Research

Paper

TESTING March 23, 2026

ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling

Authors

Byungjin Kim

Abstract

Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high-dimensional parameter spaces is intractable. We present ROBOGATE, a deployment risk management framework that combines physics-based simulation with a two-stage adaptive sampling strategy to efficiently discover failure boundaries in the operational parameter space. Stage 1 employs Latin Hypercube Sampling (LHS) across an 8-dimensional parameter space to establish a coarse failure landscape from 20,000 uniformly distributed experiments. Stage 2 applies boundary-focused sampling that concentrates 10,000 additional experiments in the 30-70% success rate transition zone, enabling precise failure boundary mapping. Using NVIDIA Isaac Sim with Newton physics, we evaluate a scripted pick-and-place controller on two robot embodiments -- Franka Panda (7-DOF) and UR5e (6-DOF) -- across 30,000 total experiments. Our logistic regression risk model achieves an AUC of 0.780 on the combined dataset (vs. 0.754 for Stage 1 alone), identifies a closed-form failure boundary equation, and reveals four universal danger zones affecting both robot platforms. We further demonstrate the framework on VLA (Vision-Language-Action) model evaluation, where Octo-Small achieves 0.0% success rate on 68 adversarial scenarios versus 100% for the scripted baseline -- a 100-point gap that underscores the challenge of deploying foundation models in industrial settings. ROBOGATE is open-source and runs on a single GPU workstation.

Metadata

arXiv ID: 2603.22126
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-23
Fetched: 2026-03-24 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.22126v1</id>\n    <title>ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling</title>\n    <updated>2026-03-23T15:52:54Z</updated>\n    <link href='https://arxiv.org/abs/2603.22126v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.22126v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high-dimensional parameter spaces is intractable. We present ROBOGATE, a deployment risk management framework that combines physics-based simulation with a two-stage adaptive sampling strategy to efficiently discover failure boundaries in the operational parameter space. Stage 1 employs Latin Hypercube Sampling (LHS) across an 8-dimensional parameter space to establish a coarse failure landscape from 20,000 uniformly distributed experiments. Stage 2 applies boundary-focused sampling that concentrates 10,000 additional experiments in the 30-70% success rate transition zone, enabling precise failure boundary mapping. Using NVIDIA Isaac Sim with Newton physics, we evaluate a scripted pick-and-place controller on two robot embodiments -- Franka Panda (7-DOF) and UR5e (6-DOF) -- across 30,000 total experiments. Our logistic regression risk model achieves an AUC of 0.780 on the combined dataset (vs. 0.754 for Stage 1 alone), identifies a closed-form failure boundary equation, and reveals four universal danger zones affecting both robot platforms. We further demonstrate the framework on VLA (Vision-Language-Action) model evaluation, where Octo-Small achieves 0.0% success rate on 68 adversarial scenarios versus 100% for the scripted baseline -- a 100-point gap that underscores the challenge of deploying foundation models in industrial settings. ROBOGATE is open-source and runs on a single GPU workstation.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <published>2026-03-23T15:52:54Z</published>\n    <arxiv:comment>12 pages, 5 figures, open-source code and 30K failure pattern dataset available at https://github.com/liveplex-cpu/robogate</arxiv:comment>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Byungjin Kim</name>\n    </author>\n    <arxiv:doi>10.5281/zenodo.19166967</arxiv:doi>\n    <link href='https://doi.org/10.5281/zenodo.19166967' rel='related' title='doi'/>\n  </entry>"
}