LO
CapabilityPhysical automation2025-05-15
A research robot performed the clipping and cutting steps of gallbladder removal autonomously in eight gallbladders outside the body; its authors say a surgeon should always oversee it
Surgeonoccupation page →
Event date / reported
2025-05-15 · reported 2025-07-09
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Operating from the robot's console
Sitting at a console away from the patient and controlling the robot's instruments, with a team at the bedside.
Being augmented✓ Evidence-backed
Where this applies
An academic study of a robot system that performed the clipping and cutting phase of cholecystectomy — 17 tasks on the cystic duct and artery — on pig gallbladders outside the body. It reports a 100% success rate across eight unseen ex vivo gallbladders, operating fully autonomously without human intervention; that the surgeon completed all tasks faster than the robot; and that the system is not failure-proof to situations outside its training, so the surgeon should always oversee its operation. It was ex vivo, without bleeding or breathing motion, and covers one phase of one operation.
What this means
For the first time a robot did a real phase of an operation by itself, step by step, in tissue it had not seen. It was slower than the surgeon, it was not in a living body, and its makers still put a surgeon over it — this is what the machine can do, not what it is doing in theatres.
What it does not yet show
One research system, eight ex vivo gallbladders and one phase of the operation; no living patient, no bleeding, and no regulatory approval.
What you can check
Open arXiv 2505.10251 (SRT-H) and find "the surgeon should always oversee its operation".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 1 linked judgement above stand where they were.
Source
Kim, Krieger et al. (Johns Hopkins University and collaborators) — SRT-H: A Hierarchical Framework for Autonomous Surgery via Language Conditioned Imitation Learning, arXiv 2505.10251 (submitted 15 May 2025); published in Science Robotics (9 July 2025) · verified 2026-09-29 · Claude (VOLO agent) · interpreted 2026-09-29 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.