Autonomous Vehicle Engineering - May 2020 - 15

Smart Mobility

AUTONOMOUS VEHICLE ENGINEERING

Even when routes are limited, trucks must be able to navigate all
kinds of roads.
how to maintain precise, up-to-date maps.
"For years, mapping companies bragged of having this many
miles," said IHS Markit's Jeremy Carlson. "Ultimately, customers
called back and said they wanted better data, with more frequently
updated information for smaller regions. Mapping is hugely important."
OEMs are also looking at keeping humans involved in autonomous
driving - but they'll be at very safe social distances, monitoring vehicle
activities from remote sites. Remote operators may be called in when
trucks encounter situations that autonomous systems can't understand.
"A remote operator can step in when decisions can't be made by
the system," said Valeo's Guillaume Devauchelle. "If there's a red light
but a policeman says please go, a human can easily decide that it's
okay not to pay attention to the red light."
- Terry Costlow

mounted near highway intersections and merging
areas can help give commercial vehicles input that
on-vehicle sensors can't necessarily see. In urban areas,
operators and smart-city planners can mount sensors
on poles and buildings.
Additional data sent to vehicles can augment information collected by onboard sensors. "We're working
with intelligent-infrastructure planners, taking sensors
usually mounted on vehicles and mounting them within
the infrastructure of cities," said Steffen Hartmann,
head of technical projects, research, for Continental
North America. "They can better see things like pedestrians emerging from between cars or people running
towards an intersection. Then messages can be sent to
vehicles so they can take action."
On-vehicle sensors have a critical role in another
domain limiter: weather. Design teams are seeking
ways to ensure weather doesn't limit system performance. Developers are trying to create systems that
match humans' abilities to drive in fog, rain and snow.
Mounting sensors where they're protected is one technique, washing camera lenses and software that reduces
the impact of dirt and moisture all are being examined.

TuSimple

Truckers set routes for autonomy
Commercial trucks and off-highway equipment often travel set
routes, a factor many say will make trucking one of the early markets
for autonomous vehicles. The current shortage of drivers provides
additional impetus for removing humans from driver's seats.
Autonomous trucks already traverse specific routes in mining sites
and autonomous systems guide tractors through fields. Self-driving
trucks are getting closer to operating on public highways, typically with plans to start driving along limited routes. "Many trucking
companies move freight along specific routes; our partner UPS has
thousands of routes that don't vary," said Chuck Price, TuSimple's
chief product officer. "We are solving how to drive on surface streets
in traffic, with all the randomness that entails. But we are containing
complexity by limiting tests to that operational domain."
Truckmakers are taking aggressive steps to move beyond controlled tests. Volvo opened its Autonomous Solutions group early
this year, focusing research that already includes vehicles operating
in a Swedish port. Daimler's Highway Pilot is preparing to make the
transition from safety system to autonomous controller.
Strategies for migrating to autonomy vary. Some in the trucking
industry have suggested limiting autonomous semis to highways, letting
drivers take over driving in urban areas. However, the logistics of getting
drivers to holding sites where many trucks are parked will be difficult.
"That model doesn't fit how trucks are used," Price said. "If trucks are limited to highways, how do they get to the highways? You need a terminal,
which would have to be huge, and a way to get drivers to the terminal."
The availability of high-resolution maps is among the factors driving operators to limited operational domains. Maps with constantly
updated data, including information about construction and road
conditions, are considered a critical element for driverless trucks.
Startups and established cartography companies are figuring out

Higher levels of autonomy will first emerge in trucking and shuttles.

"With a sensor cleaning system, the trick is to
minimize water usage. You don't want to be carrying
liters of water," said Guillaume Devauchelle, VP of
innovation at Valeo. "There are also algorithms that
will detect a drop of water on the camera lens. When
you have multiple cameras, if one is close to its operating limits, you won't take that camera into account."
No matter how good sensor and systems are,
confusing situations will arise even in limited areas.
Vehicles will typically shut down as safely as possible
when systems can't determine what action to take.
Some companies are adding technology that lets

May 2020

Autonomous Vehicle Engineering - May 2020

Table of Contents for the Digital Edition of Autonomous Vehicle Engineering - May 2020