Humans can achieve diverse in-hand manipulations, such as object pinching and tool use, which often involve simultaneous contact between the object and multiple fingers. This is still an open issue for robotic hands because such dexterous manipulation requires distinguishing between tactile sensations generated by their self-contact and those arising from external contact. Otherwise, object/robot breakage happens due to contacts/collisions. Indeed, most approaches ignore self-contact altogether, by constraining motion to avoid/ignore self-tactile information during contact. While this reduces complexity, it also limits generalization to real-world scenarios where self-contact is inevitable. Humans overcome this challenge through self-touch perception, using predictive mechanisms that anticipate the tactile consequences of their own motion, through a principle called sensory attenuation, where the nervous system differentiates predictable self-touch signals, allowing novel object stimuli to stand out as relevant. Deriving from this, we introduce TaSA, a two-phased deep predictive learning framework. In the first phase, TaSA explicitly learns self-touch dynamics, modeling how a robot's own actions generate tactile feedback. In the second phase, this learned model is incorporated into the motion learning phase, to emphasize object contact signals during manipulation. We evaluate TaSA on a set of insertion tasks, which demand fine tactile discrimination: inserting a pencil lead into a mechanical pencil, inserting coins into a slot, and fixing a paper clip onto a sheet of paper, with various orientations, positions, and sizes. Across all tasks, policies trained with TaSA achieve significantly higher success rates than baseline methods, demonstrating that structured tactile perception with self-touch based on sensory attenuation is critical for dexterous robotic manipulation.

翻译：人类能够实现多样化的手内操作，如物体捏取和工具使用，这些操作通常涉及物体与多个手指间的同步接触。对于机器人手而言，这仍是一个开放性问题，因为此类灵巧操作需要区分由自身接触产生的触觉感知与外部接触引发的触觉感知。否则，接触/碰撞将导致物体/机器人损坏。事实上，大多数方法通过约束运动以规避/忽略接触过程中的自触觉信息，从而完全忽视了自接触问题。虽然这降低了复杂性，但也限制了在自接触不可避免的真实场景中的泛化能力。人类通过自触觉感知克服了这一挑战，利用预测机制来预判自身运动产生的触觉结果，其原理称为感知衰减——神经系统通过区分可预测的自接触信号，使新物体刺激作为相关信号凸显出来。受此启发，我们提出了TaSA，一个双阶段深度预测学习框架。在第一阶段，TaSA显式学习自接触动力学，建模机器人自身动作如何生成触觉反馈。在第二阶段，将习得的模型整合至运动学习阶段，以强化操作过程中的物体接触信号。我们在系列插入任务上评估TaSA，这些任务需要精细的触觉辨别能力：将铅笔芯插入自动铅笔、将硬币投入投币口、将回形针固定于纸张，并涵盖不同朝向、位置和尺寸。在所有任务中，采用TaSA训练的策略均取得显著高于基线方法的成功率，证明基于感知衰减的自接触结构化触觉感知对于机器人灵巧操作至关重要。