Max Robotics — Global Service Robot Directory + US Certification

About

Ze Yang Ding is a robotics researcher whose work sits at the dynamic intersection of soft robotics, machine learning, and state estimation. Based at Monash University Malaysia, Ding has made significant contributions to one of the most pressing challenges in soft robotics: how to reliably sense and perceive the state of inherently compliant, difficult-to-instrument robotic systems. His most influential work, "Robust Multimodal Indirect Sensing for Soft Robots Via Neural Network-Aided Filter-Based Estimation" (2021, 61 citations), pioneered the use of neural networks combined with filtering techniques to estimate sensory variables without direct physical sensors — a breakthrough approach that circumvents the fundamental difficulty of embedding sensors in soft, deformable bodies. This indirect sensing paradigm runs throughout his research portfolio, including earlier work leveraging Extended Kalman Filters for curvature and force estimation. Recognizing the data scarcity problem inherent to soft robotics, Ding has also advanced data-efficient deep learning strategies, exploring synthetic data generation, predictive uncertainty quantification, and cross-domain transfer learning using variational Bayesian frameworks. These contributions collectively address the full pipeline from perception to reliable modeling in soft robotic systems. With nearly 115 cumulative citations, his work is shaping how the next generation of intelligent soft robots will sense and understand their world.