Henry Charlesworth

Papers

Total Citations

H-Index

About

Henry Charlesworth is a researcher at the intersection of artificial intelligence, robotics, and complex systems, whose work spans both the theoretical foundations of collective behavior and the practical challenges of robotic control. His most influential paper, “Intrinsically motivated collective motion” (2019, 52 citations), proposes a groundbreaking framework where collective motion—typically observed in animal swarms, active suspensions, and robotic agents—emerges not from hand-coded rules but from an underlying intrinsic motivation, offering a new lens for understanding self-organization in nature and engineering. In reinforcement learning, Charlesworth’s “PlanGAN” (2020, 19 citations) tackles the notoriously difficult problem of sparse rewards by integrating model-based planning with generative models, enabling agents to achieve multiple goals with remarkable efficiency. Further pushing the boundaries of dexterous manipulation, his work on trajectory optimization and reinforcement learning (2020, 5 citations) introduces a suite of challenging simulated tasks for anthropomorphic robotic hands, advancing the quest for autonomous systems capable of complex, real-world manipulation. Charlesworth’s research is notable for its ambition to unify principles from physics, biology, and machine learning, making him a rising figure in the quest for more intelligent, adaptive, and self-organizing artificial systems.