Video summary
Chris Urmson addresses the critical role of LiDAR in current autonomous vehicle sensor suites, asserting that while cameras and radars are essential components, a robust system requires the fusion of data from all three technologies. He acknowledges Elon Musk's provocative claim that LiDAR is merely a crutch by noting that humans navigate daily without lasers, proving passive vision can function; however, Urmson argues this comparison overlooks the severity of current road safety issues. Citing statistics showing approximately 37,000 Americans died on roads last year alone, he emphasizes that any technology accelerating self-driving deployment to save lives is justified, regardless of whether it involves LiDAR or high-resolution cameras like an 8-megapixel unit. The discussion extends to the inevitable evolution of automotive technology, drawing a parallel between how combustion engines served as a transitional step toward electric vehicles and how current sensor technologies may eventually be replaced by superior alternatives in the future. Urmson rejects arbitrary restrictions on using LiDAR simply because it is not human vision or camera-based, advocating instead for an approach that selects the best available tools from the "tool bin" to solve safety problems effectively. He highlights that while cost reduction is a primary concern for automotive companies and investors, prioritizing the absolute cheapest sensor suite over one that ensures functionality creates a dangerous trade-off where reliability takes precedence over minimizing expenses at all costs. Regarding the future economics of LiDAR, Urmson foresees both significant cost reductions in hardware prices and scenarios where Level 4 autonomy might operate without it, though he believes these outcomes are matters of time rather than certainty. He points out that while CMOS imaging processes used for cameras offer dramatic scalability compared to mechanical components often found in LiDAR, the fundamental expense structure will likely keep LiDAR costs higher per unit initially. Nevertheless, he maintains that substantial cost decreases remain achievable through technological advancements and optimized business models that allow manufacturers to absorb a portion of the Bill of Materials expenses while still maintaining economic viability. Ultimately, Urmson concludes that the goal should not be driving sensor costs down to zero or finding an artificially cheap alternative like a $50 sensor if it compromises safety, but rather achieving an economically viable suite where margins can drive further cost efficiencies out of the system over time. He stresses that providing extra value through superior performance justifies higher initial material costs because sustainability and scalability depend on creating systems that actually work in the real world. The path forward involves balancing immediate economic pressures with long-term safety imperatives, ensuring that autonomous vehicles become a widespread reality without sacrificing the rigorous standards required to protect human life.
Read the full video transcript
[Music]
he said leiter came into the game early
on and it's really the primary driver of
autonomous vehicles today as a sensor so
how important is the role of light are
in the sensor suite in the near term so
I think it's I think it's a central you
know I believe it but I also believe is
the cameras are essential and I believe
the radars is essential I think that you
you really need to use the composition
of data from from these different
sensors if you want the thing to to
really be robust the question I want to
ask I see if we kind of tangle is what
are your thoughts on the Elon Musk
provocative statement that lidar is a
crutch that is the kind of I guess
growing pains and that's much of the
perception tasks can be done with
cameras so I think it is undeniable that
people walk around without you know
lasers in their foreheads and they can
get into vehicles and drive them and and
so there's an existence proof that you
can drive using you know passive vision
no doubt can't argue with that in terms
of sensors yeah so yes sensors right so
like there's there's an example that you
know we all go do it many of us every
day in terms of latter being a crutch
sure but but you know in the same way
that you know the combustion engine was
a crutch on the path to an electric
vehicle the same way that you know any
technology ultimately gets
replaced by some superior technology in
the future and really what with the way
that I look at this is that the way we
get around on the ground the way that we
use transportation is broken and that we
have you know this this you know what
was I think the number I saw this
morning 37,000 Americans killed last
year on our roads and that's just not
acceptable and so tech any technology
that we can bring to bear that
accelerates the this techno you know
self-driving technology coming to market
and saving lives is technology we should
be using and it feels just arbitrary to
say well you know I'm I'm not okay with
using lasers because that's whatever but
I am okay with using an 8 megapixel
camera or a 16 megapixel camera you know
like it's just these are just bits of
technology and we should be taking the
best technology from the tool bin that
allows us to go and you know and solve a
problem the question I often talk to
well obviously you do as well to sort of
automotive companies and you know if
there's one word that comes up more
often than anything is costs and and
trying to drive costs down so while it's
it's true that it's a tragic number the
37,000 the the question is would and I'm
not the one asking these questions I
hate this question but yeah we want to
find the cheapest sensor suite that the
creates a safe vehicle so in that
uncomfortable trade-off do you foresee
lidar coming down in cost in the future
or do you see a day where level for
autonomy is possible without lidar I see
both of those but it's really a matter
of time and I think really maybe the I
would talk to the question you asked
about you know the cheapest set
certainly I don't think that's actually
what you want what you want is a sensor
suite that is economically viable and
then after that everything is about
margin and driving cost out of the
system what you also want is a sense
suite that
and so it's great to tell a story about
how you know how it'd be better to have
a self-driving system with a $50 sensor
instead of a you know $500 answer but if
the $500 sensor makes it work and the
$50 sensor doesn't work you know who
cares the long is you can actually you
have an economic offer you know there's
an economic opportunity there and the
economic opportunity is important
because that's how you actually have a
sustainable business and that's how you
can actually see this come to scale and
and and be out in the world and so when
I look at lidar I see a technology that
has no underlying fundamentally you know
expense to it fundamental expense to it
it's it's going to be more expensive
than an imager because you know CMOS
processes or you know fab processes are
dramatically more scalable than
mechanical processes but we still should
be able to drive costs down
substantially on that side and then I
also do think that with the right
business model you can absorb more you
know certainly more cost on the Bill of
Materials yeah if the sensor suite works
extra values provided thereby you don't
need to drive costs down to zero it's
the basic economics
you