http://SmartDrivingCar.com/7.25-TruckDrivers-060819
25th edition of the 7th
year of SmartDrivingCars
W. MacNaughton, June 1, "We've all heard about the advent of Autonomous Trucking - but mostly from people who work in the tech industry. So this week, I've been visiting (and sleeping, eating and showering in) truck stops in Nevada, Utah and Idaho to hear what truck drivers themselves have to say about the future of the profession. ..." Read more Hmmmm... This is excellent. One thing that was missed... If done appropriately, (operative word here is appropriately, not really what has been done so far...) ... ""autonomy" could help me drive much more safely and really help me if it focused on reducing the stress or anxiety that driving causes me. It would really be nice if I could relax and think about something else at least some of the time when I drive. Much of driving is very simple... but very boring. Please help me do my job more safely. I'll then be fresh and really be able to handle the tough hard stuff. Do for me what automation does for pilots. I'm just as important." Alain
M. O'conner, June 5, "It has become the most natural thing to do: get in the car, type a destination into a smartphone, and let an algorithm using GPS data show the way. Personal GPS-equipped devices entered the mass market in only the past 15 or so years ???... Actually we put the first nationwide GPS system, CoPilot, on the market @ J& R Computer World in August 1997 :-) ... , but hundreds of millions of people now rarely travel without them. These gadgets are extremely powerful, allowing people to know their location at all times, to explore unknown places and to avoid getting lost.
But they also affect
perception and judgment.
When people are told
which way to turn, it
relieves them of the
need to create their own
routes and remember
them. They pay less
attention to their
surroundings. And
neuroscientists can now
see that brain behavior
changes when people rely
on turn-by-turn
directions.
In a study
published in Nature
Communications in 2017,
researchers asked
subjects to navigate a
virtual simulation of
London’s Soho
neighborhood and
monitored their brain
activity, specifically
the hippocampus, which
is integral to spatial
navigation. Those who
were guided by
directions showed less
activity in this part of
the brain than
participants who
navigated without the
device. “The hippocampus
makes an internal map of
the environment and this
map becomes active only
when you are engaged in
navigating and not using
GPS,” Amir-Homayoun
Javadi, one of the
study’s authors, told
me.
Read
more Hmmmm...
Now I know why I
can't function
anymore. :-(
Abstract of the study "Topological
networks lie at the
heart of our cities
and social milieu.
However, it remains
unclear how and when
the brain processes
topological
structures to guide
future behaviour
during everyday
life. Using fMRI in
humans and a
simulation of London
(UK), here we show
that, specifically
when new streets are
entered during
navigation of the
city, right
posterior
hippocampal activity
indexes the change
in the number of
local topological
connections
available for future
travel and right
anterior hippocampal
activity reflects
global properties of
the street entered.
When forced detours
require re-planning
of the route to the
goal, bilateral
inferior lateral
prefrontal activity
scales with the
planning demands of
a breadth-first
search of future
paths. These results
help shape models of
how hippocampal and
prefrontal regions
support navigation,
planning and future
simulation."
Alain
K. Pyle, June 7, "Could
the robotaxi model that
Tesla’s Elon Musk has
been touting be a
successful approach for
a Mobility as a Service
(MaaS) model? After some
recent first-hand
experience with the
Tesla driving
experience, MaaS
champion, Princeton’s
Dr. Alain Kornhauser
states why he believes
Musk be on the right
path. In the above
video, Kornhauser
provides an overview of
some of the innovative
human-machine research
initiated at the 2019
SmartDrivingCar Summit,
the importance of
community acceptance of
autonomous vehicles and,
at approximately 03:55,
the discussion of Tesla
as a MaaS provider.
As Kornhauser mentions,
it’s plausible to
believe that such a
service could quickly
scale to something like
2.5% of the daily U.S.
rides. As he notes in
the above interview,
that would equate to a
little more than 60% of
today’s public
transportation
ridership...." Read
more Hmmmm...
See video. Think
about it. :-)
Alain
J. Pontes, June 3,
"Tesla Model 3 sales
globally are almost
three times higher than
the second best plug-in
electric car, but BYD
remains the biggest
manufacturer so far this
year. In April, global
sales of plug-in
electric cars grew at a
slower pace than we
would hope for, but 29%
gain year-over-year is
not a bad thing either.
In total, EV Sales Blog
estimates some 166,200
sales at an average
market share of 2.1%.
Taking into
consideration the growth
of all-electric cars by
43%, the slowdown was
caused by plug-in
hybrids (again), which
now hold just 29% share
out of the overall
BEV/PHEV segment. After
four months, sales stand
at over 662,000 and 2.1%
market share. The target
for 2019 is 3.5 million
(compared to 2 million
in 2018)." Read
more Hmmmm...
17,464 is not bad,
but production is
supposed to be 5,000
per week. Hmmmm ???
Alain
M. Kane, June 3, "...
#2 Tesla Model 3 — After
a delivery peak in
March, the poster child
for electromobility has
dropped to more “normal”
performances, with Tesla
delivering 3,738 units
of its sedan in April.
Looking at individual
markets, the midsize
model was mainly
delivered in Norway (720
units), Germany (514),
the Netherlands (467),
Switzerland (492), and
Sweden (446). May seems
to be following April
performances, but expect
another Tesla tide in
June..." Read
more Hmmmm...
Enormous drop from
March. They still
lead YtD with
23,322; Renault Zoe
@15,292. Alain
S. Lekach, May 31,
"Lyft's self-driving
cars powered by Aptiv
have been picking up
passengers around Las
Vegas for the past year.
This week the autonomous
ride service hit 50,000
rides. The cars are
requested through the
Lyft app as usual, but
are clearly noted as
autonomous vehicles.
Lyft works with
self-driving company
Aptiv to offer the
service, which charges
riders the same as the
equivalent usual Lyft
ride. A safety driver is
still in the car.
At the 50,000 ride
marker, Lyft pointed out
that its self-driving
cars average a 4.97 star
rating and 92 percent of
riders gave feedback
that they felt safe
during the ride. For
most riders, this was
their first time in an
autonomous car. ..." Read
more Hmmmm...
Getting there;
however, nothing is
reported about
"disengagements".
This begins to prove
that people will
ride a computer
driven car that has
an attendant
onboard. Doesn't
say anything about
"if no attendant is
onboard". There is
essentially zero
business case for an
automated mobility
system that has an
attendant onboard.
Unfortunately, this
says nothing about
the viability of the
technology
(attendant-less)
that Lyft (and Uber)
needs to support its
current stock
price. :-(
Alain
APF, June 2, "Fourteen passengers were injured after a driverless five-car train in suburban Tokyo went in the wrong direction and crashed into a buffer stop, Japanese police said Sunday. Local media reported that some injuries – the first resulting from an accident involving an automated train in 30 years – appeared to be serious but non-life-threatening....
Compared to self-driving cars that have recently taken the road in several countries on a test basis, automated trains have a relatively long history in Japan...." Read more Hmmmm... Very unfortunate, but reality. Japan will learn from this crash, improve the "30 year old (/antiquated?)" control system and move on to create an even better and safer driverless train to serve some of Japan's mobility needs. Alain
June 9, 2018, See
video Hmmmm...
Pretty amazing.
Alain
L. Bliss, Ma7 30,
"...So, given what they
already know, city
officials are surely
taking steps to steer us
away from an
all-autonomous
gridlocked
hellscape—right? Alas,
no. According to a new
study published in the
Journal of the American
Planning Association,
very few local leaders
are working to
anticipate the effects
of self-driving cars.
And though the arrival
of these vehicles en
masse could still be
decades away, the
authors write that now
is a rare window of
opportunity for cities
to write policies that
tackle both the unwanted
effects of AVs as well
as other big civic
challenges...." Read
more Hmmmm...
At the beginning,
cities aren't a good
place for driverless
vehicles. Cities
have too much
invested in their
hopelessly poor,
hopelessly bankrupt
transit systems. No
one working in any
transit system dares
to create a
welcoming
environment to a
potential
competitor.
Communities, smaller
cities and transit
deserts are he
places to start. It
is easier
technologically and
socially. Alain
E. Garsten, June 9, "...But U.K.-based CAT Driver Training has won accreditation for a four-day course aimed at teaching engineers and others involved in testing autonomous vehicles how to do so more safely.... Launched last November, the main thrust of the Autonomous Safety Driver Training Course is centered on defensive driving,...
“How can somebody develop a system to drive safely if they have no knowledge of advanced, or defensive driving?” said Hoad. “You might need to decide when to take over, you might need to anticipate a failure or a vehicle doing something extraordinary on a roundabout that might take somebody untrained by surprise and manage not only yourself and the environment around you but the potential for the system not to behave in the way you might. Quite simply they’re learning how to evaluate road correctly, assess hazards, forward plan, observe.”..." Read more Hmmmm... Training of AV "Attendants" is absolutely necessary as may well be the training of each buyer of a Tesla with AutoPilot. Attending is all about being able to sense that the AV system is about to do the wrong thing. Once the Self-driving car starts doing the wrong thing, the attendant's "knee jerk" reaction must be able to "save the day". That is NOT easy because there is essentially zero time to think. All one can do is react. Alain
K. Korosec, June 6,
"Gatik AI, an
autonomous vehicle
startup that came out of
stealth Thursday with
$4.5 million in funding
and Walmart as a
customer, is aiming for
the sweet middle spot in
the world of logistics.
The company, which
operates out of Palo
Alto and Toronto, isn’t
deploying autonomous
delivery bots built for
sidewalks, nor is it
aiming for self-driving
trucks, or even
robotaxis to shuttle
around people. Instead,
the founders of Gatik AI
are developing a
business that will do
short hauls of goods
between businesses using
autonomous
light-commercial trucks
and vans.
The Ford transit
vehicles outfitted with
Gatik’s self-driving
system will drive up to
200 miles a day and stay
within a city
environment, co-founder
and CEO Gautam Narang
told TechCrunch.... The
company has been testing
its autonomous vehicle
technology on public
roads in California for
about 18 months...." Read
more Hmmmm...
This is
Self-driving... an
Attendant is
on-board. It is NOT
Driverless. Alain
S. Lekach,
June 1, "The exit ramp is a
long, curving slope, and you
have to make sure the
50-foot big rig you're
driving carefully navigates
the bend and doesn't fly out
of control at a high speed.
But the thing is, you're not
actually there. You're in a
room in Silicon Valley,
watching the ramp unfold in
front of you on several
screens. That heavy load
you're carrying is thousands
of miles away in Florida.
Welcome to teleoperated
driving, or
remote-controlled driving
with a human in front of a
steering wheel, brake, and
gas pedals, and a
"windshield" plastered with
monitors. It's a method that
allows autonomous vehicles
to operate without anyone
inside. Instead, there's a
watchful remote driver, or
operator, there for trickier
moments that the robo-truck
or vehicle can't
handle...." Read
more Hmmmm...
Please No!!!!!!!!! This
is NOT the right way to
do "trickier
movements". This is
total Bull. No way an
operator can perform
"trickier maneuvers"
better remotely,
than she
can do it from the
driver's seat. Please
don't even try this. If
you need a driver in
your system, put the
driver in the driver's
seat, please (unless you
are on a resupply
mission in Afghanistan
or invading Moscow. ;-))
Alain
Smebiz, June
3, "FORGET drones. The
future of deliveries may be
robo-vans.
A Chinese startup called
Neolix kicked off mass
production of its
self-driving delivery
vehicles over a week ago –
saying it’s the first
company globally to do so –
and has lined up giants such
as JD.Com Inc and Huawei
Technologies Co as
customers. Neolix expects to
deliver a thousand of the
vehicles, which resemble
tiny vans, within the first
year as it broadens out..."
Read
more Hmmmm...
Spending someone else's
money to kick off mass
production of something
is easy, but it DOESN'T
make it a REALITY in
China or anywhere else,
unless what is mass
produced actually works
safely. To my
knowledge, the hard
part... that it works
safely... has NOT been
demonstrated. Alain
D. Lerner, June 2,
"...Flying Cars Will Be Huge
And No I Haven't Lost My
Mind..." Read
more Hmmmm...
Yes you have! C'mon
Man!!! Alain
[log in to unmask]" alt="" width="130" height="73">
Professor Pascal Van Hentenryck and Alain Komhauser will discuss mathematical approaches that inform transportation policies and improve transportation networks.
F. Fishkin, May 18,, "From the 3rd Annual Princeton Smart Driving Car Summit, join Professor Alain Kornhauser and co-host Fred Fishkin. In this special edition, the summit's focus on mobility for all with guests Anil Lewis, Executive Director of Blindness Initiatives at the National Federation of the Blind and ITN America Founder Katherine Freund."
April 26, F.
Fishkin, "GM's
Cruise gets ready to
take on Google's Waymo
and its new partnership
Lyft. Meanwhile Uber's
IPO stalls and Tesla
restructures its
autopilot team. Join
Princeton's Alain
Kornhauser and co-host
Fred Fishkin for that
and more on the coming
week's Smart Driving Car
Summit."
April 26, F. Fishkin, "VW unveils an Inclusive Mobility Initiative to help make future transportation better for all...a major theme of the upcoming Smart Driving Car Summit at Princeton. The University's Alain Kornhauser and co-host Fred Fishkin tackle that...plus the latest of Uber, Tesla and more in Episode 102 of the Smart Driving Cars podcast!"
April 5, F. Fishkin, "The success of on demand transit company Via is proving that ride sharing systems can work. Public Policy head Andrei Greenawalt joins Princeton's Alain Kornhauser and co-host Fred Fishkin for a wide ranging discussion. Also: Uber, Tesla, Audi, Apple and Nuro are making headlines"
April 5, F. Fishkin, "Here comes congestion pricing in New York City...but what will it mean? Former city Taxi and Limousine Commission head and transportation expert Matthew Daus joins Princeton's Alain Kornhauser and co-host Fred Fishkin. Also...Tesla, VW and even Brexit! All on Episode 98 of Smart Driving Cars."
March 28, F. Fishkin, "The Future Networked Car? From Sweden, The Dispatcher publisher, Michael Sena, joins Princeton's Alain Kornhauser and co-host Fred Fishkin for the latest edition of Smart Driving Cars. Plus ...the Boeing story has much to do with autonomous vehicles and more. Tune in and subscribe."
F. Fishkin, Sept 6, "The coming new world of driverless cars! In Episode 55 of the Smart Driving Cars podcast former GM VP and adviser to Waymo Larry Burns chats with Princeton's Alain Kornhauser and Fred Fishkin about his new book "Autonomy: The Quest to Build the Driverless Car and How it Will Reshape Our World"
K. Conger, May 30,
"Uber’s start as a
publicly traded company
has gone from bumpy to
bumpier. In its first
earnings report since
listing its shares on the
stock market this month,
the ride-hailing giant on
Thursday reported its
slowest growth in years
and steep losses for the
first three months of
2019..." Read
more Hmmmm...
In its most basic
form, the ride hailing
business has revenue
($r) and costs ($c)
proportional to number
of rides (R). Let $r
= A*R and $c = B*R.
So Profitability (P) {
P = ($r -$c) = (A -
B) * R } is all about
(A - B) . We know
that at today's
ridership, R(now),
(A(now) -B(now)) is
negative. We also
know that as ridership
increases, new drivers
will need to be paid
more (B gets bigger),
simply because the
demand for driver
services goes up. We
also know that to
attract more riders,
revenue per ride will
necessarily go down (A
gets smaller).
Yikes... Ride-hailing
faces a double
whammy... as it scales
(gets more people to
ride) it loses even
more from the average
rider than it does
today plus that bigger
negative number gets
multiplied by a bigger
number of rides.
When
each unit incurs a
loss, making up
losses by increasing
volume is known to not
be a viable approach.
Increasing volume when
unit losses increase
with increasing volume
is really not
viable!
The only road to profitability, other than a major pivot, is to be more discriminating in who you serve... Serve fewer riders. Unfortunately, when you finally get Ridership small enough so that A-B is positive, that number gets multiplied by a smaller number of riders such that the gross amount is nowhere near sufficient to justify valuations greater than that of a lemonade stand. Uber serves about 1B trips per quarter, which means today, they loses $1/ride. To be worth $40B they need to make $1 on each of the 4B trips they serve per year. How Uber gets from a history of losing $1/ride to making $1/ride @ 4B rides/year is an open question. As is making $10/ride @ 400M rides/year? As is making $0.10/ride @ 40B rides per year? Alain
P. Loeb,
May 16, "...Sponsor
Cherelle Parker says
the cameras will
photograph any car
going more than 11
miles per hour over
the speed limit..."
Read
more Hmmmm...
I really don't
understand. What
is the meaning of
the word limit
? (Hint.... "the
utmost extent")
So
for humans a
"speed" limit is
actually a "Speed
+10" limit. That
mean I can set my
Cruise Control to
"Speed Limit" +10
and I'll be just
fine. Does that
also mean that I
can code my
driverless car "to
do +10"??? If
not, then why does
a person capable
of getting a
driver's license
get to go faster
than a person who
can't get a
driver's license
who is relegated
to be driven by an
autonomousTaxi
(aTaxi) that is
mandated to drive
at a slower
speed???? (Please
don't tell me it
is because the
accuracy of the
speed sensor is
not precise (aka
reliable enough).
May I use that
excuse in my aTaxi
code?) This is a
serious question!
There needs to be
a level regulatory
(rules of the
road/traffic laws)
playing field
established for
aTaxis and human
drivers. This is
NOT easy (but it
could be as simple
as:
SpeedLimit(aTaxi) = SpeedLimit (Humans) + 10
StopSign(aTaxi)
= SropSign(Humans)
+RollOnThrough if
no one is around
RedLight(aTaxi) = Redlight(Humans) + 3 more cars after the yellow, except in Boston where 5 more car after the yellow... Alain
A. Krok, May 2, "You
can't please all the
people all the time, but
Volkswagen wants to make
sure that when it moves
into the next era of
mobility, it won't leave
any groups behind.
Volkswagen this week
unveiled its Inclusive
Mobility Initiative,
which sees the automaker
working directly with
outside groups to ensure
that its future vehicles
are capable of catering to
people with
disabilities..." Read
more Hmmmm...This
is fantastic and may
well be in line with
the focus we've taken
with the upcoming 3rd Annual
Princeton SmartDrivingCar
Summit
10 days from now. Our
focus is on all
people who have
been marginalized by
the
unnecessary/non-inclusive/exclusive designs of our current forms of
mobility, . These
designs are especially
irresponsible when one
no longer needs a
person to drive... to
keep the car from
crashing while on its
way from where people
are to where the want
to go. What an
enormous opportunity
to be of service to so
many that for what
ever reason don't want
or can't perform that
task. Yes, there are
situations in which a
professional is
required. At times,
we all need we all
need that the help of
a professional. But
for all of those
situations in which a
professional is not
needed, we have an
enormous opportunity
to be so much more
inclusive by removing
the other unnecessary
exclusivities that
have consciously or
unconsciously crept
into our cars and
transit systems. Our
mobility systems no
longer need to be big
and hold many people
to make them
affordable, no driver
needs to be paid.
They no longer need to
be constrained to only
go between the few
places than many want
to go between at only
certain times. They
can readily serve
where only a few, even
one, want to go
between at whatever
time. The skill set
needed to use and be
served diminishes to
the skill set needed
by the easiest to use
elevator. And so on...
T. Lee. April 24, "There's an old joke in the software engineering world, sometimes attributed to Tom Cargill of Bell Labs: "the first 90 percent of the code accounts for the first 90 percent of the development time. The remaining 10 percent of the code accounts for the other 90 percent of the development time."...
You can think of
self-driving car
development as occurring
in two stages. Stage one
is focused on developing
a static understanding
of the world. Where is
the road? Where are
other cars? Are there
any pedestrians or
bicycles nearby? What
are the traffic laws in
this particular area?
Once software has
mastered this part of
the self-driving task,
it should be able to
drive flawlessly between
any two points on empty
roads—and it should
mostly be able to avoid
running into things even
on crowded roads. This
is the level of autonomy
Musk has dubbed "feature
complete." Waymo
achieved this level of
autonomy around 2015,
while Tesla is aiming to
reach it later this
year....
In this second stage, a company also needs to handle a "long tail" of increasingly unusual situations: ...Waymo has spent the last three years in the second stage...
Tesla says that's a
21-fold improvement over
the Nvidia chips the
company was using
before. Of course,
Nvidia has produced
newer chips since 2016,
but Tesla says that its
chips are more powerful
than even Nvidia's
current Drive Xavier
chip—144 TOPS compared
to 21 TOPS.
But Nvidia argues that's
not a fair comparison.
The company says its
Xavier chip delivers 30
TOPS, not 21. More
importantly, Nvidia says
it typically packages
the Xavier on a chip
with a powerful GPU
chip, yielding 160 TOPS
of computing power. And
like Tesla, Nvidia
packages these systems
in pairs for redundancy,
producing an overall
system with 320 TOPS of
computing power....
Regardless, both
companies are working on
next-generation designs,
so any advantage either
company achieves is
likely to be
fleeting....", Read
more Hmmmm...
An absolute MUST
read. Alain
M. Daus, Esq, April 1, "Over the weekend, the New York State legislature agreed to pass congestion pricing legislation as part of Governor Andrew Cuomo’s budget bill for FY 2020. The legislation was finalized in the early hours today, and the Governor is expected to sign the bill into law immediately. The toll is intended to reduce traffic congestion while raising $15 billion between 2020 and 2024 to fix NYC subways and commuter rails. Starting no sooner than December 31, 2020, motorists will be charged a toll to drive into Manhattan south of 60th street, excluding the FDR Drive and the West Side highway....
Only two categories of vehicles are specifically exempt from the law: emergency vehicles and qualifying vehicles transporting a person with disabilities. The law does not specify what qualifies as a “vehicle transporting a person with disability,” leaving any such determinations to the TBTA. A recent Bloomberg article discusses exemptions for people with disabilities (click here to review full article)..." Read more Hmmmm... Congratulations NYC!!! I've never understood why this isn't called "Value Pricing". Was it the SAE??? or is it just that I don't seem to ever like the semantics used by others? This has been a long time coming and is a tribute to William Vickery, the Canadian-born Columbia University Professor of Economics and Nobel Laureate who tragically passed away shortly after being announced as the winner of the 1996 award in Economics. AlainA. Kornhauser, March 13, "The following testimony was provided to the New Jersey State Assembly’s Transportation and Independent Authorities Committee on Monday, March 11....
What we need, what my ask is, that we create in New Jersey a “welcoming environment” for the research, testing and demonstration of this technology and work to focusing it on improving the mobility of the mobility disadvantaged...
While such a
demonstration is not
prohibited in New
Jersey, it is not
permitted.
Consequently, this
provides excuses and
hurdles to bringing such
mobility to our
communities and
tarnishes any other
welcoming efforts aimed
at enabling New Jersey
to lead instead of
follow in what may well
address the fundamental
objective of this
hearing." Read
more Hmmmm....Seems
so simple. I
have found it
so incredibly
hard. Alain
Oct 16, Establishes
fully autonomous vehicle
pilot program A4573
Sponsors: Zwicker (D16);
Benson (D14)
Oct 16, Establishes
New
Jersey Advanced
Autonomous Vehicle Task
Force AJR164
Sponsors: Benson (D14);
Zwicker (D16); Lampitt
(D6)
May 24,
"About 9:58 p.m., on
Sunday, March 18, 2018,
an Uber Technologies,
Inc. test vehicle, based
on a modified 2017 Volvo
XC90 and operating with
a self-driving system in
computer control mode,
struck a pedestrian on
northbound Mill Avenue,
in Tempe, Maricopa
County, Arizona.
...The
vehicle was factory
equipped with several
advanced driver
assistance functions by
Volvo Cars, the original
manufacturer. The
systems included a
collision avoidance
function with automatic
emergency
braking, known as City
Safety, as well as
functions for detecting
driver alertness and
road sign information.
All these Volvo
functions are disabled
when the test vehicle is
operated in computer
control..."
Read more Hmmmm....
Uber must
believe that its
systems are
better at
avoiding
Collisions and
Automated
Emergency
Braking than
Volvo's.
At least this
gets Volvo "off
the hook".
"...According
to data obtained
from the
self-driving system,
the system first
registered radar and
LIDAR observations
of the pedestrian
about 6 seconds
before impact, when
the vehicle was
traveling at 43
mph..." (=
63
feet/second)
So the system
started
"seeing an
obstacle when
it was 63 x 6
= 378 feet
away... more
than a
football
field,
including end
zones!
"...As
the vehicle and
pedestrian paths
converged, the
self-driving system
software classified
the pedestrian as an
unknown object, as a
vehicle, and then as
a bicycle with
varying expectations
of future travel
path..." (NTSB:
Please tell us
precisely when
it classified
this "object'
as a vehicle
and be
explicit about
the expected "future
travel paths." Forget
the path, please
just tell us the
precise velocity
vector that
Uber's system
attached to the
"object", then
the "vehicle".
Why didn't the
the Uber system
instruct the
Volvo to begin
to slow down (or
speed up) to
avoid a
collision? If
these paths (or
velocity
vectors) were
not accurate,
then why weren't
they accurate?
Why was the
object
classified as a
"Vehicle" ??
When did it
finally classify
the object as a
"bicycle"?
Why did it
change
classifications?
How often was
the
classification
of this object
done. Please
divulge the time
and the outcome
of each
classification
of this object. In the tests that
Uber has done,
how often has
the system
mis-classified
an object as a
"pedestrian"when the object was
actually an
overpass, or
an overhead
sign or
overhead
branches/leaves
that the car
could safely
pass under, or
was nothing at
all??
(Basically,
what are the
false alarm
characteristics
of Uber's
Self-driving
sensor/software
system as a
function of
vehicle speed
and
time-of-day?)
"...At 1.3 seconds before impact, (impact speed was 39mph = 57.2 ft/sec) the self-driving system determined that an emergency braking maneuver was needed to mitigate a collision" (1.3 x 57.2 = 74.4 ft. which is about equal to the braking distance. So it still could have stopped short.
"...According to Uber,
emergency
braking
maneuvers are
not enabled
while the
vehicle is
under computer
control, to
reduce (eradicate??) the potential
for erratic
vehicle
behavior.
..." NTSB: Please describe/define potential and erratic vehicle
behavior Also
please uncover
and divulge
the design
& decision
process that
Uber went
through to
decide that
this risk
(disabling the
AEB) was worth
the reward of
eradicating "
"erratic vehicle behavior". This
is
fundamentally
BAD design.
If the Uber
system's false
alarm rate is
so large that
the best way
to deal with
false alarms
is to turn off
the AEB, then
the system
should never
have been
permitted on
public
roadways.
"...The vehicle operator
is relied on
to intervene
and take
action. " Wow! If Uber's
system
fundamentally
relies on a
human to
intervene,
then Uber is
nowhere near
creating a
Driverless
vehicle.
Without its
own Driverless
vehicle Uber
is past "Peak
valuation".
Video similar to part of Adam's Luncheon talk @ 2015 Florida Automated Vehicle Symposium on Dec 1. Hmmm ... Watch Video especially at the 13:12 mark. Compelling; especially after the 60 Minutes segment above! Also see his TipRanks. Alain
This
list is maintained by Alain Kornhauser and hosted by
the Princeton
University
Leave
|Re-enter
[log in to unmask]" alt="imap:[log in to unmask]:993/fetch%3EUID%3E/INBOX%3E3022058?part=1.39&filename=dhbhaandkmfbffia.png" class="" width="106" height="88" border="0"> [log in to unmask]" alt="imap:[log in to unmask]:993/fetch%3EUID%3E/INBOX%3E3022058?part=1.40&filename=lglcejopfgfnajaj.png" class="" width="238" height="92" border="0">[log in to unmask]">Mailto:[log in to unmask]