著者
井上 博允 溝口 博 稲葉 雅幸 池端 重樹 磯貝 文彦
出版者
公益社団法人 計測自動制御学会
雑誌
計測自動制御学会論文集 (ISSN:04534654)
巻号頁・発行日
vol.23, no.12, pp.1289-1295, 1987-12-30 (Released:2009-03-27)
参考文献数
14
被引用文献数
5

This paper describes a versatile multi-window vision system, which is developed for providing robots with flexible and multiple visual attention capability. Chapter 1 is introduction. A window is a local region to be processed for one attention. The multi window vision system provides a large number of windows. The location, shape, size, and resolution of each window can be controlled by a special LSI, independently and simultaneously. In Chapter 2, we describes the concept and architecture of the multi window vision system. The multi window vision system is designed to build a pandemonium model by means of multi microprocessors. In order to avoid the image access bottleneck in parallel processing, we introduced a transmiter-receiver into the multi window vision system. Chapter 3 describes the transmitter unit which broadcasts input images to the window receivers. In Chapter 4, the details of the logic circuits inside the window control LSI is described. The LSI chip controls window parameters which are location, size, shape, spatial sampling rate, window memory access, and the display of the window image. In Chapter 5, the image processing unit that implements the LSI chips is described. Chapter 6 shows the experimental results using the image processing unit. Chapter 7 is Concluding Remarks.
著者
小島 邦生 唐澤 達史 上月 豊隆 黒岩 英則 柚木崎 創 岩石 智志 石川 達矢 小山 遼 野田 晋太朗 植田 亮平 菅井 文仁 野沢 峻一 垣内 洋平 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.34, no.7, pp.458-467, 2016 (Released:2016-10-01)
参考文献数
37
被引用文献数
2 2

This paper presents the development of high-speed and high-power humanoid robot research platform JAXON. Researchers have studied humanoid robots widely and people expect humanoid robots to help various tasks such as housework, entertainment, and disaster-relief. Therefore it is important to develop humanoid research platform available in various fields. We considered the following as design requirements necessary to utilize humanoids for various uses. 1) Robots have humanlike body proportion to work in infrastructure matched to human body structure. 2) Robots have the same degree of physical performance as humans. 3) Robots have energy sources such as batteries and act without tethers. 4) Robots walk with two legs or four limbs and continue to work without fatal damage in unexpected rollover. JAXON satisfied these requirements. Then we demonstrates the performance of JAXON through the experiment of getting out of a vehicle, stepping over walls, squatting with heavy barbels, walking with four limbs, and operating on batteries. Further more, we assesses the performance of the strong armor and the shock absorbing structure through a backward over-turning accident.
著者
田宮 幸春 稲葉 雅幸 井上 博允
出版者
日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.17, no.2, pp.268-274, 1999-03-15 (Released:2010-08-10)
参考文献数
12
被引用文献数
2 19

We have developed a balance compansating method for dynamic motions of a full-body humanoid standing on one leg. This method could compensate tri-axial moments in any motions, using all joints of body in real-time. In this method, costraint conditions for stable motion were calculated by using physical 3D model of the robot, and the output motion was determined by solving an optimization problem so that the output should be closest to the input under the constraints. The proposed method had high generality because of independence of joints arrangement of robot. This paper describes the algorithm of the method and an experiments applied on the 16D. O. F. humanoid in kick motion.
著者
浦田 順一 中西 雄飛 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.28, no.7, pp.865-871, 2010 (Released:2012-01-25)
参考文献数
9
被引用文献数
2 3

In this paper, we show a high power prototype biped robot for application of nursing or running or jumping motions. Light and powerful actuators are required to realize the high-power performance. We propose a method to bring out maximum performance of electric motors aggressively. The technique of motor core temperature estimation and control improves the motor power performance dramatically but safely without motor burnout. High power acctuator system and robust interbody network are depeloped for high power robot. Fundamental demonstrations of high power motion are shown.
著者
矢口 裕明 溝花 弘登 堀 慎太郎 笹渕 一宏 長濱 虎太郎 齋木 拓也 椎木 靖人 稲葉 雅幸
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.37, no.4, pp.319-329, 2019 (Released:2019-05-23)
参考文献数
40
被引用文献数
1

In this paper we describe a continuous development and evaluation of multi purpose platform robot AERO via robot competitions. We participated to 4 robot competitions requiring different task with human size semi humanoid robot AERO, has same basic structure. For many types of competition tasks, the robot was designed as simple, robust, small and lightweight, furthermore it can be change parts for another situation of task. The versatility of the robot platform was increased from continuation of task analyisis, consideration of requirements, and implementation. In this paper we describe a continuous integration of robot design, cycle of task analysis, implemetation and integration, via robot competition.
著者
伊藤 秀朗 室岡 雅樹 矢野倉 伊織 野沢 峻一 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本機械学会
雑誌
ロボティクス・メカトロニクス講演会講演概要集 2018 (ISSN:24243124)
巻号頁・発行日
pp.2A2-G12, 2018 (Released:2018-12-25)

In daily lives, it is necessary for robots to execute cooperative tasks with humans. Unlike tasks in factories, household chores don't have regular orders between each chore. The difficulty in such works is that the robot is expected to take adequate actions according to the human needs. In this paper, we proposed a system for executing cooperative tasks where robot motions are decided by imitating human motions, and the robot activates those motions according to the human aural instructions.
著者
稲葉 雅幸 水内 郁夫 岡田 慧 吉海 智晃 花井 亮 山崎 公俊 稲邑 哲也 五十棲 隆勝
出版者
東京大学
雑誌
基盤研究(S)
巻号頁・発行日
2004

本研究は, 等身大ヒューマノイドプラットフォームに対して, 視聴覚・全身触覚・動的全身反応行動などの高位の情報処理技術を搭載した知能ロボットカーネルを統合し, 人からの多様な働きかけに対して対応するための行動を実現するために必要な機能とシステム構成を明らかにした.
著者
浅野 悠紀 溝口 弘悟 上月 豊隆 茂木 陽太郎 白井 拓磨 浦田 順一 中西 雄飛 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.32, no.10, pp.887-894, 2014 (Released:2015-01-15)
参考文献数
14
被引用文献数
1 1

Human knee joint has a yaw-axis rotational DOF and a locking mechanism called screw-home mechanism(SHM). We focus on this mechanism and implement it to a musculoskeletal humanoid through hardware design. In this paper, we first explained human knee characteristic of SHM and joint range of motion. Next, we explained hardware design and implementation method of the mechanism. As an evaluation of our developed knee joint, we checked the function of SHM from viewpoint of moment arm of the yaw rotational axis and the yaw angle displacement during squat motion. Lastly, as unique and integrated motions that involve the use of yaw DOF derived from SHM, we made several motion achievement including humanlike twisting squat, heel move motion and switch pedals, under a condition of contacting environment. This result demonstrates human mimetic rotational DOF of knee contributes motion achievement.
著者
川崎 宏治 趙 漠居 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.33, no.4, pp.285-291, 2015 (Released:2015-06-15)
参考文献数
12
被引用文献数
1

In our research, we focus on the information collection in multi-field by aerial vehicle. We develop hardware mechanism generating more efficient lift power to achieve the ability to tilt with continuous and infinite rotation and keep arbitrary tile angle while flying. In this work, we propose a new mechanism for aerial robot including four propellers separated to two mutually connected bi-copter modules. We call this new aerial robot Bi2Copter. With the proposed mechanism, we are able to realize take-off, landing and flight under vertical orientation of body, leading to the feasibility of image capture with full 360° spherical coverage as well as exploration and measurement parallel to the target surface of which curvature changes continuously. This paper presents the motivation to this new aerial robot, the design of proposed mechanism and flight control accompanied with experiment results.
著者
槙 俊明 野沢 峻一 神崎 秀 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本機械学会
雑誌
ロボティクス・メカトロニクス講演会講演概要集 2008 (ISSN:24243124)
巻号頁・発行日
pp._2A1-D18_1-_2A1-D18_3, 2008-06-06 (Released:2017-06-19)

Humanoids are expected to expand their playing field outside the laboratory. To widen their appeal, environment contaction works such as door opening, object transport are something that must be done. Researches on environment contaction motion s that have been done are often premised physical parameters about unknonw objects. However, to manipulate unknonw objects in the unknown environment, acquisition of target's physical model by humanoids will be needed. In this paper, we firstly categorize model estimations required for unknonw object operation. Then, we estimate physical model of a door offline. And using this model, we realize door opening motion by HRP2-JSK.
著者
種本 雅 長谷川 峻 岡田 慧 稲葉 雅幸
出版者
公益社団法人 計測自動制御学会
雑誌
計測自動制御学会論文集 (ISSN:04534654)
巻号頁・発行日
vol.58, no.6, pp.290-303, 2022 (Released:2022-06-21)
参考文献数
25

Housekeeping robot must grow as it lives with the user. To build a system that can serve as a foundation for this purpose, we need to discover what we need to research further through the realization of a housework support task by a robot, and need to solve these problems. In this paper, we tackle the task of bento-serving as a household chore support task, and describe new problems that we discovered through the implementation of it. As for the bento-serving, it has been assumed that the robot performs the task in a factory. In this paper, we reconsider the bento-serving task by a robot as a part of our household support and propose a system to make it happen. When a housework assistance robot does the bento-serving, he needs to recognize the prepared foods and environment, interact with the owner, and manipulate foods without destroying them. Through the realization of the bento-serving task, we found that the housekeeping robot has to deal with objects of the same type but with different shapes, plan movements with user preferences in mind, and perform the entire sequence of actions by himself. To achieve these goals, we propose a system consisting of five processes, recognition of the environment and food, acquisition of information through dialogue, storage of the information, devising a goal using the acquired information, and manipulation of the objects using tools.
著者
稲葉 雅幸 岡田 慧 水内 郁夫 稲邑 哲也
出版者
一般社団法人日本ソフトウェア科学会
雑誌
コンピュータソフトウェア (ISSN:02896540)
巻号頁・発行日
vol.23, no.2, pp.45-61, 2006-04-26
被引用文献数
4

ロボットは身体ハードウェアが決まればその身体にとっての認識と行動のソフトウェアをプログラミングする対象である.近年のロボットは人間のような姿形に近づいたヒューマノイドロボットの研究が進んでいる.本稿では,幾何モデルを搭載したオブジェクト指向言語Euslispにより,人間型のロボットを対象に小型から等身大,筋駆動型ヒューマノイドのロボットプログラミング環境を実装している研究をとりあげ,身体ハードウェアが進化してもソフトウェアの継承を行いながら発展させてきている環境を紹介する.
著者
矢口 裕明 長谷川 貴巨 稲葉 雅幸
出版者
一般社団法人 日本機械学会
雑誌
ロボティクス・メカトロニクス講演会講演概要集
巻号頁・発行日
vol.2017, pp.1A1-C01, 2017

<p>In this paper, we propose the method of tomato fruit and pedicel recognition method using 3D camera for tomato harvesting robot. Recognition method is constructed by 2 parts; tomato fruits detection and tomato pedicel detection. To avoid detecting stem and pedicel of neighbor fruit, we propose a robust estimation method in pedicel direction calculation. We evaluated the proposed method in the greenhouse with real tomato trees, experimental result shows its robustness.</p>
著者
稲葉 雅幸 井上 博允
出版者
The Robotics Society of Japan
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.3, no.6, pp.538-547, 1985-12-15 (Released:2010-08-25)
参考文献数
10
被引用文献数
10 28

本論文は, ロボットにより紐を操作する際の視覚・行動系の協調動作に関する研究について述べたものである.紐のように柔構造の物体を操作するには視覚情報の利用が必要不可欠である.本研究では視覚情報を利用して動作を修正し, 動作結果をもとに注視する領域を制御し動作確認をするという協調動作の作業例として紐のハンドリングをとりあげる.本論文では, 視覚・行動系の協調動作の実現方法を解析し, 紐のハンドリング実験に用いたハンド・アイ・システムと視覚処理アルゴリズムについて述べる.協調動作を実現するための手法として, 局所領域を注視する視覚機能, 座標系間の較正, 視覚による動作確認, 視覚による操作量の修正法について述べる.紐の操作実験は紐をつかんでリングに通したあと, 紐をつかみ直して結ぶという一連の動作からなる.実験システムは, 両眼立体視システム, 6+1自由度アームシステム, 作業記述用のLispシステムからなる.線分領域の画像処理を組合せて対象を認識し, 両眼立体視によって3次元計測を行ない環境の認識と動作の制御を実現している.視覚により得られる情報を基に操作量を修正し, 動作の確認を視覚により行なうことによって, 柔軟な紐を3次元空間で操作することができるということを実験により確認した.
著者
熊谷 伊織 小林 一也 野沢 峻一 垣内 洋平 吉海 智晃 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.31, no.10, pp.985-991, 2013 (Released:2014-01-15)
参考文献数
10

When a humanoid robot works with a human, it is needed for the robot to pass and receive objects. The robot has to detect that the laden objects are operated by the human on the whole body in object passing tasks. It is important that the robot detects not only push but shear generated by pulling action and twist generated by rotating action for the robot to detect human operations. In this paper, we dispersedly arranged 347 multi-axis soft tactile sensors to a humanoid robot. The multi-axis soft tactile sensors are small muti-axis sensors with urethane structure and they can be placed densely on body of a humanoid. We calculate a deformation vector from the deformation of sensor's upper surface using the output of a muti-axis soft tactile sensor. Next, we suggest the method to detect deformation state in contact surface consisting of soft tactile sensors using deformation moment and average of deformation vectors in the contact surface. Finally, we confirmed the usefulness of the fullbody tactile sensor cover and contact state detector by object passing experiment between a human and a robot.
著者
北川 晋吾 岡田 慧 稲葉 雅幸
出版者
人工知能学会
雑誌
2019年度 人工知能学会全国大会(第33回)
巻号頁・発行日
2019-04-08

近年ロボットは倉庫や工場などの社会導入が推められており人のような双腕マニピュレーション動作を行うことが期待されている。本研究では複雑環境でのターゲットピッキングを対象とし、必要に応じて単腕・双腕を使い分けるピッキングシステムを構成することを目的とし、双腕ロボットによる自律学習型のターゲットピッキングシステムを提案する。まずロボットは自動生成したデータセットを用いて把持点と物体インスタンスの可視・遮蔽領域認識を学習し、その後実世界での把持試行を通して再学習を行う。最後に単腕・双腕を選択的に実行するターゲットピッキングシステムを構成し、実世界の複雑環境での検証実験を行う。
著者
矢口 裕明 長谷川 貴巨 長濱 虎太郎 稲葉 雅幸
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.36, no.10, pp.693-702, 2018 (Released:2019-01-15)
参考文献数
17
被引用文献数
4

In this paper we propse a construction method of autonomous tomato harvesting robot. For tomato harvesting we focus to harvesting device and visual recognition method. We propose 2 types of harvesting method; cutting scissor and rotational plucking gripper. For recognition, we compare different 3 types of 3D camera, then we construct tomato fruit recognition method using color detection and sphere shape fitting, and also propose tomato pedicel detection method by robust estimation using direction from center of fruit to pedicel and gradient orientation of pedicel edge. Combining these elements, we construct some autonomous harvesting systems and evaluate harvesting of real tomatoes in the tomato robot competition and the real farming veniel house. According to evaluation results, both cutting and plucking has different advantage and disadvantage, it is important to select appropriate one for breed or individual. Also for recognition, pedicel recognition, which must be broken, increases reliability harvesting.
著者
植田 亮平 ZAOPUTRA Nikolaus 西野 環 矢口 裕明 山崎 公俊 花井 亮 岡田 慧 稲葉 雅幸
出版者
一般社団法人 日本機械学会
雑誌
ロボティクス・メカトロニクス講演会講演概要集
巻号頁・発行日
vol.2008, pp._2P1-G11_1-_2P1-G11_4, 2008

In this paper, we present a method to obtain the depth of the building using a satellite image of Google Earth and GPS receiver. Maps with 3D information are useful for robot navigation. This method is based on "3D Street View", which is a 3D model of the building automatically created with laser range finder and fish eye lens camera.