Yeongtak Oh

Papers

Total Citations

H-Index

About

Yeongtak Oh is a robotics researcher whose work bridges intelligent fault diagnosis and field-deployable robotic systems. His primary research areas include industrial robot health monitoring, deep learning-based fault detection, and legged robotic platforms for hazardous environments. Oh’s most influential contribution is his development of a deep transferable motion-adaptive fault detection method for industrial robots using a residual–convolutional neural network (2021), which has earned 31 citations. This work addresses a critical challenge in manufacturing: enabling robots to detect their own mechanical faults across varying operational conditions without requiring extensive retraining. In parallel, Oh contributed to the system design and implementation of multi-legged spider robots for landmine detection in the Korean Demilitarized Zone (DMZ) (2021, 8 citations). This project tackled the unique geological and terrain challenges of the DMZ, where conventional wheeled unmanned ground vehicles struggle. By developing legged platforms capable of climbing inclined terrain and overcoming obstacles, Oh’s work directly supports humanitarian demining efforts. His research exemplifies how advanced neural network techniques can enhance robotic autonomy and reliability, while also demonstrating the practical deployment of robots in extreme, safety-critical environments.