Articles
Publication Date: 2024
Journal of the Brazilian Society of Mechanical Sciences and Engineering (16785878)(9)
The purpose of this study is to design and construct a novel interactive game. This game is a robotic learning and imitation task. It is based on visual interaction of the player. The cornerstone technique used in this game is natural learner unit pattern generator neural networks (NLUPGNN), which is able to generate required motion trajectories based on imitation learning. The systematic design of these neural networks is the main problem solved in this paper. The unit pattern generators can be divided into two subsystems, a rhythmic system and a discrete system. A special learning algorithm is designed to use these unit pattern generators. The unit pattern generators are connected and coupled to each other to form a network, and their unknown parameters are found by a natural policy gradient learning algorithm. The motion sequences train some nonlinear oscillators, then they reproduce motions for a humanoid robot. As a result, the joints of the humanoid body imitate the movements of the teacher in real time. The main contribution of this work is the development of this learning algorithm, which is able to search the weights and topology of the network simultaneously. The algorithm synchronizes the learning steps by coupling the neurons in the last step. © The Author(s), under exclusive licence to The Brazilian Society of Mechanical Sciences and Engineering 2024.
Publication Date: 2022
Amirkabir Journal of Mechanical Engineering (20086032)(3)pp. 139-142
In this paper, a device based on wearable sensors is introduced to describe quantitative body movements in different sports. This device can be an alternative to Image processing techniques. Image processing devices have always been used to describe quantitative body movements, which in addition to being costly, have to be used in specific conditions. The device is built from a number of wireless modules that are easy to use in real-world environments with no limitations. In this method, a quantitative description of movement is made by wireless modules and is performed by the data collected from these modules. In order to analyze the data that was extracted from an athlete’s body movements with these wearable sensors, the outputs are simulated in Matlab, and some of its kinematic and kinetic parameters have been studied. Then, at the end of this paper, the quality of movement of a professional athlete and a beginner athlete are compared, and the result is shown. Kinematic and dynamic analyzes on the above activities showed the following results: The movements are generally correctly recorded. The kinematic analyzes performed for the various movements are consistent with the facts. For example, the kinematic analysis of the recorded motions showed that the coaching movement was more beautifully performed, and this was evident qualitatively during the movement. © 2022, Amirkabir University of Technology. All rights reserved.
