English(EN) TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environments

机器人通过新的TACTFUL框架仅用触觉学习识别物体

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-23 15:33

研究人员开发了TACTFUL，一个新颖的框架，使机器人能够仅通过触觉进行探索和识别物体，无需视觉。该系统允许多指机器人自主导航封闭空间，通过接触发现物体并重建其形状。TACTFUL在真实硬件上进行训练，成功率达到77%，平均重建误差为0.015米，优于现有方法。 AI

影响这种基于触觉的方法可以使机器人在视觉受限或不可能的环境中运行，扩展它们在制造和探索等领域的效用。

排序理由在arXiv上发表的研究论文，详细介绍了一个新的机器人框架。

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]

arXiv cs.AI TIER_1 English(EN) · Shivani Kamtikar, Chung Hee Kim, Camilla Tabasso, Tye Brady, Joshua Migdal, Taskin Padir · 2026-06-24 04:00

TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environments

arXiv:2606.24712v1 Announce Type: cross Abstract: Humans effortlessly locate and identify objects by touch alone, even without vision. In contrast, robotic systems rely heavily on vision and struggle with autonomous tactile exploration and object identification. We present TACTFU…
arXiv cs.AI TIER_1 English(EN) · Taskin Padir · 2026-06-23 15:33

TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environments

Humans effortlessly locate and identify objects by touch alone, even without vision. In contrast, robotic systems rely heavily on vision and struggle with autonomous tactile exploration and object identification. We present TACTFUL, a vision-free tactile exploration framework tha…