Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910059162763264 |
|---|---|
| author | Tang, Yanchuan Wang, Taowen Chen, Yuefei Zhang, Boxuan Guan, Qiang Tang, Ruixiang |
| author_facet | Tang, Yanchuan Wang, Taowen Chen, Yuefei Zhang, Boxuan Guan, Qiang Tang, Ruixiang |
| contents | Vision-Language-Action (VLA) models enable general-purpose robotic policies by mapping visual observations and language instructions to low-level actions, but they often lack reliable introspection. A common practice is to compute a token-level uncertainty signal and take its mean over a rollout. However, mean aggregation can dilute short-lived but safety-critical uncertainty spikes in continuous control. In particular, successful rollouts may contain localized high-entropy segments due to benign noise or non-critical micro-adjustments, while failure rollouts can appear low-entropy for most timesteps and only exhibit brief spikes near the onset of failure. We propose a unified uncertainty quantification approach for predicting rollout success versus failure that (1) uses max-based sliding window pooling to preserve transient risk signals, (2) applies motion-aware stability weighting to emphasize high-frequency action oscillations associated with unstable behaviors, and (3) performs DoF-adaptive calibration via Bayesian Optimization to prioritize kinematically critical axes. Experiments on the LIBERO benchmark show that our method substantially improves failure prediction accuracy and yields more reliable signals for failure detection, which can support downstream human-in-the-loop interventions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18342 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model Tang, Yanchuan Wang, Taowen Chen, Yuefei Zhang, Boxuan Guan, Qiang Tang, Ruixiang Robotics Artificial Intelligence Machine Learning Vision-Language-Action (VLA) models enable general-purpose robotic policies by mapping visual observations and language instructions to low-level actions, but they often lack reliable introspection. A common practice is to compute a token-level uncertainty signal and take its mean over a rollout. However, mean aggregation can dilute short-lived but safety-critical uncertainty spikes in continuous control. In particular, successful rollouts may contain localized high-entropy segments due to benign noise or non-critical micro-adjustments, while failure rollouts can appear low-entropy for most timesteps and only exhibit brief spikes near the onset of failure. We propose a unified uncertainty quantification approach for predicting rollout success versus failure that (1) uses max-based sliding window pooling to preserve transient risk signals, (2) applies motion-aware stability weighting to emphasize high-frequency action oscillations associated with unstable behaviors, and (3) performs DoF-adaptive calibration via Bayesian Optimization to prioritize kinematically critical axes. Experiments on the LIBERO benchmark show that our method substantially improves failure prediction accuracy and yields more reliable signals for failure detection, which can support downstream human-in-the-loop interventions. |
| title | Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.18342 |