Property-Based Brittleness Analysis of Temporal Networks

Abstract

A new framework is proposed to analyze the brittleness of task networks with respect to an arbitrary set of user-specified properties, such as dynamic controllability or minimum battery state of charge of a rover. The proposed algorithms allow the detection and enumeration of activities that, with modest task execution duration variation, make the success of execution no longer guaranteed in terms of the given set of properties. A metric for measuring an activity’s brittleness, defined as the degree of acceptable deviation from its nominal duration that preserves the desired user-specified properties, is introduced and how that measurement is mapped to task network structure is described. Complementary to existing work on temporal robustness analysis, which informs how likely a task network is to succeed or not under temporal controllability constraints, the new analysis and metric not only generalize robustness analysis to a set of user-defined properties (as opposed to strong or dynamic controllability, for instance), but they also go deeper to pinpoint the sources of potential brittleness. An analyzer is developed, which helps human designers and/or automated task network generators focus on and address sources of undesirable brittleness. The approach is applied in Mars rover and biomanufacturing operations scenarios.