Eric L. Sauser
Papers
11
Total Citations
817
H-Index
10
About
Eric L. Sauser is a leading researcher in developmental robotics and human-robot interaction, whose work focuses on enabling robots to learn and adapt through intuitive, human-guided methods. His most significant contribution is a probabilistic framework for robot learning by imitation, which uses Hidden Markov Models (HMM) and Gaussian Mixture Regression (GMR) to allow robots to robustly acquire and reproduce complex gestures from human demonstrations—a foundational approach cited over 455 times. Sauser also pioneered algorithms for a robot to visually and autonomously learn its own body schema (75 citations), a critical step toward self-aware machines. His research further explores how robots can refine their skills through tactile guidance and human corrections (67 citations), and he has investigated biologically inspired multimodal integration for more natural human-robot collaboration. By combining statistical learning, active vision, and tactile feedback, Sauser’s work has laid essential groundwork for creating robots that can adapt their motor policies in real-time, moving beyond rigid programming toward flexible, interactive skill acquisition.
Research Focus
Key Achievements
Top Papers
- 1Learning and Reproduction of Gestures by Imitation455 citations · 2010
- 2Coevolution of active vision and feature selection97 citations · 2004
- 3ONLINE LEARNING OF THE BODY SCHEMA75 citations · 2008
- 4Iterative learning of grasp adaptation through human corrections67 citations · 2011
- 5
- 6Tactile guidance for policy refinement and reuse31 citations · 2010
- 7Tactile Guidance for Policy Adaptation17 citations · 2010
- 8
- 9Tactile Guidance for Policy Adaptation12 citations · 2010
- 10