Perturbation-Based Epistemic Uncertainty for Failure Detection in Vision-Language-Action Models

Published September 1, 2026 · Category: Robotics

Overview

arXiv:2606.20754v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have shown strong performance in robotic manipulation, but reliable uncertainty quantification remains challenging, particularly under distribution shift. Unlike autoregressive policies, many modern VLA models generate continuous actions through regression or flow-based generation, where explicit predictive probabilities are unavailable. Moreover, stochastic action sampling primarily captures action-generation variability under a fixed model, while failure detection under distribution shift can benefit from capturing uncertainty in the model itself. Motivated by Bayesian perspectives on local model variations, we propose perturbation-based failure detection (PFD), a training-free framework for estimating epistemic uncertainty in VLA models through low-rank weight perturbations. Specifically, we inject random low-rank perturbations into selected transformer weight matrices and estimate epistemic uncertainty from disagreement across perturbed action predictions. Experiments on LIBERO-PRO show that PFD achieves the highest average AUROC and balanced accuracy among the evaluated methods while consistently outperforming stochastic action sampling across distribution shifts. Real-world robot experiments further demonstrate that PFD provides a competitive failure-detection signal under an unseen object shift.

Source

Originally published at arxiv.org.

Related Articles

• Event-triggered Control and Online Learning for Networked Systems under Computational Delays
• Calibration and Comparative Analysis of Forward-Looking Sonar and 3D Sonar for Enhanced Underwater Object Recognition
• Feelium: A Touchable Blimp Body for Aerial Telepresence