Alice Ellmer

About

Alice Ellmer’s research lies at the intersection of robotics, motor control, and reinforcement learning, with a central focus on how agents—both human and robotic—learn to adapt impedance for safe and robust physical interaction. Her major contributions include pioneering model-free reinforcement learning approaches for impedance control in stochastic environments, demonstrating that agents can learn to modulate stiffness and damping in response to unpredictable perturbations. This work, published in 2012, has garnered 64 citations and is foundational for developing robots that interact safely and dexterously with humans and complex environments. Ellmer’s earlier 2011 study (13 citations) further elucidated how humans combine two distinct adaptation strategies—one for predictable and one for unpredictable force fields—providing a computational framework for understanding biological motor learning. Her research has significant implications for rehabilitation robotics, prosthetics, and human-robot collaboration. By bridging insights from human motor adaptation with reinforcement learning algorithms, Ellmer has advanced the design of autonomous systems capable of learning variable impedance policies, a critical step toward truly adaptive and safe physical interaction.

Research Focus

Key Achievements

Top Papers

1. 1
   Model-Free Reinforcement Learning of Impedance Control in Stochastic Environments

   64 citations · 2012
2. 2
   Reinforcement learning of impedance control in stochastic force fields

   13 citations · 2011

Key Collaborators

Contact & Links