Image de couverture de livre

Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Chen, Nguyen, Tony Khuong, Dixon, Emma, Rodriguez, Christopher, Miller, Patrick, Lee, Robert, Shah, Paarth, Ambrus, Rares, Nishimura, Haruki, Itkina, Masha
Format:	Preprint
Publié:	2025
Sujets:	Robotics Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping
par: Snyder, David, et autres
Publié: (2025)

SAFE: Multitask Failure Detection for Vision-Language-Action Models
par: Gu, Qiao, et autres
Publié: (2025)

How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation
par: Vincent, Joseph A., et autres
Publié: (2024)

Impact of Different Failures on a Robot's Perceived Reliability
par: Violette, Andrew, et autres
Publié: (2026)

Reliably Detecting Model Failures in Deployment Without Labels
par: Nguyen, Viet, et autres
Publié: (2025)

Failure Prediction at Runtime for Generative Robot Policies
par: Römer, Ralf, et autres
Publié: (2025)

Video Generators are Robot Policies
par: Liang, Junbang, et autres
Publié: (2025)

STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
par: Goli, Hossein, et autres
Publié: (2025)

Beyond Binary Success: Sample-Efficient and Statistically Rigorous Robot Policy Comparison
par: Snyder, David, et autres
Publié: (2026)

Typicalness-Aware Learning for Failure Detection
par: Liu, Yijun, et autres
Publié: (2024)

Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?
par: Li, Shuqing, et autres
Publié: (2025)

Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning
par: Zheng, Gehan, et autres
Publié: (2026)

Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress
par: Agia, Christopher, et autres
Publié: (2024)

Interpretable Failure Detection with Human-Level Concepts
par: Nguyen, Kien X., et autres
Publié: (2025)

Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection
par: Sbeyti, Moussa Kassem, et autres
Publié: (2024)

RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning
par: Dai, Yinpei, et autres
Publié: (2024)

Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
par: Huang, Kevin, et autres
Publié: (2025)

Near-Miss: Latent Policy Failure Detection in Agentic Workflows
par: Rabinovich, Ella, et autres
Publié: (2026)

Chapter 12 Economising Failure and Assembling a Failure Regime
par: Kurunmäki, Liisa, et autres
Publié: (2023)

Bank Runs With and Without Bank Failure
par: Correia, Sergio, et autres
Publié: (2026)

RuntimeSlicer: Towards Generalizable Unified Runtime State Representation for Failure Management
par: Zhang, Lingzhe, et autres
Publié: (2026)

Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners
par: Zheng, Zhi, et autres
Publié: (2024)

Uncertainties of Failure in Bending Experiments
par: Silu Zhang, et autres
Publié: (2026)

Failure Detection for Pinching-Antenna Systems
par: Ouyang, Chongjun, et autres
Publié: (2026)

The Failure of Plagiarism Detection in Competitive Programming
par: Dickey, Ethan
Publié: (2025)

CUPID: Curating Data your Robot Loves with Influence Functions
par: Agia, Christopher, et autres
Publié: (2025)

Silent Failures in Stateless Systems: Rethinking Anomaly Detection for Serverless Computing
par: Nguyen, Chanh, et autres
Publié: (2025)

Low-Resource Safety Failures Are Action Failures, Not Representation Failures
par: Aziz, Rashad, et autres
Publié: (2026)

DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving
par: Dagdanov, Resul, et autres
Publié: (2022)

FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
par: Ma, Ruize, et autres
Publié: (2026)

Log-Anomaly-Detection-and-Failure-Prediction-System
par: VAIBHAV CHAUHAN
Publié: (2026)

Adaptive Confidence Regularization for Multimodal Failure Detection
par: Liu, Moru, et autres
Publié: (2026)

Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
par: Park, Seongheon, et autres
Publié: (2026)

Failure-Centered Runtime Evaluation for Deployed Trilingual Public-Space Agents
par: Meng, M.
Publié: (2026)

Failure Identification in Imitation Learning Via Statistical and Semantic Filtering
par: Rolland, Quentin, et autres
Publié: (2026)

Early Failure Detection in Autonomous Surgical Soft-Tissue Manipulation via Uncertainty Quantification
par: Thompson, Jordan, et autres
Publié: (2025)

FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection
par: Wang, Huanchi, et autres
Publié: (2026)

Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure
par: Sartori, Camilo Chacón
Publié: (2026)

Distributed Empirical Likelihood Inference With or Without Byzantine Failures
par: Wang, Qihua, et autres
Publié: (2024)

Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
par: Patel, Nyal, et autres
Publié: (2025)