PulseAugur
实时 12:51:37
English(EN) NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving

NTR框架增强了自动驾驶的场景令牌瓶颈

研究人员开发了神经令牌重建(NTR),一个旨在改善端到端自动驾驶系统场景令牌瓶颈的新框架。NTR使用自蒸馏掩码潜在重建目标,以确保紧凑的场景令牌保留更丰富的视觉信息用于规划。该方法在推理时移除辅助组件,在Waymo E2E和NavSim等多个自动驾驶基准测试中取得了最先进的成果。 AI

影响 改善了自动驾驶模型中的表示学习,可能带来更鲁棒的规划和决策。

排序理由 该集群包含一篇详细介绍自动驾驶系统新方法的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Jiahui Li, Jiawei Sun, Zixiang Ren, Ming Liu, Jiamin Shi, Ruiteng Zhao, Zhiyang Liu, Liying Liu, Zuoguan Wang, Kaidi Yang ·

    NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving

    arXiv:2605.31116v1 Announce Type: new Abstract: Recent perception-free end-to-end (E2E) autonomous driving methods bypass explicit perception outputs by compressing dense image patch tokens into compact scene tokens for downstream trajectory generation and scoring. While these sc…

  2. arXiv cs.CV TIER_1 English(EN) · Kaidi Yang ·

    NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving

    Recent perception-free end-to-end (E2E) autonomous driving methods bypass explicit perception outputs by compressing dense image patch tokens into compact scene tokens for downstream trajectory generation and scoring. While these scene tokens form a compact visual bottleneck for …