Tactile memory, the ability to store and retrieve touch-based experience, is critical for contact-rich tasks such as key insertion under uncertainty. To replicate this capability, we introduce Tactile Memory with Soft Robot (TaMeSo-bot), a system that integrates a soft wrist with tactile retrieval-based control to enable safe and robust manipulation. The soft wrist allows safe contact exploration during data collection, while tactile memory reuses past demonstrations via retrieval for flexible adaptation to unseen scenarios. The core of this system is the Masked Tactile Trajectory Transformer (MAT$^\text{3}$), which jointly models spatiotemporal interactions between robot actions, distributed tactile feedback, force-torque measurements, and proprioceptive signals. Through masked-token prediction, MAT$^\text{3}$ learns rich spatiotemporal representations by inferring missing sensory information from context, autonomously extracting task-relevant features without explicit subtask segmentation. We validate our approach on peg-in-hole tasks with diverse pegs and conditions in real-robot experiments. Our extensive evaluation demonstrates that MAT$^\text{3}$ achieves higher success rates than the baselines over all conditions and shows remarkable capability to adapt to unseen pegs and conditions.

翻译：触觉记忆——存储与检索触觉经验的能力——对于不确定条件下的接触密集型任务（如钥匙插入）至关重要。为复现此能力，我们提出触觉记忆软体机器人系统，该系统集成柔性腕部与基于触觉检索的控制，以实现安全、鲁棒的操控。柔性腕部支持数据采集期间的安全接触探索，而触觉记忆通过检索复用过往演示数据，灵活适应未见场景。该系统的核心是掩码触觉轨迹Transformer，其联合建模机器人动作、分布式触觉反馈、力-扭矩测量与本体感知信号间的时空交互。通过掩码标记预测，MAT$^\text{3}$能够从上下文推断缺失的感知信息，从而学习丰富的时空表征，无需显式子任务分割即可自主提取任务相关特征。我们在真实机器人实验中，通过多种销钉与条件下的销孔插入任务验证了所提方法。大量实验表明，MAT$^\text{3}$在所有条件下均比基线方法获得更高的成功率，并展现出适应未见销钉与条件的卓越能力。