Chengdong Wu
Papers
2
Total Citations
20
H-Index
2
About
Chengdong Wu is a leading researcher in intelligent robotics and automation, with a focus on deep reinforcement learning and human-robot collaboration. His work bridges the gap between simulation and real-world robotic control, particularly for complex manipulation tasks. Wu’s most-cited paper (2025, 16 citations) introduces the M2ACD (Multi-Actor-Critic Deep Deterministic Policy Gradient) algorithm, a novel framework for trajectory planning that combines a general inverse kinematics solver with simulation-efficient training. This approach enables robotic manipulators to adapt to dynamic, cluttered environments without extensive real-world data. In a related study (2025, 4 citations), Wu explores zero-force control and collision detection in collaborative robots using deep learning, advancing safe, intuitive human-robot interaction. His contributions are pivotal for next-generation manufacturing, where robots must operate flexibly alongside humans. By integrating reinforcement learning with practical control challenges, Wu is shaping the future of autonomous robotics, making his work essential reading for students and researchers in robotic manipulation, AI-driven control, and industrial automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2