Explainable deep learning improves human mental models of self-driving cars
可解释深度学习提升人类对自动驾驶汽车的心理模型
机构 * Computer Science & Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology(计算机科学与人工智能实验室(CSAIL),麻省理工学院) ; Motional AD Inc.(Motional AD公司) ; Department of Psychology and Center for Brain Science, Harvard University(心理学系和大脑科学中心,哈佛大学) ; Department of Aeronautics and Astronautics, Massachusetts Institute of Technology(航空与宇航系,麻省理工学院)
专题命中 规划决策 :autonomous agent(abstract);分类 cs.AI、cs.LG
AI总结 提出概念包装网络(CW-Net),在真实自动驾驶车上实现可解释规划,通过因果性概念解释提升驾驶员对车辆行为的预测能力,尤其在意外场景中。
Comments MST & JAS contributed equally to this work