Navid Borhani

Papers

Total Citations

H-Index

About

Navid Borhani is a researcher whose work lies at the intersection of robust control theory and neural network architectures for nonlinear dynamical systems. His primary research focus involves developing novel frameworks that leverage competing neural networks to enhance the stability and robustness of control systems—a critical challenge in applications ranging from robotic manipulation to optical systems. In his most cited work, "Competing Neural Networks for Robust Control of Nonlinear Systems" (2019), Borhani addresses the fundamental problem of controlling systems where output measurements—such as the 3D position of a robotic arm or complex speckle patterns from laser light—are accessible, but the underlying dynamics are highly nonlinear and uncertain. By introducing a competitive learning paradigm among neural networks, his approach enables more resilient control strategies that adapt to disturbances and modeling errors. While his citation count is still growing, this foundational paper has laid important groundwork for integrating adversarial or competitive principles into control design. Borhani’s contributions are particularly notable for bridging theoretical control guarantees with practical neural network implementations, offering a promising pathway for next-generation autonomous systems operating in unpredictable environments.