Learning helicopter control through "teaching by showing"

A model-free "teaching by showing" methodology is developed to train a fuzzy-neural controller for an autonomous robot helicopter. The controller is generated and tuned using training data gathered while a teacher operates the helicopter. A hierarchical behavior-based control architecture is used, with each behavior implemented as a hybrid fuzzy logic controller (FLC) and general regression neural network controller (GRNNC). The FLCs and GRNNCs are generated through "teaching by showing". The FLCs are built during initial controller generation, remain static once created, and provide coarse control of the helicopter. The GRNNCs are incrementally built and modified whenever the controller does not meet performance criteria, are dynamic, and provide fine control, enhancing the control of the FLCs. The methodology has been successfully applied in simulation and, in the future, will be applied on a radio control model helicopter for real world validation.