Papers
6
Total Citations
73
H-Index
5
About
Yunlong Dong is a robotics researcher whose work lies at the intersection of intelligent control, system identification, and human–robot collaboration. His primary research areas include online parameter estimation for time-varying dynamical systems, adaptive and deep learning–based control, and safety-critical collision detection for industrial robots. Dong’s most impactful contribution is his work on sparse Bayesian learning for real-time identification of industrial robot dynamics, which has garnered 25 citations and provides a robust framework for handling system changes during operation. He has also made significant strides in contouring control for dual-arm robots with holonomic constraints, where his modified distributed control framework ensures asymptotically stable coordination. More recently, Dong has advanced robot safety through switched momentum dynamics for collision detection, a critical enabler for human–robot shared workspaces. His work on deep adaptive control and reinforcement learning—including reward shaping for dexterous hand manipulation and energy-efficient motion planning—demonstrates a commitment to both performance and sustainability. With a growing citation record and a focus on practical, deployable algorithms, Yunlong Dong is shaping the next generation of intelligent, safe, and efficient robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Switched Momentum Dynamics Identification for Robot Collision Detection11 citations · 2024
- 4Deep adaptive control with online identification for industrial robots10 citations · 2022
- 5Reward shaping in reinforcement learning for robotic hand manipulation6 citations · 2025
- 6