Papers
6
Total Citations
53
H-Index
4
About
Ke Han is a leading researcher in human-robot interaction and dexterous manipulation, with a focus on enabling safe, intuitive collaboration between humans and robotic systems. His work centers on three key areas: dynamic obstacle avoidance for physical human-robot interaction, human-like motion planning for anthropomorphic manipulators, and multi-fingered grasp prediction. Han’s most cited paper, “Hybrid Trajectory Replanning-Based Dynamic Obstacle Avoidance for Physical Human-Robot Interaction” (2021, 21 citations), introduces a real-time replanning framework that ensures safe robot motion in shared workspaces, a critical contribution to collaborative robotics. His 2022 paper on human-like redundancy resolution (12 citations) addresses the challenge of integrating radial elbow offsets in anthropomorphic arms, advancing biomimetic control. Han has also pioneered semantic object matrices for task-based obstacle avoidance (8 citations) and developed an end-to-end deep network for high-degree-of-freedom spatial grasp prediction (2021), tackling the complexity of humanoid hand dexterity. With over 50 total citations, his work is foundational for applications in manufacturing, healthcare, and assistive robotics, bridging the gap between theoretical motion planning and practical human-robot teamwork.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Human Motion Trajectory Prediction in Human-Robot Collaborative Tasks4 citations · 2019