Oliver Grainger

Papers

Total Citations

H-Index

About

Oliver Grainger is a researcher at the intersection of robotics, scientific computing, and machine learning, with a primary focus on accelerating simulation and control for robotic manipulation. His most notable contribution is the development of a Parareal framework that integrates a learned coarse model—a data-driven surrogate—to dramatically speed up time-parallel simulations for complex manipulation tasks. This work, published in 2020 and garnering 8 citations, demonstrates how combining classical numerical methods with modern machine learning can overcome computational bottlenecks in robotics, enabling faster planning and more responsive control. Grainger’s approach is particularly impactful for tasks requiring high-fidelity dynamics, such as dexterous grasping or assembly, where traditional fine-grained simulations are too slow for real-time use. By bridging the gap between parallel-in-time algorithms and learned approximations, he has opened new pathways for efficient, scalable simulation in robotics. His research is highly relevant for students and engineers seeking to leverage AI to enhance the performance of autonomous systems, and his work continues to inspire further exploration into hybrid numerical-ML methods for embodied intelligence.