This article was originally published on Motional's Medium page, Minds of Motional, on Feb. 10, 2021
Imagine this. You’re walking down a street in a busy city and, as you’re about to cross the road, you see a vehicle approaching. Something gives you pause. You look closer, and you realize the driver’s seat is empty. There’s no one behind the wheel, and the car appears to be driving itself. What would you do? How would you feel? Is it safe to cross?
Driverless vehicles aren’t yet commonplace, so you might feel uncertain. As a pedestrian, you’re used to interacting with traffic, but you might rely on human interaction — like hand gestures, eye contact, body language, or the typical behavior of a human-driven car — to navigate it safely. Those human cues don’t exist in a driverless car.
Now take this scenario and multiply it by the number of pedestrians a single driverless vehicle may encounter in a day, a week, or a year. Then multiply that again by the dozens, then hundreds, then thousands — then millions — of driverless vehicles that are expected to be on the roads in our lifetime. It’s an immense number of interactions for which pedestrians don’t yet have a clear set of internalized instructions, and that’s ultimately because we’re asking humans to do something that’s still foreign: communicate with robots.
At Motional, we’re working to solve this. Our goal is to make driverless vehicles a safe, reliable, and accessible reality, and central to our mission is ensuring consumers understand how our vehicles fit into their communities, and feel safe in their presence. We’re aiming to make human-robot interaction simple, familiar, and intuitive.
“The goal is to help pedestrians feel comfortable with the technology. As the tech scales up and there are more vehicles around, we owe it to ourselves to really understand this, and to get it right.”
The Role of Expressive Robotics
For pedestrians to feel comfortable with driverless cars, the vehicle must act and signal its intentions in ways that a person easily understands. To facilitate and optimize this human-car communication, Motional is adopting principles from a budding field known as Expressive Robotics: the study and practice of creating robots capable of clearly expressing their intentions to humans.
Robots, like many nascent technologies, are usually designed to demonstrate proof of concept or viability. They’re not necessarily designed for user experience, and they typically behave in ways that optimize efficiency, such as time or energy. The resulting “robotic” motions can be confusing to the average observer. When prioritizing time efficiency, for example, a driverless vehicle may have a shorter braking distance than a human-driven car, and when prioritizing fuel efficiency they may move at a speed which a human perceives as unusually slow.
Expressive robotics aims to calibrate this — to prioritize both efficiency and human interaction from the outset, and help people more easily understand, process, and react to robots.
Motional’s Approach
Over the last year, Motional has conducted user research, using virtual reality (VR) to simulate pedestrian interactions with driverless vehicles in a number of scenarios.
During testing, participants wear VR goggles that replicate walking down the street and interacting with both human-driven and driverless cars on the road. As part of this testing, we borrow insights from Expressive Robotics, and ask participants a series of questions about a vehicle’s signals and movements:
- Was it clear the vehicle was planning to stop?
- How comfortable did you feel crossing in front of the vehicle?
- How would you feel if the vehicle decelerated slightly earlier or more than human drivers? What if it stopped earlier?
- How does sound impact your comfort? What if it sounded like it was braking? What if the braking noise was slightly augmented?
- What else would help you understand the intent of the vehicle? For this question, we consider features like lights and color.
Our initial results suggest that pedestrians respond positively when driverless vehicles show expressive signs, like light signals and gradual deceleration — and we are researching the effectiveness of these and other methods over repeated exposure. We plan to take the most promising signals — the signals that allow a driverless car to most clearly communicate with a pedestrian — and incorporate them into our future Motional vehicle designs.
As Motional moves towards a future where driverless vehicles are part of our everyday lives, this research is critical in helping the technology enter our lives comfortably, safely, and efficiently. We’ve moved the industry out of science fiction to reality, and to continue on our path to a driverless future, we must continue to include you — our pedestrians, passengers and partners — on that journey.
