Liqian Ma
Papers
5
Total Citations
58
H-Index
3
About
Liqian Ma is a researcher at the forefront of robotics and computer vision, with a focus on enabling intelligent systems to perceive, reason about, and physically interact with their environments. His work bridges the critical gap between simulation and reality, particularly for articulated object manipulation. Ma’s most influential contribution is the **Sim2Real²** framework, which actively builds explicit physics models to allow robots to precisely manipulate unseen articulated objects—like cabinets and drawers—in the real world without human demonstration. This work, along with its dexterous extension **DexSim2Real²**, addresses a fundamental challenge in robotics: transferring learned skills from simulation to complex, unstructured real-world settings. Beyond manipulation, Ma has advanced person re-identification for human-robot interaction with an online metric model update method (41 citations) and developed **FoV-Net**, a self-attention-based system for field-of-view extrapolation with uncertainty estimation, crucial for autonomous vehicle planning. His research consistently tackles the "Sim2Real" problem, demonstrating a clear trajectory from perception to precise physical action, and his work is increasingly cited as a key reference for researchers aiming to build robots that can operate reliably in the real world.
Research Focus
Key Achievements
Top Papers
- 1Online RGB-D person re-identification based on metric model update41 citations · 2017
- 2
- 3
- 4
- 5