Roderick Melnik

About

Roderick Melnik is a leading researcher at the intersection of computational mechanics, bio-inspired robotics, and data-driven modeling. His primary research areas include fluid-structure interaction, reduced-order modeling, and the application of machine learning to complex engineering systems. Melnik’s major contributions center on the development of advanced computational frameworks for optimizing the propulsion of bio-inspired robots, particularly jellyfish-like and mantle-undulated designs. He pioneered the use of nonintrusive reduced-order models (NIROM) combined with proper orthogonal decomposition (POD) to efficiently predict hydrodynamic forces, enabling faster and more accurate design iterations. His work on integrating deep learning—specifically long short-term memory (LSTM) neural networks—with multiple POD algorithms has established new benchmarks for real-time hydrodynamics prediction. With over 17 citations across his most prominent papers, Melnik’s research has direct implications for autonomous underwater vehicles and soft robotics. Notably, his 2022 study on jellyfish-inspired robot propulsion optimization and his 2023 framework for mantle-undulated propulsion robots demonstrate his ability to bridge theoretical modeling with practical engineering challenges, making him a key figure in the advancement of intelligent, bio-inspired robotic systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Propulsion optimization of a jellyfish-inspired robot based on a nonintrusive reduced-order model with proper orthogonal decomposition

   8 citations · 2022
2. 2
   Parameter optimization of the bio-inspired robot propulsion through the deep learning based reduced order fluid-structure interaction model

   7 citations · 2022
3. 3
   A two-dimensional hydrodynamics prediction framework for mantle-undulated propulsion robot using multiple proper orthogonal decomposition and long short term memory neural network

   2 citations · 2023

Key Collaborators

Contact & Links