We strive to provide automated solutions to improve the ease of work and life
for humans through the development of novel methods that solve real world problems.
We are interested in developing algorithmic solutions for problems in areas such as computational biology (e.g., protein folding and drug design) and motion planning (e.g., animation and robotics). Our recent work has explored robotic interaction, multi-robot systems, leveraging workspace topology, and protein-drug interaction.
Our work provides new sampling strategies to handle more challenging narrow passage problems. We have also studied now to combine existing samplers by biasing them to improve performance.
Motion planning in dynamic environments is an important topic when it comes to real-world applications. Those applications usually involve avoiding dynamic obstacles like humans or other robots while developing efficient plans to accomplish navigation, map covering, or manipulation tasks.
In this project, we are developing parallel algorithms for motion planning applications. We are particularly interested in parallelizing probabilistic roadmap motion planning methods (PRMs).