Runtime monitoring of ROS~2 systems remains an open problem: existing tools provide point-in-time snapshots without automated detection, and academic approaches operate offline or in simulation. We propose a framework combining ros2_tracing-based low-overhead data collection with a three-level self-training anomaly detection
Towards Online Anomaly Monitoring in ROS 2
M. De Carolis;F. Calefato;F. Lanubile
2026-01-01
Abstract
Runtime monitoring of ROS~2 systems remains an open problem: existing tools provide point-in-time snapshots without automated detection, and academic approaches operate offline or in simulation. We propose a framework combining ros2_tracing-based low-overhead data collection with a three-level self-training anomaly detectionFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
