E. Behrman,
June 4, "Three
decades ago,
an
experimental
Mercedes-Benz
van managed to
steer, brake
and accelerate
on its own.
But after the
technology was
refined enough
to put an
S-Class sedan
through its
paces on a
highway around
Paris in 1994,
it was largely
set aside as
commercially
unviable.
Now, the
prospect of
autonomous
vehicles is
threatening to
upend the auto
industry, and
instead of an
enviable head
start,
Mercedes is
just part of
the pack in
the race to
roll out
robo-cars....In
2015, he
unveiled the
futuristic
self-driving F
015 concept
car and
prodded
developers by
moving forward
targets for
introducing
the technology
several
times in
recent
years,..." Read more Hmmmm...
Unfortunately,
there really
isn't much
more to read.
Mercedes is at
best only
doing
Self-driving
and not doing
that well
because they,
unlike Tesla,
have not
embraced their
customers. As
I've written,
I purchased a
2014 S-550
with the 997
package that
gives me 7
seconds of
"self-driving",
a "1st of its
kind" 3 years
ago. In those
3 years, has
MB reached out
to me and
asked for any
feedback, no!
Have they
"over-the-air
updated" the
really
marginal
lane-centering
control
system, no!
(They haven't
even done
anything in
the pricy
major service
visits.) Have
they corrected
the,
enormously
unsafe in my
opinion,
turning off
the
intelligent
cruise control
(ICC) braking
function
simply because
I tapped the
brakes, no!
(Why did they
interpret that
as signal that
I want to
disengage the
ICC braking
function? A
signal that I
want to turn
off the
acceleration
function,
yes!: braking
function,
no!!! (Oh just
because this
is a way one
turned off the
whole system
when it was
stupid cruise
control was
NOT the proper
interpretation
of my action
at that time,
either. I
wanted the
acceleration
function
turned off!
Just because
that was the
only function,
therefore you
simply turned
everything
(one thing)
off should NOT
be taken as a
"turn
everything off
signal" from
the driver.
Please!!!!
Has all of
this been
fixed? I
don't know. I've
given up on MB
and there is
nothing in
this article
that suggests
that MB has
any viable
plans to
"recapture its
early lead" in
Self-driving.
There is
also no hint
that they are
really serious
about
Driverless
because they
remain focused
on the 1%ers
buying what
they make
using their
100+ year old
business
model. :-(
Alain
A. Hawkins,
June 6, "Lyft
announced a
new
partnership
today with
Boston-based
self-driving
car startup
NuTonomy to
eventually put
“thousands” of
on-demand,
autonomous
vehicles on
the road. In
the meantime,
the two
companies said
they intend to
launch a
limited pilot
in Boston
within the
next few
months, in
which Lyft
users will be
able to hail
one of
NuTonomy’s
driverless
vehicles by
using Lyft’s
app..." Read
more Hmmmm... The benefit to
Lyft is that
it responds to
what Uber has
been doing
(which may
just be a
publicity
stunt).
"Self-driving"
has little if
any value to
Lyft, Uber or
... Today,
these vehicles
are more
expensive and
require
trained
drivers, not
something that
tends to exist
in the "Gig
economy".
The benefit to NuTonomy is that its technology gets
a customer
(who is
picking up the
tab is ???)
and automated
driving
systems get to
experience
more miles. Miles
are of some
importance but
not really.
Most miles are
repetitive and
in a sense
very
"boring".
"every"
automated
driving system
can drive them
safely. The
issue is
finding the
situations,
likely
spanning very
short
distances,
feet not
miles, that
are rare and
present
challenges to
automated
driving
systems. The
main issue is
how to
experience
these rare
situations
where the
automated
systems are
challenged and
capture the
data that can
be used to
"fill these
holes" (called
'corner
cases") in the
automated
driving
algorithms.
One could just
happen to
"trip over
them" and
that's the
benefit of
accumulating a
lot of
miles... maybe
you'll
encounter one,
two or a few
and that
experience
will be really
valuable in
one's efforts
to continue to
improve the
safety of
automated
driving
systems.
Consequently
the
partnership
between Lyft
and NuTonomy
helps
NuTonomy's
algorithm
experience
more miles and
possibly
uncover some
important
corner cases.
There
are of course
other ways to
also
accumulate
such
information
using even
more
aggressive
crowd
sourcing.
MobilEye has
its cameras
and other
sensors on
numerous cars,
as has Tesla,
Mercedes, BMW,
Volvo and
others. These
systems could
be and
hopefully are,
recording and
preserving the
few minutes or
even just
seconds before
and after
every crash or
near crash
that they are
experiencing.
This is the
really
valuable
experience and
"feet" that
need to be
captured and,
in my opinion,
shared among
everyone in
the field..
NuTonomy,
Tesla,
MobilEye,
Mercedes, VW,
GM, Toyota,
etc. These
data are
critical for
everyone to
improve the
safety of each
of their
automated
driving
systems. The
objective
should be to
make them all
as safe as
possible.
NuTonomy
should NOT be
competing with
Argo or Waymo
or Tesla to be
the safest or
to "secretly
handle that
tragic
situation that
everyone else
is going to
eventually
trip over."
Each should be
warning all
others.. "Wow,
we just
uncovered this
one.
Everyone, be
careful here!"
That's the
purpose of
accumulating
the miles.
Everyone has
so many other
things to
compete over,
safety or the
handling of
these corner
case should
NOT be one of
them. That is
simply just
good societal
responsibility
that this
industry
should and
must embrace.
Alain
A. Hawkins,
June 12,
"UK-automaker
Jaguar Land
Rover is
investing $25
million in
Lyft to
support the
ride-hail
company’s
autonomous and
connected
vehicle
activities,
the two
companies
announced
today. The
money was
invested
through
InMotion,
Jaguar Land
Rover’s
mobility
services
subsidiary,
and was
included in
Lyft’s latest
round of
fundraising,
which ended in
April. .." Read
more Hmmmm... I guess this makes
some sense????
Depends on the
terms and
valuation
which aren't
mentioned.
Alain
T. Hallauer, June 1, "...Yes, it will become more difficult to get locked out of the car or run out of fuel for example. Crashes are expected to come down – requiring fewer tows – but it won’t affect breakdown assistance due to flat tyres, batteries or being stuck in a ditch. (OK, Autonomous vehicles should at least avoid the last one.)..." Read more Hmmmm... Nice focus on ADAS. Alain
F. Lambert, June 12, "While the rollout of Tesla’s latest Autopilot 2.0 update has yet to go wide, some owners have reported getting the update early and they are now testing the new features for the first time.We get our first look at the latest version of Autopilot 2.0 in a new video. Read more Hmmmm... Mostly straight road and who really cares about parking (if it is so tight, do you really want to park there???). Alain
J.
Salisbury,
March 2016, "
Almost all
behaviors
involve making
predictions.
Whether an
organism is
trying to
catch prey,
avoid
predators, or
simply move
through a
complex
environment,
the organism
uses the data
it collects
through its
senses to
guide its
actions by
extracting
from these
data
information
about the
future state
of the world.
A key aspect
of the
prediction
problem is
that not all
features of
the past
sensory input
have
predictive
power, and
representing
all features
of the
external
sensory world
is
prohibitively
costly both
due to space
and metabolic
constraints.
This leads to
the hypothesis
that neural
systems are
optimized for
prediction.
Here we
describe
theoretical
and
computational
efforts to
define and
quantify the
efficient
representation
of the
predictive
information by
the brain.
..." Read
more Hmmmm... Very interesting.
See also S.
Palmer video.
June 8, "Collectively, the startups on our map have raised approximately $17B in disclosed equity funding to date. ..." Read more Hmmmm... Informative graphic. Alain
http://orfe.princeton.edu/~alaink/SmartDrivingCars/Papers/
[log in to unmask]" alt=""> Yandex’s on-demand taxi service debuts its self-driving car project
D.
Etherington,
May 30,
"Russia search
and internet
technology
giant Yandex
is showing off
the
self-driving
vehicle
prototype
developed by
its
Yandex.Taxi
on-demand ride
service for
the first
time, and the
video above is
the first
footage of the
car in
action....The
vehicle in the
video isn’t
yet navigating
real city
streets, but
Yandex says
that testing
is coming on
public roads
within a year,
if all goes as
planned..." Read
more Hmmmm... Always nice to
have Russian
Smoke &
Mirrors in the
competition.
:-) Alain
The law
permitting the
demonstrations
or tests
is set to
expire April
1, 2018. That link states... "...For
the purposes
of this act,
the term
"autonomous
vehicle
technology"
shall mean the
hardware and
software that
are
collectively
capable of
performing part
or all of
the dynamic
driving task
on a
sustained
basis, and
the term
"dynamic
driving task"
shall mean all
of the real
time
operational
and tactical
functions
required to
operate a
vehicle in
on-road
traffic,
excluding the
strategic
functions such
as trip
scheduling and
selection of
destinations
and
waypoints...."
My car ('14MB s550) and a Tesla w/autopilot
certainly fall
under that
definition. I
guess I can
drive it but
NOT test it???
"...How to
apply... Complete
Autonomous
Vehicle
Technology
Demonstration/Testing
Application
Form (AV-1)
Autonomous
Vehicle
Technology
Demonstration/Testing
Addendum
(AV-2)..." ...This link states "...The entity named above shall reimburse the New York
State Police
for direct
supervision of
each
demonstration/test
according to
the following
schedule:
Regular Hourly
Rate: $92.73,
Overtime
Hourly Rate:
$131.67,
Mileage cost
$0.535 per
mile.
Read
more Hmmmm... Wow!! This one
takes your
breath away.
Can't wait
until April
Fools, 2018
when this
expires.
Can't imagine
anyone testing
in New York
State. This
MUST have been
written by
GM. It has
all of the
Sears/Craftsman's
monkey
wrenches in
it. Doesn't
the NY State
Police have
something
better to do
with all of
their
training,
expertise and
dedication to
serve and
protect.
Waymo has
tested over 3
million miles
and let's
assume an
average speed
of 30 mph to
guestimate a
test duration
of 100k
hours.
Further assume
a blended
regular/overtime
rate of
$100/hour.
That's
$11.5M.
Certainly
Google/Waymo
can afford it,
but..
absolutely
ZERO would
have been
contributed to
improving the
safety. If NY
State wants to
tax the test,
fine!;
but...maybe
the tax should
go to feeding,
housing and
providing
mobility for
the poor
rather than
wasting the
time and
squandering
the
opportunity
of those
Highly Trained
Police
Officers. C'mon NY State! This is really
embarrassing
and even worse
than New
Jersey. Alain
D. Hall,
Apr 17, "In
the race to
the autonomous
revolution,
developers
have realized
there aren’t
enough hours
in a day to
clock the
real-world
miles needed
to teach cars
how to drive
themselves.
Which is why
Grand Theft
Auto V is in
the mix.
The
blockbuster
video game is
one of the
simulation
platforms
researchers
and engineers
increasingly
rely on to
test and train
the machines
being primed
to take
control of the
family sedan.
Companies from
Ford Motor Co.
to Alphabet
Inc.’s Waymo
may boast
about putting
no-hands
models on the
market in
three years,
but there’s a
lot still to
learn about
drilling
algorithms in
how to respond
when, say, a
mattress falls
off a truck on
the
freeway....The
idea isn’t
that the
highways and
byways of the
fictional city
of Los Santos
would ever be
a substitute
for bona fide
asphalt. But
the game “is
the richest
virtual
environment
that we could
extract data
from,”
said Alain
Kornhauser..."
Read
More Hmmmm... Well...we have a slightly different
view of
history wrt to
GTA5. The
'Alain view'
is that Chenyi
Chen*16
independently
started
investigating
the use of
virtual
environments
as a source of
Image -
Affordances
data sets to
use as the
training sets
in a 'Direct
Perception'
approach to
creating a
self-driving
algorithm.
Images of the
road ahead are
converted into
the
instantaneous
geometry that
is implied by
those image.
An optimal
controller
then
determines the
the steering,
brake and
throttle
values to best
drive the
car. The
critical
element in
that process
are the Image - Affordances data
sets which
need to be
pristine.
Chenyi
demonstrated
in his PhD
dissertation
, summarized
in the ICCV2015
paper,
that by using
the pristine
Image -
Affordances
data sets from
an open-source
game TORCS
one could have
a virtual car
drive a
virtual race
course without
crashing.
More
importantly,
when tested on
images from
real driving
situations,
the computed
affordances
were close to
correct.
This encouraged us to look for more appropriate
virtual
environments.
For many
reasons,
including:
"wouldn't it
be amazing if
'Grand Theft
Auto 5'
actually
generated some
positive
'redeeming
social value'
by
contributing
to the
development of
algorithms
that actually
made cars
safer; saving
grief,
injuries and
lives".
Consequently,
in the Fall of
2015, Artur
Filipowicz'17
began to
investigate
using GTA5 to
train
Convolutional
Neural
Networks to
perform some
of the Direct
Perception
aspects of
automated
driving. With
Jeremiah Liu,
he continued
his efforts in
this direction
last summer
which were presented
at TRB in
January.
Yesterday, he
and Nyan
Bhat'17
turned in
their Senior
Theses focused
on this topic.
A. Kornhauser, Jan 14, "Orf467F16 Final Project Symposium quantifying implications of such a Nation-wide mobility system on Average Vehicle Occupancy (AVO), energy, environment and congestion, including estimates of fleet size, needed empty vehicle repositioning, and ridership implications on existing rail transit systems (west, east, NYC) and Amtrak of a system that would efficiently and effectively perform their '1st mile'/'last-mile' mobility needs. Read more Hmmm... Now linked are 1st Drafts of the chapters and the powerPoint summaries of these elements. Final Report should be available by early February. The major finding is, nationwide there exists sufficient casual ridesharing potential that a well--managed Nationwide Fleet of about 30M aTaxis (in conjunction with the existing air, Amtrak and Urban fixed-rail systems) could serve the vehicular mobility needs of the whole nation with VMT 40% less than today's automobiles while providing a Level-of-Service (LoS) largely equivalent and in many ways superior than is delivered by the personal automobile today. Also interesting are the findings as to the substantial increased patronage opportunities available to Amtrak and each of the fixed rail transit systems around the country because the aTaxis solve the '1st and last mile' problem. While all of this is extremely good news, the challenging news is that since all of these fixed rail systems currently lose money on each passenger served, the additional patronage would likely mean that they'll lose even more money in the future. :-( Alain
September
2016,
"Executive
Summary...For
DOT, the
excitement
around highly
automated
vehicles
(HAVs) starts
with safety.
(p5)
...The
development of
advanced
automated
vehicle safety
technologies,
including
fully
self-driving
cars, may
prove to be
the greatest
personal
transportation
revolution
since the
popularization
of the
personal
automobile
nearly a
century ago.
(p5)
...The benefits don’t stop with safety. Innovations have the potential to transform personal mobility and open doors to people and communities. (p5)
...The remarkable speed with which increasingly complex HAVs are evolving challenges DOT to take new approaches that ensure these technologies are safely introduced (i.e., do not introduce significant new safety risks), provide safety benefits today, and achieve their full safety potential in the future. (p6) Hmmm...Fantastic statements and I appreciate that the fundamental basis and motivator is SAFETY. We all have recognized safety as a necessary condition that must be satisfied if this technology is to be successful. (unfortunately it is not a sufficient condition, (in a pure math context)). This policy statement appropriately reaffirms this necessary condition. Alain
"...we
divide the
task of
facilitating
the safe
introduction
and deployment
(...defines
“deployment”
as the
operation of
an HAV by
members of the
public who are
not the
employees or
agents of the
designer,
developer, or
manufacturer
of that HAV.)
of HAVs into
four
sections:(p6)
Hmmm...Perfect!
Alain
"...2.
Model State
Policy (p7)
The Model
State Policy
confirms that
States retain
their
traditional
responsibilities...but... The shared
objective is
to ensure the
establishment
of a
consistent
national
framework
rather than a
patchwork of
incompatible
laws..." Hmmm... Well done. Alain
"...3. NHTSA Current Regulatory Tools (p7) ... This document provides instructions, practical guidance, and assistance to entities seeking to employ those tools. Furthermore, NHTSA has streamlined its review process and is committing to..." Hmmm... Excellent. Alain
"...4. New Tools and Authorities (p7)...The speed with which HAVs are advancing, combined with the complexity and novelty of these innovations, threatens to outpace the Agency’s conventional regulatory processes and capabilities. This challenge requires DOT to examine whether the way DOT has addressed safety for the last 50 years should be expanded to realize the safety potential of automated vehicles over the next 50 years. Therefore, this section identifies potential new tools, authorities and regulatory structures that could aid the safe and appropriately expeditious deployment of new technologies by enabling the Agency to be more nimble and flexible (p8)..." Hmmm... Yes. Alain
"...I.
Vehicle
Performance
Guidance for
Automated
Vehicles
(p11) A.
Guidance: if a
vehicle is
compliant
within the
existing FMVSS
regulatory
framework and
maintains a
conventional
vehicle
design, there
is currently
no specific
federal legal
barrier to an
HAV being
offered for
sale.(footnote
7) However,
manufacturers
and other
entities
designing new
automated
vehicle
systems
are subject to
NHTSA’s
defects,
recall and
enforcement
authority.
(footnote 8)
.
and the "15
Cross-cutting
Areas of
Guidance"
p17)
In sum this is a very good document and displays just
how far DoT
policy has
come from
promoting v2v,
DSRC and
centralized
control,
"connected",
focus to
creating an
environment
focused on
individual
vehicles that
responsibly
take care of
themselves.
Kudos to
Secretary Foxx
for this 180
degree policy
turn focused
on safety.
Once done
correctly, the
HAV will yield
the early
safety
benefits that
will stimulate
continued
improvements
that, in turn,
will yield the
great
mobility,
environmental
and
quality-of-life
benefits
afforded by
driverless
mobility.
What are not addressed are commercial trucking and buses/mass transit. NHTSA is auto focused, so maybe FMCSA is preparing similar guidelines. FTA (Federal Transit Administration) seems nowhere in sight. Alain
Hmmm...What we know now (and don't know):