Emmanuel Pignat
Idiap Research Institute, Universitat Politècnica de Catalunya
Papers
7
Total Citations
164
H-Index
4
About
Emmanuel Pignat is a robotics researcher whose work sits at the intersection of human-robot interaction, learning from demonstration, and adaptive control. His research focuses on enabling robots to assist humans in dynamic, real-world environments—particularly through dressing assistance, where robots must adapt to unpredictable human movements. His most cited work, "Learning adaptive dressing assistance from human demonstration" (2017, 85 citations), introduces a framework for robots to learn personalized assistance policies directly from human demonstrations, reducing the need for expert programming. He further advanced this line of research by integrating high-level symbolic planning with low-level motion primitives (2018, 33 citations), enabling safer and more flexible daily-living assistance. Pignat has also made contributions to teleoperation, developing motion mapping techniques for continuous bilateral control (2021, 28 citations), and to Bayesian inference in robotics, proposing variational inference with mixture models for representing robot configuration distributions (2020, 8 citations). His work on active improvement of control policies and interaction-limited inverse reinforcement learning demonstrates a commitment to making robot learning more efficient and accessible. With over 160 citations across his publications, Pignat is recognized for bridging the gap between theoretical machine learning and practical robotic assistance.
Research Focus
Key Achievements
Top Papers
- 1Learning adaptive dressing assistance from human demonstration85 citations · 2017
- 2
- 3Motion Mappings for Continuous Bilateral Teleoperation28 citations · 2021
- 4
- 5Bayesian Gaussian Mixture Model for Robotic Policy Imitation4 citations · 2019
- 6
- 7Interaction-limited Inverse Reinforcement Learning3 citations · 2020