Uncertainty Estimation for VLA Models

VLA: Vision-Language-Action

This field studies how Vision-Language-Action models can estimate whether their actions are likely to succeed, especially during long tasks or under unfamiliar conditions. Approaches include measuring disagreement across ensembles or perturbed models, analyzing action and attention signals, and using conformal prediction or calibrated confidence heads; estimates may be combined across time to catch brief risky moments. These signals can support failure detection, safer abstention, adaptive reasoning, and choosing new demonstrations for training, with benchmarks such as LIBERO used to evaluate them. A central challenge is making confidence both well-calibrated under distribution shift and inexpensive enough to use during real-time control.

Latest papers

32 papers3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Post-hoc Epistemic Uncertainty for Vision-Language-Action Policies
Oct 21, 2026Johannes Keller, Albrecht M. Bloße, Adrian Lindenmeyer +2Uncertainty Estimation for VLA Models Robot Learning
Innovation Center Computer Assisted Surgery (ICCAS), Leipzig University, Leipzig, Germany
Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
Oct 4, 2026Hyemin Yang, Wooseong Jeong, Giwon Lee +1Uncertainty Estimation for VLA Models Efficient VLA Model Inference
KAIST
Do Not Cut When Uncertain: Rejectable and Calibrated Decision Heads for VLA Policies in Robotic Harvesting
Sep 28, 2026Heng ZhangRobotic Harvesting Uncertainty Estimation for VLA Models
Capability-Aware Arbitration for Semantic Intent-Based Shared Control
Sep 21, 2026Zhaoda Du, Michael Bowman, Xiaoli ZhangUncertainty Estimation for VLA Models Human-Robot Collaboration
Colorado School of Mines, Golden, CO 80401, USA. · University of Pennsylvania, Philadelphia, PA 19104, USA.
Video Captioning in Low-Light Conditions through Efficient Uncertainty-Aware Caption Correction
Sep 18, 2026Arefeh RezaeiSparse Gaussian Processes Video Captioning
Faculty of Computer Engineering, K.N. Toosi University of Technology, Tehran, Iran
UDAV: Uncertainty-Driven Adaptive VLM Waypoint Planner
Sep 14, 2026Ghazal Farhani, Shabnam ShabaniUncertainty Estimation for VLA Models Trajectory Generation
The authors are with the Automotive and Surface Transportation Research Centre, National Research Council Canada, London, Ontario, Canada.
Estimating Semantic Ambiguity via Gaussian Context Distributions for VLM-Driven Traversability Analysis
Sep 8, 2026Ramona Häuselmann, Mario A. V. Saucedo, Christoforos Kanellakis +1Uncertainty Estimation for VLA Models Embodied Navigation
Robotics & AI Team, Department of Computer, Electrical and Space Engineering, Luleå University of Technology, Luleå SE-97187, Sweden.
LM-X: Explainable Vision--Language--Action Modeling via Progress, Event, and Uncertainty Prediction
Aug 26, 2026Jin Lou, Zhiyuan Jing, Xupeng Wang +21Robotic Control Uncertainty Estimation for VLA Models
Humanoid Robot (Shanghai) Co., Ltd. · E-surfing Digital Life Technology Co., Ltd., China Telecom
EVADE: Evidence-Verified Agentic Diagnosis with Escape
Aug 19, 2026Mohaimenul Azam Khan Raiaan, Nur Mohammad FahadSelective Prediction for VLMs Medical VLMs
School of Engineering and Energy, Murdoch University, Murdoch, WA 6150, Australia
MAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy
Aug 17, 2026Aniri, Chen Yilin, Jinhe Bi +7Uncertainty Estimation for VLA Models LLM Uncertainty Estimation
Ludwig Maximilian University of Munich · Munich Center for Machine Learning · East China University of Science and Technology +2
GUARD: Grounding Uncertainty and Ablation-Based Risk Detection for Diffusion-Based VLAs
Aug 5, 2026Suhas Hegde, Jitendra Yasaswi Bharadwaj KattaFailure Detection for VLA Models Uncertainty Estimation for VLA Models
Bosch Research India
The Geometry of Flow-Matching Uncertainty: A Cost-free Uncertainty Proxy and Its Application in Flow-based VLA Failure Detection
Jul 30, 2026Ziyang Rao, Yiren Zhao, Weiyu Guo +3Flow Matching Failure Detection for VLA Models
1HKUST(GZ) 2HKUST 3CUHK 4AI² Roboticss
SUREFlow: State-space Uncertainty-aware REsidual Flow Matching for Robust Robot Manipulation
Jul 11, 2026Md Tanvir Islam, Sai Navaneet Peddapalli, Sangmoon Lee +1Flow Matching Uncertainty Estimation for VLA Models
School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of Korea
When Thinking Hurts: Epistemic Signals in the Reasoning Chains of Visual Language Models
Jul 9, 2026Mayank SingalVLM Evaluation Uncertainty Estimation for VLA Models
Independent Researcher.
Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?
Jun 30, 2026Ta Duc Huy, Trang Nguyen, Townim Chowdhury +5VLM Evaluation Visual Question Answering
Australian Institute for Machine Learning, Adelaide University, Australia · Flinders University, Australia
GroundControl: Anticipating Navigation Failures in Vision-Language Agents via Trajectory-Consistent Uncertainty Estimates
Jun 18, 2026Nastaran Darabi, Divake Kumar, Sina Tayebati +2Uncertainty Estimation for VLA Models Selective Prediction
University of Illinois at Chicago (UIC)
Perturbation-Based Epistemic Uncertainty for Failure Detection in Vision-Language-Action Models
Jun 18, 2026Yousung Lee, Dongsoo HarFailure Detection for VLA Models Uncertainty Estimation for VLA Models
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea.
Uncertainty Quantification for Flow-Based Vision-Language-Action Models
Jun 16, 2026Ralf Römer, Maximilian Seeliger, Saida Liu +5Flow Matching Uncertainty Estimation for VLA Models
TU Munich · ETH Zurich · TU of Munich +1
FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty
Jun 1, 2026Harry Zhang, Luca CarloneUncertainty Estimation for VLA Models Vision-Language Models
Massachusetts Institute of Technology
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
May 28, 2026Yue Zhang, Zun Wang, Han Lin +3VLM Evaluation Spatial Reasoning Benchmarks
UNC Chapel Hill · Google Research
VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models
May 28, 2026Dehao Huang, Aoxiang Gu, Chengjie Zhang +5Confidence Estimation for VLMs Uncertainty Estimation for VLA Models
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China. · Zhongguancun Academy, Beijing, China · National Cybersecurity Academy, Wuhan University, Wuhan, China.
Uncertainty-Aware Gaussian Map for Vision-Language Navigation
May 26, 2026Jianzhe Gao, Rui Liu, Yuxuan Xu +6Uncertainty Estimation for VLA Models Vision-Language Navigation
The State Key Lab of Brain-Machine Intelligence, Zhejiang University · Department of Foundation model, 2012 Labs, Huawei · Noah’s Ark Lab, 2012 Labs, Huawei +1
Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming
May 20, 2026Yue Zhou, Erxuan Wu, Yikang Sun +5Visual Question Answering Uncertainty Estimation for VLA Models
Computer Aided Medical Procedures (CAMP), TU Munich, Germany · Munich Center for Machine Learning (MCML), Munich, Germany · Zhongshan Hospital, Fudan University, China +1
VISOR: A Vision-Language Model-based Test Oracle for Testing Robots
May 11, 2026Prasun Saurabh, Pablo Valle, Aitor Arrieta +2Uncertainty Estimation for VLA Models Automated Software Testing
Simula Research Laboratory and Oslo Metropolitan University · Mondragon University · National Institute of Informatics
Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
Apr 22, 2026Shelly Francis-Meretzki, Mirco Mutti, Yaniv Romano +1Uncertainty Estimation for VLA Models Vision-Language-Action Models
1Technion - Israel Institute of Technology.
SentryVLA: Uncertainty-Guided Action Selection and State Monitoring for Vision-Language-Action Robotic Control
Apr 17, 2026Zongyao Lyu, Lingling Chen, William J. BeksiUncertainty Estimation for VLA Models Robot Failure Detection
Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA.
ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models
Apr 10, 2026Nastaran Darabi, Amit Ranjan TrivediSpatial Grounding for VLA Models Vision-Language-Action Models
University of Illinois Chicago, IL, USA
Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model
Mar 18, 2026Yanchuan Tang, Taowen Wang, Yuefei Chen +3Uncertainty Estimation for VLA Models Uncertainty Calibration
Rutgers University · Kent State University
Decision-Aware Uncertainty Evaluation of Vision-Language Model-Based Early Action Anticipation for Human-Robot Interaction
Mar 9, 2026Zhaoda Du, Michael Bowman, Qiaojie Zheng +1Uncertainty Estimation for VLA Models VLMs for Robotics
Colorado School of Mines, Golden, CO 80401, USA · Postdoctoral Fellow in the Cancer Biology Department at the University of Pennsylvania, Philadelphia, PA 19104, USA
Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models
Mar 5, 2026Riccardo Andrea Izzo, Gianluca Bardaro, Matteo MatteucciFailure Detection for VLA Models Vision-Language-Action Models
All authors are with the Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Milan, Italy.

Oct 21, 2026J/K move · Enter open · S save

Post-hoc Epistemic Uncertainty for Vision-Language-Action Policies

Johannes Keller, Albrecht M. Bloße, Adrian Lindenmeyer, Thomas Neumuth+1

Innovation Center Computer Assisted Surgery (ICCAS), Leipzig University, Leipzig, Germany

Uncertainty Estimation for VLA Models Robot Learning

Open paper AskPDF arXiv

Vision-language-action (VLA) policies need to recognize gaps in their training knowledge to request useful demonstrations or assistance in new situations, especially when failures are costly. Disagreement within an ensemble of independently trained policies can guide these decisions, but requires training and running multiple policies. We propose post-hoc kernel-variance heads that estimate epistemic uncertainty from the embeddings of a single policy. Each head computes the conditional variance of a Gaussian process conditioned on embeddings from the training demonstrations. Fitting requires no regression targets or gradient updates and leaves the policy unchanged. In experiments with SmolVLA on LIBERO-10, the kernel variance heads perform competitively with two-policy ensemble scores in task-level correlation with task success, in demonstration acquisition during active learning, and in referral to a stronger supervisor policy as a proxy for human assistance. For SmolVLA, the head on the vision-language backbone reduces uncertainty-scoring time by up to approximately a factor of 50 compared with ensemble scores, while also substantially reducing setup costs. We also show that the established evaluation protocol on LIBERO-10 primarily rewards recognition of coverage differences between tasks, while execution variability weakens assessment of within-task rankings. Thus, controlled perturbations provide a complementary evaluation: modality-specific heads identify unfamiliar camera, instruction, or state inputs, while fused heads can detect unfamiliar combinations of individually familiar inputs. With a supervisor proxy trained on the evaluated perturbation families, the decoder head improves within-task referral over ensemble disagreement. These findings show that useful uncertainty estimates for adaptive robot learning can be obtained from a single policy.