cs.RONov 17, 2026

VoxelSBFL: Voxel-Level Spectrum-Based Failure Prediction for Vision-Language-Action Models

Authors: Arusa Kanwal, Pablo Valle, Paola Roggero, Miren Illarramendi, Shaukat Ali, Aitor Arrieta

Organizations: Mondragon University, Spain · Simula Research Laboratory, Norway

Abstract

Vision-Language-Action (VLA) models integrate visual perception, language understanding, and action generation to control robots. Testing these systems produces trajectories and task outcomes, but existing approaches provide limited guidance on using these recorded trajectories to assess subsequent executions or inform policy repair. We conjecture that, for a given policy and task, traversing certain workspace regions is associated with a higher likelihood of failure. To investigate this conjecture, we propose VoxelSBFL, a black-box adaptation of Spectrum-Based Fault Localization (SBFL) in which workspace voxels replace program elements as units of analysis. Recorded tool-center-point (TCP) trajectories provide binary voxel coverage, which is combined with execution outcomes to construct suspiciousness maps using established SBFL formulas. These maps identify failure-associated regions and score unseen trajectories without requiring internal model access. We evaluate 34 spectrum-based techniques across four VLA models using 96,000 Pick-Up trajectories in simulation and compare the leading techniques against eight action- and trajectory-based metrics. VoxelSBFL obtains an overall macro ROC-AUC of 0.704, significantly outperforming state-of-the art baselines. Sensitivity analyses show that performance varies with spatial granularity and training-set size. These findings support spatial spectra for VLA execution assessment and motivate future research on runtime monitoring, self-healing and targeted policy improvement.

Figures & tables

Explore similar work

CardsList
  1. FATE-VLA:Failue-aware test generation for vision-language-action models

    Jun 1, 2026Arusa Kanwal, Pablo Valle, Shaukat Ali +1VLM EvaluationVision-Language-Action Models

  2. Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring

    May 29, 2026Seongheon Park, Wendi Li, Changdae Oh +4Robot Failure DetectionFault Detection

  3. VLA-Scope: Shift-Aware Failure Prediction for Vision-Language-Action Models

    Sep 18, 2026Kaiwen Zhu, Dongfang Liu, Liangkai Liufailure prediction for vision-language-action modelsFailure Detection for VLA Models