Improvement of Inertia Matrix in Robot Model Identified with Neural Networks
نویسندگان
چکیده
This article presents an improvement method of an identified inertia matrix with the neural network model of a robot. A problem of a neural network model is its inability to assure the positive definiteness of an identified inertia matrix. Therefore the method of matrix regularization based on Cholesky decomposition is proposed. Simulation results show significant improvement of the accuracy of neural network models after this abovementioned regularization.
منابع مشابه
Mechanical System Modelling of Robot Dynamics Using a Mass/Pulley Model
The well-known electro-mechanical analogy that equates current, voltage, resistance, inductance and capacitance to force, velocity, damping, spring constant and mass has a shortcoming in that mass can only be used to simulate a capacitor which has one terminal connected to ground. A new model that was previously proposed by the authors that combines a mass with a pulley (MP) is shown to simulat...
متن کاملNeural Network Robot Model with Not-inverted Inertia Matrix
Abstract. The mathematical model of industrial robot is well known for example in the form of Lagrange-Euler equations, Newton-Euler equations or generalized d’Alambert equations. However, these equations require the physical parameters of robot like masses, inertia momentums, etc. that are very hard to measure. In the paper, the method for calculation of Lagrange-Euler robot model using neural...
متن کاملElectronical and Mechanical System Modeling of Robot Dynamics Using a Mass/Pulley Model
The well-known electro-mechanical analogy that equates current, voltage, resistance, inductance and capacitance to force, velocity, damping, spring constant and mass has a shortcoming in that mass can only be used to simulate a capacitor which has one terminal connected to ground. A new model that was previously proposed by the authors that combines a mass with a pulley (MP) is shown to simulat...
متن کاملComparison of Neural Network Robot Models with Not Inverted and Inverted Inertia Matrix
The mathematical model of an industrial robot is usually described in the form of Lagrange-Euler equations, Newton-Euler equations or generalized d’Alambert equations. However, these equations require the physical parameters of a robot that are difficult to obtain. In this paper, two methods for calculation of a Lagrange-Euler model of robot using neural networks are presented and compared. The...
متن کاملSaturated Neural Adaptive Robust Output Feedback Control of Robot Manipulators:An Experimental Comparative Study
In this study, an observer-based tracking controller is proposed and evaluatedexperimentally to solve the trajectory tracking problem of robotic manipulators with the torque saturationin the presence of model uncertainties and external disturbances. In comparison with the state-of-the-artobserver-based controllers in the literature, this paper introduces a saturated observer-based controllerbas...
متن کامل