Advantages of Using Edge Machine Learning for Communication Networks and Grasp Analysis in Robotic Hand Network Based on Federated AVG & Machine Learning

Abstract

Robotics provides multiple options for solving problems. Nowadays and in the future, this technology will play a vital role in daily life. Robotics not only help make things easier but also save time and money. These devices also come with challenges that need solving. Robotic hand grasp sensitivity is one of the problems in the robotics industry. Machine learning algorithms and artificial intelligence have several advantages and give clear results to solve this problem. These advantages can solve nonlinear problems well and predict contingencies at a high level. These advantages make machine learning algorithmics one of the best ways to solve problems. Nowadays, with growing internet of things technology most devices will be able to connect networks. Robotic arms also will work like IoT devices. With an internet connection, these devices will be able to send and receive data traffic. This ability will bring more challenges like data security, bandwidth usage, and latency. This study focuses on grasp precision on robotic hand networks with federated averaging which is an edge machine learning algorithm and shows the results and compares with the classical machine learning algorithms. In addition, it is aimed to discuss the performance of the federated averaging algorithm for network requirements and the advantages of this algorithm.