GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving
GraphWorld: 基于世界模型的长时域规划实现端到端自动驾驶
机构 * Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University(北京交通大学计算机科学与技术学院,交通数据挖掘与具身智能北京市重点实验室) ; School of Artificial Intelligence (School of Software), Yanshan University(燕山大学人工智能学院(软件学院)) ; School of Mechanical and Aerospace Engineering, Nanyang Technological University(南洋理工大学机械与航空航天工程学院) ; University of Macau(澳门大学) ; The University of Queensland(昆士兰大学)
专题命中 端到端驾驶 :autonomous driving(title,abstract);trajectory planning(abstract);分类 cs.CV
AI总结 提出GraphWorld框架,通过潜在世界建模增强长时域规划,利用自车中心交互图建模邻车关系,并基于世界状态条件规划实现安全轨迹生成,显著降低碰撞率。
Comments 16 pages, 5 figures