Shogo Sakata
Papers
2
Total Citations
43
H-Index
2
About
Shogo Sakata is a robotics researcher whose work centers on enabling autonomous robot navigation using only visual information, with a particular focus on semantic segmentation from monocular cameras. His major contribution lies in challenging the field’s reliance on expensive 3D LiDAR sensors, instead demonstrating that a single camera—a far more accessible and human-compatible sensor—can suffice for road-following in both urban and indoor environments. In his most-cited paper (2020, 38 citations), Sakata proposed a visual navigation framework that leverages semantic segmentation to interpret scenes, allowing robots to navigate without depth sensors. He further advanced this approach by developing methods to generate synthetic datasets from 3D scanned data to train segmentation classifiers, addressing the critical bottleneck of labeled data (2020, 5 citations). This work is notable for its potential to lower the cost and complexity of autonomous systems, making them more deployable in human-centric spaces. Sakata’s research bridges computer vision and robotics, offering a practical path toward vision-only navigation that is both scalable and robust.
Research Focus
Key Achievements
Top Papers
- 1
- 2