{"ID":2835094,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00324","arxiv_id":"2512.00324","title":"MILE: A Mechanically Isomorphic Exoskeleton Data Collection System with Fingertip Visuotactile Sensing for Dexterous Manipulation","abstract":"Imitation learning provides a promising approach to dexterous hand manipulation, but its effectiveness is limited by the lack of large-scale, high-fidelity data. Existing data-collection pipelines suffer from inaccurate motion retargeting, low data-collection efficiency, and missing high-resolution fingertip tactile sensing. We address this gap with MILE, a mechanically isomorphic teleoperation and data-collection system co-designed from human hand to exoskeleton to robotic hand. The exoskeleton is anthropometrically derived from the human hand, and the robotic hand preserves one-to-one joint-position isomorphism, eliminating nonlinear retargeting and enabling precise, natural control. The exoskeleton achieves a multi-joint mean absolute angular error below one degree, while the robotic hand integrates compact fingertip visuotactile modules that provide high-resolution tactile observations. Built on this retargeting-free interface, we teleoperate complex, contact-rich in-hand manipulation and efficiently collect a multimodal dataset comprising high-resolution fingertip visuotactile signals, RGB-D images, and joint positions. The teleoperation pipeline achieves a mean success rate improvement of 64%. Incorporating fingertip tactile observations further increases the success rate by an average of 25% over the vision-only baseline, validating the fidelity and utility of the dataset. Further details are available at: https://sites.google.com/view/mile-system.","short_abstract":"Imitation learning provides a promising approach to dexterous hand manipulation, but its effectiveness is limited by the lack of large-scale, high-fidelity data. Existing data-collection pipelines suffer from inaccurate motion retargeting, low data-collection efficiency, and missing high-resolution fingertip tactile se...","url_abs":"https://arxiv.org/abs/2512.00324","url_pdf":"https://arxiv.org/pdf/2512.00324v2","authors":"[\"Jinda Du\",\"Jieji Ren\",\"Qiaojun Yu\",\"Ningbin Zhang\",\"Yu Deng\",\"Xingyu Wei\",\"Yufei Liu\",\"Guoying Gu\",\"Xiangyang Zhu\"]","published":"2025-11-29T05:34:39Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\",\"cs.HC\"]","methods":"[]","project_urls":"[\"https://sites.google.com/view/mile-system\"]","has_code":false,"code_links":[{"ID":606484,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2835094,"paper_url":"https://arxiv.org/abs/2512.00324","paper_title":"MILE: A Mechanically Isomorphic Exoskeleton Data Collection System with Fingertip Visuotactile Sensing for Dexterous Manipulation","repo_url":"https://github.com/google/safevalues","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}