Graham W. Taylor

Papers

Total Citations

H-Index

About

Graham W. Taylor is a leading researcher in the intersection of robotics, machine learning, and motor control, with a particular focus on robotic grasping and the computational modeling of human movement. His work is distinguished by its integration of deep generative models with physical robotics, addressing fundamental challenges in how machines perceive and interact with the world. Notably, his 2017 paper on "Modeling Grasp Motor Imagery Through Deep Conditional Generative Models" (44 citations) pioneered the use of deep learning to simulate and understand the complex sensory-motor processes underlying grasping, a task that remains extremely challenging for autonomous systems. Taylor also made significant contributions to clinical robotics, as demonstrated by his 2015 study (25 citations) that used a robotic pilot to analyze spasticity, providing quantitative data to distinguish clinical populations from healthy controls—a critical step toward objective assessment of motor disorders. His work on "An Integrated Simulator and Dataset that Combines Grasping and Vision for Deep Learning" (2017) directly tackled the data scarcity problem in robotic manipulation, creating structured environments for training vision-based grasping systems. Through these contributions, Taylor has advanced both the theoretical foundations and practical applications of intelligent robotic systems, bridging the gap between human motor control and artificial intelligence.