Roshan Dhakal

I'm a Ph.D. candidate researching at the intersection of Robotics and Machine Learning in Robotic Anticipatory Intelligence & Learning (RAIL) Lab advised by Dr. Greg Stein at George Mason University (GMU), Fairfax, VA. I received my Masters degree in Computer Science from GMU in 2021. I completed Bachelors degree in Computer Engineering from Tribhuvan University, Nepal.

Feel free to contact me at dhakalrosan@gmail.com.

Email  /  Resume  /  Scholar  /  Github

profile photo

News

  • (June 2024) I passed my Ph.D. proposal defense and advanced to candidacy.
  • (August 2023) I continued as Graduate Teaching Assistant for graduate level Data Mining Course at GMU (CS 584).
  • (May 2023) I presented Anticipatory Planning paper in ICRA 2023, London, UK.
  • (January 2023) Our paper on Anticipatory Planning got accepted at ICRA 2023.
  • (May 2021) Earned M.S. in Computer Science (Machine Learning concentration) from George Mason University.
  • (May 2021) Successfully defended my Ph.D. comprehensive exam.

Research

I envision a future where household and service robots will coexist with humans, undertaking complex tasks. The focus of my research is to improve robot's performance in a long lived task and motion planning setting. Particularly, I am interested in enabling a robot to anticipate impact of its actions on the environment it lives in and acts intelligently.

My research intersects robotics and machine learning focusing on task and motion planning, learning augmented planning and lifelong robot planning. Below are some of my works.

anttamp Anticipatory Task and Motion Planning.
Roshan Dhakal, Duc M. Nguyen, Tom Silver, Xuesu Xiao, Gregory J. Stein
arxiv, 2024
bibtex

We use learning to augment integrated task and motion planning, allowing a long-lived robot to avoid side effects of its actions that may hinder future tasks.

ant-task-plan Anticipatory Planning: Improving Long-Lived Planning by Estimating Expected Cost of Future Tasks.
Roshan Dhakal, Md Ridwan Hossain Talukder, Gregory J. Stein
ICRA, 2023
video / bibtex

We propose anticipatory task planning to enable a robot consider unseen future tasks while solving a given task.

gnn-room-classif Room Classification on Floor Plan Graphs using Graph Neural Networks.
Abhishek Paudel, Roshan Dhakal, Sakshat Bhattari
arxiv, 2021
bibtex / code

We present our approach to improve room classification task on floor plan maps of buildings by representing floor plans as undirected graphs and leveraging graph neural networks to predict the room categories.


Stole website template from Jon Barron source code.