Kanta Kaneda
Papers
1
Total Citations
7
H-Index
1
About
Kanta Kaneda is a robotics researcher advancing the frontier of human-robot collaboration, with a focus on domestic service robots and physical-world search engines. Their most-cited work, “Learning-To-Rank Approach for Identifying Everyday Objects Using a Physical-World Search Engine” (2024, 7 citations), tackles a critical challenge in assistive robotics: enabling robots to reliably retrieve everyday objects in cluttered, real-world environments. Kaneda’s key contribution lies in developing a human-in-the-loop framework that seamlessly blends autonomous object identification with operator intervention—a pragmatic solution for deploying service robots in society. By applying a learning-to-rank methodology, their system allows robots to prioritize and identify target objects more accurately, reducing the cognitive load on human operators while maintaining robust performance. This work directly addresses the growing demand for daily care and support, positioning Kaneda at the intersection of machine learning, human-robot interaction, and embodied AI. Their research not only advances the technical capabilities of domestic robots but also offers a realistic pathway toward their safe and effective integration into homes and care facilities. Kaneda’s approach exemplifies how thoughtful system design can bridge the gap between full automation and human oversight.
Research Focus
Key Achievements
Top Papers
- 1