ARCHITECTURAL DESIGN FOR INTELLIGENT AUTONOMY IN UNMANNED AIRCRAFT

Autonomous aircraft are able to reduce overhead costs/risks and level of operator intervention. Hence, high autonomy degrees can make them an attractive solution to perform sophisticated air missions whilst decreasing costs and risks. The challenge is to develop a system with the ability to deal with internal faults, and changes in the environment. This paper presents the step-by-step design process (from functionality to capability) for an Intelligent Vehicle Control Architecture (IVCA) to enable multiple air vehicles to autonomously carry out airspace missions. The architectural foundation to achieve the IVCA lays on service-oriented computing and agent software technology. Thus, the IVCA is able to dynamically reconfigure and adapt itself. The ability to perform on-the-fly re-planning of activities when needed increases the chance to succeed in a given mission. The IVCA is initially planned to be realized and evaluated in computer simulation. The IVCA design is based on a structure maintenance mission. However, it is a general solution for aerospace autonomy that can be applied to other airspace missions, and UAVs. This paper also presents design considerations for fault-tolerant planning and spooling, including fault diagnosis and recovery as well as a module called matchmaker to link services with available capabilities. Conclusions and future research directions are also presented.