Papers
1
Total Citations
6
H-Index
1
About
Yi Feng is a researcher in robotics and computational intelligence, with a primary focus on solving complex kinematic problems through neural network methodologies. His most notable contribution is the development of a novel parallel algorithm that integrates Backpropagation (BP) and Radial Basis Function (RBF) neural networks to address the inverse kinematics of robotic systems. In his 2014 work, Feng proposed a method where the BP network is trained using the Levenberg-Marquardt algorithm, while the RBF network enhances computational efficiency by increasing radial basis functions. This hybrid approach offers a robust solution to the traditionally challenging problem of mapping joint parameters to end-effector positions in robot control. Although his most-cited paper has accumulated 6 citations, its impact lies in laying foundational groundwork for neural-network-based kinematic solvers, a niche area with growing relevance in adaptive robotics. Feng’s research bridges theoretical neural computation and practical robotic applications, making his work a valuable reference for students and engineers exploring intelligent control systems. His contributions highlight the potential of parallel neural architectures in advancing autonomous robotic manipulation.
Research Focus
Key Achievements
Top Papers
- 1