Gerulf K.M. Pedersen

About

Gerulf K.M. Pedersen is a researcher at the intersection of robotics, motor learning, and computational intelligence, with a focus on how artificial systems can replicate and extend human sensorimotor control. His work centers on developing models that bridge biological principles and robotic applications, particularly through the lens of reinforcement learning and evolutionary computation. Pedersen’s most cited contribution, "The SURE_REACH Model for Motor Learning and Control of a Redundant Arm" (2009, 18 citations), introduces a framework that mimics human arm control to enable robots to learn reaching tasks with redundant degrees of freedom—a key challenge in adaptive robotics. Complementing this, his paper "Learning sensorimotor control structures with XCSF" (2009, 16 citations) pioneers the application of the XCSF learning classifier system to robotics, demonstrating how this genetics-based tool can learn compact, generalizable solutions online. Despite XCSF’s proven effectiveness in data mining and reinforcement learning, its use in cognitive robotics was sparse before Pedersen’s work, making his contributions foundational. His research not only advances theoretical understanding of motor control but also offers practical pathways for creating more adaptive, human-like robots.

Research Focus

Key Achievements

Top Papers

1. 1
   The SURE_REACH Model for Motor Learning and Control of a Redundant Arm: From Modeling Human Behavior to Applications in Robotics

   18 citations · 2009
2. 2
   Learning sensorimotor control structures with XCSF

   16 citations · 2009

Key Collaborators

Contact & Links