Abstract
Language-enabled robot systems increasingly combine semantic-graph planning with temporal-logic safety monitors. We investigate a trace-completeness assumption in these systems: whether the high-level action sequence checked by a monitor represents the navigation and implicit action effects induced during execution. We audit this assumption in RoboGuard by comparing its verdict on a surface plan with its verdict on a graph-refined trace under the same Linear Temporal Logic (LTL) specification. Our evaluation comprises 28 controlled cases spanning five action-abstraction families and 14 end-to-end cases in which SPINE [1] generates plans from natural-language instructions while RoboGuard generates scene-grounded safety specifications. In the controlled evaluation, all 12 targeted abstraction cases exhibit the predicted surface-versus-refined discrepancy while all 16 controls behave as expected, motivating graph-based trace refinement as a lightweight mitigation and a diagnostic tool for physical-AI safety monitors.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Das, S., Ranjan, P., Li, X., & Qian, L. (2026). Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions. https://omanscience.com/en/articles/mind-the-refinement-gap-when-safe-high-level-robot-plans-produce-unsafe-executions
MLA 9
Das, Stabak, et al. "Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions." https://omanscience.com/en/articles/mind-the-refinement-gap-when-safe-high-level-robot-plans-produce-unsafe-executions.
Chicago (author–date)
Das, Stabak, Priyesh Ranjan, Xiangfang Li, and Lijun Qian. 2026. "Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions." https://omanscience.com/en/articles/mind-the-refinement-gap-when-safe-high-level-robot-plans-produce-unsafe-executions.
Harvard
Das, S., Ranjan, P., Li, X. and Qian, L. (2026) 'Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions', Available at: https://omanscience.com/en/articles/mind-the-refinement-gap-when-safe-high-level-robot-plans-produce-unsafe-executions.
Vancouver
Das S, Ranjan P, Li X, Qian L. Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions. https://omanscience.com/en/articles/mind-the-refinement-gap-when-safe-high-level-robot-plans-produce-unsafe-executions
IEEE
S. Das, P. Ranjan, X. Li, and L. Qian, "Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions," https://omanscience.com/en/articles/mind-the-refinement-gap-when-safe-high-level-robot-plans-produce-unsafe-executions.