RAPT:面向真实人类机器人的模型预测异常检测与故障诊断
RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Deployment
AI总结:
RAPT通过模型预测异常检测和故障诊断技术,提升人形机器人在仿真到现实转移中的鲁棒性和可解释性。
摘要:
在人形机器人上部署学习到的控制策略具有挑战性:在仿真中表现稳健的策略在仿真到现实转移后可能在分布外(OOD)状态下自信执行,导致无声故障,可能损坏硬件。尽管异常检测可以缓解这些故障,但先前的方法往往与高速控制不兼容,难以在极低的误报率下校准,或作为黑箱操作,仅提供二进制停止信号而无法解释机器人为何偏离正常行为。我们提出了RAPT,一种轻量、自监督的部署时间监控器,适用于50Hz的人形控制。RAPT从仿真中学习了正常执行的概率时空流形,并将执行时间预测偏差作为校准的、每维信号进行评估。这产生了(i)在严格误报率约束下可靠的OOD检测,以及(ii)一个连续、可解释的仿真到现实不匹配度量,可以随时间跟踪以量化部署偏离训练的程度。除了检测外,我们引入了一个自动化的事后根本原因分析流程,结合从RAPT重建目标中导出的基于梯度的时间显著性与基于LLM的推理,这些推理基于显著性和关节运动学,以在零样本设置中生成语义故障诊断。我们评估了RAPT在Unitree G1人形机器人上四个复杂任务的仿真和现实硬件上。在大规模仿真中,RAPT在固定episode级误报率为0.5%的情况下,将真阳性率(TPR)提高了37%。在现实部署中,RAPT实现了12.5%的TPR提升,并提供了可操作的可解释性,仅使用本体数据,在16个现实故障中达到75%的根本原因分类准确率。
英文摘要:
Deploying learned control policies is risky because policies that appear robust in simulation can confidently enter out-of-distribution (OOD) states after Sim-to-Real transfer, causing silent failures and potential hardware damage. Existing anomaly detectors often fail to meet the requirements of high-rate control, extremely low false-positive rates, and interpretable failure feedback. We present \textbf{RAPT} (Recurrent Anomaly Probabilistic Trajectory Model), a lightweight, self-supervised $50$\,Hz deployment monitor that learns nominal execution from large-scale simulation and produces calibrated, per-dimension predictive-deviation signals online. RAPT enables OOD detection under strict false-positive constraints while localizing \emph{when and where} real execution departs from nominal behavior. For post-hoc diagnosis, RAPT combines temporal saliency, joint-kinematic summaries, and LLM-based semantic reasoning to classify likely failure causes in a zero-shot setting. In simulation across four Isaac Lab tasks, RAPT improves TPR by $37\%$ over the strongest baseline at $0.5\%$ episode-level FPR; on hardware, it achieves $89\%$ TPR across $78$ trials with fewer false positives than high-frequency-compatible baselines, and reaches $75\%$ semantic failure diagnosis accuracy across $21$ categories on a challenging OOD subset. Project website, code, and videos: https://humphreymunn.github.io/RAPT/.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。