Shenghan Xie
Papers
4
Total Citations
42
H-Index
3
About
Shenghan Xie is a robotics researcher whose work bridges agricultural automation, human-robot interaction, and intelligent control systems. His primary research areas include path planning for robotic manipulators, deep reinforcement learning for robotics, and cloud-based service robot architectures. Xie’s most impactful contribution is his 2023 paper on workspace decomposition-based path planning for fruit-picking robots in complex greenhouse environments, which has garnered 27 citations—his highest-cited work. This research addresses critical challenges in agricultural robotics by enabling efficient, collision-free navigation in cluttered, dynamic settings. He also developed a cloud-based quadruped service robot capable of multi-scene adaptability and diverse human-robot interaction modalities, including voice and face recognition, drawing on cyber-physical system technologies. In human-robot collaboration scenarios, Xie has advanced real-time collision avoidance using deep policy networks, moving beyond traditional methods like RRT to meet dynamic safety requirements. His work on training on-policy actor-critic networks with demonstration-like sampled exploration further improves sample efficiency in deep reinforcement learning for complex robotic tasks. Through these contributions, Xie is shaping the future of autonomous robots in agriculture, service, and collaborative environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4