Kier Storey

Papers

Total Citations

379

H-Index

About

Kier Storey is a leading researcher in robotics and simulation, best known for pioneering high-performance GPU-based physics engines that accelerate robot learning. Their seminal work, *Isaac Gym: High Performance GPU-Based Physics Simulation for Robot Learning* (2021, 322 citations), introduced a revolutionary platform where both physics simulation and neural network policy training reside entirely on the GPU. By enabling direct data transfer between physics buffers and PyTorch tensors, Isaac Gym bypasses traditional CPU bottlenecks, allowing researchers to train complex robotic policies at unprecedented speeds for tasks ranging from locomotion to dexterous manipulation. This work has become foundational in the field of deep reinforcement learning for robotics. Storey further advanced robotic manipulation with the *Factory* project (2022, 54+ citations), which focuses on fast and accurate contact simulation for robotic assembly—one of the oldest and most challenging applications in robotics. By combining high-fidelity physics with modern deep learning, Factory addresses long-standing barriers in precision assembly tasks. Storey’s contributions have significantly lowered the barrier to entry for simulation-based robotics research, enabling faster iteration and more robust policy development. Their work continues to shape how robots learn complex physical interactions in simulated environments before deployment in the real world.