{"ID":2862494,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25746","arxiv_id":"2509.25746","title":"TacRefineNet: Tactile-Only Grasp Refinement Between Arbitrary In-Hand Object Poses","abstract":"Despite progress in both traditional dexterous grasping pipelines and recent Vision-Language-Action (VLA) approaches, the grasp execution stage remains prone to pose inaccuracies, especially in long-horizon tasks, which undermines overall performance. To address this \"last-mile\" challenge, we propose TacRefineNet, a tactile-only framework that achieves fine in-hand pose refinement of known objects in arbitrary target poses using multi-finger fingertip sensing. Our method iteratively adjusts the end-effector pose based on tactile feedback, aligning the object to the desired configuration. We design a multi-branch policy network that fuses tactile inputs from multiple fingers along with proprioception to predict precise control updates. To train this policy, we combine large-scale simulated data from a physics-based tactile model in MuJoCo with real-world data collected from a physical system. Comparative experiments show that pretraining on simulated data and fine-tuning with a small amount of real data significantly improves performance over simulation-only training. Extensive real-world experiments validate the effectiveness of the method, achieving millimeter-level grasp accuracy using only tactile input. To our knowledge, this is the first method to enable arbitrary in-hand pose refinement via multi-finger tactile sensing alone. Project website is available at https://sites.google.com/view/tacrefinenet","short_abstract":"Despite progress in both traditional dexterous grasping pipelines and recent Vision-Language-Action (VLA) approaches, the grasp execution stage remains prone to pose inaccuracies, especially in long-horizon tasks, which undermines overall performance. To address this \"last-mile\" challenge, we propose TacRefineNet, a ta...","url_abs":"https://arxiv.org/abs/2509.25746","url_pdf":"https://arxiv.org/pdf/2509.25746v1","authors":"[\"Shuaijun Wang\",\"Haoran Zhou\",\"Diyun Xiang\",\"Yangwei You\"]","published":"2025-09-30T04:05:03Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","project_urls":"[\"https://sites.google.com/view/tacrefinenet\"]","has_code":false,"code_links":[{"ID":608900,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2862494,"paper_url":"https://arxiv.org/abs/2509.25746","paper_title":"TacRefineNet: Tactile-Only Grasp Refinement Between Arbitrary In-Hand Object Poses","repo_url":"https://github.com/google/safevalues","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}