Ridwan Talukder

PhD Student & Graduate Research Assistant — Robotics, Machine Learning, and Planning under Uncertainty

Hi, I am Md. Ridwan Hossain Talukder, and I go by Ridwan professionally. I am a PhD Student and Graduate Research Assistant in the Robotic Anticipatory Intelligence and Learning (RAIL) Group at George Mason University, advised by Prof. Gregory Stein.

My research focuses on anticipatory task and motion planning for long-lived service robots operating in large-scale home environments. I develop learning-augmented planning methods that enable robots to reason about future tasks, proactively prepare their environment, and execute long-horizon behaviors efficiently under uncertainty.

Prior to my PhD, I worked as a Software Engineer and Founder in the tech industry. I hold an MS in Computer Science from GMU (2024) and a BSc in Computer Engineering from the University of Dhaka.

  mtalukd@gmu.edu

Ridwan Profile Picture

News

Selected Publications

Anticipatory planning for performant long-lived robot in large-scale home-like environments
Md Ridwan Hossain Talukder, Raihan Islam Arnob, Gregory J Stein
This research presents a model-based anticipatory task planning framework designed for large-scale environments like homes and restaurants. By integrating Graph Neural Networks and 3D Scene Graphs to estimate future costs, the system significantly improves long-term efficiency by allowing robots to prepare for subsequent tasks.
International Conference on Robotics and Automation (ICRA), 2025
PDF ABS BIB
Anticipatory planning: Improving long-lived planning by estimating expected cost of future tasks
Roshan Dhakal, Md Ridwan Hossain Talukder, Gregory J Stein
This paper introduces an anticipatory planning method that leverages Graph Neural Networks to predict the long-term impact of a robot's current actions on future tasks. Tested in a blockworld setting, the approach promotes organizational behaviors that reduce overall execution costs compared to traditional, myopic planning.
International Conference on Robotics and Automation (ICRA), 2023
PDF ABS BIB

Experience