About the Tutorial
An inflection point for surgical robot learning
For the first time, the field has open, cross-embodiment data at scale, attempts at generalist policy architectures that transfer from kitchen-table manipulation to the operating room, and peer-reviewed demonstrations of autonomous soft-tissue surgical steps. Yet the path from a learned policy to a system a surgeon trusts in the OR remains poorly charted.
This tutorial is explicitly instructional. We pair perspective talks from industry, academia, and practicing surgery with a guided hands-on session on the Open-H-Embodiment dataset — so attendees leave able to load the data, run a pretrained policy, and reason about how to improve the current state of the art.
Intended audience: robot-learning researchers, graduate students, and engineers entering surgical robotics, plus practitioners in surgical data science seeking a shared dataset and a current map of open problems. We assume comfort with deep learning and Python, but no surgical background.
Core Questions
Five decisions that gate progress
Each is revisited from the industry, academic, and clinical perspective during the talks, and made real through the hands-on session.
What data should we collect?
Which sensing streams and platforms yield data that actually transfers, and where the largest collection gaps remain.
What data should we annotate?
Where scarce expert-annotation budget is best spent, and how to combine sparse labels with foundation-model pretraining.
Which task should we automate?
Choosing subtasks that are clinically meaningful, technically tractable, and safely evaluable.
Bridging industry, academia & surgery
Surfacing what is lost in translation across the loop, and what each community needs from the others.
Training the next medical roboticist
What a newcomer should learn first, and what infrastructure lowers the barrier to entry.
Invited Speakers
Industry, academia, and clinical practice
Five speakers bring the clinical, academic, and industry perspectives — each framed as instruction: how they actually do this, and what a newcomer should reach for.
Clinical
Filippo Filicori, MD
Clinical reality — what autonomy must solve in the OR. Grounding every challenge in clinical need: what data and which tasks matter, what annotations are meaningful, and what it takes to earn surgeon trust.
Academic
Shan Lin, PhD
How Can Robots Act Like a Surgeon? Perception, Reasoning, and Learning
Industry
Aneeq Zia, PhD
From Data to Deployment: Challenges in Developing Surgical AI. Surgical activity and skill recognition from the seat of a company that deploys models against real surgical video at scale, and how production constraints shape data collection.
Industry
Mostafa Toloui, PhD
The Open-H ecosystem. What is being built across the Open-H ecosystem, and the strategy behind it. Sets the stage for the hands-on session that follows.
Academic
Axel Krieger, PhD
Autonomous Robotic Surgery: From Teleoperation to Learning Systems. How far learned policies can go on real anatomy — anchoring the "which task to automate" and "what data to collect" questions with concrete results.
Program · Thursday, Nov 12, 2026 · Afternoon session
A half-day that never sits still
Five 20-minute talks supply the perspectives; a 60-minute hands-on block lets attendees run the methods themselves in four short Colab notebooks; a closing panel turns the speakers toward each other. Pacing changes every 20–30 minutes.
- 4:00 · Data loading & visualization — Alaa Eldin Abdelaal
- 4:15 · Perception & scene understanding — Sreeram Kamabattula
- 4:30 · Robot learning & evaluation with ACT — Noah Barnes
- 4:45 · Robot learning & evaluation with VLAs — Kiran Bhattacharyya
All times Central Time (CT). The 3:30–4:00 break is the conference-wide afternoon coffee break.
Hands-on Materials
Bring a laptop — everything runs in the browser
The hands-on session is split into four separate Google Colab notebooks, one per segment, because each segment needs different compute. Because each notebook stands on its own, you can join at any segment without having run the earlier ones. Links will be posted here before the tutorial.
Colab notebooks
One notebook for each of the four segments: data loading & visualization, perception & scene understanding, ACT, and VLAs.
Links coming soonTutorial info doc
A Google Doc with setup steps, compute notes, dataset and model links, and other details you'll need on the day.
Link coming soonQuestions & comments doc
A shared Google Doc for your questions and comments. We'll address as many as we can during the tutorial, and follow up on the rest afterward.
Link coming soonOrganizers