My research aims to bring the precision of computer science and applied mathematics to the complexities and uncertainties inherent in real-world robotic systems.
Specifically, I am interested in improving the robots' performance in complex robot-environment interactions,
therefore enabling the robots to better deal with intricate tasks in practical scenarios.
Efficiently and effectively solving kinematics and motion planning problem
for a broad range of articulated robots and complex task constraints
with propagative euclidean distance optimization.
Developing an in-pipe truss robot with redundant joints and linkages
for pipe shape adaptation and actuation force distribution,
providing significant advantages for complex pipeline navigation
and heavy payload delivery.
A multi-task scheme for optical flow and depth estimation
that achieves mutual assistance by means of Flow to Depth mechanism,
Depth to Flow mechanism, and Exponential Moving Average.
An Atrous Convolution Neural Network based deep learning framework
for broadly reactive antibodies against SARS-CoV-2 and VOCs prediction.
Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.