C.G. Atkeson

Papers

Total Citations

H-Index

About

Christopher G. Atkeson is a pioneering researcher whose work sits at the intersection of robotics, machine learning, and motor control. Best known for his foundational contributions to **robot learning** and **adaptive control**, Atkeson has spent decades advancing how robots and computational systems can acquire and refine skills through experience. His 1987 work on adaptive feedforward control in robotics represents an early and influential exploration of how robots can learn dynamic models of their own bodies to improve movement accuracy — a challenge that remains central to modern robotics research. Atkeson's broader research portfolio spans nonparametric learning methods, locally weighted regression, reinforcement learning, and humanoid robotics, areas in which he has garnered substantial recognition within the scientific community. His contributions have helped lay conceptual groundwork for data-driven approaches to robot motor learning, influencing generations of researchers working on autonomous systems. Based at Carnegie Mellon University, Atkeson continues to push boundaries in robot learning and physical human-robot interaction, demonstrating a career-long commitment to building machines that can adapt intelligently to complex, real-world environments.