Robotic Eyes Attached to Front of Self-Driving Cars May Improve Safety

Scientists in Japan have found that sticking giant googly-looking eyes in front of self-driving cars may improve safety for pedestrians.

Safety is the most crucial hurdle that self-driving cars must navigate before they are able to roam streets. Despite companies like Tesla capturing billions of miles of real-world road data to improve its Autopilot self-driving software, the technology in general still has far to go.

Tesla still does not classify Autopilot-enabled vehicles as autonomous cars since they always require active supervision on the part of the driver, who must keep their hands on the wheel and be ready to jump in at any time, according to the company's website.

While other cars are a big part of the challenge that self-driving cars face, another is pedestrians.

"There is not enough investigation into the interaction between self-driving cars and the people around them, such as pedestrians," Professor Takeo Igarashi, a computer researcher at the Graduate School of Information Science and Technology at the University of Tokyo, said in a press release on Tuesday.

"So, we need more investigation and effort into such interaction to bring safety and assurance to society regarding self-driving cars."

One way to improve safety might be to give 'eyes' to self-driving cars, according to a new study by Igarashi and colleagues.

It's something various car manufacturers have explored, with the idea being that the eyes would serve as a means of communication from the car to pedestrians.

Cart with remote-controlled eyes
The cart used in the Japanese autonomous driving safety study, featuring remote-controlled eyes to indicate intentions to pedestrians. Chang et al. 2022

Specifically, the researchers studied a situation in which a pedestrian is in a hurry to cross a street. If the car's eyes were not looking at the pedestrian, it implied the car was not paying attention to them and would not stop. If the eyes were looking at the pedestrian, it implied the car recognized they were there and would stop.

If the pedestrian judged that the car could see them and would stop, they could continue crossing the street. If not, the pedestrian would stop for their safety.

Researchers built such a 'car' out of a cart, similar in size and shape to a golf cart, complete with eyes. They then shot 360-degree videos of the car and imported this into a virtual reality environment.

In this VR environment, 18 participants were told to make street-crossing decisions within a three-second time limit while the researchers studied their error rates. An error was counted if both the pedestrian and car stopped, or if both the car and the pedestrian continued.

The results showed that the total error rate was 50.56 percent in the car with no eyes and 29.44 percent in the car with eyes, which "indicates that an eyes car can help pedestrians make streetcrossing decisions more correctly than a no-eyes car in general," the researchers wrote.

While some of the participants reported that the eyes looked cute, others said they were creeped out by them despite the suggested improvements in safety.

"In the future, it would be better to have a professional product designer find the best design, but it would probably still be difficult to satisfy everybody," Igarashi said in a university press release.

It is important to bear in mind that the study was limited by a small number of participants involved in just one scenario, while the VR environment might have affected the results. Igarashi said he hoped the research would encourage similar investigations into anything that might improve interactions between self-driving cars and people.

The study, 'Can Eyes on a Car Reduce Traffic Accidents?', was published in AutomotiveUI '22: Proceedings of the 14th International Conference on Automotive User Interfaces and Interactive Vehicle Applications.

Pedestrians crossing road
A stock photo shows many pedestrians crossing a road. A study has investigated giving 'eyes' to an autonomous car in order to see if it improves road safety. ArtMassa/Getty