PWM: Policy Learning with Large World Models
Ignat Georgiev, Varun Giridhar, Nicklas Hansen, Animesh Garg
Hey! I'm Ignat, a Robot Learning researcher. I am currently doing a PhD at Georgia Tech, working with Animesh Garg. My deeply seeded belief is that robotics and learning have the potential to change the world for the better, and my mission is to bring intelligent star-wars-like robots one step closer to reality (minus the blasters).
Prior used to work as an ML engineer/researcher in autonomous vehicles. Nowadays I occasionally do some consulting or contracting work on projects I find interesting. Shoot me an email if you have something in mind!
This little website is my space to tell the world about me, put my resume out there, show off my research and blog some wisdom. You can find all of my research on Google Scholar.
Selected Research
Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation
Ignat Georgiev, Krishnan Srinivasan, Jie Xu, Eric Heiden, Animesh Garg
Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing
Ignat Georgiev, Christoforos Chatzikomis, Timo Völkl, Joshua Smith, Michael Mistry
Blog posts
Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing
First paper at CoRL 2020!
As a byproduct of my Master’s thesis I have had my first paper accepted into the Conference of Robot Learning (CoRL) 2020. The paper is titled Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing which is quite self-explanatory. You can read it on arxiv. It was a big team-effort and...
[Read More]
Lessons from Formula Student
Formula Student is not that only about building cars but also about building teams
Formula Student is the world’s largest competition, where students develop and build racecars. For most, it is an exciting and cutting-edge project where students can escape boring lectures, do something cool, and get practical experience. For me, it’s also a bit more - I believe Formula Student shaped me into...
[Read More]
Formula Student
My passion throughout university - I founded and led a student team to develop an autonomous racecar
For the majority of my time at University, I was with Edinburgh University Formula Student (EUFS), which is a student project competing in the prestigious Formula Student competition. I have established the autonomous racecar student project within the team, aiming to compete in the brand new competition class - Formula...
[Read More]
Sample Collection Robot
For a course in university, I developed the software for a sample collection robot based on a Turtlebot3 robot with a manipulator.
For a course in university, I developed the software for a sample collection
robot based on Turtlebot3 tasked with navigating
autonomously around a known environment, interacting with objects and collecting
rock samples with a robotic arm. More precisely, the robot was tasked to:
[Read More]
Dissertation submitted
Reaching the end of my Master's I have finally submitted my dissertation of which I am extremely proud!
After a long year, I am happy to share that I have finished my Master’s dissertation titled Adaptive Motion Control for Autonomous Racing. I managed to create a 2-stage system consisting of trajectory optimization and tracking, both of which share the same model and adapt to dynamical changes online. The...
[Read More]