Robotic Skills Research Articles

Vision-language model-based human-robot collaboration for smart manufacturing: A state-of-the-art survey

Abstract human-robot collaboration (HRC) is set to transform the manufacturing paradigm by leveraging the strengths of human flexibility and robot precision. The recent breakthrough of Large Language Models (LLMs) and Vision-Language Models (VLMs) has motivated the preliminary explorations and adoptions of these models in the smart manufacturing field. However, despite the considerable amount of effort, existing research mainly focused on individual components without a comprehensive perspective to address the full potential of VLMs, especially for HRC in smart manufacturing scenarios. To fill the gap, this work offers a systematic review of the latest advancements and applications of VLMs in HRC for smart manufacturing, which covers the fundamental architectures and pretraining methodologies of LLMs and VLMs, their applications in robotic task planning, navigation, and manipulation, and role in enhancing human–robot skill transfer through multimodal data integration. Lastly, the paper discusses current limitations and future research directions in VLM-based HRC, highlighting the trend in fully realizing the potential of these technologies for smart manufacturing.

Further Validating the Robotic Microsurgery Platform through Preclinical Studies on Rat Femoral Artery and Vein.

This research aims to validate the proficiency and accuracy of the robotic microsurgery platform using rat femoral vessel model. A total of 256 rat femoral vessels were performed, half using robotic and the other by manual microanastomosis by eight microsurgeons with less than 5 years of experience given eight trials (rats) each. Vessel demographics, proficiency (duration of suture and Structured Assessment of Robotic Microsurgical Skills [SARMS]), and accuracy (patency and scanning electron microscopic [SEM]) were analyzed between the two groups. Using the robot, an average of four trials was needed to reach a plateau in total anastomosis time and patency. Significant more time was required for each vessel anastomosis (34.33 vs. 21.63 minutes on the eighth trial, p < 0.001) one factor being a higher number of sutures compared with the handsewn group (artery: 7.86 ± 0.51 vs. 5.86 ± 0.67, p = 0.035, vein: 12.63 ± 0.49 vs. 9.57 ± 0.99, p = 0.055). The SARMS scores became nonsignificant between the two groups on the fourth trial. The SEM showed a higher tendency of unevenly spaced sutures, infolding, and tears in the vessel wall for the handsewn group. Using the robot, similar patency, accuracy, and proficiency can be reached through a fast but steep learning process within four trials (anastomosis of eight vessels) as the handsewn group. The robotic anastomosis may take longer time, but this is due to the increased number of sutures reflecting higher precision and accuracy. Further insight of precision and accuracy was found through the SEM demonstrating the possibility of the robot to prevent unexpected and unwanted complications.

Segment, Compare, and Learn: Creating Movement Libraries of Complex Task for Learning from Demonstration.

Motion primitives are a highly useful and widely employed tool in the field of Learning from Demonstration (LfD). However, obtaining a large number of motion primitives can be a tedious process, as they typically need to be generated individually for each task to be learned. To address this challenge, this work presents an algorithm for acquiring robotic skills through automatic and unsupervised segmentation. The algorithm divides tasks into simpler subtasks and generates motion primitive libraries that group common subtasks for use in subsequent learning processes. Our algorithm is based on an initial segmentation step using a heuristic method, followed by probabilistic clustering with Gaussian Mixture Models. Once the segments are obtained, they are grouped using Gaussian Optimal Transport on the Gaussian Processes (GPs) of each segment group, comparing their similarities through the energy cost of transforming one GP into another. This process requires no prior knowledge, it is entirely autonomous, and supports multimodal information. The algorithm enables generating trajectories suitable for robotic tasks, establishing simple primitives that encapsulate the structure of the movements to be performed. Its effectiveness has been validated in manipulation tasks with a real robot, as well as through comparisons with state-of-the-art algorithms.

Video-based robotic surgical action recognition and skills assessment on porcine models using deep learning.

This study aimed to develop an automated skills assessment tool for surgical trainees using deep learning. Optimal surgical performance in robot-assisted surgery (RAS) is essential for ensuring good surgical outcomes. This requires effective training of new surgeons, which currently relies on supervision and skill assessment by experienced surgeons. Artificial Intelligence (AI) presents an opportunity to augment existing human-based assessments. We used a network architecture consisting of a convolutional neural network combined with a long short-term memory (LSTM) layer to create two networks for the extraction and analysis of spatial and temporal features from video recordings of surgical procedures, facilitating action recognition and skill assessment. 21 participants (16 novices and 5 experienced) performed 16 different intra-abdominal robot-assisted surgical procedures on porcine models. The action recognition network achieved an accuracy of 96.0% in identifying surgical actions. A GradCAM filter was used to enhance the model interpretability. The skill assessment network had an accuracy of 81.3% in classifying novices and experiences. Procedure plots were created to visualize the skill assessment. Our study demonstrated that AI can be used to automate surgical action recognition and skill assessment. The use of a porcine model enables effective data collection at different levels of surgical performance, which is normally not available in the clinical setting. Future studies need to test how well AI developed within a porcine setting can be used to detect errors and provide feedback and actionable skills assessment in the clinical setting.

Comparison of perioperative outcomes of DaVinci robot and Hugo robot radical prostatectomy: A systematic review and meta-analysis.

To compare the safety and efficacy of radical prostatectomy with DaVinci robot and Hugo robot. The system searches Embase, PubMed, Cochrane library, and Web of Science 4 database. The search time ranges from database creation to June 2024. Stata17 was used for statistical analysis. A total of 5 studies were conducted, including 816 patients. The results showed that there was no difference in age, preoperative prostate volume, preoperative PSA level, operation time, estimated blood loss, length of stay, overall complications, urinary incontinence, lymph node yield, and positive margin between DaVinci robot and Hugo robot radical prostatectomy. However, the BMI of DaVinci group was larger than that of Hugo (Effect=0.47, 95%Cl [0.03, 0.91], P<0.05). The BMI of the DaVinci group seems to be larger, and Hugo robotic radical prostatectomy seems to be as effective as DaVinci robotic radical prostatectomy. But more well-designed studies are needed to assess the oncology outcomes and cost-effectiveness of both. In addition to this, the accumulation of surgeon experience and the transfer of robotic skills are worthy of further attention.

EzSkiROS: enhancing robot skill composition with embedded DSL for early error detection.

When developing general-purpose robot software components, we often lack complete knowledge of the specific contexts in which they will be executed. This limits our ability to make predictions, including our ability to detect program bugs statically. Since running a robot is an expensive task, finding errors at runtime can prolong the debugging loop or even cause safety hazards. This paper proposes an approach to help developers catch these errors as soon as we have some context (typically at pre-launch time) with minimal additional efforts. We use embedded domain-specific language (DSL) techniques to enforce early checks. We describe design patterns suitable for robot programming and show how to use these design patterns for DSL embedding in Python, using two case studies on an open-source robot skill platform SkiROS2, designed for the composition of robot skills. These two case studies help us understand how to use DSL embedding on two abstraction levels: the high-level skill description that focuses on what the robot can do and under what circumstances and the lower-level decision-making and execution flow of tasks. Using our DSL EzSkiROS, we show how our design patterns enable robotics software platforms to detect bugs in the high-level contracts between the robot's capabilities and the robot's understanding of the world. We also apply the same techniques to detect bugs in the lower-level implementation code, such as writing behavior trees (BTs), to control the robot's behavior based on its capabilities. We perform consistency checks during the code deployment phase, significantly earlier than the typical runtime checks. This enhances the overall safety by identifying potential issues with the skill execution before they can impact robot behavior. An initial study with SkiROS2 developers shows that our DSL-based approach is useful for finding bugs early and thus improving the maintainability of the code.

A Novel DMPs Framework for Robot Skill Generalizing With Obstacle Avoidance: Taking Volume and Orientation Into Consideration

A Novel DMPs Framework for Robot Skill Generalizing With Obstacle Avoidance: Taking Volume and Orientation Into Consideration

Examining the learning curves in robotic cardiac surgery wet lab simulation training.

Simulation-based training has gained distinction in cardiothoracic surgery as robotic-assisted cardiac procedures evolve. Despite the increasing use of wet lab simulators, the effectiveness of these training methods and skill acquisition rates remain poorly understood. This study aimed to compare learning curves and assess the robotic cardiac surgical skill acquisition rate for cardiac and noncardiac surgeons who had no robotic experience in a wet lab simulation setting. In this prospective cohort study, participants practiced 3 robotic tasks in a porcine model: left atriotomy closure, internal thoracic artery harvesting and mitral annular suturing. Participants were novice robotic cardiac and noncardiac surgeons alongside experienced robotic cardiac surgeons who established performance benchmarks. Performance was evaluated using the time-based score and modified global evaluative assessment of robotic skills (mGEARS). The participants were 15 novice surgeons (7 cardiac; 8 noncardiac) and 4 experienced robotic surgeons. Most novices reached mastery in 52 (±22) min for atrial closure, 32 (±18) for internal thoracic artery harvesting and 34 (±12) for mitral stitches, with no significant differences between the cardiac and noncardiac surgeons. However, for mGEARS, noncardiac novices faced more challenges in internal thoracic artery harvesting. The Thurstone learning curve model indicated no significant difference in the learning rates between the groups. Wet lab simulation facilitates the rapid acquisition of robotic cardiac surgical skills to expert levels, irrespective of surgeons' experience in open cardiac surgery. These findings support the use of wet lab simulators for standardized, competency-based training in robotic cardiac surgery.

An Improved Method for Enhancing the Accuracy and Speed of Dynamic Object Detection Based on YOLOv8s.

Accurate detection and tracking of dynamic objects are critical for enabling skill demonstration and effective skill generalization in robotic skill learning and application scenarios. To further improve the detection accuracy and tracking speed of the YOLOv8s model in dynamic object tracking tasks, this paper proposes a method to enhance both detection precision and speed based on YOLOv8s architecture. Specifically, a Focused Linear Attention mechanism is introduced into the YOLOv8s backbone network to enhance dynamic object detection accuracy, while the Ghost module is incorporated into the neck network to improve the model's tracking speed for dynamic objects. By mapping the motion of dynamic objects across frames, the proposed method achieves accurate trajectory tracking. This paper provides a detailed explanation of the improvements made to YOLOv8s for enhancing detection accuracy and speed in dynamic object detection tasks. Comparative experiments on the MS-COCO dataset and the custom dataset demonstrate that the proposed method has a clear advantage in terms of detection accuracy and processing speed. The dynamic object detection experiments further validate the effectiveness of the proposed method for detecting and tracking objects at different speeds. The proposed method offers a valuable reference for the field of dynamic object detection, providing actionable insights for applications such as robotic skill learning, generalization, and artificial intelligence-driven robotics.

Virtual reality simulations in robotic surgery training: a systematic review and meta-analysis.

To compare VR simulations with other training methods regarding improvements in objective assessment scores and task completion times. A database search was conducted on 20 May 2024 across Central, MEDLINE, EMBASE, Web of Science, and Scopus. Included were randomised controlled trials comparing VR simulations to other training methods, assessing objective scores and task times. The Risk of Bias-2 tool was used for bias assessment. Eighteen studies were included. VR significantly improved objective scores (n = 339, SMD 1.04, 95% CI 0.40-1.69, P = 0.002) and reduced task completion times (n = 357, SMD of -1.08, 95% CI of as -2.05 to -0.12, P = 0.03) compared to no additional training. VR was as effective as dry lab training for improving scores (n = 213, SMD -0.47, 95% CI -1.34 to 0.41, P = 0.30) and task times (n = 98, SMD -0.37, 95% CI -1.51 to 0.78, P = 0.53). However, one study found wet lab training significantly reduced task times compared to VR (n = 20, SMD of 1.7, 95% CI of 0.65-2.76, P = 0.002). No significant differences were found when VR alone was compared to VR with expert advice. VR is more effective than no additional training and is as effective as dry lab training in robotic skill acquisitions. Therefore, VR is effective in enhancing robotic surgery skills and warrants an expanded role in surgical training programmes.

Rubric development and validation for assessing educational robotics skills

The current study describes the process of development and validation of a rubric for assessing educational robotics skills among middle school students. A multiphase method has been followed, including a literature study, expert consultation, content validation, pilot testing, reliability analysis, and construct validation. The resulting dual-category rubric designing and programming skills were further elaborated by specific criteria and performance levels. Content validation identified seven key criteria: stability and durability, motors, innovation, code organization, dependability and reliability, movement and rotation, and innovative use of sensors. The results of inter-rater reliability analysis for all criteria indicated good agreement, with Krippendorff’s alpha ranging from 0.941 to 1.000. Additionally, construct validation using exploratory factor analysis confirmed a two-factor structure that aligns with the intended domains of design and programming skills, explaining 67.4% of the total variance. The rubric was consistent with learning/teaching theories such as Bloom’s taxonomy, constructivist learning theory, and self-determination theory. This rubric fulfills the existing need for a specific assessment tool in educational robotics and supports educational practices through very detailed feedback to students on their performance. This adds much to educational assessment and education in robotics and enhances teaching and learning outcomes for STEAM education in various settings.

A robotic skill transfer learning framework of dynamic manipulation for fabric placement

Placing fabric poses a challenge to robots since fabric with high dimensional configuration space can deform during manipulation. Existing methods for placing fabric mostly rely on static operations, which are inefficient and require a large workspace. Therefore, this study applies dynamic manipulation (manipulating uncontrollable parts of the fabric by swinging) to fabric placement, proposing a novel learning framework for robotic dynamic fabric placement skill learning and generalization. The proposed framework integrates reinforcement learning with imitation learning, leveraging expert demonstration data to guide and accelerate skill acquisition. Additionally, fabric characteristics are combined with imitation learning to enable the transfer and generalization of the learned policy to real-world environments The experiments suggest that the proposed framework is capable of achieving the placement tasks for a range of positions and fabrics. For success rate, the policy of the proposed framework ultimately achieves a flatness of exceeding 95% and a placement distance error of less than 2 mm. Moreover, the proposed approach is similar in operation time to the fastest method, while it can reduce the space required for manipulating the fabric by over 15%. Compared with other placement policies, it is promising because of its high accuracy, flexibility, efficiency, as well as adaptability.

From gaming to surgery: the influence of digital natives on robotic skills development

Our study investigates the potential correlation between generational differences, like age and previous experience with digital innovations, such as video games and smartphones, and the performance on the Da Vinci Skills Simulator, the cornerstone of robotic surgery training. Thirty participants were involved from three age groups: Generation Alpha, Generation Z, and Generation X. None had prior robotic surgical experience. Participants performed the Wrist Articulation 1 task on the Da Vinci Skills Simulator after two practice rounds. Analysis of performance metrics and statistical tests were conducted to assess the differences between groups. Additionally, participants had completed a survey on their habits related to video gaming, smartphone, and computer usage. A trend was observed where performance declined with age, meaning that Generation Alpha performed the most successfully compared to the other generations, although the difference was not statistically significant (p = 0.51). However, significant differences were found in Glass Movement (GM) by Generation Z showing superior precision, making less errors (p = 0.019). The study found no correlation between simulator performance and early or frequent exposure to smartphones or video games. Interestingly, frequent two-thumb typing on smartphones correlated with better performance in the GM metric (p = 0.006). Generation Z demonstrated greater precision in handling the simulator, reflecting that robotic surgery training might be best to be started at the beginning of residency programs. Young doctors using two-thumb typing develop robotic surgery skills faster. Further studies are needed to determine whether this quicker learning would also lead to better skills later on.

OGC SO16 - International upper GI robotic fellowship on the CMR Versius platform

Abstract Background The impetus for UGI surgery trainees to attain skills in robotic surgery is likely to increase following the global acceptance and utilisation of robotic platforms. UGI robotic fellowship programs are few in number and highly desirable providing trainees with a unique selling point when embarking on independent consultant practice. We describe the first UGI robotic surgery fellowship on the CMR Versius platform at the Gloucestershire Royal Hospital which has the largest experience of UGI robotic surgery on the CMR Versius platform in the UK, having performed over 200 cases including the first robot assisted minimally invasive oesophagectomy. Method A structured robotic training curriculum was created in collaboration with CMR Versius. It consists of a pre-clinical phase of E-learning (10 modules), simulator training (16 assessed tasks) and dry-laboratory training (a two-day course encompassing robotic system set-up, bed-side assist and assessed dry lab practical tasks). The clinical phase begins with bed-side assisting of robotic cases followed by supervised operating on the console. Operations performed on the console are recorded for review and evaluation. The videos will be scored by two independent surgeons using the modified Global Evaluation Assessment of Robotic Skills (mGEARS) score to track growth and progress. Results The E-learning modules and assessments were completed prior to commencement of the fellowship. The remainder of the pre-clinical phase of the curriculum were completed within 4 weeks of commencement followed by bed-side assisting. Once competent at bed-side assisting and able to demonstrate proficiency in set-up (selecting port site placement, docking, arm spacing and configuration), supervised console training was commenced 6 weeks into the fellowship. Console training began with robotic assisted laparoscopic assisted cholecystectomy to gain familiarity, confidence, and efficiency. After 6 cases as the only console surgeon, the surgical complexity of cases was progressed to hiatal surgery and Heller’s cardiomyotomy Conclusion A structured training curriculum with defined phases provides a feasible and effective framework for robotic fellowship training. Adherence to the pre-clinical phase of training allows safe and efficient progression to hands-on console experience. This is achievable within relatively short timeframe to allow for ample independent console surgeon experience and the development of proficiency within a 12-month fellowship period.

Assessment of first-touch skills in robotic surgical training using hi-Sim and the hinotori surgical robot system among surgeons and novices

PurposeSurgeons’ adaptability to robotic manipulation remains underexplored. This study evaluated the participants’ first-touch robotic training skills using the hinotori surgical robot system and its simulator (hi-Sim) to assess adaptability.MethodsWe enrolled 11 robotic surgeons (RS), 13 laparoscopic surgeons (LS), and 15 novices (N). After tutorial and training, participants performed pegboard tasks, camera and clutch operations, energizing operations, and suture sponge tasks on hi-Sim. They also completed a suture ligation task using the hinotori surgical robot system on a suture simulator. Median scores and task completion times were compared.ResultsPegboard task scores were 95.0%, 92.0%, and 91.5% for the RS, LS, and N groups, respectively, with differences between the RS group and LS and N groups. Camera and clutch operation scores were 93.1%, 49.7%, and 89.1%, respectively, showing differences between the RS group and LS and N groups. Energizing operation scores were 90.9%, 85.2%, and 95.0%, respectively, with a significant difference between the LS and N groups. Suture sponge task scores were 90.6%, 43.1%, and 46.2%, respectively, with differences between the RS group and LS and N groups. For the suture ligation task, completion times were 368 s, 666 s, and 1095 s, respectively, indicating differences among groups. Suture scores were 12, 10, and 7 points, respectively, with differences between the RS and N groups.ConclusionFirst-touch simulator-based robotic skills were partially influenced by prior robotic surgical experience, while suturing skills were affected by overall surgical experience. Thus, robotic training programs should be tailored to individual adaptability.

Video Review Can Measure Surgical Robotic Skill Development in a Resident Robotic Hernia Curriculum: A Retrospective Cohort Study.

Hernia repairs are one of the most common general surgery procedures and an essential part of training for general surgery residents. The widespread incorporation of robotic hernia repairs warrants the development of a procedure-specific robotic curriculum to assist novice surgeons in improving technical skills. To evaluate a robotic hernia simulation-based curriculum for general surgery residents using video review. Retrospective cohort study of PGY-3 general surgery residents from the University of Chicago from 2019 to 2021. The residents completed inguinal hernia repair (IHR) and ventral hernia repair (VHR) drills as part of a robotic simulation curriculum. The drills were recorded and graded according to the modified objective structured assessment of technical skills (OSATS) and time to completion. The drills were completed by 3 attending surgeons to establish gold-standard benchmarks. In total, 20 residents started the curriculum, 19 completed all IHR drills and 17 completed all VHR drills. Attending surgeon total OSATS scores and time to completion were significantly better than the trainees on the first attempt (P < 0.05). When comparing 1st to 4th attempt, resident OSATS scores improved significantly for IHR (15.5 vs 23.3; P < 0.001) and VHR (16.8 vs 23.3; P < 0.001). Time also improved over 4 attempts (IHR: 28.5 vs 20.5 minutes; P < 0.001 and VHR: 29.6 vs 21.2 minutes; P < 0.001). Residents achieved attending-level OSATS scores by their fourth attempt for VHR, but not for IHR. Residents did not achieve attending-level times for either hernia drills. The robotic hernia curriculum improved resident performance on hernia repair drills and was well-received by the residents.

Robot-Assisted Nerve-Sparing Eradication of Deep Endometriosis Using the da Vinci SP

ObjectiveThe evolution of nerve-sparing surgery has been supported by a growing body of literature on anatomic details, dissection techniques, and functional outcomes, suggesting that nerve-sparing surgery for deep endometriosis (DE) reduces postoperative pelvic organ dysfunction, including voiding and rectal dysfunction [1]. Recently, newer single-port robotic systems (da Vinci SP) have become available with articulating instruments and cameras that allow for intracorporeal triangulation, which may overcome some of the weaknesses of conventional single-port laparoscopic surgery [2]. Although such systems are believed to allow more complex surgeries than conventional single-port laparoscopic surgery, the scope of application remains unexplored. The objective of this video is therefore to demonstrate the anatomical and technical highlights of a complex intrapelvic procedure, nerve-sparing modified radical hysterectomy and complete removal of DE using the da Vinci SP (SP). SettingAn urban general hospital. Stepwise demonstration of the technique with narrated video footage. ParticipantsThe patient was a 47-year-old woman who presented with chronic pelvic pain resistant to pharmacotherapy. Magnetic resonance imaging showed uterine adenomyosis and bilateral ovarian endometrioma with DE, involving the uterosacral ligament and surface of the rectum, with complete cul-de-sac obliteration. InterventionsThe surgical steps were completely identical to conventional multiport laparoscopic robotic surgery [3,4]. This suggests that conventional laparoscopic or robotic skills are highly transferrable to SP. SP offer several advantages, including high-resolution three-dimensional visualization, articulating instruments, and improved dexterity and range of motion. These advantages allow us to comfortably perform meticulous dissection and suturing even in difficult situations such as DE. The postoperative course was uneventful, with no perioperative complications, including no postoperative bladder or rectal dysfunction [5]. She was very satisfied with the invisible operative scar and low degree of postoperative pain. ConclusionNerve-sparing eradication of DE using SP is technically safe and feasible, with cosmetic advantages and less pain.

Bridging vision and touch: advancing robotic interaction prediction with self-supervised multimodal learning.

Predicting the consequences of the agent's actions on its environment is a pivotal challenge in robotic learning, which plays a key role in developing higher cognitive skills for intelligent robots. While current methods have predominantly relied on vision and motion data to generate the predicted videos, more comprehensive sensory perception is required for complex physical interactions such as contact-rich manipulation or highly dynamic tasks. In this work, we investigate the interdependence between vision and tactile sensation in the scenario of dynamic robotic interaction. A multi-modal fusion mechanism is introduced to the action-conditioned video prediction model to forecast future scenes, which enriches the single-modality prototype with a compressed latent representation of multiple sensory inputs. Additionally, to accomplish the interactive setting, we built a robotic interaction system that is equipped with both web cameras and vision-based tactile sensors to collect the dataset of vision-tactile sequences and the corresponding robot action data. Finally, through a series of qualitative and quantitative comparative study of different prediction architecture and tasks, we present insightful analysis of the cross-modality influence between vision, tactile and action, revealing the asymmetrical impact that exists between the sensations when contributing to interpreting the environment information. This opens possibilities for more adaptive and efficient robotic control in complex environments, with implications for dexterous manipulation and human-robot interaction.

Fellow perceptions of robotic surgery preparedness for fellowship.

Many surgical fellowship programs incorporate robotic surgery, yet not all residency programs offer robotic training for residents. Given the variability of pre-fellowship robotic exposure, the goal of this study was to explore whether standardized robotic skills assessment would be useful to fellows at the start of their training. In partnership with the Fellowship Council, we surveyed current fellows of accredited Thoracic, Colorectal, HPB, and Advanced GI/MIS/Bariatrics/Foregut Fellowship programs. Main outcome measurements included amount of robotic exposure during residency, fellows' robotic skills at the start of fellowship, and fellows' attitudes towards a standardized skills assessment. In total, 78 fellows completed the survey. Mean percentage of cases performed robotically during fellowship was 38.1% (SD ± 32.25%). From our respondents, 46% had no robotic curriculum during residency and 86.9% felt a standardized robotic curriculum during residency would have been beneficial. When asked if they started fellowship with adequate robotic skills to operate autonomously, 31% strongly agreed, but 24.4% strongly disagreed. The majority of fellows reported their fellowship program did not conduct an assessment of their robotic skills (71.5%), or provide a specific robotic curriculum (75.6%). On the other hand, 73.3% felt a formal proficiency assessment at the start of fellowship would be helpful for individualized support and training. Given the significant variability in resident exposure to robotic surgery, a standardized robotic curriculum during residency would likely be beneficial. Additionally, a robotic skills assessment at the start of fellowship could help provide a tailored training experience for fellows interested in this skillset.

Has robotic surgery finally found robotic surgeons? The confluence of technology and the perfect user

Objective: Our study aims to identify traits of a surgeon that might determine facility with robotic surgery.Methods: Several robotics lab sessions were organised for 129 medical students, where they were introduced to robotics surgery. Their demographic and self-reported data regarding their experience was collected.Results: Our data suggests that traits commonly believed to facilitate robotic surgery skill acquisition, such as technological proficiency and playing musical instruments do not confer an advantage in robotic surgery.Conclusion: One compelling explanation is the ubiquitous familiarity with technology that characterises this generation of surgeons. This ability to easily interface with digital technology to perform tasks is a more significant contributor to facility in robotic surgery than any trait of dexterity. These findings are interesting and inform the need for further investigation into the relationship between technology, the acquisition of dexterity, and ultimately the evolution of how surgeons are trained.