cs.ROMar 3, 2026

Give me scissors: Collision-Free Dual-Arm Surgical Assistive Robot for Instrument Delivery

Authors: Xuejin Luo, Shiquan Sun, Runshi Zhang, Ruizhi Zhang, Junchen Wang

Organizations: School of Mechanical Engineering and Automation, Beihang University, Beijing, China

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

During surgery, scrub nurses are required to frequently deliver surgical instruments to surgeons, which can lead to physical fatigue and decreased focus. Robotic scrub nurses provide a promising solution that can replace repetitive tasks and enhance efficiency. Existing research on robotic scrub nurses relies on predefined paths for instrument delivery, which limits their generalizability and poses safety risks in dynamic environments. To address these challenges, we present a collision-free dual-arm surgical assistive robot capable of performing instrument delivery. A vision-language model is utilized to automatically generate the robot's grasping and delivery trajectories in a zero-shot manner based on surgeons' instructions. A real-time obstacle minimum distance perception method is proposed and integrated into a unified quadratic programming framework. This framework ensures reactive obstacle avoidance and self-collision prevention during the dual-arm robot's autonomous movement in dynamic environments. Extensive experimental validations demonstrate that the proposed robotic system achieves an 83.33% success rate in surgical instrument delivery while maintaining smooth, collision-free movement throughout all trials. The project page and source code are available at https://give-me-scissors.github.io/.

Figures & tables

Fig. 1: Surgical instruments transfer process. (a) Scrub nurse instrument delivery. (b) Robot-assisted instrument delivery.
Fig. 2: The pipeline of the collision-free dual-arm surgical assistive robot for instrument delivery. The robot system receives multi-modal inputs from the physical world (i.e., surgeon instruction, color image, depth data). The real-time obstacle perception module computes the minimum distance between robot and environmental obstacles. The QP framework is built upon the minimum distance, ensuring the dual-arm robot’s collision-free operation. The high-level task planning utilizes VLM to generate the desired motion objectives for the QP framework.
Fig. 3: Real-time obstacle perception process. The robot joint configuration and point cloud of obstacles are taken as input. Output is the minimum distance between robot and obstacle.
Fig. 4: Obstacle and self-collision avoidance process of the dual-arm robot in simulation. The red arrows indicate the avoidance directions for dual-arm robot. (a) Self-collision avoidance. (b) Obstacle avoidance.
Fig. 5: The trajectories of dual-arm robot’s end-effector and obstacles during simulation. The avoidance motion is achieved by our method.
MethodObsSelfOpt Cost Time (s)Mean Pos Error (m)Max Accel ( m/s2m/s^{2} )
DawnIK [ 28 ]✘✔0.0340.11631.94
CollisionIK [ 29 ]✔✔0.0380.13632.10
CBF-QP [ 30 ]✔✔0.0350.05539.47
Ours✔✔0.0220.05417.77
’Obs’ represents the obstacle avoidance. ’Self’ indicates the self-collision avoidance.
TABLE I: Comparison results between the competing methods and our method
Fig. 6: Minimum self-distance between dual arms and minimum distance between right arm and obstacle. The shadow region represents the portion where the minimum distance falls below the safety distance threshold.
Fig. 7: Dual-arm robot avoids obstacle and self-collision during motion. Yellow and blue ellipses represent the desired trajectories of dual-arm robot end-effector. Red/blue arrow denotes the motion direction of the left/right arm.
Fig. 8: The results of the collision avoidance real-world experiment. (a) Histogram of optimization cost time. (b) Right arm end-effector’s acceleration. (c) Left arm end-effector’s acceleration.
Fig. 9: The experimental process of robot-assisted surgical instrument delivery. The dual-arm robot grasped different surgical instruments in accordance with the surgeon’s instructions. The surgical instruments were then transferred to the surgeon’s hand in sequence. The entire process was conducted within the proposed QP framework to prevent collisions.
Fig. 10: The keypoints in the experimental process. They represent the 3D positions of the corresponding objects. The arrows indicate the sub-goals of the robot.
TypeCollisionDetectGraspDeliverySuccess Rate
Scalpel015/1513/1513/1386.67%
Tweezer015/1515/1515/15100.0%
Scissors014/1512/1412/1280.00%
Hemostat014/1511/1410/1166.67%
TABLE II: Results of Instrument Delivery Experiment
More in this topic

Healthcare Robotics

See all 24 papers

Explore similar work

CardsList

  1. RoboAssist: Interactive Human-Humanoid Planning for Long-Horizon Surgical Assistance

    Sep 30, 2026Jingwei Jia, Keyu Zhou, Jiewei Wang +7Robot SafetyHuman-Robot Collaboration

    Hangzhou Dianzi University, China. · Zhejiang University, China. · New York University, USA. +1

  2. AGRO-SUVIDE: Agentic Robotics for Surgical Viscoelastic Debridement

    Sep 28, 2026Shutong Jin, Ziyang Chen, Preethi Satish +4Robot Skill LearningAgentic AI for Robotics

    Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA. · Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, SE 10044, Sweden. · Intuitive Surgical, Sunnyvale, CA 94086, USA.

  3. An Open-Source Robotics Research Platform for Autonomous Laparoscopic Surgery

    Mar 9, 2026Ariel Rodriguez, Lorenzo Mazza, Martin Lelis +4Laparoscopic SurgerySurgical Robotics

    Department of Translational Surgical Oncology, NCT/UCC Dresden, a partnership between DKFZ, MF UKD, TUD, HZDR Dresden, Germany · Cluster of Excellence-CeTI, TUD, Germany · Department of Visceral, Thoracic and Vascular Surgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD, Germany