System helps humans predict when self-driving cars will make mistakes

T1Covered by 1 source · first reported by MIT News (research) / Quanta / The Conversation at 02 Sept, 15:00 UTC

A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.

Sources

• T1System helps humans predict when self-driving cars will make mistakesMIT News (research) / Quanta / The Conversation02 Sept, 15:00