An Efficient Integration of Artificial Intelligence-based Mobile Robots in Critical Frames for the Internet of Medical Things (IoMTs) Using (ADP2S) and Convolutional Neural Networks (CNNs)

Moving in complex environments is an essential capability of intelligent mobile robots. Decades of research and engineering have been dedicated to developing sophisticated navigation systems to move mobile robots from one point to another. Despite their overall success, a recently emerging research thrust is devoted to developing machine learning techniques to address the same problem, based in large part on the success of deep learning techniques. Real-time systems are widely used in industry, including technological process control systems, industrial automation systems, SCADA systems, testing, and measuring equipment, and robotics. Artificial intelligence-based Mobile robots have been receiving attention from researchers worldwide in recent years, especially in developing autonomous mobile robots. Artificial intelligence and Machine learning play a great role in the development of humanoid robots, they have increased humanoids efficiency and their functionality. This paper presents an optimal machine learning-assisted intelligent Convolutional Neural Network (CNN) based approach for humanoid function identification using AI and Machine learning that enable humanoid robots to evolve  Human-Robot Interaction (HRI) that helps resolve crucial issues concurrently while discussing improvements in Accuracy, Precision, decision-making, and interaction skills. The paper also tests and trains the ML model using the open source dataset named direct kinematics of an IRB 120 robotic. The proposed P-CNN outperformed the other renowned algorithm designs by evaluating the performance by considering the real-time sensor data, machine learning models, and natural language processing. The proposed technique demonstrates the practical uses of humanoid robotics technologies, highlighting notable accomplishments in areas like better locomotion and human-robot interaction. Despite the encouraging progress we achieved, safety and efficiently learning the representation of non-expert strategies on large-scale real-world data using reinforcement learning remain challenging. The implementation results proved that this system operated effectively with a minimal response delay of 0.77–2.67s and a high detection accuracy (98.25%) in two experimental cases, which makes it suitable for real-time applications.  This article also addresses the prospective opportunities for further research and development in humanoid robotics while suggesting further advancements in this field that could result from interdisciplinary efforts.. Key words: Mobile robot navigation, Machine learning, Motion planning, Motion control, ResNet, Deep neural network, CNN, Healthcare, Prediction models, Segmentation