Taylor Howell
Research Scientist at Google DeepMind
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolTaylor Howell is a research scientist specializing in high-performance robotics, with eight years of experience spanning simulation, planning, control, and machine learning. He completed a PhD at Stanford developing optimization-based tools and differentiable physics for drone coordination, legged locomotion, and dexterous manipulation, and has translated that work into industry roles at DeepMind and Google Brain. At DeepMind he led development of MuJoCo MPC, a laptop-capable real-time predictive-control tool for robot behavior synthesis, and has hands-on experience implementing core planning algorithms like iLQG. His background also includes experimental mechatronics and novel control of microrobots and biomedical microfluidics from undergraduate research, reflecting a rare blend of theory, simulation, and hardware. Based in London, he maintains an active open-source presence (thowell) and a track record of making research systems practical and interactive.
8 years of coding experience
8 years of employment as a software developer
The University of UtahDoctor of Philosophy - PhD Optimization Control Simulation Robotics, Doctor of Philosophy - PhD Optimization Control Simulation Robotics at Stanford University
English
Github Skills (6)
mpc10
trajectory-optimization10
mujoco10
trajectory-generation10
cprogramming-language9
c-language9
Programming languages (5)
Github contributions (5)
google-deepmind/mujoco_mpc
Dec 2022 - Mar 2023
Real-time behaviour synthesis with MuJoCo, using Predictive Control
Role in this project:
Back-end Developer & Algorithm Implementer
Back-end Developer & Algorithm ImplementerContributions:166 reviews, 61 commits, 142 PRs in 3 months
Contributions summary:Taylor primarily contributed to the MuJoCo MPC (Model Predictive Control) project by modifying and updating planner and trajectory files. Their changes focused on spacing and formatting within the code, suggesting an effort to maintain code quality. The commits demonstrate involvement with core components, including iLQGPlanner and Trajectory, which are critical to the real-time behavior synthesis using MuJoCo and predictive control algorithms. The user's work suggests a focus on the implementation of predictive control algorithms within the MuJoCo environment.
roboticsmpcpybulletsynthesismodel-predictive-control
thowell/mjx_warp
Feb 2025 - Mar 2025
Contributions:166 pushes, 103 branches in 1 month
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.