Zubair Irshad
PhD Candidate at Georgia Tech Researcher at Institute of Robotics & Intelligent Machines, Georgia Tech


I am a PhD Candidate at Georgia Institute of Technology. I’m working with Dr. Zsolt Kira at the Institute of Robotics & Intelligent Machines. My current research focuses on Visual Embodied Navigation, 3D perception, Semantic & Spatial Reasoning and Imitation Learning. My other interests include autonomous driving, perception & control for robots.

This spring, I am an incoming research intern at Toyota Research Institute (ML-R). In the past, I have been fortunate to spend time at Toyota Research Institute (Robotics) as a Research Intern. I worked on 3D perception, scene understanding and generalized behaviors for robotics manipulation with Thomas Kollar and Michael Laskey. The summer before, I Interned at SRI International in the Vision and Learning Lab on multi-modal semantic and spatial reasoning for embodied agents.

I was fortunate enough to be awarded a Fulbright Scholarship & ASME Rice Cullimore Scholarship for my Masters’ at Georgia Tech. These awards allowed me to find my passion in Robotics & Machine Learning and develop a great network of fellow Fulbrighters around the world. Feel free to contact me to talk anything related to Robotics, Deep Learning, Finance or related to some of my projects. Below you will find my projects portfolio. You can find my resume here


  • PhD, Mechanical Engineering & Robotics, 2023 (Expected)
    Georgia Institute of Technology
  • M.S, Mechanical Engineering & Robotics, 2019
    Georgia Institute of Technology



Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation

Muhammad Zubair Irshad, Chih-Yao Ma, Zsolt Kira

IEEE International Conference on Robotics and Automation, ICRA 2021
Project Page arXiv Code

Semantically-aware Spatio-Temporal Reasoning Agent for Vision-and-Language Navigation

Muhammad Zubair Irshad, Niluthpol Mithun, Zachary Seymour, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar In Submission to WACV 2022

Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation 

Muhammad Zubair Irshad, Thomas Kollar, Michael Laskey, Kevin Stone, Zsolt Kira
In Submission 

Project Page/arXiv (Coming Soon)

Deep Reinforcement Learning Agents

Deep Reinforcement Learning based control of complex robotic agents

Habitat Point Goal Navigation

Embodied Visual Navigation in Habitat


Learning inverse dynamics of 7-DOF Robot Arm


Complex robot maze navigation using image classification and ROS


Vehicle Control for Autonomous Driving


Environment perception stack for Self Driving Cars


Sentiment prediction using Reccurent Neural Networks


Visual Odometry for Autonomous Driving

Image: University of Toronto (Self Driving Cars Specialization)

Motion planning stack for Self Driving Cars


End to end imitation learning of dynamically unstable systems