Autonomous Vehicle Engineering - March 2021 - 10

Software

"

Stripping the intelligence out of the sensor enables the use of smaller,
cheaper, lighter and easier-to-package sensors.

Aptiv

"

Aptiv's Scalable Sensing and Perception configuration enables ADAS systems scaling regardless of vehicle type or levels of automation.

  " [The ASDC is] where all of the software regarding
the perception system and the environmental models,
the sensor fusion, planning and all of the ADAS features
reside, "  he explained. Under a distributed or a smart
sensor-based architecture, the sensors themselves
have intelligence to make some decisions. For entrylevel systems like RACam (Aptiv's integrated radar
and camera device), that works just fine, De Vos said.
But increasing the number of inputs or repositioning
sensors across various  vehicle models  requires  a
different system. 
  " It's not a scalable or a flexible architecture, "  he
said.  " What we've done with  'satellite'  architecture
is we've stripped all of the intelligence out of the
sensor, anything except the most rudimentary image
processing, and whatever it takes to get it back to the
central controller. " This enables the use of smaller,
cheaper, lighter and easier-to-package sensors. 
 Shifting away from 'smart' sensors required tying
together the SVA and the ASDC, De Vos said, both for
low- and high-voltage systems. Integrating brain and
nervous system, and thinking of the vehicle holistically, also helped Aptiv's OEM customers to optimize
those architectures. It allowed them to better manage
complexity, maintain and deliver required performance levels at the lowest total operating cost over
the full lifecycle of the vehicle, he claimed. 

10 March 2021	

  " SVA, for us, remains a central theme as part of
how we think about our portfolio and how we think
about our technical strategies going forward, "  he noted.
And it's those future technologies where Aptiv's SVA
could prove most valuable. Currently, for the five OEMs
that currently use or are about to launch vehicles with
the SVA, the technology offers autonomous capabilities
somewhere between SAE Level 1 and the unofficial
(and increasingly popular) Level 2+. 
 

Capabilities converging 

To configure a capable L2 system, Aptiv uses up to five
radar sensors, a camera and potentially a connection to
an HD map, De Vos said. This relatively simple set-up
keeps the cost for an L2 system somewhere between
$450 and $550, while L2+ is closer to between $750 and
$1200, depending on the system and connectivity, he
said. To get to SAE Level 3 and above, lidar will likely
be needed. That ramps up cost significantly. 
  " When you get to Level 3, we think [lidar] is
required, in particular in the forward-looking direction, " he said. " So, as we scale these systems to L3, you
need to plug in that forward-looking lidar component
and redundancy. "  The good news from Aptiv's perspective, De Vos said, is that it can add lidar to the L2
and L2+ systems in use today. That system architecture serves  effectively as the foundation for an  L3

AUTONOMOUS VEHICLE ENGINEERING
Autonomous Vehicle Engineering - March 2021

Table of Contents for the Digital Edition of Autonomous Vehicle Engineering - March 2021
