Soft Robotic Gloves, Exosuits & Rehabilitation
Wearable robots have the potential to restore lost function and enhance human capabilities. My research focuses on creating seamless interfaces between the human body and robotic systems.
I work on Soft Wearable Gloves for rehabilitation and assistance, using deep learning to estimate fingertip forces on deformable objects. Additionally, I am developing vision-based intention detection systems that allow users to control these devices intuitively.
Proposed a deep-learning model that can accurately estimate the fingertip forces applied to deformable objects using motor encoder values, motor current, and wire tension. Our model estimates stiffness of the grasped objects and incorporates it for predicting the fingertip forces, achieving a 45% increase in accuracy.
Proposed a hand rehabilitation system comprising a vision-based intention detection framework and an 8-degree-of-freedom soft-robotic glove. The framework analyzes images and depth data to predict intentions for multiple hand postures, helping stroke survivors actively train.
Research on point cloud-based grasping strategies for soft hand exoskeletons.