Wenxing Liu
Papers
2
Total Citations
13
H-Index
2
About
Wenxing Liu is a robotics researcher whose work focuses on bridging the gap between simulation and real-world robot control, with particular emphasis on manipulation tasks and motion planning. His most significant contribution lies in advancing sim-and-real reinforcement learning, a paradigm that trains policies using both simulated and real-world data simultaneously, rather than the traditional sim-to-real transfer. In his 2023 paper, Liu proposed a consensus-based approach that dramatically improves both the efficiency and effectiveness of this training process, achieving faster convergence to optimal policies while requiring substantially less real-world robot data—a critical advancement given the constraints of hardware budgets and time in practical robotics. This work has already garnered 10 citations, reflecting its growing influence in the field. Liu has also contributed to the comparative analysis of obstacle avoidance inverse kinematics, systematically evaluating null-space-based and optimization-based methods in his 2020 study. His research is particularly valuable for students and practitioners seeking practical, data-efficient solutions for deploying robotic manipulation systems in real-world environments, where the sim-to-real gap remains a fundamental challenge.
Research Focus
Key Achievements
Top Papers
- 1
- 2