Papers
9
Total Citations
173
H-Index
6
About
Syungkwon Ra is a leading researcher in humanoid robotics and bio-inspired movement control, whose work has fundamentally advanced how robots learn, generate, and stabilize natural, human-like motions. His core contributions span movement primitives, imitation learning, and evolutionary algorithms, with a particular focus on enabling robots to replicate and adapt human arm and full-body motions. His most influential work, "Movement Primitives, Principal Component Analysis, and the Efficient Generation of Natural Motions" (2005, 81 citations), introduced a groundbreaking framework combining movement storage, dynamic models, and optimization to produce efficient, human-like robot movements. Ra has also made significant strides in practical robot design, as seen in his 2018 work on modeling and control of articulated arms with embedded joint actuators (26 citations), which supports cost-effective human-cooperative robots like the UR5. His innovative use of Evolutionary Algorithm-based imitation learning (2009, 22 citations) and neural oscillators for self-stabilizing bipedal locomotion (2008, 10 citations) demonstrates his commitment to biologically inspired control. With a career spanning over a decade and nearly 200 total citations, Ra’s research remains essential reading for anyone interested in the intersection of machine learning, control theory, and humanoid robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Imitation Learning of Robot Movement Using Evolutionary Algorithm12 citations · 2008
- 5Self-stabilizing bipedal locomotion employing neural oscillators10 citations · 2008
- 6
- 7PCA-based genetic operator for evolving movements of humanoid robot5 citations · 2008
- 8Real-time arm motion imitation for human–robot tangible interface4 citations · 2009
- 9