Building Geofences to Speed AV Adoption

Limiting operational domains for driverless vehicles may help get autonomous technology on the road sooner.

Even when routes are limited, trucks must be able to navigate all types of roads. (TuSimple)

Vehicle and system developers have always pushed to get the most from every component and material, but design teams focused on autonomous vehicles are increasingly adopting a less-is-more strategy. Limiting operational domains for driverless vehicles may help get cars and vans on the road more quickly. Limiting vehicles to fixed routes can dramatically reduce the complexity of driving without humans, making shuttles and commercial vehicles some of the areas that will be first to totally eliminate drivers.

Sensors mounted along streets used by geofenced vehicles can provide information vehicle sensors may miss. (Continental)

For robotaxis, geofences that limit taxis to specified urban areas serves a similar purpose. Setting limits is expected to become a popular strategy. “When you’re working on systems that have to respond and react to a number of infinitely complex scenarios, the most logical way to simplify the challenge is to limit the number of options the vehicle needs to respond to,” said Jeremy Carlson, principal automotive analyst at IHS Markit. “Narrowing the scope of what you address makes it possible to get to market sooner than trying to do everything everywhere.”

Valeo is looking at ways to improve sensor performance in bad weather. (Valeo)
Over the air updates are necessary to keep vehicles up to date. (Elektrobit)
Valeo’s Devauchelle aims to help automakers hasten their move to autonomy. (Valeo)

On today’s vehicles, safety systems require that humans remain attentive. Emerging SAE Level 2+ and Level 3 systems loosen that limitation but still require constant human monitoring. Those systems will be augmented to eliminate drivers. Many proponents feel that completely removing humans can best be accomplished by proving the safety of autonomous vehicles running in defined areas.

“The business today comes from Level 2 to Level 3 vehicles,” said Nand Kochhar, VP Automotive and Transportation Industry at Siemens Digital Industries Software. “We need to start merging targets for Level 4 and Level 5 together with the realities of today. The big question is, ‘how safe is safe?’ There’s a lack of standards for how systems are tested. When people define operational domains, they’re saying ‘let’s walk before we run.’”

Starting small

Driving in geofenced areas has benefits beyond reducing variables. It may enable operators to deploy sensors that are built into the infrastructure. Sensors 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 on-vehicle 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 that conditions don’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 are all being examined.

“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 remote operators step in before that occurs.

Vehicles could alert people in remote centers so these remote operators can take over and analyze the situation. “If a shuttle is programmed to pick-up and drop-off passengers only in designated bus-stops and one of those is blocked, for example by a delivery truck, the shuttle may stop in the road while waiting for the bus stop to become free,” said Torsten Gollewski, head of autonomous mobility systems for ZF. “In this case the remote driver could maneuver the shuttle to an available curb space, to avoid blocking traffic and permit passenger loading and unloading.”

The deep-neural enabler

After vehicles have proven they can operate safely in limited domains, operators will want to expand their capabilities. Once vehicles are in the field, over the air (OTA) updates will provide a straightforward way to update the software that keeps passengers safe and secure.

Martin Schleicher, executive VP business management at Elektrobit, noted that these technologies encompass redesigned architectures for safety, security, infotainment and more. “Keeping the vehicle up-to-date requires OTA updates,” he noted. “OTA is necessary for distributing everything from the latest infotainment system features to operating system security patches and ECU updates or configuration changes.”

Going forward, these enhancements will increasingly be powered by artificial intelligence programs that may leverage input from the vehicles’ driving experiences. These software improvements are often being processed by FPGAs, which provide a level of hardware customization that most semiconductors can’t offer.

“Convolutional neural networks/deep neural networks are going to be a huge enabler,” said Willard Tu, senior director, automotive business unit, at Xilinx. “An example is a CNN that started with 32 bit, moved to 8-bit integer and now is moving to 4-bit quantization.” Xilinx devices supported each of those transitions with the same device, where as other companies have to design a new device for each transition. Having powerful and efficient AI that can be upgraded on the same hardware is also very valuable to developers.

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.”

Truck manufacturers 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 how to maintain precise, up-to-date maps. “For years, mapping companies bragged of having this many miles,” said Jeremy Carlson, the IHS Markit analyst. “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 at 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 OK not to pay attention to the red light.”