Joe H. Doerr
PhD Student · Rutgers University, New Brunswick · jhd79@scarletmail.rutgers.edu
I am a PhD student in Computer Science at Rutgers, advised by Professor Kostas Bekris. I am interested in solving difficult robot manipulation problems for practical deployment. I am invested in the direction of robot learning to address these problems, specifically reinforcement learning as it is a compelling path toward scalable robot behavior generation.
Research projects
-
Sequencing Diversified Policy Variants For Targeted Object Retrieval From Cluttered Shelves
Joe H. Doerr, (other authors order TBD), Kostas E. Bekris
-
Robot Motion Generation: Explicit to Implicit Models and Methods
Joe H. Doerr*, Patrick Meng*, Sumanth Tangirala*, Kostas E. Bekris
-
Integrating Model-based Control and RL for Zero-shot Transfer of Tight Insertion Policies
Isidoros Marougkas*, Dhruv Metha Ramesh*, Joe H. Doerr, Edgar Granados, Aravind Sivaramakrishnan, Abdeslam Boularias, and Kostas E. Bekris
-
The State of Robot Motion Generation
Kostas E. Bekris, Joe H. Doerr, Patrick Meng, Sumanth Tangirala
-
Multiplane light conversion design with physical neural network
Zheyuan Zhu, Joe H. Doerr, Guifang Li, Shuo Pang