22nd edition of the 10th year of SmartDrivingCars eLetter
June 15, Press release, “Today, as part of the U.S. Department of Transportation’s efforts to increase roadway safety and encourage innovation, the National Highway Traffic Safety Administration published the initial round of data it has collected through its Standing General Order issued last year and initial accompanying reports summarizing this data.
The SAE Level 2 advanced driver assistance systems summary report is available here, while the SAE Levels 3-5 automated driving systems summary report is available here. Going forward, NHTSA will release data updates monthly…” Read more Hmmmm… This is a good start; however, as NHTSA repeats many times, this is just a start and there are many “data limitations”. The most severe may well be the possibility of substantial “sampling bias“, the most severe of which is that each OEM sourced the reported data very differently. That makes the data between OEMs incomparable.
Also un reported is any measure that would enable a “crash rate” for an OEM to be determined. One only has a numerator value but no denominator value.
Finally, 392 crashes of “Level 2” cars were reported during the “10” month period of July 2021 and May 15, 2022. About 12 million vehicles are involved in traffic crashes every year among the 283 million vehicles that operate in the US. Assuming any one vehicle is unlikely to be involved in more than one crash per yer, it means that each vehicle, on average is involved in 12M/283M = 0.0424 crashes per year. Thus, if these ADAS cars were involved in crashes at the average rate, and had their ADAS on all the time, the 500 vehicle crashes per year contained in these data would expect to be generated from a fleet of only about 11,800 vehicles (or 0.0042% of the vehicles (“everything being equal”, ADAS on all the time.).
Consequently, either, …
- These system outrageously reduce crash probabilities, and/or
- maybe some, but we’re probably not much luckier.
- very few of the cars in use during that “10” month period had Level 2 capabilities, and/or
- unfortunately, the VIN number doesn’t identify these cars and only Tesla announces how many sold (I may have missed the reportings)
- very few of the drivers of those cars rarely engaged the Level 2 features, and/or
- likely. Only Tesla releases data on the utilization of its level 2 features but does so only in aggregate terms that don’t allow for correction of sampling bias associated with engagement in “easy” driving conditions versus “challenging” driving conditions.
- enormous under counting
- likely, only Tesla has the opportunity to either “know all” or sample effectively because of their OtA monitoring of its vehicles. Everyone else has conveniently kept their heads in the sand. Mercedes didn’t report any; however, during that period I think my Intelligent Cruise Control and Lane Centering were engaged when I hit a deer. Mercedes must not have been watching me, I didn’t report it and I didn’t get the memo that informed me to do anything.
Anyway. It is a start and at least to me the numbers are not startling.
What needs improvement is sourcing of the incidents. Maybe OtA should be mandated. At minimum, the VIN should specify the existence of theses capabilities. Then normal police reportings can begin to “automatically” access the “black box event recorders” (see also Accident data recorder and NHTSA) that are in most cars today. Unfortunately, privacy concerns makes this not-easy. So here we are. It wont be easy to do much better, but we should continue to try.
What the data do point out is that a substantial number of the crashes involved the rear ending of a stationary object. I have pointed out repeatedly that the source code of these systems explicitly disregard stationary objects in the lane ahead. Justifying this explicit process is that current sensors incur unacceptable false positives when trying to determine if sufficient headroom exists under detected stationary object in the lane ahead. Thus, to avoid braking in response to these rare false positives, stationary objects in the lane ahead are all assumed to be “pass under-able”.
As one drives, one encounters many stationary objects in the lane ahead. These are readily sensed and precisely located ahead. Readily sensed are overpasses, signs, tree canopies, traffic lights, … all of which can usually be readily passed under. (As can vehicles ahead that come to rest in vehicle-follower mode. These are not disregarded because one is in vehicle-follower mode.)
But when one is in vehicle-leader mode and one encounters a stationary object ahead, I believe, most, if not all “Level 2” systems disregard that object and assume the car can pass underneath. So if you are in vehicle leader mode and come over the crest of a hill to be confronted with a stopped object ahead, your system will disregard that object. Similarly, if the vehicle that you are following changes lanes forcing you to become a leader, any stationary object ahead will be disregarded. Alain
SmartDrivingCars ZoomCast Episode 272/ PodCast 272 Ed Niedermeyer
F. Fishkin, June 16, “With NHTSA releasing the data on 392 crashes involving driver assistance systems, we dive into the significance and take-aways with guest Ed #Niedermeyer, author, journalist and co-host of the #Autonocast. Join Princeton’s Alain Kornhauser & co-host Fred Fishkin for episode 272 of Smart Driving Cars.“
Technical support provided by: https://www.cartsmobility.com/
G. Laniewsky, June 17, “Plotting Each Crash on a Map We created an interactive map that shows where each accident happened and some relevant information. Tesla Autopilot is colored in red, every other manufacturer is in blue. …” Read more Hmmmm… just the beginning of our look at the data. Alain
R. Mitchell, June 15, “… But far more detail and context are required before regulators can say definitively whether such systems can outperform human drivers, or one another.
“The data may raise more questions than they answer,” NHTSA head Steven Cliff told reporters….” Read more Hmmmm… This is a beginning. While there is still a lot we don’t know, we know a lot more today than we knew before the release. Alain
A. Hawkins, June 16, “This week, for the first time ever, the National Highway Traffic Safety Administration released data on crashes involving cars equipped with advanced driver-assist systems and automated driving technology. A lot of headlines — including The Verge’s — focused on the number of Tesla vehicles that crashed, which is understandable because Tesla had a lot of crashes.
But the numbers themselves don’t tell us the whole story. In fact, they don’t really tell us much of any story at all. Not yet…” Read more Hmmmm… Yup. Alain
A. Hawkins, June 15, “.The federal government released two new reports highlighting — for the first time — crashes and fatalities involving autonomous vehicles (AV) and vehicles equipped with advanced driver-assist systems (ADAS). Tesla reported the most crashes involving driver-assist technology, while Alphabet’s Waymo disclosed the most incidents involving its autonomous vehicles.
Car and tech companies insist these technologies save lives, but more people died in auto crashes last year than in the last three decades. More data is needed to accurately determine whether these new systems are making roads safer or simply making driving more convenient..” Read more Hmmmm… Yup. Alain
N. Boudette, June 15, “…” Read more Hmmmm… The article is fine, but the headline is a non-subtle and unfair dig at Tesla and the whole sector. True, the data set was restricted to Driver-Assist Systems and reported Crashes. Consequently, these two terms are “linked”.
And hundreds were involved, but the tabloid-styled wording of the headline is insulting to the image of the “back in the day” NY Times.
If the authors wished to provide a quantitative measure for the linkage, they should have put their measure in some perspective, like … in the US there are roughly 12 million vehicles annually involved in road crashes. They could then have stated “… linked to 0.0042% of crashes” Just as accurate, much different inference by many. C’mon NY Times!!! Alain
R. Mitchell, June 2, “.Robotaxis are now a real thing in California.
On Thursday, state officials green-flagged the launch of a fare-based ride-hailing business featuring cars with no human driver at the wheel.
Robot-operated Chevy Bolt EVs will be rolled out over the next few weeks by autonomous vehicle maker Cruise. The San Francisco company, owned by General Motors, wouldn’t say how many.
With a permit from the California Public Utilities Commission, Cruise becomes the first commercial robotaxi business in the state and the second in the U.S. The first was launched in 2020 by Alphabet-owned Waymo in Chandler, Ariz…..” Read more Hmmmm… Congratulations Kyle, Mo, Carter, … Time now to come do the same in Trenton. Thank you for actively participating in the 5th Summit.😁 Alain
A. Krok, June 16, “Will the ever-increasing glut of advanced driver-assistance systems eventually claim supercars? Is there even room for exotica in a world full of sensors and onboard artificial intelligence? Ferrari sure seems to think there is.
Ferrari on Thursday unveiled its strategic plan for from now until 2026. While it’s mighty impressive that the Italian automaker intends to unveil 15 new cars over the next several years, including a hypercar and a battery-electric vehicle, it’s the mention of conditional autonomy that might be of interest to some.
“Ferrari will limit the autonomy of its cars to Level 2/Level 2 Plus, in order to preserve all the extraordinary emotions reserved for the driver,” the company said in its press release. Level 2 and Level 2 Plus include ADAS arrays that are capable of controlling the car in certain conditions, but they still require the driver’s full attention. … Read more Hmmmm… Not at all surprising. So will every other OEM including “Yugo“. As I wrote many years ago and still believe.. No way “the ultimate driving machine”, becomes “the ultimate riding machine” . Alain
Calendar of Upcoming Events