Nissan examines human side of autonomous cars

Anthropologists among experts working toward 2020 target for autonomy

Published: August 12, 2016, 12:30 PM
Updated: April 29, 2018, 12:50 PM

Nissan autonomous car sensors

In its drive toward autonomous driving, Nissan has assembled a team of experts on automotive engineering, computer science, sensor technology, artificial intelligence, production and anthropology.

Yes, anthropology — somebody to analyze human driving interactions and ensure the autonomous vehicle is a “good citizen” on the road.

“Car technology is continuing to evolve and change,” said Melissa Cefkin, principal scientist and design anthropologist at the Nissan Research Center in Silicon Valley. “And now, we’re adding this autonomous dimension to it that will bring around further changes in society, all the way down to the everyday way in which we interact and behave on the road.”

A corporate and design anthropologist, Cefkin represents a decidedly modern branch of the anthropology — ethnography, or the systematic study of people and cultures from the viewpoint of the subject.

In relation to autonomous vehicles, Cefkin says that means looking at how humans interact with the “deeply and profoundly cultural object” that is the automobile, and gaining insights into how new technologies might interpret or act on those interactions.

Cefkin and her team have been tasked with the third phase of Nissan’s autonomous vehicle program — the ability of the vehicle to navigate city driving and safely get around intersections without driver intervention. She says it’s all leading to a future where there may not even be somebody in the driver’s seat.

The city navigation module is due for introduction in 2020. The first of the technologies, ProPILOT, is being introduced now. It’s designed for single lane highway use. The multi-lane highway technologies are due for introduction in 2018.

Cefkin has been with Nissan since March last year, when she began documenting interactions between drivers, as well as between drivers and pedestrians, cyclists and road features (speed bumps, pylons, etc.)

“We’re trying to distill some key lessons for what an autonomous vehicle will need to know —  what it perceives in the world and then how it can make sense (of it), make judgments and behave itself to be able to interact effectively in those different (situations),” said Cefkin.

Nissan autonomous car message

She cited 4-way stops a something the team had to examine closely because it’s one of those intersections that require driver intervention.

“What happens at a 4-way stop – it’s open to a lot of interpretation,” she explained. “Yeah, I’m supposed to stop, (but) once I’ve stopped it doesn’t tell me when to go again.”

In the real world, drivers, pedestrians and cyclists often use eye contact and forms of direct communication (such as a wave) to send clear signals about intentions, but vehicles naturally can’t detect or send those signals.

That type of needed interaction lead to the development of a real-time messaging system on the IDS Concept Car that would allow the autonomous car to communicate its intentions to other road users. Among the features is an LED strip running the length of the side of the car that actually acknowledges the presence of a cyclist, for example, by having a light directly shadow the cyclist as the car passes.

Cefkin says the features on the concept may end up directly in production or closely resembling the actual future car’s features. The idea is to communicate what the car’s intentions are so that they can’t be misinterpreted in any way by anybody.

“What’s different for (Nissan) is we are working at the heart, the guts of the core technology and bringing insights and the kind of understanding that we have about human practices and human experience right into the fundamental design,” concluded Cefkin.