Developing Safe Autonomous Vehicles

To fix this problem, a team of researchers used artificial intelligence to train virtual vehicles that can challenge autonomous vehicles in a virtual or augmented reality testing environment. The virtual cars were only fed safety-critical training data, making them better equipped to challenge AVs with more of those rare events in a shorter amount of time. In an era of uncertainty towards AVs, this solution can save auto manufacturers a prohibitive amount of time and money to ensure their systems are safe.

This research was led by Professor Henry Liu, Director of Center for Connected and Automated Transportation (CCAT), Director of Mcity

Paper:
"Dense reinforcement learning for safety validation of autonomous vehicles"
Journal: Nature
Date: March 22, 2023
DOI: 10.1038/s41586-023-05732-2

Learn more:

------
Watch more videos from University of Michigan Engineering and subscribe: @MichiganEngineering

The University of Michigan College of Engineering is one of the world’s top engineering schools. Michigan Engineering is home to 12 highly-ranked departments, and its research budget is among the largest of any public university.

Follow University of Michigan Engineering:

[kakashi_senpai]

Wow! I Love Engineering is such an amazing site! As an engineer myself, I am so grateful for the incredible resources this site shares to help other engineers stay up-to-date on trending topics and tips & tricks to improve their engineering abilities. I especially love how it enables engineers to constantly learn and refine their skills. It's an essential resource for all sorts of engineering projects, and I'm grateful for the knowledge and inspiration it provides. Keep up the great work!

[cfb]

I wonder what an Autonomous Vehicle is programmed to do if it is stopped at a red light and it "sees" another car approaching it from behind at a high rate of speed. Will it run the red light to avoid being rear-ended?