Papers
6
Total Citations
314
H-Index
5
About
Chengtao Wen is a robotics researcher whose work sits at the intersection of reinforcement learning, robotic manipulation, and intelligent manufacturing. His research focuses on developing autonomous robot control systems capable of performing complex, contact-rich assembly tasks that challenge conventional feedback control methods. Wen's most influential contribution, "Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly" (2019), has garnered 177 citations and demonstrates how incorporating operational space force/torque information into reinforcement learning frameworks can enable robots to acquire precise industrial assembly skills autonomously. His complementary work on deep reinforcement learning for mixed deformable and rigid object assembly (2018, 94 citations) further established his reputation by tackling the notoriously difficult problem of inserting rigid components into deformable structures — a task previously resistant to classical control approaches. Beyond learning-based manipulation, Wen has contributed to motion planning through iterative convex optimization for contact-rich trajectory generation in confined environments, and more recently to robotic surface inspection using multimodal visual and tactile perception for large-scale manufacturing components. Collectively, his research addresses critical bottlenecks in intelligent automation, making meaningful strides toward adaptable, autonomous industrial robots capable of operating reliably in real-world production settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6