Sooho Park

About

Sooho Park is a robotics researcher whose work sits at the intersection of machine learning and autonomous robot systems, with particular focus on robot control, path planning, and intelligent inspection automation. His most recognized contribution, "A Computational Framework for Automatic Online Path Generation of Robotic Inspection Tasks via Coverage Planning and Reinforcement Learning" (2018, 53 citations), addresses a critical industrial challenge: automating repetitive surface and shape inspection tasks on factory production lines using near-optimal robotic path planning driven by reinforcement learning. This work has established him as a notable voice in industrial robotics automation. Park's earlier research laid important groundwork in learning-based robot control, leveraging Gaussian process methods to help robots adapt to complex, unknown environments. His 2013 papers on localized sparse online Gaussian processes and sequential Gaussian processes explored how experience-based learning could enable robots to model uncertain interactions more effectively. He continued this thread with later work on Gaussian Process Mixture Models for learning robot kinematics and dynamics. Together, these contributions reflect a coherent research vision: equipping robots with the adaptive intelligence needed to operate reliably in unpredictable real-world settings, bridging theoretical machine learning with practical robotics engineering.

Research Focus

Key Achievements

Top Papers

1. 1
   A Computational Framework for Automatic Online Path Generation of Robotic Inspection Tasks via Coverage Planning and Reinforcement Learning

   53 citations · 2018
2. 2
   Learning-based robot control with localized sparse online Gaussian process

   11 citations · 2013
3. 3
   Learning based robot control with sequential Gaussian process

   7 citations · 2013
4. 4
   Robot Model Learning with Gaussian Process Mixture Model

   2 citations · 2018

Key Collaborators

Contact & Links