Researchers from MIT and Motional have developed CW-Net, an AI system designed to explain the reasoning behind decisions made by self-driving cars. The system translates complex machine-learning processes into understandable concepts and provides explanations in real time. Tests involving a robotaxi and simulation participants showed that the explanations helped people better predict vehicle behaviour. The research could also provide engineers with information to identify problems in autonomous driving systems.
Read more at the source
Disclaimer: The content of this post is sourced from external sites and is for informational purposes only. All rights and credits belong to the original authors and publishers.