Sheng‐De Wang

Papers

Total Citations

H-Index

About

Sheng‐De Wang is a pioneering researcher in robotics and intelligent control systems, with a career spanning foundational work in fuzzy logic control to cutting-edge deep reinforcement learning. His early landmark contribution, "Adaptive tuning of the fuzzy controller for robots" (2000), with 54 citations, established adaptive fuzzy control as a robust method for managing the nonlinear dynamics of robotic systems, enabling more precise and flexible automation. Building on this legacy, Wang has advanced into modern AI-driven control, as demonstrated in his 2018 work on distributed continuous control with meta-learning for robotic arms. This research leverages Deterministic Deep Policy Gradient (DDPG) to overcome the limitations of stochastic policies, achieving superior efficiency in continuous action spaces. By integrating meta-learning, his approach allows robotic arms to rapidly adapt to new tasks with minimal retraining, a critical step toward general-purpose robotics. Wang’s trajectory from adaptive fuzzy tuning to deep reinforcement learning reflects a sustained commitment to bridging classical control theory with contemporary machine learning, making his work essential reading for students and researchers exploring autonomous robotic manipulation and intelligent adaptive systems.