Papers
7
Total Citations
43
H-Index
4
About
Chengfei Yue is a rising leader in space robotics, whose research centers on task and motion planning (TAMP), multi-arm robot collaboration, and adaptive control for dynamic environments. His most impactful work tackles the core challenge of making robotic algorithms robust enough for real-world space operations. Yue’s 2024 paper on a modular multi-level replanning TAMP framework (11 citations) directly addresses the fragility of traditional planners by enabling robots to recover from interference and control errors, a critical step toward practical deployment. He has also pioneered the integration of learning from demonstration with reinforcement learning for multi-arm space robots (10 citations), allowing them to acquire complex collaborative skills from human examples. His development of probabilistic movement primitives for multi-task learning (10 citations) further expands robots’ ability to generalize across diverse operations. Yue’s contributions extend to control theory, where his priority-based switching model predictive control method (2025, 6 citations) enables efficient sequential manipulation. Notably, he designed and demonstrated an air-bearing-based testbed (2022, 4 citations) that provides a high-fidelity microgravity simulator for validating these algorithms on Earth. With a growing citation footprint and a clear focus on bridging simulation to reality, Yue is shaping the future of autonomous space robots for on-orbit servicing and debris removal.
Research Focus
Key Achievements
Top Papers
- 1Modular Multi-Level Replanning TAMP Framework for Dynamic Environment11 citations · 2024
- 2
- 3Probabilistic movement primitives based multi-task learning framework10 citations · 2024
- 4
- 5Design and Demonstration for an Air-bearing-based Space Robot Testbed4 citations · 2022
- 6
- 7