# RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Deployment

arXiv: https://arxiv.org/abs/2602.01515 · HTML: https://mlsanity.com/paper/2602.01515/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks](https://mlsanity.com/paper/1903.08792/) (2019)
- [A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder](https://mlsanity.com/paper/1711.00614/) (2017)
- [Lyapunov-based Safe Policy Optimization for Continuous Control](https://mlsanity.com/paper/1901.10031/) (2019)
- [Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies](https://mlsanity.com/paper/2503.08558/) (2025)
- [Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection](https://mlsanity.com/paper/2404.07099/) (2024)
- [PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection](https://mlsanity.com/paper/2401.09793/) (2024)
- [Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning](https://mlsanity.com/paper/2112.02694/) (2021)
- [Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation](https://mlsanity.com/paper/2503.05238/) (2025)
- [Mamba Adaptive Anomaly Transformer with association discrepancy for time series](https://mlsanity.com/paper/2502.07858/) (2025)
- [Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution](https://mlsanity.com/paper/2509.14816/) (2025)
- [Whole-Body Dynamic Throwing with Legged Manipulators](https://mlsanity.com/paper/2410.05681/) (2024)

## Built on by (most cited first, 1 of 1)

- [Self-Evolving AI for Humanoids: Mechanisms, Safety, and Evaluation of Post-Deployment Self-Improvement](https://mlsanity.com/paper/2609.13236/) (2026)

## Abstract (arXiv)

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 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 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/.