Shuyuan Yang

Shuyuan Yang

M.S. in Computer Science, Case Western Reserve University

Vision-based Force Estimation of Surgical Robot

less than 1 minute read

Published:

In scenarios where access to robot kinematic and camera parameters data is not available, this research devises an alternative approach to estimate a normalized 3D end-effector position from video data based on extracted keypoints from DeepLabCut. The movement of the end-effector is tracked from stereoscopic video of the surgical robot and then deep neural network (DNN) and graph neural network (GNN) are used to estimate the relative depth of the end-effector.

Sample of Dataset

dVRK Data

Keypoints Tracking and Usage in GNN

Keypoints gnn

Cropped and Enhanced Images for Contact Deteaction

cropper

2D Keypoints Coordinates -> 3D Positions of the End-effector

result

You May Also Enjoy

Application of Microblog Data Mining Based on k-means Algorithm

less than 1 minute read

Published:

This project used a web crawler to collect a certain range of data. Natural language processing (NLP) techniques were employed for embedding the raw data, making it fit the k-means clustering algorithm. To enhance the clustering performance, a user feature model was constructed by the principal component analysis (PCA). The project applied the k-means clustering algorithm to categorize user data effectively

Fighting Robot Project in TYUT Robot Team

less than 1 minute read

Published:

This was a 4 kg-class combat robot series competition, where I led a team of five to design and manufacture several wheeled robots. The contest had a set of specifications for robot size and technology, for instance, the robot’s projection size before starting couldn’t exceed 300mm x 300mm, and it was required to autonomously climb onto a 60mm high platform. Most crucially, the competition prohibited remote control of the robots, all movements and behaviors were based on sensors and microprocessors. In the summer of 2018, after overcoming many challenges, we achieved second place (first prize) in this project.