Over the past decade, significant advancements have been made in the research and industrialization of robotic systems for endovascular procedures, yet their clinical application remains relatively limited. Physicians commonly report that these robots lack certain intelligent assistive capabilities during procedures. There has been increasing interest and attempts to apply learning-centered algorithms to the training and enhancement of surgical robot skills. This paper proposes an autonomous navigation algorithm for interventional guidewires that is initially trained solely in a virtual simulation environment and subsequently deployed to a real-world robot. Experimental results demonstrate the feasibility of this approach for real-world applications. The proposed approach can help physicians reduce the learning curve for guidewire manipulation and elevate the robot to a higher level of autonomous operation, thereby breaking through the current bottleneck in the level of intelligence for clinical applications of interventional robots. It also holds promise for bringing intelligent transformation to future interventional procedures.

Visual Question Answering (VQA) in robotic surgery is rapidly becoming a pivotal technology in medical AI, addressing the complex challenge of interpreting multimodal surgical data to support real-time decision-making. This comprehensive review synthesizes key advancements in Surgical VQA, highlighting the integration of large language models (LLMs), multimodal fusion techniques, and visual grounding methods. By reviewing 62 key studies selected through a systematic search of major scientific databases, including IEEE Xplore, Google Scholar, SpringerLink, and PubMed, we trace the evolution of VQA systems and their application in surgical environments. Current limitations, including dataset scarcity, multimodal alignment challenges, and issues of interpretability, are critically examined. This survey aims to not only provide a structured overview of the field but also identify critical research gaps and propose future directions to enhance VQA systems for robotic surgery, with the ultimate goal of improving intraoperative performance and patient outcomes.

Endovascular interventions require precise, cooperative control of multiple instruments, such as guidewires and catheters, to navigate complex vascular anatomies. Current robotic systems, reliant on leader-follower control, depend heavily on operator expertise and lack intelligence. Learning-based methods, often limited to single-instrument control, fall short in complex clinical scenarios requiring multi-instrument coordination. This study proposes a Multi-Agent Fuzzy Reinforcement Learning (MAFRL) framework, guided by large language models (LLMs), for task-level autonomous, cooperative navigation in endovascular robotics. LLMs provide procedural priors and context-aware policy guidance, enabling adaptive decision-making for collaborative guidewire and catheter agents. Central to the framework, fuzzy reinforcement learning mitigates LLM-induced uncertainties by adaptively embedding clinical constraints into reward functions, ensuring strict adherence to procedural safety and precise alignment with the complexities of real-world endovascular interventions. Validated in a 3D vascular simulation, this approach achieves superior navigation performance and procedural efficiency compared to conventional methods, underscoring the transformative potential of fuzzy reinforcement learning in advancing LLM-guided MARL for endovascular robotics.

Non-invasive and continuous blood glucose monitoring is crucial for effective diabetes management. Photoplethysmography (PPG) signal in wearable devices has gained recognition as a potential approach because of its simplicity, accessibility, and remote monitoring capability. This systematic analysis comprehensively assesses the feasibility, accuracy, and limitations of using PPG for measuring blood glucose levels. This review synthesizes 106 peer-reviewed studies, comprehensively analyzing the physiological principles and technological advancements of PPG-based glucose monitoring, while comparing it with conventional and emerging methods. Our analysis reveals several promising research directions in key areas. For PPG sensors, near-infrared wavelengths (850–940 nm) with reflective mode show better glucose sensitivity. AI-based methods, particularly deep learning approaches, often show improved performance in PPG signal preprocessing for motion artifact reduction compared to traditional techniques. Physical–mathematical models incorporating blood volume pulse characteristics could help identify novel PPG features correlating with glucose variations. Furthermore, hybrid approaches combining machine learning with physiological models show the most potential for accurate glucose level interpretation from PPG signals. These findings provide guidance for future research to advance PPG-based glucose monitoring toward clinical implementation.