System helps humans predict when self-driving cars will make mistakes
中文摘要
CW-Net通过将自动驾驶AI的推理过程转化为易懂概念，帮助人类理解其行为并预测错误。
English Summary
CW-Net translates autonomous vehicle AI reasoning into understandable concepts, helping humans explain behavior and predict mistakes.
Original Excerpt
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.