AI search, physician removal: Bronchoscopy robot bridges collaboration in foreign body aspiration.

Journal: Science robotics
Published Date: Jul 30, 2025

Abstract

Bronchial foreign body aspiration is a life-threatening condition with a high incidence across diverse populations, requiring urgent diagnosis and treatment. However, the limited availability of skilled practitioners and advanced medical equipment in community clinics and underdeveloped regions underscores the broader challenges in emergency care. Here, we present a cost-effective robotic bronchoscope capable of computed tomography (CT)-free, artificial intelligence (AI)-driven foreign body search and doctor-collaborated removal over long distances via fifth-generation (5G) communication. The system is built around a low-cost (<5000 USD), portable (<2 kilograms) bronchoscope robotic platform equipped with a 3.3-millimeter-diameter catheter and 1-millimeter biopsy forceps designed for safe pulmonary search and foreign body removal. Our AI algorithm, which integrates classical data structures with modern machine learning techniques, enables thorough CT-free lung coverage. The tree structure is leveraged to memorize a compact exploration process and guide the decision-making. Both virtual and physical simulations demonstrate the system's effective autonomous foreign body search, minimizing bronchial wall contact to reduce patient discomfort. In a remote procedure, a physician in Hangzhou successfully retrieved a foreign body from a live pig located 1500 kilometers away in Chengdu using 5G communication, highlighting effective collaboration of AI, robotics, and human experts. We anticipate that this 5G-enabled, low-cost, AI expert-collaborated robotic platform has notable potential to reduce medical disparities, enhance emergency care, improve patient outcomes, decrease physician workload, and streamline medical procedures through the automation of routine tasks.

Authors

  • Lilu Liu
    State Key Laboratory of Industrial Control and Technology, Zhejiang University, 310027, Hangzhou, China.
  • Jingyu Zhang
    Hangzhou Institute of Innovative Medicine, Institute of Drug Discovery and Design, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, 310058, PR China.
  • Fei Wang
    Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, United States.
  • Jiyu Yu
    Department of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China.
  • Yuxiang Cui
    Zhejiang Humanoid Robot Innovation Center, Ningbo 315000, China.
  • Zhibin Li
    Epidemiology Research Unit, The First Affiliated Hospital of Xiamen University, Xiamen, China, zhibinli33@163.com.
  • Jian Hu
    Department of Chemistry, Michigan State University, MI, 48824, USA.
  • Rong Xiong
    State Key Laboratory of Industrial Control and Technology, Zhejiang University, 310027, Hangzhou, China. rxiong@zju.edu.cn.
  • Haojian Lu
    State Key Laboratory of Industrial Control and Technology, Zhejiang University, 310027, Hangzhou, China. luhaojian@zju.edu.cn.
  • Yue Wang
    Department of Pharmacology, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States.

Keywords

External Resources

Popular Topics
Recent Journals