Boo-Ho Yang

About

Boo-Ho Yang is a pioneering researcher in robot learning and control, best known for developing the concept of **progressive learning**—a stable learning control method inspired by human skill acquisition. His major contribution is an excitation scheduling technique that guarantees stability during robot impedance learning, overcoming traditional adaptive control instabilities. This work, first introduced in his 1996 paper (32 citations), enables high-speed robotic assembly by allowing systems to learn quasi-static behaviors before progressing to dynamic tasks. Yang also advanced **skill acquisition from human experts**, processing teaching data to extract manipulation strategies for applications like robotic deburring (1990, 7 citations). His research bridges logic task descriptions with impedance generation, and he has explored reinforcement learning for assembly robots. With a career spanning from the 1990s to 2005, Yang’s progressive learning framework remains foundational for stable, human-like robot control, influencing both industrial automation and adaptive robotics research.

Research Focus

Key Achievements

Top Papers

1. 1
   Progressive learning and its application to robot impedance learning

   32 citations · 1996
2. 2
   Progressive learning for robotic assembly: learning impedance with an excitation scheduling method

   9 citations · 2002
3. 3
   Skill acquisition from human experts through pattern processing of teaching data.

   7 citations · 1990
4. 4
   Robot impedance generation from logic task description through progressive learning

   5 citations · 2002
5. 5
   Progressive learning for robot impedance control

   3 citations · 2005
6. 6
   Reinforcement learning of assembly robots

   3 citations · 2005
7. 7
   Adaptive Reinforcement Learning and Its Application to Robot Compliance Learning

   3 citations · 1995

Key Collaborators

Contact & Links