A Multi-Layer Autonomous Intelligent Control Architecture for Unmanned Aerial Vehicles
Jovan D. Bošković, R. Prasanth, Raman K. Mehra · Journal of Aerospace Computing Information and Communication · 2004
In the past several years there has been a lot of interest in the design of efficient autonomous intelligent controllers for Unmanned Aerial Vehicles (UAV). This is a highly complex and challenging problem since future UAVs will be expected to complete autonomously a wide variety of complex missions, and achieve performance comparable to that of manned vehicles. In this paper a four-layer autonomous intelligent control architecture for UAVs is described, and related issues are discussed. The architecture consists of the following layers: (i) Redundancy Management Layer that consists of the online Failure Detection and Identification (FDI) and robust feedback Adaptive Reconfigurable Controller (ARC); (ii) Autonomous Trajectory Generation (ATG) layer whose role is to fit feasible trajectories through the desired way-points in real time; (iii) Autonomous Path Planning (APP) layer that generates way-points on-line in response to a dynamically changing environment; and (iv) Autonomous Decision Making (ADM) layer whose role is to assess the available control authority after failures, and make missionrelated decisions in near-real time. The main distinguishing feature of the architecture is that its layers are connected through the Achievable Dynamic Performance (ADP) calculation module which results in a system in which all the decisions are made based on the current available resources. Recent extensions of this architecture are also discussed and described in detail. At the end, a discussion is included on the Verification and Validation (V&V) of intelligent and adaptive control systems, and some recent results are presented.