Xinghua Chang

China Aerodynamics Research and Development Center, National Defense University

Papers

Total Citations

H-Index

About

Xinghua Chang is a leading researcher at the intersection of computational fluid dynamics (CFD), bio-inspired robotics, and artificial intelligence. Their work focuses on unlocking the secrets of fish locomotion to create more agile, intelligent robotic swimmers. Chang’s major contributions lie in developing novel coupling methods that integrate hydrodynamics, kinematics, and motion control. They pioneered the use of deep reinforcement learning (DRL) to enable self-propelled, autonomous swimming in simulated bionic fish, allowing these virtual models to learn complex maneuvers like obstacle avoidance without pre-programmed instructions. Chang’s most cited work, “A numerical simulation method for bionic fish self-propelled swimming under control based on deep reinforcement learning” (2020, 36 citations), established a foundational framework for this approach. This was followed by “CFD based parameter tuning for motion control of robotic fish” (2020, 28 citations), which addressed the critical challenge of translating simulation insights into real-world robotic performance. Their 2021 study on obstacle avoidance further demonstrated the power of DRL for maneuvering in complex environments. Collectively, Chang’s research provides a powerful blueprint for designing next-generation autonomous underwater vehicles that can navigate unpredictable real-world conditions with fish-like grace and efficiency.