Robot-WATCHDOG:基于以对象为中心的图表示的故障检测
Robot-WATCHDOG : failure detection through object-centric graph representation
AI总结:
提出Robot-WATCHDOG自监督框架,以对象为中心的时空图建模操纵场景,结合TPC与GnnT两种故障分数,在6项任务的数据集上优于图像类故障检测器,提升了语义与交互级故障检测性能。
摘要:
可靠的实时故障检测对于部署学习到的机器人策略至关重要,但在开放世界环境中明确界定故障是不可行的,这促使仅从正常演示中进行故障检测。然而,现有方法难以在对良性变化的鲁棒性与捕捉语义和交互级错误的能力之间取得平衡。我们提出Robot-WATCHDOG,这是一个将操纵场景建模为以对象为中心的时空图的自监督框架。基于该表示,我们研究两种互补的故障分数:轨迹投影与相关性(TPC),一种用于几何偏差和关系一致性的非参数度量;以及GnnT,一种带有Transformer的图注意力网络,用于预测未来对象状态。我们在一个公共基准和一个新的语义复杂操纵任务数据集上对两者进行评估,涉及6个任务和10个随机种子。两种分数均优于基于图像的故障检测器,尤其在语义和交互级故障上表现突出。TPC在两个数据集的平均AUPR和MCC上提供最强性能,且种子间方差低。定性结果可在该https URL获取。
英文摘要:
Reliable real-time failure detection is critical for deploying learned robotic policies, yet defining failures explicitly is infeasible in open-world settings. This motivates failure detection from nominal demonstrations alone. Existing methods, however, struggle to balance robustness to benign variations with the ability to capture semantic and interaction-level errors. We introduce Robot-WATCHDOG, a self-supervised framework that models manipulation scenes as object-centric spatio-temporal graphs. Building on this representation, we investigate two complementary failure scores: Trajectory Projection and Correlation (TPC), a non-parametric measure of geometric deviation and relational consistency, and GnnT, a Graph Attention Network with a Transformer that predicts future object states. We evaluate both on a public benchmark and on a new dataset of semantically complex manipulation tasks, across six tasks and ten random seeds. Both scores outperform image-based failure detectors, particularly on semantic and interaction-level failures. TPC provides the strongest performance in AUPR and MCC on both dataset averages, with low variance across seeds. Qualitative results are made available at https://cea-list.github.io/Robot-WATCHDOG/.
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。