to no input from the pilots once it was setup. We still had to actively monitor the system and maintain situational awareness throughout. Sort of the same thing should be done in a car.
This all sounds reasonable to me. Except for calling an ADAS suite on a road vehicle driven by normal (barely trained) consumers "autopilot."

Did you undergo rigorous pilot training, and receive professional training on the capabilities and operational domain limitations of aircraft autopilot?

I'm not too concerned about autopilot in airplanes, or the term autopilot in that context. I've got the impression that pilots who know how to enable that function are fully aware of their own professional responsibilities. And the operational domain seems to be fairly well defined compared to surface streets and highways.

Sometimes when I talk to friends with Teslas, or nearly anytime I dip into Tesla Twitter, it makes me think that they've mentally carried their notions of airplane autopilot, with its high level of automation and safety standards, into Tesla "self driving."

In the MCU, and in the owners manual, Tesla warns drivers that they must drive -- meaning, always be attentive and ready to take over with little to no notice.

Yet at the same time, Tesla encourages overconfidence in an only-sometimes capable vehicle. They name features Full Self Driving, and their executives boast that the vehicles are "intelligent," using buzzwords like deep neural network. This is PT Barnum level crap. They've wrongly convinced some Tesla owners to think their vehicle is a better driver than they can ever be.

At best, this corporate leadership behavior is childish and irresponsible. At worst, people will die. And maybe it's hard to know for sure, but it sure seems like several of the deaths and accidents that have already occurred were related to an over trust of Autopilot.
 
Last edited:

Kamuelaflyer

Well-Known Member
Joined
Feb 18, 2020
Threads
9
Messages
7,924
Reaction score
15,846
Location
Hawaii
Vehicles
2021 Premium Infinite Blue. ER AWD. 2020 Raptor
Country flag
This all sounds reasonable to me. Except for calling an ADAS suite on a road vehicle driven by normal (barely trained) consumers "autopilot."

Did you undergo rigorous pilot training, and receive professional training on the capabilities and operational domain limitations of aircraft autopilot?

I'm not too concerned about autopilot in airplanes, or the term autopilot in that context. I've got the impression that pilots who know how to enable that function are fully aware of their own professional responsibilities. And the operational domain seems to be fairly well defined compared to surface streets and highways.

Sometimes when I talk to friends with Teslas, or nearly anytime I dip into Tesla Twitter, it makes me think that they've mentally carried their notions of airplane autopilot, with its high level of automation and safety standards, into Tesla "self driving."

In the MCU, and in the owners manual, Tesla warns drivers that they must drive -- meaning, always be attentive and ready to take over with little to no notice.

Yet at the same time, Tesla encourages overconfidence in an only-sometimes capable vehicle. They name features Full Self Driving, and their executives boast that the vehicles are "intelligent," using buzzwords like deep neural network. This is PT Barnum level crap. They've wrongly convinced some Tesla owners to think their vehicle is a better driver than they can ever be.

At best, this corporate leadership behavior is childish and irresponsible. At worst, people will die. And maybe it's hard to know for sure, but it sure seems like several of the deaths and accidents that have already occurred were related to an over trust of Autopilot.
Nah got it out of a cracker jacks box. Or so some of the people who gave me check rides over the years thought. ;)

No seriously, your point is well taken. And personally I hate calling any form of driving assistance "autopilot." It's not, and it misses by a long shot. In addition, the tolerances in driving are, frankly, a lot tighter than in flying. I might have 30 feet laterally to work with on a CAT 3 (0-0 auto-landing) approach before I have to abort the approach. You have less than 10% of that in a car trying to decide if a lane change is safe. Yes, I have a lot of mass and really fast landing speeds, but I'm not inches from a collision either.

And yes, initial training for about a month (or longer) on each type of aircraft and then training every 6 months which includes the auto lands. Imagine the same level of training before you could even drive a Mach-e. Yeah, "autopilot" should never be used as a name when it comes to equipment on a car.
 

ChasingCoral

Well-Known Member
First Name
Mark
Joined
Feb 3, 2020
Threads
376
Messages
12,403
Reaction score
24,517
Location
Maryland
Vehicles
GB E4X FE, Leaf, Tacoma, F-150 Lightning ordered
Occupation
Retired oceanographer
Country flag
Nah got it out of a cracker jacks box. Or so some of the people who gave me check rides over the years thought. ;)

No seriously, your point is well taken. And personally I hate calling any form of driving assistance "autopilot." It's not, and it misses by a long shot. In addition, the tolerances in driving are, frankly, a lot tighter than in flying. I might have 30 feet laterally to work with on a CAT 3 (0-0 auto-landing) approach before I have to abort the approach. You have less than 10% of that in a car trying to decide if a lane change is safe. Yes, I have a lot of mass and really fast landing speeds, but I'm not inches from a collision either.

And yes, initial training for about a month (or longer) on each type of aircraft and then training every 6 months which includes the auto lands. Imagine the same level of training before you could even drive a Mach-e. Yeah, "autopilot" should never be used as a name when it comes to equipment on a car.
I agree with where @macchiaz-o was going in his post as well as @Kamuelaflyer here. Just think of the required trining for the automotive systems (none) vs. the intensive training to each aircraft for pilots. Now let's think of the analogy in a plane: what if you had a radically different design in aircraft automation and assumed minimal training was needed (an hour on an iPad for example). The result is the Boeing 737 Max. We all know how well that's gone.

There's a good reason why Level 5 automation is really hard. It has to be really good to take the driver out of the equation.
 

JamieGeek

Well-Known Member
Joined
Dec 29, 2019
Threads
82
Messages
3,556
Reaction score
6,746
Location
Southeastern Michigan
Website
spareelectrons.wordpress.com
Vehicles
Mach-E, old: Bolt, C-Max Energi, Focus Electric
Country flag
Hmmm ya think there is a reason we don't have flying cars by now?? LOL (er apart from the huge physics/energy draw problem LOL).
 

zhackwyatt

Well-Known Member
Joined
Dec 18, 2019
Threads
14
Messages
1,603
Reaction score
2,616
Location
Arizona
Vehicles
'21 InfBlu Prem MMEx Past: '13 C-Max '98 Explorer
Country flag
Yep.

It's disappointing that AAA fails to notice the naming distinction between "autopilot/FSD" and "assist" systems.
Isn't the whole point of the AAA study to point out the flaws in the current system?
 

macchiaz-o

Well-Known Member
First Name
Jonathan
Joined
Nov 25, 2019
Threads
168
Messages
8,157
Reaction score
15,299
Location
🔑 ]not/A/gr8'Place.2.store-mEyePassword[ 👀
Vehicles
MY21 J1 Premium RWD SR
Country flag
Isn't the whole point of the AAA study to point out the flaws in the current system?
Yeah that's what I mean. They pose the question "Why are ADAS related accidents far more likely with Tesla?" and they try to answer it but make barely any effort and just leave it out there unanswered.
Sponsored

 
 




Top