Papers
10
Total Citations
134
H-Index
8
About
Yu-Chi Lin is a leading researcher in humanoid robotics and intelligent manipulation, whose work bridges the gap between dynamic motion planning and real-world robotic autonomy. His primary research areas include humanoid contact planning, locomotion in complex environments, and robotic object search and grasping. Lin’s major contribution lies in integrating machine learning with traditional control to enable humanoid robots to navigate dynamically and robustly. His seminal work, "Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction" (35 citations), pioneered the use of learned dynamics to plan contact sequences that consider balance and external disturbances, moving beyond quasi-static assumptions. This was further advanced in his 2020 study on zero- and one-step capturability prediction (16 citations), which enhanced robustness against perturbations. Lin also made significant strides in service robotics, developing planners for occluded object search (20 citations) and depth-gradient-based grasping (13 citations). His work on reusing previous experience for navigation (14 citations) and affordance detection has reduced planning times in unstructured settings. With over 130 total citations, Lin’s research is foundational for creating humanoid robots that can safely and efficiently interact with human environments, from offices to disaster zones.
Research Focus
Key Achievements
Top Papers
- 1
- 2Planning on searching occluded target object with a mobile robot manipulator20 citations · 2015
- 3
- 4Using previous experience for humanoid navigation planning14 citations · 2016
- 5
- 6Human-oriented recognition for intelligent interactive office robot12 citations · 2013
- 7Integrated affordance detection and humanoid locomotion planning8 citations · 2016
- 8
- 9
- 10