Gregory Izatt
Research Engineer at Boston Dynamics
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolGregory Izatt is a research engineer in robotic perception and manipulation with 12 years of experience bridging model-based and data-driven approaches to tackle challenging manipulation environments. Based in Cambridge, MA, he combines academic rigor from Caltech and MIT (Ph.D. work in robotics) with hands-on system development at Boston Dynamics. Gregory has contributed meaningful back-end and simulation improvements to notable open-source projects like Drake and the widely used trimesh library, improving depth-sensor fidelity and mesh/URDF tooling. He also built visualization tools for the MIT underactuated course, reflecting an ability to turn complex dynamics into practical, debuggable software. Colleagues would describe him as someone who looks for a middle ground between theory and engineering—practical, precise, and quietly focused on robustness in real-world robot systems.
12 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy (Ph.D.), Computer Science -- Robotics, Doctor of Philosophy (Ph.D.), Computer Science -- Robotics at Massachusetts Institute of TechnologyBachelor’s Degree, Computer Science, and Engineering and Applied Science (Computation and Neural Systems), Bachelor’s Degree, Computer Science, and Engineering and Applied Science (Computation and Neural Systems) at California Institute of Technology
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (18)
simulation10
mesh10
visualization10
robotics10
c-language10
geometry10
python10
matplotlib10
simulations10
collision-detection10
dynamics10
rigid-bodies10
cprogramming-language10
visualizations10
numpy9
Programming languages (9)
Github contributions (5)
RobotLocomotion/drake
Oct 2014 - Nov 2021
Model-based design and verification for robotics.
Role in this project:
Back-end Developer, System Architect
Back-end Developer, System ArchitectContributions:18 reviews, 178 commits, 66 PRs in 7 years 2 months
Contributions summary:Gregory's commits focused on improving the accuracy and functionality of depth sensors within the robotics simulation framework, Drake. They addressed issues with margin calculations for raycasts onto collision objects, specifically boxes and meshes, which resulted in more precise depth sensor readings. The user also introduced features for controlling the use of collision margins, providing a way to toggle them for different collision detection methods within the RigidBodyManipulator class and optimizing Lidar integration.
model-basedmodel-based-designroboticsdrakeverification
RussTedrake/underactuated
Jan 2018 - May 2019
The course text for MIT 6.832 (and 6.832x on edX)
Role in this project:Back-end Developer
Back-end DeveloperContributions:61 commits, 21 PRs, 1 push in 1 year 3 months
Contributions summary:Gregory primarily worked on implementing a planar rigid body visualizer for the MIT 6.832 course. They developed the core logic for visualizing rigid body dynamics, including building view patches for different shapes, handling transformations, and drawing the robot state. They also made several updates and improvements to the visualizer, fixing frame bugs and enhancing color handling. The user’s contributions focused on creating and refining a visual tool for robotics simulations.
edxpythonmit
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.