Evidence map›Paper›PMID 40632876›Full record

ArticleScience robotics2025

SRT-H: A hierarchical framework for autonomous surgery via language-conditioned imitation learning.

Ji Woong Brian Kim, Juo-Tung Chen, Pascal Hansen, Lucy Xiaoyang Shi, Antony Goldenberg, Samuel Schmidgall, Paul Maria Scheikl, Anton Deguet, Brandon M White, De Ru Tsai and 4 more

Abstract read
PubMed Publisher
In one paragraph

Article in Science robotics, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 42 papers, 2 of them syntheses that pooled it.

0numbers the graph read from it
0cells of the map it votes in
42citing papers in PubMed, 2 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

42 citing papers in PubMed, 2 syntheses or guidelines pooled it.

  1. [Artificial intelligence in urological surgery].Urologie (Heidelberg, Germany) · 2026
    Pooled it
  2. Pooled it
  3. An Expertise Transfer Framework For Autonomous Surgical Assistance.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026
    Article
  4. Review
  5. Technology Review: The Hidden Influence of AI in Orthopaedic Surgery.Journal of the American Academy of Orthopaedic Surgeons. Global research & reviews · 2026
    Review
  6. Review
  7. Review
  8. [Current applications and prospects of artificial intelligence in burn diagnosis and treatment].Zhongguo xiu fu chong jian wai ke za zhi = Zhongguo xiufu chongjian waike zazhi = Chinese journal of reparative and reconstructive surgery · 2026
    Review
  9. Review
  10. Article
  11. Spartan: surgical peg-and-ring triplet and workflow anticipation benchmark.International journal of computer assisted radiology and surgery · 2026
    Article
  12. Article
  13. Investigating robot control policy learning for autonomous x-ray-guided spine procedures.International journal of computer assisted radiology and surgery · 2026
    Article
  14. Review
  15. Review
  16. Article
  17. Review
  18. Review
  19. Review
  20. Review
4 · The record

Corrections and comments

5 · Who and what money

Authors and funding

14 authors.

Ji Woong Brian KimLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0000-0001-8669-205X
Juo-Tung ChenLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0009-0002-5118-6610
Pascal HansenLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0009-0002-4833-4184
Lucy Xiaoyang ShiDepartment of Computer Science, Stanford University, Stanford, CA 94305, USA.ORCID 0009-0007-9323-9844
Antony GoldenbergLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0009-0008-7744-401X
Samuel SchmidgallLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0000-0001-8192-9337
Paul Maria ScheiklLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0000-0002-8079-1425
Anton DeguetLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0000-0003-3856-2095
Brandon M WhiteDepartment of Surgery, Johns Hopkins University, Baltimore, MD 21218, USA.
De Ru TsaiOptosurgical, Columbia, MD 21046, USA.
Richard Jaepyeong ChaOptosurgical, Columbia, MD 21046, USA.ORCID 0000-0003-2169-1464
Jeffrey JoplingDepartment of Surgery, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0000-0002-0694-1704
Chelsea FinnDepartment of Computer Science, Stanford University, Stanford, CA 94305, USA.
Axel KriegerLaboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA.ORCID 0000-0001-8169-075X

Funding

Next Generation Robotic System for Supervised-Autonomous Bowel AnastomosisR56EB033807 · NIBIB · JOHNS HOPKINS UNIVERSITY · PI HSIEH, MICHAEL HARRISON, KANG, JIN U · 2023 to 2023
$748k
NIBIB NIH HHS R56 EB033807
6 · The paper itself

Abstract

Research on autonomous surgery has largely focused on simple task automation in controlled environments. However, real-world surgical applications demand dexterous manipulation over extended durations and robust generalization to the inherent variability of human tissue. These challenges remain difficult to address using existing logic-based or conventional end-to-end learning strategies. To address this gap, we propose a hierarchical framework for performing dexterous, long-horizon surgical steps. Our approach uses a high-level policy for task planning and a low-level policy for generating low-level trajectories. The high-level planner plans in language space, generating task-level or corrective instructions that guide the robot through the long-horizon steps and help recover from errors made by the low-level policy. We validated our framework through ex vivo experiments on cholecystectomy, a commonly practiced minimally invasive procedure, and conducted ablation studies to evaluate key components of the system. Our method achieves a 100% success rate across eight different ex vivo gallbladders, operating fully autonomously without human intervention. The hierarchical approach improved the policy's ability to recover from suboptimal states that are inevitable in the highly dynamic environment of realistic surgical applications. This work demonstrates step-level autonomy in a surgical procedure, marking a milestone toward clinical deployment of autonomous surgical systems.

Indexed as

LanguageRobotic Surgical ProceduresSurgery, Computer-AssistedAlgorithmsHumansLearningTask Performance and Analysis

Identifiers

PMID40632876

What OpenQuestion holds

Textmetadata
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.