Citation

Paterson C, Picardi C. Nature 2023; 615(7953): 594-595.

Copyright

(Copyright © 2023, Holtzbrinck Springer Nature Publishing Group)

DOI

10.1038/d41586-023-00798-4

PMID

36949332

Abstract

Collecting training data by focusing on dangerous scenarios offers an efficient way for artificial intelligence to improve the safety of autonomous vehicles. Augmented reality allows the approach to be tested without risking lives.

Every year, collisions involving road vehicles kill or seriously injure tens of thousands of people in the United Kingdom alone (see go.nature.com/3ekkex4). Autonomous vehicles could reduce these numbers, but their safety is yet to be guaranteed (see go.nature.com/3ykw43v). .../

Language: en

Keywords

Machine learning; Technology; Computer science; Engineering; *Automobile Driving; *Automobiles; Accidents, Traffic/prevention & control