Handing Wang

Papers

Total Citations

H-Index

About

Handing Wang is a rising leader in the intersection of evolutionary computation and soft robotics, pioneering methods to automate the co-design of robot morphology and control. Her core research tackles the fundamental bottleneck in soft robot design: the prohibitive computational cost of training reinforcement learning controllers for every candidate structure. Wang’s major contributions include introducing **action inheritance** to dramatically accelerate controller training, and developing **morphological transfer-based multi-fidelity algorithms** that leverage knowledge from simpler designs to inform more complex ones. Her work on **cross-task collaborative optimization** further advances the field by enabling knowledge transfer across different design tasks, making the automated design of adaptive soft robots practical. With her most-cited paper (2023) already garnering 8 citations, Wang’s impact is growing rapidly. Notably, her 2024 study on multi-fidelity evolution was recognized for addressing a critical gap in adapting soft robots to unpredictable environments. For students and researchers, Wang’s work offers a compelling blueprint for using surrogate-assisted and transfer learning techniques to solve expensive, real-world optimization problems in robotics.