Predictive vision-language monitoring for proactive safety in robot task execution
Frontiers in Robotics and AI · 03.08.2026 · 13
DOI: 10.3389/frobt.2026.1870024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Robotics and AI, online erschienen am 03.08.2026. Verfasst von Juan Diego Peña-Narvaez und 4 weiteren Autor:innen. Beteiligte Einrichtung: Intelligent Robotics Lab, Signal Theory, Communications, Telematics Systems, and Computation Department, International Doctoral School, Rey Juan Carl…. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Robots that execute language-conditioned tasks in dynamic environments often rely on feedback only after an action has failed, which can be insufficient when failures involve collisions or workspace conflicts. This paper presents a predictive monitoring framework that uses Vision-Language Models (VLMs) to assess near-future execution risk during robot task execution. The framework first generates structured plans with action execution conditions and a plan-level fallback action. During execution, a monitoring module combines visual observations, the current action, and the relevant execution conditions to estimate whether a condition is likely to be violated within a short future time window. When the predicted risk exceeds a task-specific threshold, the robot halts the current action, executes the fallback behavior, and replans from the updated state. We evaluate the approach in Gazebo simulation on mobile navigation with a moving human obstacle and manipulation with two robot arms sharing a workspace. Across controlled collision-risk settings, the proposed method achieves higher task success rates than reactive VLM-based baselines while requiring fewer replanning events than conservative current-state precondition checking. The results indicate that predictive vision-language monitoring can improve task completion in simulated dynamic robot tasks, while remaining subject to limitations such as VLM latency, prompt sensitivity, and evaluation beyond simulation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Intelligent Robotics Lab, Signal Theory, Communications, Telematics Systems, and Computation Department, International Doctoral School, Rey Juan Carlos University, Fuenlabrada, Spain.
- Intelligent Robotics Lab, Universidad Rey Juan Carlos, Fuenlabrada, Spain.
Zitieren
APA
Peña-Narvaez, J. D., Pérez-Rodríguez, R., Aguado, E., Moreno, F. M., & Rico, F. M. (2026). Predictive vision-language monitoring for proactive safety in robot task execution. Frontiers in Robotics and AI, 13. https://doi.org/10.3389/frobt.2026.1870024
Vancouver
Peña-Narvaez JD, Pérez-Rodríguez R, Aguado E, Moreno FM, Rico FM. Predictive vision-language monitoring for proactive safety in robot task execution. Frontiers in Robotics and AI. 2026;13. doi:10.3389/frobt.2026.1870024
BibTeX
@article{PeaNarvaez2026,
author = {Peña-Narvaez, Juan Diego and Pérez-Rodríguez, Rodrigo and Aguado, Esther and Moreno, Francisco Miguel and Rico, Francisco Martín},
title = {Predictive vision-language monitoring for proactive safety in robot task execution},
journal = {Frontiers in Robotics and AI},
year = {2026},
volume = {13},
doi = {10.3389/frobt.2026.1870024}
}
EUVIMED