The latest idea to reduce accidents in autonomous cars: keep track of them

Research from the University of Tokyo claims that robotic surveillance of autonomous vehicles will reduce traffic accidents. To prove this, the study team presented Various scenarios in virtual reality And some of the participants had to decide whether to cross the street or not.

Some simulations show self-driving cars with eyes closed. When they saw the pedestrian (participant), they decided safer or more efficient.

“Not enough research has been done on the relationship between self-driving cars and the people around them, such as pedestrians,” says Professor Takeo Igarashi from the Graduate School of Information Science and Technology. “That’s why we need more research and effort in that conversation.” Provide security and guarantee to society When it comes to self driving cars.

When a person is driving, pedestrians know that the pilot has noticed their presence, thanks to the fact that he sees them. However, if there is no one behind the wheel, the person They may be suspicious and do not feel safe when crossing, Eyes will eliminate this deficiency to a great extent.

Different scenarios of ‘Looker Car’

To test this outside the simulation, Japanese researchers put Remote control of two robotic eyes For a self-driving golf cart. the name given to the vehicle ‘Looker Car’ And they have shown that pedestrians will dare to cross quickly in front of you if they know you have seen them.

in the study he prepared four scenarios: Two of them had vehicle eyes and the rest did not. In the case of a ‘peeping car’, the passerby looked at him when he was about to stop, and when he was not about to stop, he did not do so.

The team installed 360-degree video cameras to capture the movements of 18 participants (9 men and 9 women), between 18 to 49 years. He experienced different scenarios several times and randomly and took only 3 seconds to decide whether to cross or not.

Although there are still many fatal traffic accidents, technology helps reduce them.

To elaborate on the results, the researchers analyzed how often participants chose to stop when they could have crossed and how many times they crossed when they should have waited.

Chia-Ming Chang, professor and member of the research team, emphasized that there was “A clear distinction between the genders”, However, he acknowledged that there may be other factors that “could also influence participants’ responses”, such as age or origin.

Notably, men were those who made the most risky decisions, although errors were reduced in the ‘peeping car’ scenarios. other thing, women make better decisions And the results even improved thanks to the eyestrained vehicles.

Now, Igarashi proposes a new purpose for developing automatic control of robotic eyes So far they do it with a remote control, through an artificial intelligence.

Sign up for our newsletter and receive the latest tech news in your email.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button