Joonho Lee is a senior engineer and researcher with a Ph.D. in nonlinear control systems who has spent a decade applying advanced control theory and machine learning to autonomy problems across automotive, aerospace, and robotics domains. He has driven multi-time-scale deep reinforcement learning, stochastic approximation methods, and estimator design (including graph neural networks) at General Motors and now Boeing Research & Technology, combining model-based control (MPC, Kalman/GP-based filters) with modern learning approaches. His work spans under-actuated systems from quadrotors and helicopters to vehicle chassis and powered prosthetics, and he has a track record of making controllers robust to uncertainty and measurement noise. Based in Berkeley and a visiting scholar at UC Berkeley, he researches robotic world models and brings both rigorous academic training and practical production experience in R&D environments. An uncommon strength is his ability to bridge singular perturbation/multi-time-scale theory with hands-on implementation of perception and segmentation models for real-world autonomy.
Code repository for Semantic Terrain Classification for Off-Road Autonomous Driving (https://openreview.net/forum?id=AL4FPs84YdQ) (CoRL 2021)
Contributions:12 commits, 2 pushes, 1 branch in 9 days
autonomous-drivingclassification
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.