Integrating Robotics and Artificial Intelligence in Healthcare: Towards Adaptive and Semi-Autonomous Medical Systems

The integration of robotics and artificial intelligence (AI) is reshaping contemporary healthcare through the emergence of adaptive and semi-autonomous medical systems that operate within structured human-in-the-loop frameworks. This narrative review synthesizes recent advances in AI-enabled medical robotics across sensing, perception, control, and human–robot interaction, with applications spanning surgical intervention, diagnostic imaging, rehabilitation, hospital logistics, and telemedicine. Evidence from clinical and experimental studies indicates that robotic systems enhance procedural precision, operational efficiency, and consistency in care delivery, particularly when combined with deep learning-based perception and data-driven decision-support mechanisms (Topol, 2019; Yang et al., 2018; Esteva et al., 2017). In parallel, AI-driven diagnostic models have demonstrated high performance in pattern recognition tasks, while robotic platforms in rehabilitation and assistive care enable personalized, feedback-driven therapy that improves functional outcomes in selected patient populations (Litjens et al., 2017; Veerbeek et al., 2017).Despite these advances, real-world deployment remains constrained by limitations in model generalizability, system interpretability, data heterogeneity, and integration within complex clinical workflows, necessitating sustained clinician oversight and validation (Jiang et al., 2017). Furthermore, logistical and teleoperated robotic systems highlight both the potential and infrastructural dependencies of healthcare automation, particularly in relation to network reliability, interoperability, and cybersecurity constraints (Kruse et al., 2020). Across all domains, findings consistently indicate that healthcare robotics is progressing toward semi-autonomous systems characterized by shared control and collaborative decision-making rather than full automation.The review concludes that future progress will depend on advances in trustworthy AI, robust multimodal sensing, adaptive control architectures, and clinically validated deployment frameworks, ensuring that robotic systems remain safely embedded within human-centered healthcare ecosystems.