Related Experiment Video
Updated: Jun 27, 2026
05:12
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
Published on: August 12, 2021
Neural Minimum-Distance Estimation for Collision-Aware Operation of Multi-Arm Laparoscopy Surgical Robots Through
Sarvin Ghiasi1, Majid Roshanfar2, Jake Barralet1
1Surgical Performance Enhancement and Robotics (SuPER) Centre, Department of Surgery, McGill University, Montreal, QC H4A 3J1, Canada.
Sensors (Basel, Switzerland)
|June 26, 2026
Summary
This study introduces a framework for robotic surgery safety, using machine learning to predict collisions between surgical robotic arms. It enhances operational efficiency and patient safety by providing early collision warnings during procedures.
Area of Science:
- Robotics
- Surgical Technology
- Machine Learning
Background:
- Minimizing collisions between multiple robotic arms is critical for safe laparoscopic surgery.
- Existing methods may lack real-time predictive capabilities for complex multi-arm interactions.
Purpose of the Study:
- To develop an integrated framework for estimating minimum distances between robotic arms.
- To implement a collision-aware warning system for enhanced surgical safety and operational efficiency.
Main Methods:
- Developed an analytical model for theoretical minimum distance calculation.
- Created a 3D simulation environment with two 7 DOF Kinova robotic arms to generate data.
- Trained a deep residual neural network using joint configurations for predictive modeling.
Main Results:
- The deep residual neural network achieved high accuracy (R2=0.940, RMSE =42.0 mm, MAE =28.7 mm).
- The framework provides an early warning when predicted inter-arm distance falls below a 0.2 m threshold.
- Demonstrated strong generalization across the robotic workspace.
Conclusions:
- Combining analytical modeling and machine learning effectively enhances robotic arm safety.
- The proposed framework improves precision and reliability in multi-arm robotic systems for surgery.
- This approach offers a robust solution for ensuring safe robotic operations in clinical settings.
