Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Open-source High-precision Autonomous Suturing Framework With Visual Guidance

Hongbin Lin, Bin Li, Yunhui Liu, Kwok Wai Samuel Au

TL;DR

Open-source, image-guided framework for high-precision autonomous suturing evaluated in the AccelNet Surgical Robotics Challenge. The approach combines an algebraic-geometry needle pose estimator with a monocular-camera joint calibration model, integrated with trajectory planning, analytical IK, a high-level PI controller, and a calibration compensator. The method achieves state-of-the-art performance on the challenge and provides reproducible software for benchmarking autonomous suturing research. This work enhances autonomous suturing by enabling precise, occlusion-robust needle handling and compensating joint biases in real-time, with broad implications for robot-assisted surgery.

Abstract

Autonomous surgery has attracted increasing attention for revolutionizing robotic patient care, yet remains a distant and challenging goal. In this paper, we propose an image-based framework for high-precision autonomous suturing operation. We first build an algebraic geometric algorithm to achieve accurate needle pose estimation, then design the corresponding keypoint-based calibration network for joint-offset compensation, and further plan and control suture trajectory. Our solution ranked first among all competitors in the AccelNet Surgical Robotics Challenge. Videos and codes can be found in https://sites.google.com/view/accel-2022-cuhk.

Open-source High-precision Autonomous Suturing Framework With Visual Guidance

TL;DR

Open-source, image-guided framework for high-precision autonomous suturing evaluated in the AccelNet Surgical Robotics Challenge. The approach combines an algebraic-geometry needle pose estimator with a monocular-camera joint calibration model, integrated with trajectory planning, analytical IK, a high-level PI controller, and a calibration compensator. The method achieves state-of-the-art performance on the challenge and provides reproducible software for benchmarking autonomous suturing research. This work enhances autonomous suturing by enabling precise, occlusion-robust needle handling and compensating joint biases in real-time, with broad implications for robot-assisted surgery.

Abstract

Autonomous surgery has attracted increasing attention for revolutionizing robotic patient care, yet remains a distant and challenging goal. In this paper, we propose an image-based framework for high-precision autonomous suturing operation. We first build an algebraic geometric algorithm to achieve accurate needle pose estimation, then design the corresponding keypoint-based calibration network for joint-offset compensation, and further plan and control suture trajectory. Our solution ranked first among all competitors in the AccelNet Surgical Robotics Challenge. Videos and codes can be found in https://sites.google.com/view/accel-2022-cuhk.
Paper Structure (11 sections, 4 equations, 1 figure)

This paper contains 11 sections, 4 equations, 1 figure.

Table of Contents

  1. Introduction
  2. Method and Result
  3. Visual Perception
  4. Needle Tracking
  5. Joint Calibration with Monocular Camera
  6. Robot Control
  7. Trajectory Planning
  8. IK
  9. PI Controller
  10. Calibration Compensator
  11. Conclusion

Figures (1)

  • Figure 1: (a) Our proposed framework for autonomous suturing in AccelNet Challenge, (b) disentangled needle physical projection model, and (c) trajectory design for needle insertion and extraction.