Applications of Knowledge-Integrated Machine Learning in Robotics

Due to recent developments in theory at the interface between optimization and machine learning, robot learning mainly has encountered significant challenges. Robotics learning limit has been recognized as one of the fundamental difficulties artificial intelligence. In various fields of advanced mechanics, machine learning (ML) has for quite some time been recognized as the center method. Given the significance of certain correspondence in relational collaborations, robotics frameworks should have this capacity. This would enable a robot to ascertain the intents and sentiments of the human being it is cooperating with. Affect recognition uses a variety of machine learning algorithms to accurately predict an individual’s emotional state from a collection of physiological characteristics. The adequacy of K-Nearest Neighbor, Regression Tree (RT), Bayesian network, and Support Vector Machine (SVM) on the errand of recognizing mind-set from physiological data sources is looked at in this review. The findings showed that, despite all approaches performing well, SVM had the greatest classification accuracy. The next-best categorization accuracy was provided by RT, which also used the least amount of space and time.