Research map / Label-efficient and robust learning / OOD and anomaly detection
RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation
Shijie Zhou, Bin Zhu, Jiarui Yang, Xiangyu Zhao, Jingjing Chen, Yu-Gang Jiang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add task embedding conditioning (ablation) | RC-NF · LIBERO-Anomaly-10 Spatial Misalignment | AUC: 0.8139 -> 0.9676 | Improved |
| add task embedding conditioning (ablation) | RC-NF · LIBERO-Anomaly-10 Average | AUC: 0.8643 -> 0.9309 | Improved |
| add robot state conditioning (ablation) | RC-NF · LIBERO-Anomaly-10 Gripper Open | AUC: 0.6327 -> 0.9312 | Improved |
| add robot state conditioning (ablation) | RC-NF · LIBERO-Anomaly-10 Average | AUC: 0.7152 -> 0.9309 | Improved |
| add Positional Residual branch (ablation) | RC-NF · LIBERO-Anomaly-10 Average | AUC: 0.8947 -> 0.9309 | Improved |
| add Dynamic Shape branch (ablation) | RC-NF · LIBERO-Anomaly-10 Average | AUC: 0.6841 -> 0.9309 | Improved |
| add Dynamic Shape branch (ablation) | RC-NF · LIBERO-Anomaly-10 Spatial Misalignment | AUC: 0.1022 -> 0.9676 | Improved |
| replace VLM monitor GPT-5 with RC-NF | anomaly monitor · LIBERO-Anomaly-10 Spatial Misalignment | AUC: 0.4904 -> 0.9676 | Improved |
| replace FailDetect with RC-NF | anomaly monitor · LIBERO-Anomaly-10 Average | AUC: 0.7181 -> 0.9309 | Improved |
| replace GPT-5 with RC-NF | anomaly monitor · LIBERO-Anomaly-10 Gripper Open | AUC: 0.9137 -> 0.9312 | Improved |
Closest papers by meaning
- SAFE: Multitask Failure Detection for Vision-Language-Action Models (NeurIPS 2025 · similarity 0.87)
- RoboProcessBench: Benchmarking Process-Aware Understanding in Visual-Language Robotic Manipulation (NeurIPS 2026 · similarity 0.86)
- AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation (ICLR 2025 · similarity 0.86)
- FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation (AAAI 2025 · similarity 0.85)
- Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation (ICLR 2025 · similarity 0.85)
- Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
