Generic Architecture for Autonomous Uninhabited Vehicles.

摘要

Research on autonomy is performed for various types of uninhabited vehicles: ground, aerial, surface, underwater and space vehicles. A quick state- of-the-art highlights that industry and research develop their own architectures and that no standard is emerging; few solutions propose architecture adaptive to several types of platform. Autonomous vehicles that move in partially known and dynamic environments have to deal with asynchronous disruptive events. Hence the need for implementing onboard decision capabilities that allow the vehicle to perform the mission even when the initial plan prepared offline is not valid any more. Decision capabilities, which guarantee the adaptability of the vehicle to variable environmental conditions, must be implemented in a dedicated architecture able to manage the components of the whole control loop (perception, situation assessment, decision, and action). This paper focuses on the ProCoSA software package used by ONERA for controlling and monitoring highly autonomous systems. This software allows the development of decision architectures for any type of autonomous vehicle performing its mission in a partially known and dynamic environment. We present the software package, a tutorial example, and architecture implementations on an Autonomous Underwater Vehicle (AUV) and on an autonomous Uninhabited Aerial Vehicle (UAV).