Tetsuya Narita

Papers

Total Citations

H-Index

About

Tetsuya Narita is a robotics researcher whose work focuses on the frontier of dexterous manipulation, specifically addressing how robots can handle unknown objects and tools with human-like adaptability. His key research areas include adaptive grasping, multimodal sensing (tactile, proximity, and force), and skill transfer for contact-rich tasks. Narita’s major contribution lies in developing theoretical frameworks for real-time grasp force control, most notably through his work on rotational incipient slip detection, which allows robots to dynamically adjust their grip on objects with unknown physical properties—a critical step toward truly autonomous manipulation. His 2020 paper on this topic has garnered 15 citations, establishing a foundation for subsequent work. He further advanced the field by introducing policy blending and recombination techniques that integrate multimodal sensory feedback for stable, complex manipulations, and by pioneering few-shot transfer methods that enable robots to learn tool-use skills from just a handful of human demonstrations. These contributions are particularly notable for bridging the gap between theoretical control and practical, sensor-driven execution, positioning Narita as a rising leader in the quest for robots that can seamlessly interact with the unstructured physical world.