Slippage estimation of a two wheeled mobile robot using deep neural network

Download
2018
Özçil, İsmail
Mobile robot navigaiton is an important task for the operations of the mobile robots. Due to the wheel slippages, performance of the dead reckoning in estimating speed of the robot and the position of the robot is not sufficient. To overcome the errors in navigation estimates, usage of the recurrent deep neural networks is porposed. Neural networks are used to understand the behaviour of the linear and nonlinear systems. Since wheel-ground interaction will be modeled with non-linear models and the estimating parameters of those models are difficult, usage of the neural networks is preferable since they do not require system models and parameters. In this work, a recurrent deep neural network is proposed to estimate the speed and yaw angle of the 2 wheeled differentially driven mobile robot. By recording data from the training experiments of the navigation of the mobile robot, network is trained. After that, performance of the network is evaluated by plotting and tabulating outputs of the network, sensor data calculation and ground truth. Finally, results are compared with the results from the literature.
Citation Formats
İ. Özçil, “Slippage estimation of a two wheeled mobile robot using deep neural network,” M.S. - Master of Science, Middle East Technical University, 2018.