Zhivko Zhekov

Papers

Total Citations

H-Index

About

Zhivko Zhekov’s research focuses on the intersection of neural networks and robotics, with a particular emphasis on intelligent control systems for robotic manipulators. His major contributions lie in developing neural control architectures for two-link planar robots, where he pioneered methods for both online and offline neural network training to handle complex kinematic and dynamic tasks. In his most cited work (2019, 5 citations), Zhekov proposed a system using a single feedforward neural network that simultaneously serves as a neural model and controller, learning via gradient descent and error backpropagation. He extended this in 2020 (3 citations) by introducing a dual-network approach, where one network approximates inverse kinematics offline, while the other handles real-time control. More recently (2024, 2 citations), Zhekov has addressed practical challenges in industrial robotics through camera calibration techniques, ensuring accurate alignment between camera and robot coordinate systems—a critical step for machine vision applications. His work bridges theoretical neural control with real-world robotic implementation, making significant strides in autonomous robot manipulation.