研究者詳細 - 戸田　雄一郎

論文 - 戸田　雄一郎

分割表示 96 件中 61 - 80 件目／全件表示 >>

Improvement of 3D Pose Estimation Abilities by Light-Emitting-3D Marker for AUV Docking

Kohei Yamashita, Hsu Horng Yi, Daiki Yamada, Naoki Mukada, Khin New Lwin, Myo Myint, Yuichiro Toda, Takayuki Matsuno, Mamoru Minami

OCEANS 2018 MTS/IEEE CHARLESTON 2018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

Disturbances of turbidity and low illuminance are problems in real sea areas when recognizing objects with cameras. Therefore, the recognition target was made to emit light so that it can be recognized correctly even in that environment. However, a suitable light intensity of the target was not decided and it is obvious that recognition results was changed by light intensity of the target. This paper presents the analysis of recognition accuracy of the Real-time 3D estimation system by changing the current value of each color LED (red, green, blue) under turbid and low illuminance. Recognition experiments were conducted at the distance 600 [mm] between the ROV and 3D marker. The turbidity level was set constant value. The current value was changing from 0 [mA] to 16 [mA] for each LED individually. The best current for each LED was optimized by the fitness value and estimation value of position and orientation. The results showed that the recognition accuracy of the proposed system was improved by using optimized lighting intensity.

Applying Lighting Marker and Stereo-vision to V-shaped-thruster Vehicle for AUV Deep Sea Docking

Yoshiki Kanda, Myo Myint, Naoki Mukada, Daiki Yamada, Khin Lwin, Takayuki Matsuno, Yuichiro Toda, Mamoru Minami

OCEANS 2018 MTS/IEEE CHARLESTON 2018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

A stereo-vision-based system of autonomous under-water vehicles (AUVs) for sea-bottom docking that enables for battery recharging to extend persistence time of underwater operation has been developed. This paper presents the docking experiment using a developed V-shaped-thruster typed under-water vehicle. A real-time 3D pose (position and orientation) estimation method using a real-time multi-step genetic algorithm (RM-GA) has been proposed by the authors in previous works and used for docking based on 3D recognition as a feedback pose information in real-time, named as 3D Move on Sensing (3D-MoS). Sea docking experiment results have confirmed the functionality and practicality of proposed docking approach using a hovering typed ROV in previous works. Since the hovering typed underwater vehicles are limited in mobilities concerning speed and operational space, verification of the 3D-MoS system using underwater vehicle that has more mobility deem to be meaningful direction for vision-based docking system to expand the utility value of AUVs. Therefore, in this study, control system for a new V-shaped-thruster typed vehicle is developed and docking experiment is conducted. This paper presents the development of the hardware design of V-shaped-thruster typed underwater vehicle and improvement of controlling with consideration of coupled configuration of thrusters.

Development of Dual-eyes Docking System for AUV with Lighting 3D Marker

Sho Nakamura, Daiki Yamada, Naoki Mukada, Myo Myint, Khin New Lwin, Takayuki Matsuno, Yuichiro Toda, Mamoru Minami

OCEANS 2018 MTS/IEEE CHARLESTON 2018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 that our proposed docking system could apply for a new Remotely Operated Vehicle(ROV). The authors have proposed a 3D-perception based Move on Sensing (3D-MoS) system using a new 3D position and orientation (pose) estimation method with dual-eye camera that exploits the parallactic nature that enables reliable 3D pose estimation in real-time, named as "Real-time Multi-step Genetic Algorithm (RM-GA)." We confirmed ROV have conducted docking that assumes charging battery under water by the system, having shown it effective. As a next step, docking experiment using the new ROV were conducted to verify the proposed system apply for new ROV. But, the new ROV is different from a ROV that have used previous experiments, on the point of thruster setting structure. Then, a new control system using Jacobian that shows relationship voltage and velocity was constructed. After it is confirmed the system is effective, docking experiments In the pool have been conducted. In this report, the structure and result of experiments are reported in detail.

Unsupervised neural network based topological learning from point clouds for map building. 査読

Yuichiro Toda, Wei Hong Chin, Naoyuki Kubota

International Symposium on Micro-NanoMechatronics and Human Science, MHS 2017, Nagoya, Japan, December 3-6, 2017 1 - 6 2017年

An odometry-free approach for simultaneous localization and online hybrid map building

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

Frontiers Robotics AI 3 ( NOV ) 2016年11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：FRONTIERS MEDIA SA

In this article, we propose a new approach for mobile robot localization and hybrid map building simultaneously without using any odometry hardware system. The proposed method termed as Genetic Bayesian ARAM comprises two main components: (1) steady-state genetic algorithm (SSGA) for self-localization and occupancy grid map building and (2) Bayesian Adaptive Resonance Associative Memory (ARAM) for online topological map building. The model of the explored environment is formed as a hybrid representation, both topological and grid based, and it is incrementally constructed during the exploration process. During occupancy map building, the robot-estimated self-position is updated by SSGA. At the same time, the robot-estimated self-position is transmitted to Bayesian ARAM for topological map building and localization. The effectiveness of our proposed approach is validated by a number of standardized benchmark datasets and real experimental results carried on the mobile robot. Benchmark datasets are used to verify the proposed method capable of generating topological map in different environment conditions. Real robot experiment to verify the proposed method can be implemented in real world.

DOI： 10.3389/frobt.2016.00068

Evolution strategy sampling consensus for robust estimator 査読

Yuichiro Toda, Naoyuki Kubota

Journal of Advanced Computational Intelligence and Intelligent Informatics 20 ( 5 ) 788 - 802 2016年9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：Fuji Technology Press

RANdom SAmple Consensus (RANSAC) has been applied to many 3D image processing problems such as homography matrix estimation problems and shape detection from 3D point clouds, and is one of the most popular robust estimator methods. However, RANSAC has a problem related to the trade-off between computational cost and stability of search because RANSAC is based on random sampling. Genetic Algorithm SAmple Consensus (GASAC) based on a population-based multi-point search was proposed in order to improve RANSAC. GASAC can im-prove the performance of search. However, it is sometimes difficult to maintain the genetic diversity in the search if the large size of outliers is included in a data set. Furthermore, a computational time of GASAC sometimes is slower than that of RANSAC because of calculation of the genetic operators. This paper proposes Evolution Strategy SAmple Consensus (ESSAC) as a new robust estimator. ESSAC is based 011 Evolution Strategy in order to maintain the genetic diversity. In ESSAC, we apply two heuristic searches to ESSAC. One is a search range control, the other is adaptive/self-adaptive mutation. By applying these heuristic searches, the trade-off between computational speed and search stability can be improved. Finally, this paper shows several experimental results in order to evaluate the effectiveness of the proposed method.

DOI： 10.20965/jaciii.2016.p0788

Multi-channel Bayesian Adaptive Resonance Associate Memory for on-line topological map building 査読

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

APPLIED SOFT COMPUTING 38 269 - 280 2016年1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：ELSEVIER SCIENCE BV

In this paper, a new network is proposed for automated recognition and classification of the environment information into regions, or nodes. Information is utilized in learning the topological map of an environment. The architecture is based upon a multi-channel Adaptive Resonance Associative Memory (ARAM) that comprises of two layers, input and memory. The input layer is formed using the Multiple Bayesian Adaptive Resonance Theory, which collects sensory data and incrementally clusters the obtained information into a set of nodes. In the memory layer, the clustered information is used as a topological map, where nodes are connected with edges. Nodes in the topological map represent regions of the environment and stores the robot location, while edges connect nodes and stores the robot orientation or direction. The proposed method, a Multi-channel Bayesian Adaptive Resonance Associative Memory (MBARAM) is validated using a number of benchmark datasets. Experimental results indicate that MBARAM is capable of generating topological map online and the map can be used for localization. (C) 2015 Elsevier B.V. All rights reserved.

DOI： 10.1016/j.asoc.2015.09.031

Real-time 3D Point Cloud Segmentation using Growing Neural Gas with Utility 査読

Yuichiro Toda, Hui Yu, Zhaojie Ju, Naoyuki Takesue, Kazuyoshi Wada, Naoyuki Kubota

2016 9TH INTERNATIONAL CONFERENCE ON HUMAN SYSTEM INTERACTIONS (HSI) 418 - 422 2016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 proposes a real-time feature extraction and segmentation method for a 3D point cloud. First of all, we apply Growing Neural Gas with Utility (GNG-U) to the point cloud for learning a topological structure. However, the standard GNG-U cannot learn the topological structure of 3D space environment and color information simultaneously. To this end, we then modify the GNG-U algorithm by using a weight vector. we propose a surface feature extraction and segmentation method by efficiently utilizing the topological structure. Our segmentation method is based on a region growing method whose similarity value uses the inner value of two normal vectors connected by the topological structure. We show experimental results of the proposed method and discuss the effectiveness of the proposed method.

DOI： 10.1109/HSI.2016.7529667

Intensity Histogram Based Segmentation of 3D Point Cloud Using Growing Neural Gas 査読

Shin Miyake, Yuichiro Toda, Naoyuki Kubota, Naoyuki Takesue, Kazuyoshi Wada

INTELLIGENT ROBOTICS AND APPLICATIONS, ICIRA 2016, PT II 9835 335 - 345 2016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：SPRINGER INT PUBLISHING AG

This paper proposes a 3D point cloud segmentation method using a reflection intensity of Laser Range Finder (LRF). In this paper, we use LRF and tilt unit for acquiring a 3D point cloud. First of all, we apply Growing Neural Gas (GNG) to the point cloud for learning a topological structure of the point cloud. Next, we proposed a segmentation method based on an intensity histogram that is composed of the nearest data of each node. Finally, we show experimental results of the proposed method and discuss the effectiveness of the proposed method.

DOI： 10.1007/978-3-319-43518-3_33

Bézier curve model for efficient bio-inspired locomotion of low cost four legged robot. 査読

Azhar Aulia Saputra, Nuo Wi Noel Tay, Yuichiro Toda, ános Botzheim, Naoyuki Kubota

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016, Daejeon, South Korea, October 9-14, 2016 4443 - 4448 2016年

Simultaneous Localization and Mapping Based on (μ+1)-Evolution Strategy for Mobile Robots. 査読

Yuichiro Toda, Naoyuki Kubota

Intelligent Robotics and Applications - 8th International Conference, ICIRA 2015, Portsmouth, UK, August 24-27, 2015, Proceedings, Part III 9246 62 - 69 2015年

Genetic Bayesian ARAM for Simultaneous Localization and Hybrid Map Building 査読

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

2015 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI) 275 - 279 2015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 new framework for mobile robot to perform localization and build topological-metric hybrid map simultaneously. The proposed framework termed as Genetic Bayesian ARAM consists of two main components: 1) Steady state genetic algorithm (SSGA) for self-localization and occupancy grid map building and 2) Bayesian Adaptive Resonance Associative Memory (ARAM) for topological map building. The proposed method is validated using a mobile robot. Result show that Genetic Bayesian ARAM capable of generate hybrid map online and perform localization simultaneously.

DOI： 10.1109/SSCI.2015.48

Behavior Analysis of Evolution Strategy Sample Consensus 査読

Yuichiro Toda, Naoyuki Kubota

2014 10TH FRANCE-JAPAN/ 8TH EUROPE-ASIA CONGRESS ON MECATRONICS (MECATRONICS) 250 - 255 2014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

Recently, robust estimators are expected in various fields such as signal processing and machine learning. In our previous work, we proposed Evolution Strategy Sample Consensus (ESSAC) as a new robust estimator method and improved a trade off between a calculation time and stability of SAmple Consensus (SAC) algorithms. In this paper, we show several experiments for behavior analysis of ESSAC in order to discuss why ESSAC enable to search stably in the dataset including the huge number of noises. and analyze several experiments related with the fitness function of SAC and the behavior of ESSAC.

Self-Localization Based on Multiresolution Map for Remote Control of Multiple Mobile Robots 査読

Yuichiro Toda, Naoyuki Kubota

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 9 ( 3 ) 1772 - 1781 2013年8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：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

This paper proposes a localization method using multiresolution maps for the navigation of multiple mobile robots based on formation behaviors. The remote control of multiple mobile robots is one the most important tasks in robotics to realize distributed remote monitoring in unknown and/or dynamic environments. However, it is very difficult for a human operator to control multiple mobile robots separately at the same time. Therefore, autonomous formation behaviors of multiple robots are required to reduce mental and physical loads of the human operator. If each mobile robot can estimate the self-position or relative position in a group, it is easier for multiple mobile robots to realize formation behaviors. First, we propose a method of simultaneous localization and mapping based on a grid approach. Next, we explain how to share the build map among multiple mobile robots, and propose a self-localization method based on multiresolution maps. Furthermore, we explain the formation behaviors of multiple mobile robots. Finally, we show several experimental results, and discuss the effectiveness of the proposed method.

DOI： 10.1109/TII.2013.2261306

Initial Self-localization Based on Shared Information for Multi-robot Teleoperation System 査読

Shintaro Suzuki, Yuichiro Toda, Naoyuki Kubota

2013 PROCEEDINGS OF SICE ANNUAL CONFERENCE (SICE) 2721 - 2726 2013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 proposes a localization method using shared information for teleoperation of multiple robots based on formation behaviors. The localization is one of the most important capabilities. However, other robots can be considered as unknown objects when a mobile robot performs initial self-localization. It is difficult to estimate the initial position if the other robots enter the sensing range of the mobile robot. However, the robot can perform the initial self-localization more efficiently by sharing the map information and each self-position. Therefore, we propose a method of effective initial self-localization using the position information of the other mobile robots and the subtracted measurement data of LRF for multi-robot systems. Finally, we show several experimental results, and discuss the effectiveness of the proposed method.

Attention allocation for multi-modal perception of human-friendly robot partners 査読

Yuichiro Toda, Naoyuki Kubota

IFAC Proceedings Volumes (IFAC-PapersOnline) 12 ( 1 ) 324 - 329 2013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：International Federation of Automatic Control

This paper proposes a method of attention allocation for multi-modal perception of humanfriendly robot partners based on various types of sensors built in a smart phone. First, we propose human and object detection method using octagonal templates based on evolutionary robot vision. Next, we propose an integration method for estimating human behaviors based on the human detection using color image by the multi-layered spiking neural network using the time series of positions of human and object. Furthermore, we propose a method of attention allocation based on the time series of human behavior recognition. Finally, we show several experimental results of the proposed method, and discuss the future direction on this research. Copyright © 2013 IFAC.

DOI： 10.3182/20130811-5-US-2037.00054

Feature Extraction based on Hierarchical Growing Neural Gas for Informationally Structured Space 査読

Yuichiro Toda, Naoyuki Kubota

2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) 1 - 7 2013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 proposes a method of feature extraction from 3D point clouds for informationally structured space including sensor networks and robot partners for co-existing with people. The informationally structured space realizes the quick update and access of valuable and useful information for both people and robots on real and virtual environments. Our method is based on Hierarchical Growing Neural Gas (HGNG). This method is one of self-organizing neural network based on unsupervised learning First, we propose 3D map building method using Kinect in order to acquire the 3D point clouds. Next, we propose the method of the feature extracting method based on HGNG. Finally, we show experimental results of the proposed method and discuss the effectiveness of the proposed method.

DOI： 10.1109/IJCNN.2013.6706825

Cooperative Formation of Multi-robot Based on Spring Model 査読

Naoyuki Kubota, Yuichiro Toda, Shintaro Suzuki

2013 SECOND INTERNATIONAL CONFERENCE ON ROBOT, VISION AND SIGNAL PROCESSING (RVSP) 72 - 77 2013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 proposes a method of constituting the formation of a multi-robot system for exploration and monitoring. First, we apply a method of multi-objective behavior coordination for integrating behavior outputs from the fuzzy control for collision avoidance and target tracing. Second, we apply a spring model to calculate the temporary target position of each robot for the formation behavior. Third, we constitute monitoring formation, which is realized by enclosing behavior of multi-robot. Finally, we discuss the effectiveness of the proposed method through several simulation results.

DOI： 10.1109/RVSP.2013.24

Multimodal Communication for Human-Friendly Robot Partners in Informationally Structured Space 査読

Naoyuki Kubota, Yuichiro Toda

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS 42 ( 6 ) 1142 - 1151 2012年11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：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

This paper proposes a multimodal communication method for human-friendly robot partners based on various types of sensors. First, we explain informationally structured space to extend the cognitive capabilities of robot partners based on environmental systems. Next, we discuss the suitable measurement range for recognition technologies of touch interface, voice recognition, human detection, gesture recognition, and others. Based on the suitable measurement ranges, we propose an integration method to estimate human behaviors based on the human detection using color image and 3-D distance information, and gesture recognition by the multilayered spiking neural network using the time series of human-hand positions. Furthermore, we propose a conversation system to realize the multimodal communication with a person. Finally, we show several experimental results of the proposed method, and discuss the future direction of this research.

DOI： 10.1109/TSMCC.2012.2213810

Bacterial memetic algorithm for simultaneous optimization of path planning and flow shop scheduling problems 査読

János Botzheim, Yuichiro Toda, Naoyuki Kubota

Artificial Life and Robotics 17 ( 1 ) 107 - 112 2012年10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：Springer Tokyo

The paper deals with simultaneous optimization of path planning of mobile robots and flow shop scheduling problem. The goal of the path planning problem is to determine an optimal collision-free path between a start and a target point for a mobile robot in an environment surrounded by obstacles. The objective is to minimize the path length without colliding with an obstacle. On the other hand, shop scheduling problems deal with processing a given set of jobs on a given number of machines. Each operation has an associated machine on which it has to be processed for a given length of time. The problem is to minimize the overall time demand of the whole process. In this paper, we deal with two robots carrying items between the machines. Bacterial memetic algorithm is proposed for solving this combined problem. The algorithm is verified by experimental simulations and compared to classical techniques.

DOI： 10.1007/s10015-012-0021-9

　前のページ - 次のページ　

1
2
3
4
5