Model-based Approach to Validation and Verification of Flight Critical Software

The time and cost associated with the development and certification of flight-critical software have been escalating at an alarming rate for modern, software-enabled air vehicles. This upward trend is expected to continue as future vehicles will be increasingly autonomous and intelligent. Affordable, efficient processes and tools are needed to control development costs and schedule, as well as to ensure the safety of these vehicles. This paper presents the results of a U. S. Air Force Research Laboratory (AFRL) sponsored project on the development of validation and verification (V&V) technologies for flight-critical software. The purpose of the project is to improve the affordability and safety for software V&V, specifically, for adaptive and/or mixed-criticality software. Adaptive software introduces uncertainties; mixed-criticality refers to the information passed between flight critical and mission critical software partitions, hence affecting in-flight adaptation (or control reconfiguration). The methodology developed in this project strongly suggests that an integrated, model-based approach be used in the V&V of adaptive software. In this approach, the same physical model is used for design, implementation, and testing, while emphasis has been placed on checking the uncertainty and the accuracy of the models, which often are implemented in flight control and health management software. In the paper, we use a scenario to illustrate the capabilities of the proposed V&V methodology. The scenario describes an unmanned air vehicle (UAV) executing an autonomous aerial refueling mission.