Koya Sakamoto
Papers
1
Total Citations
3
H-Index
1
About
Koya Sakamoto is a rising researcher at the intersection of embodied AI and robotics, with a primary focus on enabling machines to understand and interact with physical environments through natural language. His most notable contribution is the development of a "Map-based Modular Approach for Zero-shot Embodied Question Answering" (EQA), a novel framework that allows robots to navigate unfamiliar spaces and answer human queries about objects without prior training on specific environments. This work directly addresses a critical limitation of existing EQA methods, which are typically confined to simulated settings and restricted vocabularies. By leveraging modular map-based representations, Sakamoto’s approach pushes toward more practical, real-world deployment of intelligent agents. Although early in his career—with his 2024 paper already garnering 3 citations—his research signals a significant step forward in zero-shot generalization for embodied systems. Sakamoto’s work is particularly relevant for students and researchers interested in bridging language understanding, spatial reasoning, and autonomous navigation, offering a scalable pathway for robots to operate in dynamic, unseen environments.
Research Focus
Key Achievements
Top Papers
- 1Map-based Modular Approach for Zero-shot Embodied Question Answering3 citations · 2024