A Language for Describing Agent Behavior as Hybrid Models

Abstract

Air Traffic conflict detection and resolution (CDR) involves multiple domains, the modeling of physical systems such as aircraft, encoding conflict detection algorithms as well as the procedures(tasks) for conflict resolution. Depending on the analysis being conducted, an implementation language is usually chosen to cater for easy rendering of algorithms in the primary domain of interest. The more specialized the choice of implementation language, the greater the difficulty in expanding the fidelity of models in other domains. This paper takes a unified view of continuous equations, algorithms and procedures. Events that occur in sequence as well as in parallel are represented in a unified manner by interpreting them as hierarchical state-charts at a low-level and as procedures or task trees at a higher level. The relationship between the two levels are recognized and utilized in decomposing task trees in to hierarchical state charts and eventually into C++ code for implementation.