Pages: 35 – 49
|M Yasir Amir and Vali uddin Abbas|
Quadrotor Helicopter or simply quadrotor is rotorcraft that has four lift-generating propellers. Two of the propellers spin clock wise and the other two counter-clockwise. Control of the machine can be achieved by varying relative speed of the propellers. Quadrotor concept is not new, however the modern quadrotors are mostly unmanned. Advancement in miniaturized IMU technology, availability of high speed brushless motors and high power to weight ratio Li-Polymer battery technology, quadrotors can now be successfully designed and fabricated. This paper proposes a mathematical model of quadrotor dynamics and a control scheme based on Direct Inverse Neural Control. In modeling A simplified approach is adopted where the gyroscopic effect and air friction on frame of machine has been neglected, resulting in a simplified model, which is useful for designing a controller to stabilize the plant in hover state. Proposed model is non-linear since the rotor dynamics are a function of square of motor inputs. The neural network based controller, exploits the multiple layer perceptron trained by the back propagation algorithm. Direct inverse control scheme uses the idea of canceling out the dynamics of a plant by training the controller to approximate the inverse of the plant. This scheme however requires the plant to have a stable inverse.