Learning Helicopter Model Through “Examples”
نویسندگان
چکیده
In this paper, a neuro-fuzzy system identification using measured input and output data are carried out. A model-free learning from “examples” methodology is developed to train a neuro-fuzzy model of a smallsize helicopter. The helicopter model is obtained and tuned using training data gathered while a teacher operates the helicopter. Behavior-based model architecture is used, with each behavior implemented as a hybrid neurofuzzy model. The neural network structure learns the parameters of the fuzzy membership functions and finally the fuzzy-based model works alone. The neuro-fuzzy architecture and the helicopter hardware system used to measure the sensors and command data are also described. The methodology has been successfully applied in the behavior-based model of a radio control model helicopter. The identified behavior model can be used in the position control also based on the neuro-fuzzy theory. Key-Words: neuro-fuzzy modeling, learning from examples, helicopter, behavior-based model, avionics box.
منابع مشابه
Intelligent Auto pilot Design for a Nonlinear Model of an Autonomous Helicopter by Adaptive Emotional Approach
There is a growing interest in the modeling and control of model helicopters using nonlinear dynamic models and nonlinear control. Application of a new intelligent control approach called Brain Emotional Learning Based Intelligent Controller (BELBIC) to design autopilot for an autonomous helicopter is addressed in this paper. This controller is applied to a nonlinear model of a helicopter. This...
متن کاملLearning Through Interaction
Reinforcement learning is an approach for learning optimal action policy via experiencing, i.e. using observed reward in environment states. Reinforcement learning algorithms include adaptive dynamic programming, temporal difference learning and Q-learning[1]. Examples of successful applications of reinforcement learning are controller for sustained inverted flight on an autonomous helicopter [...
متن کاملA direct adaptive neural command controller design for an unstable helicopter
This paper presents an off-line (finite time interval) and on-line learning direct adaptive neural controller for an unstable helicopter. The neural controller is designed to track pitch rate command signal generated using the reference model. A helicopter having a soft inplane four-bladed hingeless main rotor and a four-bladed tail rotor with conventional mechanical controls is used for the si...
متن کاملAutonomous Helicopter Flight via Reinforcement Learning
Autonomous helicopter flight represents a challenging control problem, with complex, noisy, dynamics. In this paper, we describe a successful application of reinforcement learning to autonomous helicopter flight. We first fit a stochastic, nonlinear model of the helicopter dynamics. We then use the model to learn to hover in place, and to fly a number of maneuvers taken from an RC helicopter co...
متن کاملFinite Time Terminal Synergetic Controller for Nonlinear Helicopter Model
In this paper, an almost new control approach called terminal synergetic control which works based on user defined manifold is applied to a nonlinear helicopter model. Stability analysis is convestigated using Lyapunov stability theory. Synergetic controller is applied to this nonlinear fifth-order helicopter model to control height and angle. Simulation results showed that it has faster and sm...
متن کامل