PulseAugur
中
实时 09:24:14

新H-Tac数据集和TTP系统推动机器人触觉操作发展

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员推出了H-Tac，这是一个包含160小时人类视频的大型数据集，涵盖300多个任务，旨在改善机器人操作的触觉感知。他们还开发了可迁移触觉预训练（TTP）系统，该系统利用这些人类数据对机器人进行预训练。这种方法使用统一的触觉和动作空间，促进人类到机器人的知识迁移，并明确建模接触动力学以增强精细操作能力。 AI

影响 通过实现人类触觉技能更有效的迁移，增强了机器人的灵巧性和操作能力。

排序理由 这是一篇详细介绍机器人操作新数据集和预训练系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新H-Tac数据集和TTP系统推动机器人触觉操作发展

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Xinghao Zhu, Zixi Liu, Shalin Jain, Chenran Li, Milad Noori, Huihua Zhao, John Welsh, Michael Andres Lin, Wei Liu, Tingwu Wang, Xingye Da, Zhengyi Luo, Vishal Kulkarni, Naema Bhatti, Yuke Zhu, Linxi Fan, Bowen Wen, Danfei Xu, Soha Pouya, Yan Chang ·

    Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration

    arXiv:2607.00033v1 Announce Type: cross Abstract: Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration in Roboti…

  2. arXiv cs.CV TIER_1 English(EN) · Chi Zhang, Penglin Cai, Ziheng Xi, Haoqi Yuan, Hao Luo, Wanpeng Zhang, Sipeng Zheng, Chaoyi Xu, Zongqing Lu ·

    Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation

    arXiv:2607.01067v1 Announce Type: cross Abstract: As an essential modality for dexterous and contact-rich tasks, tactile sensing provides precise force feedback that cannot be reliably inferred from vision. However, limited by hardware and data collection systems, existing datase…

  3. arXiv cs.CV TIER_1 English(EN) · Zongqing Lu ·

    面向人类的可迁移触觉预训练用于灵巧机器人操作

    As an essential modality for dexterous and contact-rich tasks, tactile sensing provides precise force feedback that cannot be reliably inferred from vision. However, limited by hardware and data collection systems, existing datasets with tactility remain small in scale and narrow…

相关实体

相关话题