VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving
VECTOR-Drive: 紧密耦合的视觉-语言与轨迹专家路由用于端到端自动驾驶
机构 * College of Automotive Engineering, Jilin University(吉林大学汽车工程学院) ; The National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University(吉林大学汽车底盘集成与生物力学国家级重点实验室) ; ReeFocus AI Technology(ReeFocus人工智能技术)
专题命中 动作表示与策略 :VLA(abstract,abstract_cn);vision-language-action(abstract);分类 cs.RO、cs.CV、cs.AI
AI总结 本文提出VECTOR-DRIVE框架,通过紧密耦合的视觉-语言与轨迹专家路由,解决端到端自动驾驶中视觉语言理解和轨迹预测之间的耦合问题,实现更高的任务性能。