Multi-Agent Paradigm to Design the Next Generation of Airborne Platforms


A. El Fallah Seghrouchni (Sorbonne Université), L. Grivault (Thales Defense Mission Systems)

Airborne platforms such as Remote Piloted Aircraft Systems (RPAS) operate in highly critical contexts. The next generation of RPAS will be endowed with multifunction sensors (i.e., each sensor offers a large panel of functions to the platform's manager during the mission). As a platform, RPAS carry out a wide collection of complex tasks, thanks to the interleaving of the various services of sensors. The sensors are in charge of collecting data from the environment. Our main goal is to design a system as a software medium layer between the platform manager and the hardware resources on board the airborne platform (i.e., multifunction sensors). Today, the requirements of the platform in terms of autonomy, modularity, robustness and reactivity, as well as the industrial constraints, call for the design of a new multifunction system architecture. Such a design may rely on a multi-agent paradigm since it is modular by nature and the agents naturally bring autonomy and pro-activity to the system. This paper presents new and original contributions: (1) an original agentification of the system, in the form of a multi-agent architecture that captures the dynamics of the environment by creating agents depending on objects that may appear in the mission theater; (2) agents that generate a task plan (a task is an action that will require a sensor to be achieved) according to the resources (e.g., the sensors) needed; (3) a scheduler that handles the task plans issued by the agents in order to provide efficient sensor scheduling.

AL15-03.pdf1.38 MB