专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2008023630A Arm-guiding moving body and method for guiding arm 有权
标题翻译： ARM指导移动体和引导ARM的方法
公开(公告)号：JP2008023630A
公开(公告)日：2008-02-07
申请号：JP2006196912
申请日：2006-07-19
申请人： Toyota Motor Corp , トヨタ自動車株式会社
发明人： RI KAIKEN , NAKAJIMA YUICHIRO , NOMURA HIDEKI
IPC分类号： B25J5/00 , B25J13/08
摘要： PROBLEM TO BE SOLVED: To provide an art capable of guiding an arm to a target object on an appropriate route without handling large data more than necessary when guiding both of a moving body and an arm movably connected to the body.
SOLUTION: This moving body is provided with a movable body and the arm movably connected to the body, and guides the arm to the target object. In the moving object, the moving route of the body is formed based on a global map and the moving route of the arm is formed based on a local map. The local map is updated based on the shape of surrounding environment and the position of the arm. The shape of the surrounding environment is recognized by measuring the distance from the body of the moving object to the surrounding environment.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：提供一种能够在适当的路线上将目标物体引导到目标物体上的技术，而不需要在可移动地连接到身体的移动体和臂上引导两者而不需要大量的数据。解决方案：该移动体设置有可移动体，臂可移动地连接到身体，并将臂引导到目标对象。在移动物体中，基于全局映射形成身体的移动路线，并且基于局部地图形成臂的移动路线。基于周围环境的形状和手臂位置更新本地图。通过测量从运动物体到周围环境的距离来识别周围环境的形状。版权所有（C）2008，JPO＆INPIT

2. 发明专利

JP2014106597A Autonomous moving body, object information acquisition device, and object information acquisition method 审中-公开
标题翻译：自动移动体，对象信息获取装置和对象信息获取方法
公开(公告)号：JP2014106597A
公开(公告)日：2014-06-09
申请号：JP2012257310
申请日：2012-11-26
申请人： Toyota Motor Corp , トヨタ自動車株式会社 , Tokyo Kogei Univ , 学校法人東京工芸大学
发明人： RI KAIKEN , KYO ARINOBU
IPC分类号： G05D1/02 , G06T7/60
摘要： PROBLEM TO BE SOLVED: To acquire object information of an object located around a moving body in an unknown environment.SOLUTION: An autonomous moving body includes: a current location specifying part which specifies a predetermined area corresponding to a current location of a moving body by means of known map information; a first storage part which stores an image of a predetermined object which is considered to be located in an area in substantially the same environment as the predetermined area; a second storage part which stores feature quantity extracted from the image of the predetermined object; an imaging device for capturing an image of the predetermined area; and an environment recognition machine. The environment recognition machine acquires the images of the predetermined objects considered to be located in the predetermined area from the first storage part, recognizes the acquired image of the object, as a recognition object, in the image of the predetermined area captured by the imaging device by use of the feature quantity of the recognition object acquired from the second storage part, determines that the recognition object is located in the predetermined area when the image recognition is successful, and outputs object information of the recognition object.
摘要翻译：要解决的问题：在未知环境中获取位于移动体周围的物体的物体信息。解决方案：自主移动体包括：当前位置指定部，其指定与移动体的当前位置相对应的预定区域已知地图信息的手段; 第一存储部，其存储被认为位于与所述预定区域基本相同的环境中的区域中的预定对象的图像; 第二存储部，其存储从所述预定对象的图像提取的特征量; 用于捕获所述预定区域的图像的成像装置; 和环境识别机。环境识别机从第一存储部分获取被认为位于预定区域中的预定对象的图像，将获取的对象图像作为识别对象识别在由成像装置拍摄的预定区域的图像中通过使用从第二存储部分获得的识别对象的特征量，在图像识别成功时确定识别对象位于预定区域中，并且输出识别对象的对象信息。

3. 发明专利

JP2013152673A Object recognition device, recognition method and recognition program 有权
标题翻译：对象识别装置，识别方法和识别程序
公开(公告)号：JP2013152673A
公开(公告)日：2013-08-08
申请号：JP2012013887
申请日：2012-01-26
申请人： Toyota Motor Corp , トヨタ自動車株式会社
发明人： RI KAIKEN
IPC分类号： G06T7/60 , G06T7/00
摘要： PROBLEM TO BE SOLVED: To highly accurately recognize an object in a prescribed area.SOLUTION: An object recognition device includes: first storage means for storing a plurality of feature quantities of prescribed objects; photographing means for photographing a prescribed area including a recognition object; feature quantity calculation means for calculating a feature quantity of the recognition object on the basis of the photographic image of the photographed recognition object; candidate extraction means for extracting a recognition object candidate from among the prescribed objects on the basis of the calculated feature quantity of the recognition object and the feature quantities of the prescribed objects stored in the first storage means; second storage means for storing positional relation information between the prescribed objects present in substantially the same environment area as the prescribed area; positional relation calculation means for calculating positional relation information on the recognition object in the prescribed area and surrounding prescribed object thereof from the photographic image in the photographed prescribed area; and determination means for determining the recognition object on the basis of the calculated positional relation information, the positional relation information stored in the second storage means and the recognition object candidate extracted by the candidate extraction means.
摘要翻译：要解决的问题：高度精确地识别规定区域中的物体。解决方案：一种物体识别装置，包括：第一存储装置，用于存储多个特征量的规定物体; 用于拍摄包括识别对象的规定区域的拍摄装置; 特征量计算装置，用于基于所拍摄的识别对象的摄影图像来计算识别对象的特征量; 候选提取装置，用于根据计算出的识别对象的特征量和存储在第一存储装置中的规定对象的特征量，从规定对象中提取识别目标候选; 第二存储装置，用于存储在与规定区域基本相同的环境区域中存在的规定对象之间的位置关系信息; 位置关系计算装置，用于从拍摄的规定区域中的摄影图像计算关于在规定区域中的识别对象及其周围规定对象的位置关系信息; 以及确定装置，用于基于所计算的位置关系信息，存储在第二存储装置中的位置关系信息和由候选提取装置提取的识别对象候选来确定识别对象。

4. 发明专利

JP2010131751A Mobile robot 有权
标题翻译：移动机器人
公开(公告)号：JP2010131751A
公开(公告)日：2010-06-17
申请号：JP2010057267
申请日：2010-03-15
申请人： Toyota Motor Corp , トヨタ自動車株式会社
发明人： NAKAJIMA YUICHIRO , RI KAIKEN , NOMURA HIDEKI
IPC分类号： B25J13/08
摘要： PROBLEM TO BE SOLVED: To provide a technique capable of always recognizing the whole area of a surrounding environment by eliminating an unknown environment generated by entering a part of a body such as a connection section at the operation of a robot into a visual field while a camera different from a camera prepared at a body core is arranged on the body core via a joint.
SOLUTION: The robot has the body core 103 made from a head and a body, at least one connection section 104 connected with the body core 103 via the driving shoulder joint 203, the body core-side cameras 105 in which at least one is arranged on the body core, and the connection section-side cameras 106 in which at least one is arranged on the connection section. Further, the robot has a composed image creating means for creating a composed image by composing both a body core-side image photographed by the body core-side camera 105 and a connection section-side image photographed by the connection section-side camera 106; and a recognition means for recognizing positions of peripheral objects by the composed image.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供一种技术，其能够通过消除在机器人的操作期间将诸如连接部分的主体的一部分进入视觉而产生的未知环境来始终识别周围环境的整个区域而通过接头将不同于准备在体芯上的相机的照相机布置在身体芯上。解决方案：机器人具有由头部和主体制成的主体芯体103，至少一个连接部分104经由驱动肩部接头203与主体芯103连接，主体芯侧相机105至少一个布置在主体芯上，并且连接部侧摄像机106中至少一个配置在连接部上。此外，机器人具有合成图像创建装置，用于通过组合由身体核心侧照相机105拍摄的身体核心侧图像和由连接部分侧相机106拍摄的连接部分侧图像来创建合成图像; 以及识别装置，用于通过合成图像识别周边物体的位置。版权所有（C）2010，JPO＆INPIT

5. 发明专利

JP2009140348A Behavior determination device, behavior learning device, and robot device 审中-公开
标题翻译：行为测定装置，行为学习装置和机器人装置
公开(公告)号：JP2009140348A
公开(公告)日：2009-06-25
申请号：JP2007317453
申请日：2007-12-07
申请人： Toyota Motor Corp , トヨタ自動車株式会社
发明人： RI KAIKEN , INAMURA TETSUYA , INABA MASAYUKI
IPC分类号： G06N5/04 , B25J5/00 , B25J13/00
CPC分类号： G06N3/008 , G05B2219/39441 , G10L15/26
摘要： PROBLEM TO BE SOLVED: To provide a behavior learning apparatus and method capable of constructing an intelligent determination system in which input information is modularized into a single information space, a behavior determination apparatus and method using a learning result generated by the behavior learning apparatus, a robot apparatus installed with these apparatuses. SOLUTION: The robot includes: a knowledge acquisition part 21 for extracting words from external instruction information; a network construction part 22 for constructing a network from the extracted words and updating weightings between the words; and a behavior determination part 23 for determining a behavior on the basis of the word network in which relationships between the words are weighted on a network. COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：提供一种能够构建将输入信息模块化为单个信息空间的智能确定系统的行为学习装置和方法，使用由行为学习产生的学习结果的行为确定装置和方法装置，安装有这些装置的机器人装置。解决方案：机器人包括：知识获取部分21，用于从外部指令信息中提取单词; 一个网络构造部分22，用于从提取出的单词中构建一个网络，并更新这些单词之间的加权; 以及行为确定部分23，用于确定在网络上对这些单词之间的关系加权的单词网络的行为。版权所有（C）2009，JPO＆INPIT

6. 发明专利

JP2009066693A Motion data generating device, method, and robot device 审中-公开
标题翻译：运动数据生成装置，方法和机器人装置
公开(公告)号：JP2009066693A
公开(公告)日：2009-04-02
申请号：JP2007236629
申请日：2007-09-12
申请人： Nara Institute Of Science & Technology , Research Organization Of Information & Systems , Toyota Motor Corp , トヨタ自動車株式会社 , 国立大学法人奈良先端科学技術大学院大学 , 大学共同利用機関法人情報・システム研究機構
发明人： RI KAIKEN , INAMURA TETSUYA , SHIBATA TOMOHIRO
IPC分类号： B25J9/22 , B25J5/00
摘要： PROBLEM TO BE SOLVED: To provide a motion data generating device which generates various motion patterns from a predetermined motion pattern, and also to provide a motion pattern generating method, a program, and a robot device.
SOLUTION: The motion data generating device has: a symbol generating section 12 which generates a new source symbol from two or more source symbols in a source symbol space where similar information between the source symbols is held, upon projection of the source symbols, based on a gap amount between the same; and a pattern generating section 13 which generates an output time sequence pattern from a state transition probability and an output probability of the new source symbol. The source symbol corresponds to a predetermined motion by which the state transition probability and the output probability are calculated by using a hidden Markov model, and the symbol generating section 12 converts the state transition probabilities of the two or more source symbols into information concerning a speed, and calculates the state transition probability of the new source symbol.
COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：提供一种从预定运动模式生成各种运动模式的运动数据生成装置，并且还提供运动模式生成方法，程序和机器人装置。运动数据产生装置具有：符号生成部分12，其在源符号空间中从源符号空间中的两个或更多个源符号生成新的源符号，其中源符号的投影被保持在源符号之间，，基于相同的间隙量; 以及模式生成部13，其从新的源符号的状态转移概率和输出概率生成输出时间序列模式。源符号对应于通过使用隐马尔可夫模型来计算状态转移概率和输出概率的预定运动，并且符号生成部12将两个或更多个源符号的状态转移概率转换为关于速度的信息，并计算新的源符号的状态转移概率。版权所有（C）2009，JPO＆INPIT

7. 发明专利

JP2012115913A System for providing service by robot, device and method for controlling robot 有权
标题翻译：用于机器人提供服务的系统，用于控制机器人的装置和方法
公开(公告)号：JP2012115913A
公开(公告)日：2012-06-21
申请号：JP2010264945
申请日：2010-11-29
申请人： Toyota Motor Corp , トヨタ自動車株式会社
发明人： RI KAIKEN , TRUNG LAM NGO , MIZUKAWA MAKOTO
IPC分类号： B25J13/00
摘要： PROBLEM TO BE SOLVED: To obtain a knowledge structure with high flexibility similar to those of human beings.SOLUTION: In a system 1 for providing a service by a robot 3, each layer is generated based on information acquired from information sources each having different nature where a relationship between elements is built based on a predetermined point of view in a plurality of layers. The system includes: a knowledge NW 11 including the plurality of layers; an ontology generation unit 12 which extracts, based on the information contained in a request task from a user, elements related to the information from the layers provided in the knowledge NW 11 and describes a relationship between the extracted elements and the information to generate task base ontology according to the request task; and a robot movement control unit 13 for controlling the movement of the robot 3 using the generated task base ontology.
摘要翻译：要解决的问题：获得与人类相似的高度灵活性的知识结构。解决方案：在用于由机器人3提供服务的系统1中，基于从具有不同性质的信息源获取的信息生成每个层，其中基于多个元素中的预定视点构建元素之间的关系的层。该系统包括：包括多层的知识NW11; 本体生成单元12，根据来自用户的请求任务中包含的信息，提取与来自知识NW11中提供的层的信息有关的元素，并描述所提取的元素与信息之间的关系以生成任务基础本体根据请求任务; 以及机器人运动控制单元13，用于使用所生成的任务基本本体来控制机器人3的移动。版权所有（C）2012，JPO＆INPIT

8. 发明专利

JP2008105132A Method and apparatus for producing path of arm in joint space 审中-公开
标题翻译：在联合空间生产ARM路径的方法和装置
公开(公告)号：JP2008105132A
公开(公告)日：2008-05-08
申请号：JP2006290171
申请日：2006-10-25
申请人： Toyota Central R&D Labs Inc , Toyota Motor Corp , トヨタ自動車株式会社 , 株式会社豊田中央研究所
发明人： RI KAIKEN , NOMURA HIDEKI
IPC分类号： B25J9/10 , B25J5/00
摘要： PROBLEM TO BE SOLVED: To provide a technique which produces the path of an arm in a joint space at a low calculation cost even when the order of the joint space is large and even when the joint space has been represented by being discretized in detail.
SOLUTION: The method for producing the path of the arm having a plurality of joints in the joint space comprises steps of: determining the position of the start point of the path; determining the position of the target point of the path; determining the position and the shape of an obstacle, a step of making the start point of the path an object point for evaluation; (A1) straightly elongating the path from the object point for evaluation to the target point when the obstacle does not exist between the object point for evaluation and the target point; (A2) straightly elongating the path in the direction tilting from the direction of the target point viewed from the object point for evaluation and making the tip end of the elongated path a new object point for evaluation when the obstacle exists between the object point for evaluation and the target point; and repeating each of the (A1) and (A2) steps until the path elongated from the start point reaches the target point.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：即使当接合空间的顺序很大并且即使当通过离散化表示接合空间时，提供以低的计算成本在接合空间中产生臂的路径的技术详细。解决方案：用于制造具有在关节空间中的多个关节的臂的路径的方法包括以下步骤：确定路径的起始点的位置; 确定路径的目标点的位置; 确定障碍物的位置和形状;使路径的起始点成为评价对象的步骤; （A1）在评价对象点与目标点之间不存在障碍物时，将从评价对象点到目标点的路径直线延伸; （A2）在从用于评价的对象点观察的从目标点的方向倾斜的方向上直线地延伸路径，并且当在评估对象点之间存在障碍物时使细长路径的末端成为评价的新对象点和目标点; 并且重复（A1）和（A2）步骤中的每一个，直到从起始点延伸的路径到达目标点。版权所有（C）2008，JPO＆INPIT

9. 发明专利

JP2007216350A Mobile type robot 有权
标题翻译：移动式机器人
公开(公告)号：JP2007216350A
公开(公告)日：2007-08-30
申请号：JP2006041323
申请日：2006-02-17
申请人： Toyota Motor Corp , トヨタ自動車株式会社
发明人： NAKAJIMA YUICHIRO , RI KAIKEN , NOMURA HIDEKI
IPC分类号： B25J19/04 , G01B11/00 , G05D1/02 , G06T3/00
CPC分类号： G05D1/0251 , B25J5/007 , G01B11/03 , G05D1/0274 , G06T2200/32
摘要： PROBLEM TO BE SOLVED: To provide a technique for ordinarily recognizing all surrounding environmental regions by eliminating an unknown environment generated due to coming into sight of a part of a body such as a connecting portion when a robot is operated by providing a camera separate from a camera provided in a body trunk at the connecting portion connected to the body trunk via a joint. SOLUTION: This robot has the body trunk 103 constituted of head part and the body, at least one connecting portion 104 connected to the body trunk 103 via a driven shoulder joint 203, at least a body trunk side camera 105 provided in the body trunk 103, and at least a connecting portion side camera 106 provided at the connecting portion. The robot is provided with a synthetic image preparation means for preparing a synthetic image by synthesizing a body trunk side image imaged by the body trunk side camera 105 and a connecting portion side image imaged by the connecting portion side camera 106, and a recognition means for recognizing the position of a surrounding object by the synthetic image. COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：提供一种通过在通过提供照相机操作机器人时消除由于看到诸如连接部分的身体的一部分而产生的未知环境而通常识别所有周围环境区域的技术与通过接头连接到身体躯干的连接部分处设置在身体躯干中的照相机分离。解决方案：该机器人具有由头部和身体构成的身体躯干103，至少一个连接部分104经由从动肩关节203连接到身体躯干103，至少设置在身体躯干侧照相机105中身体躯干103和设置在连接部分的至少一个连接部分侧照相机106。机器人设有合成图像准备装置，用于通过合成由躯干侧相机105成像的体干侧图像和由连接部分侧相机106成像的连接部分侧图像来准备合成图像;以及识别装置，通过合成图像识别周围物体的位置。版权所有（C）2007，JPO＆INPIT

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式