MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
MeanFuser: 一种基于MeanFlow的高效多模态轨迹生成与自适应重构方法用于端到端自动驾驶
机构 * SKL-MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室) ; School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) ; Xiaomi EV(小米汽车) ; Institute for AI Industry Research (AIR), Tsinghua University(清华大学智能产业研究院)
专题命中 规划控制 :autonomous driving(title,abstract);trajectory planning(abstract);分类 cs.RO、cs.CV
AI总结 本文提出MeanFuser,通过引入Gaussian Mixture Noise、MeanFlow Identity和轻量级ARM模块,实现了高效且鲁棒的多模态轨迹生成与自适应重构,提升了端到端自动驾驶的性能和效率。
Comments Accepted by CVPR 2026