Related Experiment Video
Updated: Jan 9, 2026
11:28
Robotic-Guided Stereoelectroencephalography for Invasive Epilepsy Monitoring
Published on: June 13, 2025
1.2K
Tremor estimation and filtering in robotic-assisted surgery.
Boqiang Jia1,2, Wenjie Wang1,2, Xin Tian1,2
1Xian Polytechnic University Branch of Shaanxi Artificial Intelligence Joint Laboratory, Xi'an Polytechnic University, Shaangu Avenue, Xi'an, 710600 Shaanxi China.
Cognitive Neurodynamics
|December 9, 2025
Summary
This study introduces a deep learning method to predict and suppress surgical hand tremors by integrating long-term and short-term signal features. The novel approach significantly reduces tremor estimation errors, enhancing surgical robot accuracy.
Area of Science:
- Robotics
- Biomedical Engineering
- Artificial Intelligence
Background:
- Spontaneous hand tremors in surgeons can compromise the accuracy of surgical robots.
- Accurate measurement and modeling of tremor signals are crucial for effective suppression.
Purpose of the Study:
- To propose a deep learning-based prediction method for surgical hand tremor suppression.
- To integrate long-term and short-term tremor signal features for improved estimation.
Main Methods:
- Utilized a bidirectional Long-short-term memory network for long-term feature extraction.
- Employed a Temporal Convolutional Network for short-term feature extraction.
- Integrated features, optimized time step-size with a genetic algorithm, and used an end data compensation strategy.
Main Results:
- The proposed deep learning model demonstrated superior performance compared to existing methods.
- Significantly reduced tremor signal estimation error.
- Suture experiments in a virtual surgical environment validated the method's effectiveness.
Conclusions:
- The integrated deep learning approach effectively estimates and compensates for surgical hand tremors.
- The method enhances surgical robot accuracy by suppressing hand tremors.
- This provides a promising solution for improving precision in robotic surgery.
