Phongtharin Vinayavekhin
IBM Research - Tokyo, University of Electro-Communications, Tokyo University of Science
Papers
7
Total Citations
86
H-Index
5
About
Phongtharin Vinayavekhin is a leading researcher at the intersection of robotics, computer vision, and machine learning, with a core focus on enabling robots to learn complex manipulation tasks from human demonstration. Her work has pioneered novel methods for teaching robots dexterous skills such as regrasping and pick-and-place operations, using recurrent neural networks and topological task models to translate human motion into robotic actions. A major contribution is her development of spatio-temporal anomaly detection systems for industrial robots, where she introduced an unsupervised learning approach that uses deep feature extraction from monocular camera feeds—a method that has garnered 45 citations and proven critical for real-world surveillance. Vinayavekhin has also advanced robot learning through force-torque datasets for multi-shape insertion tasks, providing essential benchmarks for the field. Her earlier work on detecting dance motion structure from body components demonstrates her versatility in applying computational methods to human movement analysis. With over 80 total citations across her publications, Vinayavekhin’s research continues to shape how robots perceive, learn from, and safely interact with their environments, making her a notable figure in modern robotics and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Human-Like Hand Reaching by Motion Prediction Using Long Short-Term Memory10 citations · 2017
- 4Teaching a Robot Pick and Place Task using Recurrent Neural Network6 citations · 2016
- 5
- 6
- 7