Roshan Dhakal

I am a Ph.D. candidate in Computer Science at George Mason University and a member of the Robotic Anticipatory Intelligence & Learning (RAIL) Lab, advised by Dr. Greg Stein. My research sits at the intersection of robotics, machine learning, and task and motion planning, with a focus on anticipatory decision-making for household and service robots.

More broadly, my research focuses on enabling robots to reason about the consequences of their actions and guiding them toward forward-thinking behaviors such as organization, tidiness, and preparation. This opens exciting opportunities to develop robots capable of serving as long-term assistive companions.

Portrait of Roshan Dhakal
Fairfax, Virginia · George Mason University
rdhakal2@gmu.edu · dhakalrosan@gmail.com

Research Overview

My work focuses on enabling long-lived autonomy for robots and embodied AI operating in persistent, real-world environments. I study how intelligent agents can anticipate the impact of their actions and make better decisions in the present that would otherwise be difficult to achieve. My research spans anticipatory task and motion planning, learning-augmented planning, and lifelong robot autonomy. Most recently, I have developed methods that integrate anticipatory decision-making estimates into classical planning systems, guiding search toward world states that improve efficiency, robustness, and performance across sequences of future tasks.

Background

  • Ph.D. Candidate, Computer Science, George Mason University
  • M.S. in Computer Science, George Mason University, 2021
  • B.E. in Computer Engineering, Tribhuvan University, Nepal
  • Research areas: robotics, planning, learning for decision-making, long-horizon autonomy

News

Selected recent updates.

  • November 2025 Awarded the Dissertation Completion Grant from the Provost’s Office at George Mason University.
  • October 2025 Our paper on Anticipatory Task and Motion Planning was accepted to IEEE Robotics and Automation Letters (RA-L).
  • May 2025 Awarded the Provost Scholarship at George Mason University.
  • November 2024 Recognized as an Outstanding Reviewer at CoRL LEAP 2024.
  • June 2024 Successfully defended my Ph.D. proposal and advanced to candidacy.
  • May 2023 Presented our work on Anticipatory Planning at ICRA 2023.
  • January 2023 Our paper on Anticipatory Planning was accepted to ICRA 2023.
  • May 2021 Successfully completed and defended my Ph.D. comprehensive exam.

Selected Publications

Recent work in anticipatory planning, task and motion planning, and graph learning.

Projects

Selected technical projects beyond published papers.

Fast Downward planner integration

Integrating Learned Cost Estimators into Fast Downward with C++, PyBind, and PyTorch

I built a system that injects learned anticipatory cost models into the Fast Downward planning stack, allowing neural cost estimation to be composed with standard symbolic heuristics such as FF, max, and goal-count.

Navigation among movable obstacles demonstration

Navigation Among Movable Obstacles with PDDLStream

In a 2D navigation setting, I formulated the domain in PDDL and used PDDLStream to plan obstacle relocations that open a feasible path to the goal.

Lunar Lander reinforcement learning comparison

Reinforcement Learning Comparison on Lunar Lander

I compared Proximal Policy Optimization (PPO) and Deep Q-Networks (DQN) on the Lunar Lander benchmark to study differences in learning stability, sample efficiency, and control performance.