让机器人模型更敏感地响应操作变化，提升异常状态检测能力。
Sensitivity Shaping for Latent Modeling
- 通过控制敏感性正则化增强模型在高支持区域的响应灵敏度。
- 实验显示在障碍避障、操控和真实机器人导航中异常检测准确率显著提升。
- 适合需要安全闭环规划的机器人系统研发人员参考。
生成式动力学模型可实现复杂机器人系统的规划，但安全部署需可靠检测策略引发的分布外（OOD）状态转移。现有方法通常将学习到的动力学视为固定，并附加后验支持代理。我们发现，当动力学对关键动作选择局部不敏感时，这些代理可能失效：未受支持的动作可能产生与示范状态相似的潜在预测，从而抑制了实际巨大预测误差所应产生的OOD信号。为此，我们提出支持条件下的控制敏感性正则化，使学习到的动力学在高支持训练区域对控制输入变化保持敏感响应。该方法在保留控制诱导变化的同时，限制了因弱经验支持导致的不稳定外推。视觉引导的障碍避障、操纵及真实机器人导航实验表明，该方法提升了OOD检测能力，实现了更安全的闭环规划。
原文摘要 · Abstract (English)
Generative dynamics models enable planning in challenging robotic systems, but safe deployment requires reliably detecting policy-induced out-of-distribution (OOD) transitions. Existing methods typically treat the learned dynamics as fixed and attach post hoc support surrogates. We show that these surrogates can fail when the dynamics are locally insensitive to critical action choices: unsupported control actions may produce latent predictions that resemble demonstrated transitions, suppressing OOD signals despite large true predictive errors. To address this, we introduce support-conditioned control-sensitivity regularization, which promotes sensitive local response to control input changes in learned dynamics in high-support training regions. This preserves control-induced variation while limiting unstable extrapolation due to weak empirical support. Experiments in vision-based obstacle avoidance, manipulation, and real-robot navigation show improved OOD detection and safer closed-loop planning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。