Jun-Cheol Park

Korea Advanced Institute of Science and Technology

Papers

Total Citations

H-Index

About

Jun-Cheol Park is a leading researcher in developmental neurorobotics and robot imitation learning, with a focus on how artificial systems can acquire goal-directed actions through biologically inspired mechanisms. His most influential work, "Learning for Goal-Directed Actions Using RNNPB: Developmental Change of 'What to Imitate'" (2017, 14 citations), tackles one of the most challenging problems in robotics: determining which aspects of an action to imitate. Park’s approach leverages the concept of developmental change, showing that robots can learn to focus on salient action properties rather than copying every detail—a solution inspired by human cognitive development. In his earlier foundational work, "Predictive Coding Strategies for Developmental Neurorobotics" (2012, 8 citations), Park explored how the brain might manage overwhelming sensory data by using predictive coding to guide action, rather than processing raw inputs. This work bridges neuroscience and robotics, proposing that robots can act more efficiently by anticipating sensory consequences. Park’s contributions are notable for their interdisciplinary impact, offering engineering solutions grounded in developmental psychology and computational neuroscience. His research continues to influence how robots learn from demonstration, making him a key figure in the field of neurorobotics.