Self-driving cars: Near-miss driving data can expedite AV algorithm training

Дата публикации: 13-07-2026 14:20:01

The safety performance of autonomous vehicle (AV) algorithms is boosted by 90% using simulation data that better incorporates near-miss incidents with outright failures, according to new research led by University of Michigan Engineering.

Основное содержимое страницы с новостью.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Steering wheel communicates for better semiautonomous driving performance	0	6.4	01-10-2026
2	Autonomous vehicles can still see lanes through tampered sensors—but in the wrong place	0	7.59	08-10-2026
3	From 'hands-free' to 'eyes-off': How General Motors is simulating its way to autonomous driving	0	10.42	12-10-2026
4	Self-Driving Cars Are Getting Better. The Risks Are Getting Bigger.	0	11.68	23-09-2026
5	New autonomous monitor prevents drone crashes in real time	5	7	07-07-2026
6	Нейросети против ДТП: технологии меняют правила безопасности на российских дорогах	5	7	09-06-2026
7	A new technology teaching drones to feel pain could stop your self-driving car from harming itself	5	7	03-07-2026
8	New driving AI ranks possible routes for safer, clearer decisions	5	7	19-07-2026
9	Электромобиль "Атом" сможет предотвращать 80% аварий по вине водителя	0	0	17-09-2025
10	Нарушения ПДД в Москве начали фиксировать с помощью нейронной сети	0	0	26-12-2018

Классификация: Наука. Схожих патентов: 0. Схожих новостей: 10. Тональность: 7. Информативность: 8. Источник: phys.org.