Alert button
Picture for Kanata Suzuki

Kanata Suzuki

Alert button

Realtime Motion Generation with Active Perception Using Attention Mechanism for Cooking Robot

Sep 26, 2023
Namiko Saito, Mayu Hiramoto, Ayuna Kubo, Kanata Suzuki, Hiroshi Ito, Shigeki Sugano, Tetsuya Ogata

Viaarxiv icon

Interactively Robot Action Planning with Uncertainty Analysis and Active Questioning by Large Language Model

Aug 30, 2023
Kazuki Hori, Kanata Suzuki, Tetsuya Ogata

Viaarxiv icon

Deep Predictive Learning : Motion Learning Concept inspired by Cognitive Robotics

Jun 26, 2023
Kanata Suzuki, Hiroshi Ito, Tatsuro Yamada, Kei Kase, Tetsuya Ogata

Figure 1 for Deep Predictive Learning : Motion Learning Concept inspired by Cognitive Robotics
Figure 2 for Deep Predictive Learning : Motion Learning Concept inspired by Cognitive Robotics
Figure 3 for Deep Predictive Learning : Motion Learning Concept inspired by Cognitive Robotics
Figure 4 for Deep Predictive Learning : Motion Learning Concept inspired by Cognitive Robotics
Viaarxiv icon

Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data

Mar 08, 2022
Minori Toyoda, Kanata Suzuki, Yoshihiko Hayashi, Tetsuya Ogata

Figure 1 for Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
Figure 2 for Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
Figure 3 for Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
Figure 4 for Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
Viaarxiv icon

Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss

Oct 30, 2021
Akira Sakai, Taro Sunagawa, Spandan Madan, Kanata Suzuki, Takashi Katoh, Hiromichi Kobashi, Hanspeter Pfister, Pawan Sinha, Xavier Boix, Tomotake Sasaki

Figure 1 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
Figure 2 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
Figure 3 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
Figure 4 for Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance loss
Viaarxiv icon

Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm

Oct 03, 2021
Kanata Suzuki, Taro Sunagawa, Tomotake Sasaki, Takashi Katoh

Figure 1 for Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm
Figure 2 for Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm
Figure 3 for Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm
Figure 4 for Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm
Viaarxiv icon

Embodying Pre-Trained Word Embeddings Through Robot Actions

Apr 17, 2021
Minori Toyoda, Kanata Suzuki, Hiroki Mori, Yoshihiko Hayashi, Tetsuya Ogata

Figure 1 for Embodying Pre-Trained Word Embeddings Through Robot Actions
Figure 2 for Embodying Pre-Trained Word Embeddings Through Robot Actions
Figure 3 for Embodying Pre-Trained Word Embeddings Through Robot Actions
Figure 4 for Embodying Pre-Trained Word Embeddings Through Robot Actions
Viaarxiv icon

In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning

Mar 17, 2021
Kanata Suzuki, Momomi Kanamura, Yuki Suga, Hiroki Mori, Tetsuya Ogata

Figure 1 for In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning
Figure 2 for In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning
Figure 3 for In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning
Figure 4 for In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning
Viaarxiv icon

Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask

Jan 18, 2021
Kanata Suzuki, Tetsuya Ogata

Figure 1 for Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask
Figure 2 for Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask
Figure 3 for Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask
Figure 4 for Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask
Viaarxiv icon

HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation

Mar 31, 2020
Pin-Chu Yang, Mohammed Al-Sada, Chang-Chieh Chiu, Kevin Kuo, Tito Pradhono Tomo, Kanata Suzuki, Nelson Yalta, Kuo-Hao Shu, Tetsuya Ogata

Figure 1 for HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation
Figure 2 for HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation
Figure 3 for HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation
Figure 4 for HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation
Viaarxiv icon