Maxwell Hwang

Zhejiang University, Second Affiliated Hospital of Zhejiang University

Papers

Total Citations

H-Index

About

Maxwell Hwang is a leading researcher in the intersection of robotics, computer vision, and reinforcement learning. His primary contributions lie in advancing **image-based visual servoing (IBVS)** and **inverse reinforcement learning (IRL)**. Hwang’s most impactful work, "Adaptive Image-Based Visual Servoing Using Reinforcement Learning With Fuzzy State Coding" (2020, 32 citations), introduces a novel method that uses reinforcement learning to dynamically optimize the mixture parameter β in the image Jacobian matrix, dramatically improving positioning precision for robotic systems. He further refined this approach with a fuzzy CMAC learning framework (2021, 14 citations), enabling more robust visual feedback control. In the domain of IRL, Hwang’s "An Efficient Unified Approach Using Demonstrations for Inverse Reinforcement Learning" (2019) tackles the critical challenge of reward function design, proposing a streamlined method that learns optimal policies directly from expert demonstrations without hand-crafted rewards. His work bridges the gap between theoretical reinforcement learning and practical robotic control, offering scalable solutions for autonomous systems. With a growing citation record, Hwang is recognized for making visual servoing more adaptive and IRL more accessible, positioning him as an emerging authority in intelligent robotic control.