Towards Trustworthy and Explainable AI for Perception Models: From Concept to Prototype Vehicle Deployment
面向感知模型的可信与可解释人工智能:从概念到原型车辆部署
机构 * Institute for Automotive Engineering, RWTH Aachen University(汽车工程研究所,亚琛工业大学)
专题命中 感知 :autonomous driving(abstract);driving perception(abstract);分类 cs.RO、cs.AI
AI总结 本文提出一个结合鲁棒性、可解释性和不确定性校准的Transformer感知模块,并部署于原型车辆,通过实时可视化验证可信AI的可行性。
Comments Accepted for publication at IEEE ITSC 2026