Grady Williams
Planning & Controls Lead at Overland AI
Seattle, Washington, United States
Summary
👤
Senior🎓
Top SchoolGrady Williams is a robotics engineer and planning & controls leader with 13 years of experience building perception, planning, and control systems for high-speed and heavy-vehicle autonomy. He has led cross-functional teams at Embark and Overland AI, delivering production-grade mapping, localization, and MPC-based control stacks that enabled investor traction and commercial truck programs. As a hands-on IC and manager he established engineering best practices while continuing to contribute core algorithms, including QP-based longitudinal planning and stochastic MPC implementations in C++/CUDA. His academic work at Georgia Tech produced multiple top-tier papers and powered the AutoRally platform and a finalist quadrotor racing entry, demonstrating a rare blend of research rigor and applied systems engineering. Active in open-source, his AutoRally contributions focus on model-predictive path integral control and controller-plant integration—work that directly influences real-world vehicle behavior. Based in Seattle with a PhD in Robotics and a BS in Mathematics, he excels at turning cutting-edge controls research into reliable, deployable systems.
13 years of coding experience
6 years of employment as a software developer
Bachelor of Science (B.S.), Mathematics, Bachelor of Science (B.S.), Mathematics at University of WashingtonDoctor of Philosophy (PhD), Robotics, Doctor of Philosophy (PhD), Robotics at Georgia Institute of Technology
Github Skills (7)
cuda10
c-language10
eigen10
cprogramming-language10
ros9
neural-network9
machine-learning9
Programming languages (2)
Github contributions (5)
AutoRally/autorally
May 2017 - Mar 2019
Software for the AutoRally platform
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:76 commits, 1 PR, 61 pushes in 1 year 9 months
Contributions summary:Grady's commits primarily focus on implementing model predictive path integral control code, indicating involvement in the core control system. The changes include the creation and modification of code related to costs, a neural network model, and run control loops. The user also worked on integrating the controller with the autorally plant. The user's work is highly relevant to the AutoRally platform's functionality.
ignitionrosoccupancy-grid-mapyarpgazebo-simulator
gradyrw/gtsam
Feb 2022 - Apr 2022
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
Contributions:5 pushes in 1 month
smoothingsparsec-plus-plusgtsamrobotics
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.