Development of a real-time-position prediction algorithm for under-actuated robot manipulator by using of artificial neural network

Abstract

An adaptive learning algorithm using an artificial neural network (ANN) has been proposed to predict the passive joint position of under-actuated robot manipulator. In this approach, a specific ANN model has been designed and trained to learn a desired set of joint angular positions for the passive joint from a given set of input torque and angular position for the active joint over a certain period of time. Trying to overcome the disadvantages of many used techniques in the literature, the ANNs have a significant advantage of being a model-free method. The learning algorithm can directly determine the position of its passive joint, and can, therefore, completely eliminate the need for any system modelling. Even though it is very difficult in practice, data used in this study were recorded experimentally from sensors fixed on robot's joints to overcome the effect of kinematics uncertainties present in the real world such as ill-defined linkage parameters and backlashes in gear trains. An ANN was trained using the experimentally obtained data and then used to predict the path of the passive joint that is positioned by the dynamic coupling of the active joint. The generality and efficiency of the proposed algorithm are demonstrated through simulations of an under-actuated robot manipulator; finally, the obtained results were successfully verified experimentally.

Arm Exoskeleton for Rehabilitation Following Stroke by Learning Algorithm Prediction

“…For the sigmoid activation function given in equation (3), the so-called delta rule for iterative convergence towards a solution, stated in general is given as (6) where is the learning rate parameter, and the error K at an output layer unit K is given by (7) Also, the error J at a hidden layer unit is given by (8) Using the generalized data delta rule to adjust weights leading to the hidden units is back propagating the error adjustment, which allows for adjustment of weights leading to the hidden layer neurons in addition to the usual adjustments to the weights leading to the output layer neurons.…”

“…AI implemented in Robots for predicting and making robot systems able to attribute more intelligence with a higher degree of autonomy. Researchers have recommended Artificial Neural Network (ANN) from its arbitrary for learning from examples and predict from a large number of data [6]. The ANN will learn the target parameters based on weight adoption via reducing the error between the target and the calculated output throughout an iteration during the training process.…”

Real-Time Fuzzy Logic Control of Two-Link Flexible Manipulators

“…It can dampen high vibrational modes less effectively handled by active control. However, passive control alone cannot eliminate the large amplitude deflections, which must be dealt with using (Pedro and Tshabalala, 2015;Jiang, 2015;Al-Assadi et al, 2011;Yan and Wang, 2012;Rahmani and Belkheiri, 2019). Hybrid neuro-fuzzy controllers consist of two significant parts: The NN controller, followed by the FLC.…”

Neural extended Kalman filter for monocular SLAM in indoor environment

“…2 Neural networks (NN) are versatile modeling tool for function approximation. [3][4][5][6][7][8][9] In robotics, neural networks and bio-inspired techniques are used for control of a mobile robot, 10,11 robot manipulator 12,13 or to predict robot failures during exploitation. 14 Likewise, neural networks are often used in the development of control approaches for mobile robots in structured/unstructured environments.…”