Detecting Execution Anomalies As an Oracle for Autonomy Software Robustness
Deborah S. Katz,Casidhe Hutchison,Milda Zizyte,Claire Le Goues,Deborah S. Katz,Casidhe Hutchison,Milda Zizyte,Claire Le Goues
We propose a method for detecting execution anomalies in robotics and autonomy software. The algorithm uses system monitoring techniques to obtain profiles of executions. It uses a clustering algorithm to create clusters of those executions, representing nominal execution. A distance metric determines whether additional execution profiles belong to the existing clusters or should be considered ano...
