Xingfang Wang
Papers
3
Total Citations
25
H-Index
2
About
Xingfang Wang is a robotics researcher specializing in safe human-robot collaboration, with a focus on collision avoidance and motor learning. His work centers on integrating depth visual perception, model-based policy search, and sampling-based model predictive control (MPC) to enable robots to operate safely and adaptively in dynamic environments. Wang’s most-cited paper, “Multi-Joint Active Collision Avoidance for Robot Based on Depth Visual Perception” (2022, 13 citations), addresses a critical gap by extending collision avoidance beyond the end-effector to the entire robotic arm, enhancing safety in smart city applications. His subsequent work, “Guided Model-Based Policy Search Method for Fast Motor Learning of Robots With Learned Dynamics” (2024, 10 citations), tackles the sim-to-real transfer challenge in reinforcement learning, proposing a guided approach that reduces the need for extensive physical training. Most recently, his 2025 paper on constrained sampling-based MPC introduces a path integral method to handle equality hard constraints during human-robot interaction, achieving real-time, collision-free manipulation. With a growing citation record and a clear trajectory toward practical, constraint-aware robotics, Wang is establishing himself as a contributor to safer, more capable autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3