论文/arXiv 2609.33235·1 个月前

面向机器人操作的触觉交互感知物体中心表征学习

针对视觉难以推断的物体属性，提出触觉探索学习物体中心表征，并在三类视觉歧义操作任务上验证提升。

AI 整理

• 数据与采集
• 评测与安全

原文链接：Learning with Object-centric Representations of Tactile Interactive Perception for Robot Manipulation（arXiv 2609.33235 · 发布日期：2026-09-27）

Learning with Object-centric Representations of Tactile Interactive Perception for Robot Manipulation

针对视觉难以推断的物体属性，提出触觉探索学习物体中心表征，并在三类视觉歧义操作任务上验证提升。

核心要点

• 视觉难以直接推断材料、内容物、柔软度等隐式属性，触觉信号又短暂稀疏。
• 框架通过触觉探索学习任务无关表征，token learner从长时探索中选取代表性片段。
• 与描述性文本嵌入做对比对齐，形成捕捉多种物理属性的潜在空间并指导策略。
• 实验中属性估计在已见/未见物体达93%/84%，三类任务成功率较基线提高。

验证范围与局限：验证范围为已见和未见物体上的多物体重排、倒取和开盒三类视觉歧义任务。

英文摘要 (Abstract)

Implicit object properties that are difficult to directly infer from vision, such as material, container contents, or softness, can be revealed through tactile sensing and exploratory interactions. However, because tactile signals are transient and sparse, extracting informative tactile events and effectively incorporating them into robotic manipulation remains a challenge. In this work, we present an object-centric context-aware manipulation framework that learns task-agnostic object representations through tactile exploration. A token learner autonomously selects representative tactile segments from long-horizon exploration, while contrastive alignment with descriptive text embeddings enables a latent space that captures multiple physical object properties. These learned representations are then used as semantic context to guide object-centric manipulation policies and adapt strategies based on object properties. Experiments show that the learned representations achieve 93% and 84% property estimation accuracy on seen and unseen objects. Evaluated on three tasks involving visually ambiguous objects, i.e. multi-object rearrangement, pouring, and box opening, the proposed framework improves both target selection and property-dependent manipulation adaptation, raising task success, aggregated over all evaluation trials, from 41% to 92% on seen objects and from 19% to 67% on unseen objects over baseline policies without object-context conditioning. Videos and additional results are available at https://xinyiyxyx.github.io/tactile-object-centric/.

作者：Xinyi Yang, Zilin Si, Zhuowei Xu, Zeynep Temel, Oliver Kroemer

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2609.33235：Learning with Object-centric Representations of Tactile Interactive Perception for Robot Manipulation访问 2026-10-21