Innovations in digital intelligence are transforming robotic surgery through more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential, yet despite decades of research, most machine learning models rely on small datasets and still struggle to generalize. Recently, Vision-Language Models (VLMs) have achieved transformative advances in multimodal reasoning, suggesting strong potential for intelligent robotic surgery. However, surgical VLMs remain underexplored, and existing models show limited performance, underscoring the need for systematic benchmarks to assess their capabilities, limitations, and future development. To this end, we benchmark the zero-shot performance of several advanced VLMs on two public robotic-assisted laparoscopic datasets for instrument and action classification. Beyond standard evaluation, we integrate explainable AI to visualize VLM attention and uncover causal explanations behind predictions, providing a previously underexplored perspective for assessing model reliability. We also propose explainability-based metrics to complement standard evaluations. Our analysis reveals that surgical VLMs, despite domain-specific training, often rely on weak contextual cues rather than clinically meaningful visual evidence, highlighting the need for stronger visual and reasoning supervision in surgical applications. The code is provided in our public repository at: https://github.com/jiajun344/SurgXBench-Explainable-Vision-Language-Model-Benchmark-for-Surgery.

Robot-assisted neurological surgery is receiving growing interest due to the improved dexterity, precision, and control of surgical tools, which results in better patient outcomes. However, such systems often limit surgeons' natural sensory feedback, which is crucial in identifying tissues particularly in oncological procedures where distinguishing between healthy and tumorous tissue is vital. While imaging and force sensing have addressed the lack of sensory feedback, limited research has explored multimodal sensing options for accurate tissue boundary delineation. We present a userfriendly, modular test bench designed to evaluate and integrate complementary multimodal sensors for tissue identification. Our proposed system first uses vision-based guidance to estimate boundary locations with visual cues, which are then refined using data acquired by contact microphones and a force sensor. Real-time data acquisition and visualization are supported via an interactive graphical interface. Experimental results demonstrate that multimodal fusion significantly improves material classification accuracy. The platform provides a scalable hardware-software solution for exploring sensor fusion in surgical applications and demonstrates the potential of multimodal approaches in real-time tissue boundary delineation.

Laser-based surgical ablation relies heavily on surgeon involvement, restricting precision to the limits of human error and perception. The interaction between laser and tissue is governed by various laser parameters that control the laser irradiance on the tissue, including the power, distance, spot size, orientation, and exposure time. This complex interaction lends itself to robotic automation, allowing the surgeon to focus on high-level tasks, such as choosing the region and method of ablation, while the lower-level ablation plan can be handled autonomously. This paper describes a sampling-based model predictive control (MPC) scheme to plan ablation sequences for arbitrary tissue volumes. Using a steady-state point ablation model to simulate a single laser-tissue interaction, a random search technique explores the reachable state space while preserving sensitive tissue regions. The sampled MPC strategy provides an ablation sequence that accounts for parameter uncertainty without violating constraints, such as avoiding nerve bundles.

In robotic laser surgery, shape prediction of an one-shot ablation crater is an important problem for minimizing errant overcutting of healthy tissue during the course of pathological tissue resection and precise tumor removal. Since it is difficult to physically model the laser-tissue interaction due to the variety of optical tissue properties, complicated process of heat transfer, and uncertainty about the chemical reaction, we propose a 3D crater prediction model based on an entirely data-driven method without any assumptions of laser settings and tissue properties. Based on the crater prediction model, we formulate a novel robotic laser planning problem to determine the optimal laser incident configuration, which aims to create a crater that aligns with the surface target (e.g. tumor, pathological tissue). To solve the one-shot ablation crater prediction problem, we model the 3D geometric relation between the tissue surface and the laser energy profile as a non-linear regression problem that can be represented by a single-layer perceptron (SLP) network. The SLP network is encoded in a novel kinematic model to predict the shape of the post-ablation crater with an arbitrary laser input. To estimate the SLP network parameters, we formulate a dataset of one-shot laser-phantom craters reconstructed by the optical coherence tomography (OCT) B-scan images. To verify the method. The learned crater prediction model is applied to solve a simplified robotic laser planning problem modelled as a surface alignment error minimization problem. The initial results report about$(91.2\pm 3.0)\%$3D-crater-Intersection-over-Union (3D-crater-IoU) for the 3D crater prediction and an average of about 98.0% success rate for the simulated surface alignment experiments.

In this paper, we present an autonomous RGB-D and 2D ultrasound-guided robotic system for collecting 3D localized volumes of peripheral vessels. This compact design, with available commercial components, lends itself to platform utility throughout the human body. The fully integrated system works with force limits for future safety in human use. We propose a PID force controller for smooth and safe robot scanning following a priori 3D trajectory generated from a surface point cloud. System calibration is implemented to determine transformations among sensors, end-effector and robot base. A vascular localization pipeline that consists of detection and tracking is proposed to find the 3D vessel positions in real-time. Precision tests are performed with both predesignated and autonomously selected areas in an arm phantom. The average variance of the autonomously collected ultrasound images (to construct 3D volumes) between repeated tests is shown to be around 0.3 mm, similar to the theoretical spatial resolution a clinical ultrasound system. This fully integrated system demonstrates the capability of autonomous collection of peripheral vessels with built-in safety measures for future human testing.

This paper proposes a stereovision-guided robotic laser system that can conduct laser ablation on targets selected by human operators in the color image, referred as StereoCNC. Two digital cameras are integrated into a previously developed robotic laser system to add a color sensing modality and formulate the stereovision. A calibration method is implemented to register the coordinate frames between stereo cameras and the laser system, modelled as a 3D-to-3D Least-squares problem. This problem is solved by a RANSAC-based 3D rigid transformation method and the calibration reprojection errors are used to characterize a 3D error field by Gaussian process regression. This regression error model is used to predict an error value for each data point of a stereo-reconstructed point cloud and an optimization problem is formulated to adjust the surgical site to a new position with minimum reprojection errors. Based on the calibrated system and the error model, a stereovision-guided laser-tissue removal pipeline is proposed to precisely locate, target, and ablate a surface region. The pipeline is validated by the experiments on phantoms with color texture and various geometric shapes. The overall targeting accuracy of the system achieves an average RMSE of 0.13±0.02 mm and maximum error of 0.34±0.06 mm, as measured by pre- and post-laser ablation images. The results show potential applications of using the developed stereovision-guided robotic system for superficial laser surgery, including dermatologic applications or removal of exposed tumorous tissue in neurosurgery.

Laser scalpels are utilized across a variety of surgical and dermatological procedures due to their precision and non-contact nature. This paper presents a novel laser scalpel system for superficial laser therapy applications. The system integrates a RGB-D camera, a 3D triangulation sensor and a carbon dioxide (CO2) laser scalpel for computer-assisted laser surgery. To accurately ablate targets chosen from the color image, a 3D extrinsic calibration method between the RGB-D camera frame and the laser coordinate system is implemented. The accuracy of the calibration method is tested on phantoms with planar and cylindrical surfaces. Positive error and negative error, as defined as undershooting and overshooting over the target area, are reported for each test. For 60 total test cases, the root-mean-square of the positive and negative error in both planar and cylindrical phantoms is less than 1.0 mm, with a maximum absolute error less than 2.0 mm. This work demonstrates the feasibility of automated laser therapy with surgeon oversight via our sensor system.

Concentric tube robots are catheter-sized continuum robots that are well suited for minimally invasive surgery inside confined body cavities. These robots are constructed from sets of pre-curved superelastic tubes and are capable of assuming complex 3D curves. The family of 3D curves that the robot can assume depends on the number, curvatures, lengths and stiffnesses of the tubes in its tube set. The robot design problem involves solving for a tube set that will produce the family of curves necessary to perform a surgical procedure. At a minimum, these curves must enable the robot to smoothly extend into the body and to manipulate tools over the desired surgical workspace while respecting anatomical constraints. This paper introduces an optimization framework that utilizes procedureor patient-specific image-based anatomical models along with surgical workspace requirements to generate robot tube set designs. The algorithm searches for designs that minimize robot length and curvature and for which all paths required for the procedure consist of stable robot configurations. Two mechanics-based kinematic models are used. Initial designs are sought using a model assuming torsional rigidity. These designs are then refined using a torsionally-compliant model. The approach is illustrated with clinically relevant examples from neurosurgery and intracardiac surgery.

Surgical robots are gaining favor in part due to their capacity to reach remote locations within the body. Continuum robots are especially well suited for accessing deep spaces such as cerebral ventricles within the brain. Due to the entry point constraints and complicated structure, current techniques do not allow surgeons to access the full volume of the ventricles. The ability to access the ventricles with a dexterous robot would have significant clinical implications. This paper presents a concentric tube manipulator mated to a robotically controlled flexible endoscope. The device adds three degrees of freedom to the standard neuroendoscope and roboticizes the entire package allowing the operator to conveniently manipulate the device. To demonstrate the improved functionality, we use an in-silica virtual model as well as an ex-vivo anatomic model of a patient with a treatable form of hydrocephalus. In these experiments we demonstrate that the augmented and roboticized endoscope can efficiently reach critical regions that a manual scope cannot.