July 8, 2026 · Wednesday2026 年 7 月 8 日 · No. 4 NEWSACCESSABOUT

AUTOSIGNAL 车智信号

Human-curated. Expert-annotated. Every signal traced to source. 人工精选 · 专家点评 · 每条信号可溯源

← All signals← 返回全部信号

Research Frontier研究前沿

H-Tac Released: 160-Hour Tactile Dataset Advances Human-to-Robot Knowledge TransferH-Tac 发布:160小时触觉数据集实现人-机知识转移

S 1.7 T1 1 sources1 个来源 R7-research
  1. Researchers submitted a paper introducing H-Tac, a large-scale tactile-action dataset with 160 hours of egocentric human videos containing over 300 tasks and 135,000 episodes, paired with a Transferable Tactile Pre-Training (TTP) framework for robotic manipulation.
  2. The dataset addresses critical limitations in existing tactile sensing systems, which suffer from small scale and narrow contact coverage; H-Tac's scale and task diversity enable larger-scale tactile-based pre-training compared to current alternatives.
  3. The TTP framework preserves human knowledge during robot transfer by using unified tactile and action spaces across pre-training and post-training phases, with a tactile expert for future tactile prediction to improve performance on downstream dexterous tasks.
  1. 研究人员发表论文介绍 H-Tac 数据集,包含 160 小时第一人称人类视频、300+ 任务和 135k 个 episode,并提出可转移触觉预训练系统 (TTP)。
  2. H-Tac 解决了现有触觉数据集规模小、接触覆盖面窄的问题,通过 160 小时人类视频和 135k 个 episode 在 300+ 任务上实现大规模触觉预训练。
  3. TTP 框架在预训练和微调阶段使用统一的触觉和动作空间,通过触觉专家进行未来触觉预测,保留人类到机器人的知识转移,提升下游灵巧操作任务的性能。