Max Robotics — Global Service Robot Directory + US Certification

About

Tae-Dok Eom’s research lies at the intersection of neural network theory, dynamic system control, and robotic motion planning. His work addresses fundamental challenges in applying neural networks to continuous-time dynamic systems, particularly the stability issues that arise when training samples are nonuniform due to system nonlinearities—a problem he explored in his 2002 paper. Eom also pioneered a novel skill learning paradigm that models artificial neurons after human neurons, incorporating chaotic neuron filters and supervisory controllers to update both the weights and structure of feedforward neural network controllers. This approach, detailed in his 1998 and 2002 papers, offers a biologically inspired method for adaptive control. In robotics, he contributed to reactive motion planning for soccer-playing robots, using curvature variation to enable real-time obstacle avoidance. While his citation counts (2–3 per paper) reflect a focused, niche impact, his work on stability in neural dynamic systems and bio-inspired learning paradigms provides foundational insights for researchers tackling adaptive control in nonlinear environments.