الملخص
Benchmarks expose vision-language-action (VLA) policies to few canonical instructions, while exhaustive deployment testing is impossible. We introduce Object-Grounded Attention Monitoring (OGAM), connecting systematic testing to runtime assurance: testing reveals attention divergence between successful and failed executions, and OGAM uses this signal to stop failures beyond the finite suite. We generate scene-grounded instructions through pairwise combinations of action templates and objects, and separately test meaning-preserving paraphrases. All 87 out-of-benchmark cases reveal problematic behavior across OpenVLA, OpenVLA-OFT, UniVLA, and $π_{0.5}$: none completes any of the 24 feasible instructions, while infeasible or hazardous requests also trigger behavior substitution. At each action query, we project gradient-weighted visual attention through object masks and group it by instruction role for comparison across tasks and policies. Dynamic time warping aligns this course with a successful reference despite speed differences; conformal calibration on successful episodes sets the early-stopping threshold for sustained deviations, with a nominal false-stop target of $α=0.05$. Across four policies, OGAM stops 87-100% of failed episodes at median times of 5-12s within a 20s budget, with observed false-stop rates of 3-5%, without failure-labeled training. Finite testing thus identifies attention patterns that support online intervention before failure fully unfolds.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Darwish, H., Yin, X., Li, C., Yan, R., Neto, F. G. D. O., & Cheng, C. H. (2026). OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies. https://omanscience.com/ar/articles/ogam-connecting-systematic-testing-to-runtime-assurance-through-object-grounded-attention-monitoring-for-vla-policies
MLA 9
Darwish, Haki, et al. "OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies." https://omanscience.com/ar/articles/ogam-connecting-systematic-testing-to-runtime-assurance-through-object-grounded-attention-monitoring-for-vla-policies.
شيكاغو (المؤلف–التاريخ)
Darwish, Haki, Xiangyu Yin, Changwen Li, Rongjie Yan, Francisco Gomes de Oliveira Neto, and Chih-Hong Cheng. 2026. "OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies." https://omanscience.com/ar/articles/ogam-connecting-systematic-testing-to-runtime-assurance-through-object-grounded-attention-monitoring-for-vla-policies.
هارفارد
Darwish, H., Yin, X., Li, C., Yan, R., Neto, F. G. D. O. and Cheng, C. H. (2026) 'OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies', Available at: https://omanscience.com/ar/articles/ogam-connecting-systematic-testing-to-runtime-assurance-through-object-grounded-attention-monitoring-for-vla-policies.
فانكوفر
Darwish H, Yin X, Li C, Yan R, Neto FGDO, Cheng CH. OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies. https://omanscience.com/ar/articles/ogam-connecting-systematic-testing-to-runtime-assurance-through-object-grounded-attention-monitoring-for-vla-policies
IEEE
H. Darwish, X. Yin, C. Li, R. Yan, F. G. D. O. Neto, and C. H. Cheng, "OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies," https://omanscience.com/ar/articles/ogam-connecting-systematic-testing-to-runtime-assurance-through-object-grounded-attention-monitoring-for-vla-policies.