A Transformer anomaly detector trained on Nets-within-Nets-generated trajectories from LTL specifications reaches 91.3% accuracy on execution inefficiencies and 88.3% on core mission violations in multi-robot settings.
Enhanc- ing multi-robot systems cooperation through machine learning-based anomaly detection in target pursuit
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
High-Level Multi-Robot Trajectory Planning And Spurious Behavior Detection
A Transformer anomaly detector trained on Nets-within-Nets-generated trajectories from LTL specifications reaches 91.3% accuracy on execution inefficiencies and 88.3% on core mission violations in multi-robot settings.