A Survey of Machine Learning and Deep Learning Techniques Over Advanced Robotics in Surgical Applications

ABSTRACT The innovative robotic surgical approach brings a modern solution to complex minimal procedures through precise execution of small instruments through limited opening sites. Through this technique, multiple advantages emerge, which reduce bleeding as well as shorten patients' medical stays and accelerate their healing time, mainly affecting bladder, prostate, heart, and digestive conditions. The da Vinci robotic system represents the first‐ever single‐site platform, which served as a foundation for multiple advanced robotic systems that followed. The article provides an exhaustive evaluation of how machine learning (ML), deep learning (DL), generative adversarial networks (GAN), and reinforcement learning (RL) influence robotic surgery. The research targets the analysis of learning technologies and how these technologies improve surgery precision, healthcare results, and clinical management decisions. Also, this study provides an application of robotics surgery in gynecology, oncology, cardiology, neurology, and urology. This review research analyzes the literature thoroughly to present ML and DL methodology implementations across the studied areas, paying attention to the problems of limited data availability, real‐time system adaptivity, and system interoperability challenges. The study adopts new ideas regarding robotic surgery and AI unification through actionable recommendations that enhance performance against data insufficiency and system integration issues. The paper presents detailed information about new trends together with predictions about ML and DL while providing essential knowledge to robotic surgery specialists and artificial intelligence (AI) scientists to advance robotic surgical assimilation with AI technology.