Rui Wang

I am a robotics engineer at Diligent Robotics, revolutionizing intelligent robotics system to facilitate medical staff in hospitals.
I obtained my Ph.D. from Rutgers University. I was fortunate to be advised by Prof. Kostas Bekris . My research interests lie in the field of robot planning, vision-based manipulation, as well as multi-robot system.
Prior to my Ph.D., I earned my Master Degree in Mechanical Engineering from Columbia University in the city of New York, where I worked with Peter Allen on several robot car navigation tasks. I earned my Bachelor Degree in Vehicle Engineering from Nanjing University of Aeronautics and Astronautics, Nanjing, China.
In addition to research, I have also actively participated in outreach activities related to AI and robotics. I had been the course instructor for Introduction to Artificial Intelligence for two consecutive summers. I had also contributed a book chapter covering how robotics can strengthen resiliency to disasters such as Covid-19 pandemic.

Email  /  CV  /  Google Scholar  /  GitHub  /  LinkedIn  / 

This work formulates the general, occlusion-aware manipulation task without access to object models, and focuses on safe object reconstruction in a confined space with in-place relocation.

This work proposes a lazy evaluation framework for solving object rearrangement in confined spaces, which effectively reduces the number of computationally expensive motion planning and collision checking calls to achieve significant improvement on efficiency and scalability.

This work proposes an efficient constraint informed monotone solver, a high-quality global task planner as well as an effective pre-processing labeled roadmap to significantly improve the solutions for object rearrangement in cluttered and confined spaces such as shelves.

This work proposes a robotic system for picking and constrained placement of novel objects, which keeps learning object features and updates their reconstructed models to enhance manipulation efficiency.

This work explores the use of topological tools - persistent Homology for achieving effective non-prehensile manipulation in cluttered and constrained workspaces.

This work discusses the roles robotics can play towards providing resiliency to disasters in terms of pre-emptive measures and post-disaster responses.

This work introduces a framemwork with a compact region graph, an efficient monotone solver and an effective informed search structure to solve uniform object rearrangement problems.

This work proposes a perception and a motion planning pipeline which computes safe picking paths under object uncertainty which achieve minimum collision probability and maximum success likelihood.