Shoya Koga
Papers
2
Total Citations
8
H-Index
2
About
Shoya Koga is a robotics researcher focused on enabling autonomous navigation in GPS-denied environments—a critical challenge for indoor, underground, or urban-canyon operations. His work centers on marker-based localization and deep learning-driven motion control for mobile robots. In his most-cited paper (2023, 5 citations), Koga developed a system that uses a camera-mounted mobile robot to recognize markers via deep learning, calculating relative positions and angles to achieve autonomous travel without GPS. His earlier 2021 study (3 citations) advanced this concept by integrating internal and external camera images to compute marker size and relative pose, allowing the robot to follow a predefined path. Together, these contributions demonstrate a practical, vision-based approach to robust robot autonomy. While still early in his career, Koga’s work addresses a fundamental bottleneck in field robotics—reliable navigation without satellite signals—and his methods offer a scalable solution for warehouse, search-and-rescue, and industrial applications. His research sits at the intersection of computer vision, deep learning, and control systems, promising safer and more adaptable mobile robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2