Papers
10
Total Citations
430
H-Index
7
About
KeJun Ning is a pioneering robotics researcher whose work bridges the gap between human demonstration and robot learning, with a particular focus on movement generation and hyper-redundant mechanisms. His most influential contributions center on two key areas: learning manipulation semantics from observation and developing novel trajectory generation methods. Ning's seminal 2011 paper on learning object–action relations (180 citations) introduced a groundbreaking representation for encoding object relationships during manipulation, enabling robots to recognize and replicate human actions—a fundamental challenge in robotic imitation learning. His work on Modified Dynamic Movement Primitives (140 citations) revolutionized how robots join and generate complex movement sequences, with applications ranging from handwriting to industrial manipulation. Beyond these core contributions, Ning has made significant advances in hyper-redundant chain robot design, developing the innovative "3D-Trunk" system—a wire-driven, state-controllable robot with passive joints that demonstrated unprecedented flexibility. His research has accumulated over 430 citations, reflecting its lasting impact on both theoretical frameworks and practical robotic systems. Ning's work continues to influence modern approaches to robot learning from demonstration and adaptive motion control.
Research Focus
Key Achievements
Top Papers
- 1Learning the semantics of object–action relations by observation180 citations · 2011
- 2
- 3A Novel Concept for Building a Hyper-Redundant Chain Robot45 citations · 2009
- 4
- 5
- 6A Novel Trajectory Generation Method for Robot Control13 citations · 2012
- 7Modified dynamic movement primitives for joining movement sequences7 citations · 2011
- 8Research on embedded MAS based manipulator control4 citations · 2006
- 9
- 10