Ruixuan Liu
Papers
9
Total Citations
99
H-Index
6
About
Ruixuan Liu is a robotics researcher whose work sits at the intersection of human-robot collaboration, motion prediction, and multi-robot planning. With a cumulative citation count exceeding 100 across his published work, Liu has established himself as a meaningful contributor to the challenge of making robots safer, smarter, and more responsive in human-shared environments. His most recognized contribution — a 2020 framework combining recurrent neural networks with inverse kinematics for human arm motion prediction (47 citations) — addressed a foundational problem in human-robot collaboration: anticipating human movement to enable safe, efficient interaction. This work reflects his broader commitment to proactive robot behavior, further demonstrated through research on intention-aware co-assembly and task-agnostic handover systems that adapt robustly to real-world variability. Liu has also pushed boundaries in multi-robot coordination, developing hierarchical task allocation frameworks grounded in temporal logic and asynchronous planning systems for cooperative assembly. His practical engineering contributions include jerk-bounded motion controllers and a lightweight manipulation system for precision Lego assembly, showcasing his range from theoretical planning to hands-on implementation. Collectively, Liu's research advances the vision of flexible, intelligent robots capable of safely partnering with humans in complex manufacturing and collaborative settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Task-Agnostic Adaptation for Safe Human-Robot Handover7 citations · 2022
- 6A Lightweight and Transferable Design for Robust Lego Manipulation6 citations · 2024
- 7
- 8
- 9Safe Interactive Industrial Robots using Jerk-based Safe Set Algorithm2 citations · 2022