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.

Vision-Language Models (VLMs) have demonstrated great potential in real-world applications. While existing research primarily focuses on improving their accuracy, the efficiency remains underexplored. Given the real-time demands of many applications and the high inference overhead of VLMs, efficiency robustness is a critical issue. However, previous studies evaluate efficiency robustness under unrealistic assumptions, requiring access to the model architecture and parameters-an impractical scenario in ML-as-a-service settings, where VLMs are deployed via inference APIs. To address this gap, we propose VLMInferSlow, a novel approach for evaluating VLM efficiency robustness in a realistic black-box setting. VLMInferSlow incorporates fine-grained efficiency modeling tailored to VLM inference and leverages zero-order optimization to search for adversarial examples. Experimental results show that VLMInferSlow generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%. We hope this research raises the community's awareness about the efficiency robustness of VLMs.

Billions of vascular access procedures are performed annually worldwide, serving as a crucial first step in various clinical diagnostic and therapeutic procedures. For pediatric or elderly individuals, whose vessels are small in size (typically 2 to 3 mm in diameter for adults and <1 mm in children), vascular access can be highly challenging. This study presents an image-guided robotic system aimed at enhancing the accuracy of difficult vascular access procedures. The system integrates a 6-DoF (Degrees of Freedom) robotic arm with a 3-DoF end-effector, ensuring precise navigation and needle insertion. Multi-modal imaging and sensing technologies have been utilized to endow the medical robot with precision and safety, while ultrasound (US) imaging guidance is specifically evaluated in this study. To evaluate in vivo vascular access in submillimeter vessels, we conducted ultrasound-guided robotic blood drawing on the tail veins (with a diameter of 0.7 ± 0.2 mm) of 40 rats. The results demonstrate that the system achieved a first-attempt success rate of 95%. The high first-attempt success rate in intravenous vascular access, even with small blood vessels, demonstrates the system's effectiveness in performing these procedures. This capability reduces the risk of failed attempts, minimizes patient discomfort, and enhances clinical efficiency.

Robotic-assisted percutaneous coronary intervention (PCI) holds considerable promise for elevating precision and safety in cardiovascular procedures. Nevertheless, current systems heavily depend on human operators, resulting in variability and the potential for human error. To tackle these challenges, Sim4EndoR, an innovative reinforcement learning (RL) based simulation environment, is first introduced to bolster task-level autonomy in PCI. This platform offers a comprehensive and risk-free environment for the development, evaluation, and refinement of potential autonomous systems, enhancing data collection efficiency and minimizing the need for costly hardware trials. A notable aspect of the groundbreaking Sim4EndoR is its reward function, which takes into account the anatomical constraints of the vascular environment, utilizing the geometric characteristics of vessels to steer the learning process. By seamlessly integrating advanced physical simulations with neural network-driven policy learning, Sim4EndoR fosters efficient sim-to-real translation, paving the way for safer, more consistent robotic interventions in clinical practice, ultimately improving patient outcomes.

Accurate three-dimensional (3D) reconstruction of guidewire shapes is crucial for precise navigation in robot-assisted endovascular interventions. Conventional 2D Digital Subtraction Angiography (DSA) is limited by the absence of depth information, leading to spatial ambiguities that hinder reliable guidewire shape sensing. This paper introduces a novel multimodal framework for real-time 3D guidewire reconstruction, combining preoperative 3D Computed Tomography Angiography (CTA) with intraoperative 2D DSA images. The method utilizes robust feature extraction to address noise and distortion in 2D DSA data, followed by deformable image registration to align the 2D projections with the 3D CTA model. Subsequently, the inverse projection algorithm reconstructs the 3D guidewire shape, providing real-time, accurate spatial information. This framework significantly enhances spatial awareness for robotic-assisted endovascular procedures, effectively bridging the gap between preoperative planning and intraoperative execution. The system demonstrates notable improvements in real-time processing speed, reconstruction accuracy, and computational efficiency. The proposed method achieves a projection error of 1.76±0.08 pixels and a length deviation of 2.93±0.15%, with a frame rate of 39.3 1.5 frames per second (FPS). These advancements have the ±potential to optimize robotic performance and increase the precision of complex endovascular interventions, ultimately contributing to better clinical outcomes.

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed down-sampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware down-sampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection performance.The code will be made publicly available.

The advent of dual-polarization meteorological sensing systems has revolutionized our capacity to comprehend atmospheric precipitation dynamics through electromagnetic signal analysis. However, the intricate non-linear relationships within high-dimensional polarimetric signatures present formidable challenges in extracting actionable intelligence for meteorological multimedia applications. This manuscript presents HyperSpectral-M, a computational framework that enhances polarimetric signal interpretation through systematic manifold learning approaches in non-Euclidean spaces, enabling more precise analysis of complex atmospheric phenomena. The proposed HyperSpectral-M framework addresses the limitations of existing methods by incorporating two key innovations: a signal disentanglement mechanism and a physics-constrained reconstruction paradigm. The disentanglement mechanism employs quaternion-based geodesic flow mapping coupled with adaptive spectral decomposition to project polarimetric signatures onto lower-dimensional manifolds while preserving critical microphysical properties. This is augmented by a multi-scale differential geometry analyzer that captures intricate spatiotemporal correlations across varying atmospheric conditions. The reconstruction paradigm leverages adversarial manifold alignment with structured probabilistic inference to synthesize high-fidelity radar representations while maintaining electromagnetic consistency constraints. HyperSpectral-M demonstrates significant real-world impact on meteorological applications by improving precipitation nowcasting accuracy by 15-20% compared to operational methods, enabling more timely and accurate flood warnings. Field validation with emergency management agencies shows that reduces false alarm rates by 30-40% while increasing lead time for severe weather warnings by 15-30 minutes.

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. Note to Practitioners—This work is motivated by the emerging need to increase the level of autonomy in robotic-assisted endovascular procedures, which has the potential to improve procedural efficiency, standardize procedures, and broaden the adoption of robotic systems in clinical practice. The proposed simulation-based reinforcement learning provides a safe and efficient method for training robotic systems, enabling them to master complex tasks in simulation environments prior to real-world application. The successful deployment of models trained in simulation onto physical robotic platforms demonstrates the feasibility of this method for real-world applications. The proposed simulation-based reinforcement learning method offers a promising and viable pathway for enhancing skill acquisition in endovascular interventional robots.