Papers
8
Total Citations
195
H-Index
6
About
Jianghua Duan is a robotics researcher whose work sits at the intersection of robot learning, motion planning, and intelligent control. His research focuses primarily on learning from demonstration (LfD), dynamical systems-based motion modeling, and trajectory tracking control for robot manipulators — areas where he has made meaningful contributions to both theory and practical application. Duan's most influential work, "Fast and Stable Learning of Dynamical Systems Based on Extreme Learning Machine" (2017, 71 citations), addressed a central challenge in robot learning: simultaneously achieving accuracy, stability, and speed when encoding human demonstrations into robot motion policies. This contribution has become a foundational reference in the LfD community. He extended this work to trajectory tracking control, kinematic learning strategies, and compliant manipulation from force demonstrations, reflecting a consistent drive to make robots more adaptive in unstructured environments. More recently, Duan has advanced model predictive optimization for imitation learning and robust inverse dynamic control under uncertainty, demonstrating a maturing research agenda that bridges machine learning and classical control theory. His 2025 work on starshaped roadmap navigation signals a growing interest in autonomous robot navigation in complex real-world workspaces. With over 190 cumulative citations, Duan represents an emerging voice in human-robot interaction and intelligent robotic systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2Robot trajectory tracking control using learning from demonstration method32 citations · 2019
- 3
- 4
- 5Model predictive optimization for imitation learning from demonstrations19 citations · 2023
- 6
- 7Learning Compliant Manipulation Tasks from Force Demonstrations6 citations · 2018
- 8