K
Keisuke Nakamura
Researcher at Honda
Publications - 153
Citations - 1631
Keisuke Nakamura is an academic researcher from Honda. The author has contributed to research in topics: Acoustic source localization & Signal. The author has an hindex of 18, co-authored 143 publications receiving 1324 citations. Previous affiliations of Keisuke Nakamura include Tokyo Institute of Technology & Centre national de la recherche scientifique.
Papers
More filters
Proceedings ArticleDOI
Intelligent sound source localization for dynamic environments
TL;DR: A new localization system “Selective Attention System”, implemented into a humanoid robot, and the experimental validation is successfully verified even when the robot microphones move dynamically, addressing sound source localization working in dynamic environments for robots.
Proceedings ArticleDOI
Outdoor auditory scene analysis using a moving microphone array embedded in a quadrocopter
TL;DR: A prototype system for auditory scene analysis based on the proposed MUltiple SIgnal Classification based on incremental Generalized EigenValue Decomposition (iGEVD-MUSIC) showed that dynamically-changing noise is properly suppressed with the proposed method and multiple human voice sources are able to be localized even when the AR.Drone is moving in an outdoor environment.
Journal ArticleDOI
Human-Centered Reinforcement Learning: A Survey
TL;DR: The state-of-the-art human-centered RL algorithms are described and become a starting point for researchers who are initiating their endeavors in human- centered RL and references to the most interesting and successful works are provided.
Proceedings ArticleDOI
Improvement in outdoor sound source detection using a quadrotor-embedded microphone array.
TL;DR: Experimental results showed that the combination of iGSVD-MUSIC and CMS improves sound source detection performance drastically and achieves real-time processing.
Proceedings ArticleDOI
Real-time super-resolution Sound Source Localization for robots
TL;DR: This work proposes two methods, MUSIC based on Generalized Singular Value Decomposition (GSVD-MUSIC), and Hierarchical SSL (H-SSL), which drastically reduces the computational cost while maintaining noise-robustness in localization.