State-of-the-art surgery is performed robotically under direct surgeon control. However, surgical outcome is limited by the availability, skill, and day-to-day performance of the operating surgeon. What will it take to improve surgical outcomes independent of human limitations? In this Review, we explore the technological evolution of robotic surgery and current trends in robotics and artificial intelligence that could lead to a future generation of autonomous surgical robots that will outperform today’s teleoperated robots.

Head and neck cancers are the seventh most common cancers worldwide, with squamous cell carcinoma being the most prevalent histologic subtype. Surgical resection is a primary treatment modality for many patients with head and neck squamous cell carcinoma, and accurately identifying tumor boundaries and ensuring sufficient resection margins are critical for optimizing oncologic outcomes. This letter presents an innovative autonomous system for tumor resection (ASTR) and conducts a feasibility study by performing supervised autonomous midline partial glossectomy for pseudotumor with millimeter accuracy. The proposed ASTR system consists of a dual-camera vision system, an electrosurgical instrument, a newly developed vacuum grasping instrument, two 6-DOF manipulators, and a novel autonomous control system. The letter introduces an ontology-based research framework for creating and implementing a complex autonomous surgical workflow, using the glossectomy as a case study. Porcine tongue tissues are used in this study, and marked using color inks and near-infrared fluorescent (NIRF) markers to indicate the pseudotumor. ASTR actively monitors the NIRF markers and gathers spatial and color data from the samples, enabling planning and execution of robot trajectories in accordance with the proposed glossectomy workflow. The system successfully performs six consecutive supervised autonomous pseudotumor resections on porcine specimens. The average surface and depth resection errors measure $0.73\pm 0.60$ $\text{mm}$ and $1.89\pm 0.54$ $\text{mm}$, respectively, with no positive tumor margins detected in any of the six resections. The resection accuracy is demonstrated to be on par with manual pseudotumor glossectomy performed by an experienced otolaryngologist.

Background: Pericardial access is necessary for the application of epicardial cardiac therapies including ablation catheters, pacing and defibrillation leads, and left atrial appendage closure systems. Pericardial access under fluoroscopic guidance is difficult in patients without pericardial effusions and may result in coronary artery damage, ventricular injury, or perforation with potentially life-threatening pericardial bleeding in up to 10% of cases. There is a clinical need for a pericardial access technique to safely deliver epicardial cardiac therapies. Methods: In this paper, we describe the design and evaluation of a novel videoscope and tool kit to percutaneously access the pericardial space under direct visualization. Imaging is performed by a micro-CMOS camera with an automatic gain adjustment software to prevent image saturation. Imaging quality is quantified using known optical targets, while tool performance is evaluated in pediatric insufflation and pericardial access simulators. Device safety and efficacy is demonstrated by infant porcine preclinical studies (N = 6). Results: The videoscope has a resolution of 400 × 400 pixels, imaging rate of 30 frames per second, and fits within the lumen of a 14G needle. The tool can resolve features smaller than 39.4 µm, achieves a magnification of 24x, and has a maximum of 3.5% distortion within the field of view. Successful pericardial access was achieved in pediatric simulators and acute in vivo animal studies. During in vivo testing, it took the electrophysiologist an average of 66.83 ± 32.86 s to insert the pericardial access tool into the thoracic space and visualize the heart. After visualizing the heart, it took an average of 136.67 ± 80.63 s to access the pericardial space under direct visualization. The total time to pericardial access measured from needle insertion was 6.7 × quicker than pericardial access using alternative direct visualization techniques. There was no incidence of ventricular perforation. Conclusions: Percutaneous pericardial access under direct visualization is a promising technique to access the pericardial space without complications in simulated and in vivo animal models.

Autonomous robotic suturing has the potential to improve surgical outcomes compared to manual operations due to better accuracy and consistency of suture placement. In this letter, we develop an autonomous system with model-based planning and markerless tissue tracking techniques for autonomous vaginal cuff closure. The proposed planning method constructs an optimal suture plan that minimizes tissue collisions with the robotic suturing tool. Moreover, DeepLabCut is utilized for autonomous markerless soft-tissue tracking in robotic vaginal cuff closure. Furthermore, an instruction-based autonomous surgery interface (ASI) is designed to automate the complex suturing workflow. The proposed planning method is evaluated via a robotics simulator and real-world suture-placement tests. End-to-end vaginal cuff closure via Smart Tissue Autonomous Robot (STAR) on synthetic tissues was carried out and compared to the suturing results via conventional laparoscopic and robot-assisted approaches performed by experienced surgeons. The comparison results indicate that by using the proposed planning pipeline, STAR outperforms conventional laparoscopic and robotic-assisted methods with better accuracy and consistency, thus achieving a higher success rate of autonomous suture placement.

This paper reports the design and evaluation of a novel piezo based actuator for needle drive in autonomous Deep Anterior Lamellar Keratoplasty (piezo-DALK). The actuator weighs less than 8g and is 20mm x 20mm x 10.5mm in size, making it ideal for eye-mounted applications. Mean open loop positional deviation was 1.17 ± 3.15um, and system repeatability and accuracy were 17.16um and 18.33um, respectively. Stall force was found to vary linearly with the cooling cycle and the actuator achieved a maximum drive force of 3.98N. When simulating the DALK procedure in synthetic corneal tissue, the piezo-DALK achieved a penetration depth of 643.56um which was equivalent to 92.1% of the total corneal thickness. This correlated closely with our desired depth of 90% ± 5% and took 2.5 hours to achieve. This work represents the first eye mountable actuator capable of "Big Bubble" needle drive for autonomous DALK procedures.