Masaki Kojima
Papers
1
Total Citations
3
H-Index
1
About
Masaki Kojima is a researcher whose work sits at the intersection of robotics, artificial intelligence, and precision agriculture. His primary research areas include autonomous robotic systems, machine learning applications for environmental sensing, and the emerging concept of Digital Twins for robotic control. Kojima’s most notable contribution is his comparative study of shallow neural networks (SNN) versus random forest algorithms for estimating lawn grass lengths in robotic lawn mowers. This work, published in 2020, demonstrates how machine learning can enhance the autonomous navigation and operational efficiency of robotic mowers by enabling real-time, sensor-based grass height estimation. Although his most-cited paper currently holds 3 citations, its significance lies in its foundational approach to integrating Digital Twin and Hybrid Twin methodologies into robotic control systems—a forward-looking concept that bridges virtual simulation with physical actuation. Kojima’s research is particularly relevant for students and engineers interested in the practical deployment of AI in outdoor robotics, where accurate environmental perception is critical. His work underscores the potential of lightweight neural networks for embedded systems, offering a scalable solution for smart lawn care and autonomous ground vehicles.
Research Focus
Key Achievements
Top Papers
- 1