Peg-in-hole (PiH) assembly is a fundamental yet challenging robotic manipulation task. While reinforcement learning (RL) has shown promise in tackling such tasks, it requires extensive exploration. In this paper, we propose a novel visual-tactile skill learning framework for the PiH task that leverages its inverse task, i.e., peg-out-of-hole (PooH) disassembly, to facilitate PiH learning. Compared to PiH, PooH is inherently easier as it only needs to overcome existing friction without precise alignment, making data collection more efficient. To this end, we formulate both PooH and PiH as Partially Observable Markov Decision Processes (POMDPs) in a unified environment with shared visual-tactile observation space. A visual-tactile PooH policy is first trained; its trajectories, containing kinematic, visual and tactile information, are temporally reversed and action-randomized to provide expert data for PiH. In the policy learning, visual sensing facilitates the peg-hole approach, while tactile measurements compensate for peg-hole misalignment. Experiments across diverse peg-hole geometries show that the visual-tactile policy attains 6.4% lower contact forces than its single-modality counterparts, and that our framework achieves average success rates of 87.5% on seen objects and 77.1% on unseen objects, outperforming direct RL methods that train PiH policies from scratch by 18.1% in success rate. Demos, code, and datasets are available at https://sites.google.com/view/pooh2pih.

翻译：销孔装配（PiH）是机器人操作中一项基础但具有挑战性的任务。尽管强化学习（RL）在解决此类任务中展现出潜力，但其需要大量探索。本文提出一种新颖的视觉-触觉技能学习框架，通过利用PiH的逆任务——拔销脱孔（PooH）拆解——来促进PiH学习。与PiH相比，PooH本质上更易实现，因其仅需克服现有摩擦而无需精确对齐，从而提升数据收集效率。为此，我们在统一环境中将PooH和PiH均建模为部分可观测马尔可夫决策过程（POMDPs），并共享视觉-触觉观测空间。首先训练视觉-触觉PooH策略；其轨迹包含运动学、视觉和触觉信息，通过时间反转和动作随机化处理，为PiH提供专家数据。在策略学习中，视觉感知辅助销-孔接近，而触觉测量补偿销-孔未对准。跨不同销孔几何形状的实验表明，视觉-触觉策略的接触力比单模态策略低6.4%，且本框架在已知物体上的平均成功率达87.5%，在未知物体上达77.1%，相较于从头训练PiH策略的直接RL方法，成功率提升18.1%。演示、代码和数据集见https://sites.google.com/view/pooh2pih。