Papers
1
Total Citations
18
H-Index
1
About
Andy Yan is a robotics researcher whose work focuses on enabling robots to learn complex tasks from human demonstrations with greater efficiency and adaptability. His key research areas include robot imitation learning, task-parameterized models, and sequential decision-making. Yan's most notable contribution is the development of a framework for sequential robot imitation learning from observations, published in 2021. This work introduced a family of task-parameterized hidden semi-Markov models that can automatically extract invariant sub-goals or options from demonstrated trajectories, allowing robots to understand the sequential structure of tasks rather than simply mimicking motions. By optimizing these models, Yan's approach helps robots generalize learned behaviors to new situations, a critical step toward more autonomous and flexible robotic systems. With 18 citations, this paper has already influenced subsequent research in imitation learning and robot skill acquisition. Yan's work bridges the gap between raw observation data and structured, reusable robot skills, making him a promising voice in the field of learning from demonstration.
Research Focus
Key Achievements
Top Papers
- 1Sequential robot imitation learning from observations18 citations · 2021