K
Keigo Watanabe
Researcher at Okayama University
Publications - 737
Citations - 5764
Keigo Watanabe is an academic researcher from Okayama University. The author has contributed to research in topics: Mobile robot & Robot. The author has an hindex of 32, co-authored 720 publications receiving 5450 citations. Previous affiliations of Keigo Watanabe include Beijing Institute of Technology & National Institute for Materials Science.
Papers
More filters
Proceedings ArticleDOI
Fusion Method of Convolutional Neural Network and Support Vector Machine for High Accuracy Anomaly Detection
Fusaomi Nagata,Kenta Tokuno,Kento Nakashima,Akimasa Otsuka,Takeshi Ikeda,Hiroyuki Ochi,Keigo Watanabe,Maki K. Habib +7 more
TL;DR: In this paper, binary classification methods using support vector machines (SVM) obtained from one- class learning and two-class learning are introduced and a template matching technique is further applied to enhance the reliability and accuracy for binary classification.
Journal ArticleDOI
The Polishing Robot for PET Bottle Molds Using a Fuzzy Force Controller
Yukihiro Kusumoto,Fusaomi Nagata,Kiminori Yasuda,Osamu Tsukamoto,Kunihiro Tsuda,Keigo Watanabe +5 more
Proceedings ArticleDOI
A switching control of underactuated manipulators by introducing a definition of monotonically decreasing energy
TL;DR: A novel energy definition in the sense of monotonic decreasing is introduced and the corresponding switching rules with such energy are developed, to reduce the number of switching times.
Journal ArticleDOI
Stabilization of a Fire Truck Robot by an Invariant Manifold Theory
TL;DR: In this article, a switching control method based on an invariant manifold theory is proposed for stabilizing an underactuated system with three inputs, where a chained form model is assumed to be used as a canonical model.
Journal ArticleDOI
A study on rings gymnastic robot: (Fuzzy control rules for realizing exercises)
TL;DR: The purpose of this paper is to acquire suitable fuzzy rules for realizing a series of exercises, which is a handstand from backward giant circle, and simulation results show the effectiveness of the fuzzy rules.