FLYING ROBOTS: Sensing, Control and Decision Making

This paper presents a flight management system (FMS) implemented as on-board intelligence for rotorcraftbased unmanned aerial vehicles (RUAVs). This hierarchical flight management system endows each vehicle with autonomy resembling sense-reason-act processes of intelligent agents in nature. Sensor measurements are processed by flight control computers in order to gradually refine given abstract mission commands into real-time control signals for each vehicle. Intelligence based on probabilistic reasoning is provided by an on-board strategy planner. An on-board trajectory generates a sequence of way-points associated with flight modes, as a result of intelligent reasoning. A tracking control layer is designed using nonlinear model predictive control as well as conventional multi-loop PD control, and integrated with a trajectory generator for logistical action planning. The proposed structure has been implemented on radio-controlled helicopters and validated in a variety of experiments. Results from way-point navigation, a probabilistic pursuit-evasion game and vision-based tracking of a moving target show the promising potential of intelligent flying robots.