An In-Depth Analysis of Artificial Intelligence on Service Capabilities of Humanoid Robots

Artificial intelligence (AI) emulates human intelligence in digital devices and machines. A humanoid robot is designed to imitate the look and form of a human body and is primarily used for humanitarian assistance and interaction. AI is applied to humanoid robots to allow intelligent behavior and decision-making, resulting in the ability to execute service activities and achieve goals intelligently in the human-robot interaction environment. The paper is a systematic literature review of studies published in the last four years that presents and assesses how AI techniques and methods have been applied to humanoid robots to implement and enhance service capabilities. The research papers used for the systematic literature review were carefully selected under the directives of the PRISMA method. Eighty studies were screened, and eighteen were used for the review. The results show that the primary AI technique applied in humanoid robots is the Convolutional Neural Network (CNN). The results show that the effective AI techniques used in humanoid robots based on a specific area are Hybrid Convolutional Neural Network (CNN) – Long-Short Term Memory (LSTM), Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Deep Convolutional Neural Network DCNN), Recurrent Neural Network (RNN), and Grow-when-required Network (GWR). The study provides AI techniques and methods utilized in modern studies that can be used as a reference for future studies, research, and innovation.