The development of truly autonomous vehicles (AVs) has been hindered by the cost and time associated with safety testing, but a new system created at the University of Michigan in Ann Arbor shows that artificial intelligence can reduce the testing miles required by 99.99 percent.
This system could lead to a paradigm shift that enables manufacturers to verify more quickly whether their autonomous vehicle technology can operate safely and reduce the incidence of crashes. In a simulated environment, vehicles trained by artificial intelligence perform perilous maneuvers, forcing the AV to make decisions that confront drivers only rarely on the road, a necessary step in training the vehicles.
Read more here.
