研究者詳細 - 戸田　雄一郎

論文 - 戸田　雄一郎

分割表示 96 件中 41 - 60 件目／全件表示 >>

An incremental episodic memory framework for topological map building 査読

Wei Hong Chin, Azhar Aulia Saputra, Yuichiro Toda, Naoyuki Kubota

International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2018 - Proceedings 322 - 327 2019年1月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：IEEE

In this paper, an episodic memory learning framework is proposed for categorizing and encoding sensory information that acquired from a robot for environment adaptation and sensorimotor map building. The proposed learning model termed as Incremental Episodic Memory Adaptive Resonance Theory (In-EMART), consists two layers of ART networks which used to detect novel event encountered by the robot and learn the spatio-temporal relationship by creating neurons incrementally. A set of connected episodes forms a sensorimotor map that can be used for path planning and goal navigation autonomously. The experimental results for a mobile robot show that: (i) In-EMART can learn sensory data in real time which is important for robot implementation; (ii) the model solves the perceptual aliasing issue by recalling the connected episode neurons; (iii) compared with previous works, the proposed method further generates a sensorimotor map for connecting episodes together to navigate from one place to another continuously.

DOI： 10.1109/KCIC.2018.8628468

Web of Science

Scopus

researchmap

Region of Interest Growing Neural Gas for Real-Time Point Cloud Processing. 査読

Yuichiro Toda, Xiang Li, Takayuki Matsuno, Mamoru Minami

Intelligent Robotics and Applications - 12th International Conference, ICIRA 2019, Shenyang, China, August 8-11, 2019, Proceedings, Part III 11742 82 - 91 2019年

Episodic Memory Multimodal Learning for Robot Sensorimotor Map Building and Navigation. 査読

Wei Hong Chin, Yuichiro Toda, Naoyuki Kubota, Chu Kiong Loo, Manjeevan Seera

IEEE Trans. Cogn. Dev. Syst. 11 ( 2 ) 210 - 220 2019年

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

In this paper, an unsupervised learning model of episodic memory is proposed. The proposed model, enhanced episodic memory adaptive resonance theory (EEM-ART), categorizes and encodes experiences of a robot to the environment and generates a cognitive map. EEM-ART consists of multilayer ART networks to extract novel events and encode spatio-temporal connection as episodes by incrementally generating cognitive neurons. The model connects episodes to construct a sensorimotor map for the robot to continuously perform path planning and goal navigation. Experimental results for a mobile robot indicate that EEM-ART can process multiple sensory sources for learning events and encoding episodes simultaneously. The model overcomes perceptual aliasing and robot localization by recalling the encoded episodes with a new anticipation function and generates sensorimotor map to connect episodes together to execute tasks continuously with little to no human intervention.

DOI： 10.1109/TCDS.2018.2875309

Web of Science

researchmap

Dynamic Density Topological Structure Generation for Real-Time Ladder Affordance Detection 査読

Azhar Aulia Saputra, Wei Hong Chin, Yuichiro Toda, Naoyuki Takesue, Naoyuki Kubota

2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) 3439 - 3444 2019年

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：IEEE

This paper presents a method with dynamic density topological structure generation for low-cost real-time vertical ladder detection from 3D point cloud data. Dynamic Density Growing Neural Gas (DD-GNG) is proposed to generate a dynamic density of the topological structure. The density of the structure and the number of nodes will be increased in the targeted object area. Feature extraction model is required to classify suspected objects for being processed in the next time process. After that, rungs of the vertical ladder is processed using an inlier-outlier method. Thus, the ladder detection model represents the ladder with a set of nodes and edges. Next, affordance detection is processed for detecting the feasible grasped location. To validate the effectiveness of the proposed method, a series of experiments are conducted on a 4-legged robot with a non-GPU board for real-time vertical ladder detection and climbing to validate the effectiveness of the proposed method. Results show that our proposed method able to detect and track the ladder structure in real-time with a much lower computational cost. The affordance of the ladder provides safety information for robot grasping.

Web of Science

researchmap

A Novel Capabilities of Quadruped Robot Moving through Vertical Ladder without Handrail Support 査読

Azhar Aulia Saputra, Yuichiro Toda, Naoyuki Takesue, Naoyuki Kubota

2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) 1448 - 1453 2019年

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：IEEE

This paper presents the novel capabilities of a quadruped robot by performing horizontal-vertical-horizontal movement transition through vertical ladder without handrailing supporter. To overcome the proposed problem, we propose a multi-behavior generation model using independent stepping and pose control in the quadruped robot. The model is able to generate appropriate behavior depending on external (3D point clouds) and internal sensors (ground touch sensor, and Inertial Measurement Unit). Posture condition, safe movement area, possible touchpoint, grasping possibility, and target movement are the information that is analyzed from the sensors. There are four options developed in behavior generation, which are, Approaching, Body Placing, Stepping, and Grasping behavior. In order to prove the effectiveness of the proposed algorithm, the model was implemented on the computer simulation and the real application. Before being applied in the real robot, the proposed model is optimized in the computer simulation. Then, the optimized parameter is used for applying in the real robot. As a result, the robot succeeded to move through the ladder without handrail from lower stair to upper stair. From the analysis, the body placing behavior is the most important strategy in the proposed case.

Web of Science

researchmap

WAREC-1 – A Four-Limbed Robot with Advanced Locomotion and Manipulation Capabilities 査読

Kenji Hashimoto, Takashi Matsuzawa, Xiao Sun, Tomofumi Fujiwara, Xixun Wang, Yasuaki Konishi, Noritaka Sato, Takahiro Endo, Fumitoshi Matsuno, Naoyuki Kubota, Yuichiro Toda, Naoyuki Takesue, Kazuyoshi Wada, Tetsuya Mouri, Haruhisa Kawasaki, Akio Namiki, Yang Liu, Atsuo Takanishi, Satoshi Tadokoro

128 327 - 397 2019年

自律移動ロボットによる未知環境の位相構造獲得と目標物への経路学習査読

岩朝睦美, 戸田雄一郎, 新井智之, 久保田直行

システム制御情報学会論文誌 32 ( 6 ) 2019年

予測可能な移動障害物のある環境における時空間グラフを用いた大域的経路探索と行動計画査読

岩朝睦美, 戸田雄一郎, 久保田直行

日本機械学会論文集(Web) 85 ( 876 ) 18 - 00254 2019年

Guidance Control and Docking of Remote Operated Vehicles 査読

Xiang Li, Yuichirou Toda, Mamoru Minami

24th International Symposium on Artificial Life and Robotics 2019年

Improving pose estimation accuracy and expanding of visible space of lighting 3D marker in turbid water 査読

Horng-Yi Hsu, Naoki Mukada, Daiki Yamada, Khin I Lwin, Myo Myint, Yuichiro Toda, Takayuki Matsuno, Keigo Watanabe, Mamoru Minami

Proceedings of 2019 IEEE Underwater Technology 2019年

Needle Angle Offset Compensation Based on Volume CT Image for Needle Puncture Robot 査読

Takayuki Matsuno, Tetsushi Kamegawa, Takao Hiraki, Yuichiro Toda, Mamoru Minami

24th International Symposium on Artificial Life and Robotics 2019年

Neuro-Activity-Based Dynamic Path Planner for 3-D Rough Terrain 査読

Azhar Aulia Saputra, Yuichiro Toda, Janos Botzheim, Naoyuki Kubota

IEEE Transactions on Cognitive and Developmental Systems 10 ( 2 ) 138 - 150 2018年6月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Institute of Electrical and Electronics Engineers Inc.

This paper presents a natural mechanism of the human brain for generating a dynamic path planning in 3-D rough terrain. The proposed paper not only emphasizes the inner state process of the neuron but also the development process of the neurons in the brain. There are two algorithm processes in this proposed model, the forward transmission activity for constructing the neuron connections to find the possible way and the synaptic pruning activity with backward neuron transmission for finding the best pathway from current position to target position and reducing inefficient neuron with its synaptic connections. In order to respond and avoid the unpredictable obstacle, dynamic path planning is also considered in this proposed model. An integrated system for applying the proposed model in the real cases is also presented. In order to prove the effectiveness of the proposed model, we applied it in the pathway of a four-legged robot on rough terrain in both computer simulation and real cases. Unpredictable collision is also performed in those experiments. The model can find the best pathway and facilitate the safe movement of the robot. When the robot found an unpredictable collision, the path planner dynamically changed the pathway. The proposed path planning model is capable to be applied in further advance implementation.

DOI： 10.1109/TCDS.2017.2711013

Web of Science

Scopus

researchmap

Path planning of the autonomous mobile robot by using real-time rolling risk estimation with fuzzy inference 査読

Mutsumi Iwasa, Yuichiro Toda, Azhar Aulia Saputra, Naoyuki Kubota

2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings 2018- 1 - 6 2018年2月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：Institute of Electrical and Electronics Engineers Inc.

Along with the advancement of research on intelligent robotics, the situation where the robot moves independently and performs work in real environment is expanding. In such situation, it is one of the highest priority for the autonomous mobile robot to reach the destination point without failure. Therefore, we consider the transfer of the mobile robot on pre-planned paths to a partially observed environment. When the mobile robot encounters danger in the observing environment and determines to take a detour, it is necessary to re-plan safe routes in a short time. In this study, we focused on the rollover risk of mobile robot. And we simulate the autonomous rerouting of the mobile robot for finding a more secure route such that it can safely arrive at the destination point, whenever it senses high possibility of rollover. By using fuzzy inference to judge rollover risk, the mobile robot judges the necessity of route change according to the magnitude of risk. We also aimed to quickly perform rerouting by using the D∗ Lite algorithm in real-time for robot movement. We propose a method to realize route planning modification based on evaluation and judgment of rollover risk by combining fuzzy inference and D∗ Lite algorithm. As a result, we confirm that the autonomous mobile robot can reach the destination point by real-time evaluation of the risk and taking detour action as necessary. Experiments are conducted through computer simulation using a virtual mobile robot and a 3D path based on graph theory. Finally, we discuss about the result of the simulation.

DOI： 10.1109/SSCI.2017.8285367

Web of Science

Scopus

researchmap

Topological Structure Learning Based Enclosing Formation Behavior for Monitoring System. 査読

Yuichiro Toda, Naoyuki Kubota

IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Miyazaki, Japan, October 7-10, 2018 831 - 836 2018年

A Multi-channel Episodic Memory Model for Human Action Learning and Recognition. 査読

Kunpei Kato, Wei Hong Chin, Yuichiro Toda, Naoyuki Kubota

IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Miyazaki, Japan, October 7-10, 2018 843 - 849 2018年

Integrated Robotic Control System for Public Nursing. 査読

Wei Quan, Yuichiro Toda, Jinseok Woo, Naoyuki Kubota

2018 World Automation Congress, WAC 2018, Stevenson, WA, USA, June 3-6, 2018 1 - 5 2018年

Intelligent Control of Variable Ranging Sensor Array Using Multi-objective Behavior Coordination. 査読

Sasuga Kitai, Yuichiro Toda, Naoyuki Takesue, Kazuyoshi Wada, Naoyuki Kubota

Intelligent Robotics and Applications - 11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9-11, 2018, Proceedings, Part I 10984 393 - 403 2018年

An Episodic Memory Model with Slow Features Extraction for Topological Map Building. 査読

Wei Hong Chin, Yuichiro Toda, Naoyuki Kubota, Jinseok Woo, Chu Kiong Loo

International Symposium on Micro-NanoMechatronics and Human Science, MHS 2018, Nagoya, Japan, December 9-12, 2018 1 - 6 2018年

The Return Way Path Planning of an Autonomous Mobile Robot considering Traveling Risk of the Road. 査読

Mutsumi Iwasa, Yuichiro Toda, Naoyuki Kubota

2018 Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) and 19th International Symposium on Advanced Intelligent Systems (ISIS), Toyama, Japan, December 5-8, 2018 1406 - 1409 2018年

Reinforcement Learning Based on State Space Model using Growing Neural Gas for a Mobile Robot. 査読

Tomoyuki Arai, Yuichiro Toda, Iwasa Mutsumi, Shuai Shao, Ryuta Tonomura, Naoyuki Kubota

　前のページ - 次のページ　

<戸田 雄一郎>

論文 - 戸田 雄一郎

<戸田　雄一郎>

論文 - 戸田　雄一郎