Nanae Sekiguchi

Papers

Total Citations

H-Index

About

Nanae Sekiguchi is a researcher whose work lies at the intersection of robotics, neural networks, and inverse problem-solving. Her primary research focus involves applying machine learning techniques—specifically network inversion using multilayer neural networks—to solve complex inverse problems in robotics. Her most notable contribution, detailed in her 2007 paper "Inverse estimation of joint angles of robot arm by network inversion," demonstrates a novel approach to estimating robotic joint angles by treating the task as an inverse problem. Rather than predicting outcomes from known inputs, her method reverses the process, using neural networks to infer the underlying causes (joint angles) from observed results. While her citation count remains modest, with her key paper accumulating 2 citations, her work represents an early and thoughtful application of neural network inversion to robotics—a concept that has since gained broader relevance in fields ranging from control systems to computer vision. Sekiguchi’s research offers a foundational perspective for students and researchers interested in the intersection of neural computation and robotic kinematics, highlighting how inverse modeling can unlock new ways of understanding and controlling complex mechanical systems.