发表机构
Nanyang Technological University; Daimon Robotics（南洋理工大学; 戴蒙机器人）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对相似触觉观测可能对应不同任务风险的问题，提出RATE方法，通过历史条件化预测和警报监督学习风险感知触觉表征，并借助轻量级残差适配器提升机器人操作任务成功率。
AI 中文摘要
触觉感知对于接触丰富的机器人操作尤为有价值。近期工作在机器人操作的触觉表征学习方面取得了显著进展。然而，相似的触觉观测可能源于具有截然不同任务风险含义的交互条件，例如传感器噪声、任务必要的变化以及出现的不良接触。在没有基于上下文的风险信息的情况下，这些情况对下游策略而言可能产生歧义，导致对良性变化进行不必要的修正，或对真正有风险的接触反应迟缓。为解决这一局限，我们提出了风险感知触觉编码（RATE），它学习编码任务条件化交互风险的触觉表征。具体而言，历史条件化预测捕获交互上下文，而警报监督将该上下文与任务条件化风险相关联。学习到的风险感知表征通过轻量级残差适配器补充传统触觉特征。在仿真和真实世界中的实验均表明任务成功率有显著提升，受控消融实验证实了警报引导学习与预测性时间建模的互补优势。
英文摘要
Tactile sensing is particularly valuable for contact-rich robotic manipulation. Recent work has made substantial progress in tactile representation learning for robotic manipulation. However, similar tactile observations can arise from interaction conditions with very different task-risk implications, such as sensor noise, task-necessary variations, and emerging undesirable contact. Without context-grounded risk information, these cases can be ambiguous to downstream policies, leading to unnecessary corrections to benign variations or delayed responses to genuinely risky contact. To address this limitation, we propose Risk-Aware Tactile Encoding (RATE), which learns tactile representations that encode task-conditioned interaction risk. Specifically, history-conditioned prediction captures interaction context, while alert supervision associates this context with task-conditioned risk. The learned risk-aware representation complements conventional tactile features through a lightweight residual adapter. Experiments in both simulation and the real world demonstrate substantial improvements in task success, with controlled ablations confirming the complementary benefits of alert-guided learning and predictive temporal modeling.
Comments8 pages, 3 figures, 3 tables
