Emily Kieson

About

Emily Kieson is a pioneering researcher at the intersection of human-robot interaction, reinforcement learning, and robotic pedagogy. Her work addresses a critically underexplored challenge: rather than focusing solely on how robots learn, she investigates how robots can effectively *teach* humans. Through her groundbreaking research using the humanoid robot Baxter, Kieson has developed novel frameworks in which robots autonomously acquire instructional policies from expert demonstration and deploy them to guide human learners through complex tasks. Her most influential contributions include developing reinforcement learning models inspired by human cognition to enhance robot-led instruction, and pioneering Mutual Reinforcement Learning (MRL), a paradigm in which both humans and robots function as empathetic learning agents, continuously adapting through feedback. These ideas, accumulated across several works published between 2016 and 2019 and collectively cited over 37 times, have helped establish robotic teaching as a legitimate and promising field of study. Kieson's semantic structures for robotic instruction further demonstrate her commitment to making human-robot collaboration practical in real-world, non-standardized environments. Her research is essential reading for anyone interested in collaborative robotics, cognitive modeling, and the future of human-machine skill transfer.

Research Focus

Key Achievements

Top Papers

1. 1
   Using Human Reinforcement Learning Models to Improve Robots as Teachers

   9 citations · 2018
2. 2
   Learning Task-Based Instructional Policy for Excavator-Like Robots

   9 citations · 2018
3. 3
   A Reinforcement Learning Model for Robots as Teachers

   8 citations · 2018
4. 4
   Mutual Reinforcement Learning with Robot Trainers

   6 citations · 2019
5. 5
   Semantic structure for robotic teaching and learning

   3 citations · 2017
6. 6
   Can Co-robots Learn to Teach?

   2 citations · 2016

Key Collaborators

Contact & Links