Imitation learning (IL) has shown immense promise in enabling autonomous dexterous manipulations, including in learning surgical tasks. To fully unlock the potential of IL for surgery, access to clinical datasets is needed, which unfortunately lack the kinematic data required for current IL approaches. A promising source of large-scale surgical demonstrations is monocular surgical videos available online, making monocular pose estimation a crucial step toward enabling large-scale robot learning. Towards this end, we propose SurgiPose, a differentiable rendering-based approach to estimate kinematic information from monocular surgical videos, eliminating the need for direct access to ground-truth kinematics. Our method infers tool trajectories and joint angles by optimizing tool pose parameters to minimize the discrepancy between rendered and real images. To evaluate the effectiveness of our approach, we conduct experiments on two robotic surgical tasks—tissue lifting and needle pickup—using the da Vinci Research Kit Si (dVRK Si). We train imitation learning policies with both ground-truth measured kinematics and with estimated kinematics from video and compare their performance. Our results show that policies trained on estimated kinematics achieve comparable success rates to those trained on ground-truth data, demonstrating the feasibility of using monocular video-based kinematic estimation for surgical robot learning. By enabling kinematic estimation from monocular surgical videos, our work lays the foundation for large-scale learning of autonomous surgical policies from online surgical data.

Robotic suturing is a prototypical long-horizon dexterous manipulation task, requiring coordinated needle grasping, precise tissue penetration, and secure knot tying. Despite numerous efforts toward end-to-end autonomy, a fully autonomous suturing pipeline has yet to be demonstrated on physical hardware. We introduce SutureBot: an autonomous suturing benchmark on the da Vinci Research Kit (dVRK), spanning needle pickup, tissue insertion, and knot tying. To ensure repeatability, we release a high-fidelity dataset comprising 1,890 suturing demonstrations. Furthermore, we propose a goal-conditioned framework that explicitly optimizes insertion-point precision, improving targeting accuracy by 59\%-74\% over a task-only baseline. To establish this task as a benchmark for dexterous imitation learning, we evaluate state-of-the-art vision-language-action (VLA) models, including $\pi_0$, GR00T N1, OpenVLA-OFT, and multitask ACT, each augmented with a high-level task-prediction policy. Autonomous suturing is a key milestone toward achieving robotic autonomy in surgery. These contributions support reproducible evaluation and development of precision-focused, long-horizon dexterous manipulation policies necessary for end-to-end suturing. Dataset is available at: \href{https://huggingface.co/datasets/jchen396/suturebot}{Hugging Face}

Large Language Models (LLMs) have the potential to catalyze a paradigm shift in end-user robot programming---moving from the conventional process of user specifying programming logic to an iterative, collaborative process in which the user specifies desired program outcomes while LLM produces detailed specifications. We introduce a novel integrated development system, Alchemist, that leverages LLMs to empower end-users in creating, testing, and running robot programs using natural language inputs, aiming to reduce the required knowledge for developing robot applications. We present a detailed examination of our system design and provide an exploratory study involving true end-users to assess capabilities, usability, and limitations of our system. Through the design, development, and evaluation of our system, we derive a set of lessons learned from the use of LLMs in robot programming. We discuss how LLMs may be the next frontier for democratizing end-user development of robot applications.

In this paper, we present a targeted training approach for remote teleoperation aimed at achieving consistent proficiency levels across users with varying capabilities. Our approach begins by assessing users’ abilities to perform robot motion control, workspace adaptation, and gripper control. It then provides tailored training based on identified skill gaps to enhance the learning effectiveness and user experience. To demonstrate our approach, we conducted a user study, with one group undergoing conventional, free-form training and the other engaging in targeted training in accordance with their skill gaps; after the training phase, participants teleoperated a robotic arm in a simulated medication preparation task for performance evaluation. Our results show that the targeted training approach effectively reduces performance variability and mitigates the influence of spatial ability on both training and task completion time. We discuss the implications of our results for practical teleoperation training and future research.