An algorithm developed by researchers at Carnegie Mellon University (CMU) could enable autonomous vehicles to navigate crowded, narrow streets where vehicles traveling in opposite directions do not have enough space to pass each other and there is no knowledge about what the other driver may do.
Such a scenario requires collaboration among drivers, who must balance aggression with cooperation.
The researchers modeled different levels of cooperation between drivers and used them to train the algorithm.
In simulations, the algorithm was found to outperform current models; it has not yet been tested on real-world vehicles.
From Carnegie Mellon University School of Computer Science
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found