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. 发明授权

US08725510B2 HMM learning device and method, program, and recording medium 有权
标题翻译： HMM学习装置和方法，程序和记录介质
公开(公告)号：US08725510B2
公开(公告)日：2014-05-13
申请号：US12829984
申请日：2010-07-02
申请人： Yukiko Yoshiike , Kenta Kawamoto , Kuniaki Noda , Kohtaro Sabe
发明人： Yukiko Yoshiike , Kenta Kawamoto , Kuniaki Noda , Kohtaro Sabe
IPC分类号： G10L15/14
CPC分类号： G06N99/005
摘要： An HMM (Hidden Markov Model) learning device includes: a learning unit for learning a state transition probability as the function of actions that an agent can execute, with learning with HMM performed based on actions that the agent has executed, and time series information made up of an observation signal; and a storage unit for storing learning results by the learning unit as internal model data including a state-transition probability table and an observation probability table; with the learning unit calculating frequency variables used for estimation calculation of HMM state-transition and HMM observation probabilities; with the storage unit holding the frequency variables corresponding to each of state-transition probabilities and each of observation probabilities respectively, of the state-transition probability table; and with the learning unit using the frequency variables held by the storage unit to perform learning, and estimating the state-transition probability and the observation probability based on the frequency variables.
摘要翻译： HMM（隐马尔可夫模型）学习装置包括：用于学习作为代理可以执行的动作的函数的状态转移概率的学习单元，基于代理已经执行的动作执行的HMM的学习以及作出的时间序列信息观察信号; 以及存储单元，用于将所述学习单元的学习结果存储为包括状态转换概率表和观察概率表的内部模型数据; 学习单元计算用于HMM状态转换和HMM观察概率的估计计算的频率变量; 存储单元保持状态转移概率表中分别对应于状态转换概率和每个观察概率的频率变量; 并且所述学习单元使用由所述存储单元保持的频率变量来执行学习，并且基于所述频率变量来估计所述状态转换概率和观察概率。

2. 发明申请

US20110010176A1 HMM LEARNING DEVICE AND METHOD, PROGRAM, AND RECORDING MEDIUM 有权
标题翻译： HMM学习设备和方法，程序和记录介质
公开(公告)号：US20110010176A1
公开(公告)日：2011-01-13
申请号：US12829984
申请日：2010-07-02
申请人： Yukiko YOSHIIKE , Kenta Kawamoto , Kuniaki Noda , Kohtaro Sabe
发明人： Yukiko YOSHIIKE , Kenta Kawamoto , Kuniaki Noda , Kohtaro Sabe
IPC分类号： G10L15/14
CPC分类号： G06N99/005
摘要： An HMM (Hidden Markov Model) learning device includes: a learning unit for learning a state transition probability as the function of actions that an agent can execute, with learning with HMM performed based on actions that the agent has executed, and time series information made up of an observation signal; and a storage unit for storing learning results by the learning unit as internal model data including a state-transition probability table and an observation probability table; with the learning unit calculating frequency variables used for estimation calculation of HMM state-transition and HMM observation probabilities; with the storage unit holding the frequency variables corresponding to each of state-transition probabilities and each of observation probabilities respectively, of the state-transition probability table; and with the learning unit using the frequency variables held by the storage unit to perform learning, and estimating the state-transition probability and the observation probability based on the frequency variables.
摘要翻译： HMM（隐马尔可夫模型）学习装置包括：用于学习作为代理可以执行的动作的函数的状态转移概率的学习单元，基于代理已经执行的动作执行的HMM的学习以及作出的时间序列信息观察信号; 以及存储单元，用于将所述学习单元的学习结果存储为包括状态转换概率表和观察概率表的内部模型数据; 学习单元计算用于HMM状态转换和HMM观察概率的估计计算的频率变量; 存储单元保持状态转移概率表中分别对应于状态转换概率和每个观察概率的频率变量; 并且所述学习单元使用由所述存储单元保持的频率变量来执行学习，并且基于所述频率变量来估计所述状态转换概率和观察概率。

3. 发明申请

US20100318478A1 INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM 审中-公开
标题翻译：信息处理设备，信息处理方法和程序
公开(公告)号：US20100318478A1
公开(公告)日：2010-12-16
申请号：US12791240
申请日：2010-06-01
申请人： Yukiko Yoshiike , Kenta Kawamoto , Kuniaki Noda , Kohtaro Sabe
发明人： Yukiko Yoshiike , Kenta Kawamoto , Kuniaki Noda , Kohtaro Sabe
IPC分类号： G06N5/02 , G06F15/18
CPC分类号： G06N3/006 , G06K9/00335 , G06K9/00664 , G06K9/6297
摘要： An information processing device includes: a calculating unit configured to calculate a current-state series candidate that is a state series for an agent capable of actions reaching the current state, based on a state transition probability model obtained by performing learning of the state transition probability model stipulated by a state transition probability that a state will be transitioned according to each of actions performed by an agent capable of actions, and an observation probability that a predetermined observation value will be observed from the state, using an action performed by the agent, and an observation value observed at the agent when the agent performs an action; and a determining unit configured to determine an action to be performed next by the agent using the current-state series candidate in accordance with a predetermined strategy.
摘要翻译：一种信息处理设备，包括：计算单元，被配置为基于通过执行状态转移概率的学习获得的状态转移概率模型来计算作为达到当前状态的动作的代理的状态序列的当前状态序列候选由状态转移概率规定的模式，其状态将根据由能够执行动作的代理执行的动作而转变，并且使用由代理执行的动作从该状态观察到预定观察值的观察概率，以及当代理人执行动作时在代理处观察到的观察值; 以及确定单元，被配置为根据预定策略来确定所述代理使用所述当前状态序列候选来执行的动作。

4. 发明授权

US07840508B2 Information processing apparatus, information processing method, and program 失效
标题翻译：信息处理装置，信息处理方法和程序
公开(公告)号：US07840508B2
公开(公告)日：2010-11-23
申请号：US11732807
申请日：2007-04-04
申请人： Yukiko Yoshiike , Masato Ito , Katsuki Minamino , Hirotaka Suzuki , Kenta Kawamoto
发明人： Yukiko Yoshiike , Masato Ito , Katsuki Minamino , Hirotaka Suzuki , Kenta Kawamoto
IPC分类号： G06F15/18 , G06N3/08
CPC分类号： G06N3/02
摘要： An information processing apparatus includes a storage unit configured to store a node holding dynamics; an input-weight-coefficient adjuster configured to adjust input-weight coefficients on a dimension-by-dimension basis, the input-weight coefficients being weight coefficients for individual dimensions of input data input to input units of the node, the input data being observed time-series data having a plurality of dimensions; and an output-weight-coefficient adjuster configured to adjust output-weight coefficients on a dimension-by-dimension basis, the output-weight coefficients being weight coefficients for individual dimensions of output data having a plurality of dimensions and output from output units of the node.
摘要翻译：一种信息处理装置，包括：存储单元，被配置为存储保存动态的节点; 输入权重系数调整器，其被配置为在逐个维度的基础上调整输入权重系数，输入权重系数是输入到节点的输入单元的输入数据的各个维度的权重系数，观察到的输入数据具有多个维度的时间序列数据; 以及输出权重系数调整器，其被配置为在逐个维度的基础上调整输出权重系数，所述输出权重系数是具有多个维度的输出数据的各个维度的权重系数，并且从所述输出单元的输出单元输出节点。

5. 发明授权

US07814037B2 Information processing apparatus and method, and program for teaching an action to a device in a time-series pattern 失效
标题翻译：信息处理装置和方法，以及用于以时间序列模式向装置教导动作的程序
公开(公告)号：US07814037B2
公开(公告)日：2010-10-12
申请号：US11397148
申请日：2006-04-04
申请人： Masato Ito , Yukiko Yoshiike , Kuniaki Noda , Jun Tani
发明人： Masato Ito , Yukiko Yoshiike , Kuniaki Noda , Jun Tani
IPC分类号： G05B13/02
CPC分类号： B25J9/161 , G05B2219/36442 , G05B2219/40391 , G06N3/008
摘要： An information processing apparatus including a learning unit that learns a predetermined time-series pattern. An output unit outputs a time-series pattern corresponding to the result of learning by the learning unit. An adjusting unit supplied with a time-series pattern obtained from an action by an action unit on the basis of a time-series pattern supplied from the output unit and external teaching for the action adjusts a time-series pattern supplied from the output unit correspondingly to the input time-series pattern. The learning unit learns the time-series pattern supplied from the output unit and adjusted by the adjusting unit.
摘要翻译：一种信息处理设备，包括学习单元，该学习单元学习预定的时间序列模式。输出单元输出与学习单元的学习结果相对应的时间序列模式。相应地，从由输出单元提供的时间序列模式和由动作的外部教导基于由动作单元的动作获得的时间序列模式的调整单元相应地调整从输出单元提供的时间序列模式到输入时间序列模式。学习单元学习从输出单元提供并由调整单元调整的时间序列模式。

6. 发明授权

US07103447B2 Robot apparatus, and behavior controlling method for robot apparatus 失效
标题翻译：机器人装置和机器人装置的行为控制方法
公开(公告)号：US07103447B2
公开(公告)日：2006-09-05
申请号：US10651577
申请日：2003-08-29
申请人： Ugo Di Profio , Masahiro Fujita , Tsuyoshi Takagi , Yukiko Yoshiike , Hideki Shimomura
发明人： Ugo Di Profio , Masahiro Fujita , Tsuyoshi Takagi , Yukiko Yoshiike , Hideki Shimomura
IPC分类号： G06F19/00
CPC分类号： G06N3/008
摘要： A robot (1) is provided which includes a situated behaviors layer (SBL) (58). This SBL (58) is formed in the form of a tree structure in which a plurality of schemata (behavior modules) is connected hierarchically in such a matter that the schemata are highly independent of each other for each of them to behave uniquely. A patent schema can define a pattern in which child schemata are connected, such as an OR type pattern in which the child schemata are caused to behave uniquely, AND type pattern in which the plurality of child schemata are caused to behave simultaneously or a SEQUENCE type pattern indicating a sequence in which the plurality of child schemata should behave, thereby permitting to select a behavior pattern of the robot (1). Also, a new child schema can additionally be included in the SBL (58) without having to rewrite the schemata connection in the tree structure, whereby a new behavior or function can be added to the robot (1). Namely, the plurality of behavior modules permits to enable the robot (1) to show a complicated behavior and have units thereof recombined.
摘要翻译：提供了一种包括位置行为层（SBL）（58）的机器人（1）。该SBL（58）形成为树结构的形式，其中多个模式（行为模块）在层级上连接，使得模式对于它们中的每一个独立地彼此高度独立。专利模式可以定义连接子模式的模式，例如使子模式在其中被执行为唯一的OR类型模式，以及使多个子模式被同时行为的类型模式或SEQUENCE类型模式，其指示多个子图案应该行为的顺序，从而允许选择机器人（1）的行为模式。另外，SBL（58）中还可以包括新的子模式，而不需要重写树形结构中的模式连接，从而可以向机器人（1）添加新的行为或功能。也就是说，多个行为模块允许机器人（1）显示复杂的行为并且其单元重新组合。

7. 发明授权

US08738555B2 Data processing device, data processing method, and program 有权
标题翻译：数据处理装置，数据处理方法和程序
公开(公告)号：US08738555B2
公开(公告)日：2014-05-27
申请号：US13248296
申请日：2011-09-29
申请人： Takashi Hasuo , Kohtaro Sabe , Kenta Kawamoto , Yukiko Yoshiike
发明人： Takashi Hasuo , Kohtaro Sabe , Kenta Kawamoto , Yukiko Yoshiike
IPC分类号： G06F15/18
CPC分类号： G06N3/006 , G06N99/005
摘要： A data processing device includes a state value calculation unit which calculates a state value of which the value increases as much as a state with a high transition probability for each state of the state transition model, an action value calculation unit which calculates an action value, of which the value increases as a transition probability increases for each state of the state transition model and each action that the agent can perform, a target state setting unit which sets a state with great unevenness in the action value among states of the state transition model to a target state that is the target to reach by action performed by the agent, and an action selection unit which selects an action of the agent so as to move toward the target state.
摘要翻译：数据处理装置包括状态值计算单元，其计算与状态转移模型的每个状态的转移概率高的状态一起增加的状态值，动作值计算单元，其计算动作值，其中该值随状态转换模型的每个状态和代理可以执行的每个动作的转移概率增加而增加;目标状态设置单元，其在状态转换模型的状态之间设置动作值中具有很大不均匀性的状态到作为由代理执行的动作达到的目标的目标状态;以及动作选择单元，其选择代理人的动作以朝向目标状态移动。

8. 发明申请

US20050197739A1 Behavior controlling system and behavior controlling method for robot 审中-公开
标题翻译：机器人行为控制系统和行为控制方法
公开(公告)号：US20050197739A1
公开(公告)日：2005-09-08
申请号：US11035811
申请日：2005-01-14
申请人： Kuniaki Noda , Shinya Ohtani , Tsutomu Sawada , Yukiko Yoshiike , Masahiro Fujita
发明人： Kuniaki Noda , Shinya Ohtani , Tsutomu Sawada , Yukiko Yoshiike , Masahiro Fujita
IPC分类号： B25J13/00 , B25J5/00 , G06F19/00
CPC分类号： B25J11/001 , G06N3/008
摘要： A behavior control system and a behavior control method for a robot apparatus are disclosed. The behavior control system and the behavior control method for a robot apparatus include a function of adaptively switching between a behavior selection standard, taking into account the own state, required of an autonomous robot, and a behavior selection standard, taking into account the state of a counterpart, responsive to a situation. A behavior selection control system in a robot apparatus includes a situation-dependent behavior layer (SBL), capable of selecting a particular behavior from plural behaviors, and outputting the so selected behavior, and an AL calculating unit 120 for calculating the AL (activation level), indicating the priority of execution of the behaviors, for behavior selection. This AL calculating unit 120 includes a self AL calculating unit 122 and a counterpart AL calculating unit 124 for calculating the self AL and the counterpart AL, and an AL integrating unit 125 for summing the self AL and the counterpart AL with weighting by a parameter used for determining whether emphasis is to be placed on the self state or on the counterpart state, to output an ultimate AL. The counterpart is a subject of interaction of the robot apparatus. The self AL and the counterpart AL indicate the priority of execution of the behavior with the self and with the co8unbterpart as a reference, respectively.
摘要翻译：公开了一种用于机器人装置的行为控制系统和行为控制方法。用于机器人装置的行为控制系统和行为控制方法包括考虑到自身状态，自动机器人所需的行为选择标准和行为选择标准之间的自适应切换的功能，同时考虑到一个对应的，对情况做出回应。机器人装置中的行为选择控制系统包括能够从多个行为中选择特定行为并输出所选行为的情境相关行为层（SBL），以及AL计算单元120，用于计算AL（激活水平），指示执行行为的优先级，用于行为选择。该AL计算单元120包括自身AL计算单元122和用于计算自身AL和对方AL的对方AL计算单元124以及用于通过所使用的参数加权来对自身AL和对方AL进行加和的AL积分单元125 用于确定是否重点放在自我状态或对方的状态，以输出最终的AL。对应物是机器人装置相互作用的主体。自身AL和对方AL分别指示执行行为的优先级，并以co8unbterpart作为参考。

9. 发明授权

US07672920B2 Apparatus and method for embedding recurrent neural networks into the nodes of a self-organizing map 有权
标题翻译：将循环神经网络嵌入到自组织图的节点中的装置和方法
公开(公告)号：US07672920B2
公开(公告)日：2010-03-02
申请号：US11699428
申请日：2007-01-30
申请人： Masato Ito , Katsuki Minamino , Yukiko Yoshiike , Hirotaka Suzuki , Kenta Kawamoto
发明人： Masato Ito , Katsuki Minamino , Yukiko Yoshiike , Hirotaka Suzuki , Kenta Kawamoto
IPC分类号： G06N5/00
CPC分类号： G06K9/00536 , G06K9/00335 , G06N3/0445 , G06N99/005
摘要： A learning system is provided, which includes network storage means for storing a network including a plurality of nodes, each of which holds a dynamics; and learning means for self-organizationally updating the dynamics of the network on the basis of measured time-series data.
摘要翻译：提供了一种学习系统，其包括用于存储包括多个节点的网络的网络存储装置，每个节点保持动态; 以及基于测量的时间序列数据自组织地更新网络动态的学习手段。

10. 发明申请

US20070239644A1 Learning apparatus, learning method, and program 失效
标题翻译：学习机器，学习方法和程序
公开(公告)号：US20070239644A1
公开(公告)日：2007-10-11
申请号：US11732773
申请日：2007-04-04
申请人： Katsuki Minamino , Masato Ito , Kenta Kawamoto , Yukiko Yoshiike , Hirotaka Suzuki
发明人： Katsuki Minamino , Masato Ito , Kenta Kawamoto , Yukiko Yoshiike , Hirotaka Suzuki
IPC分类号： G06N3/00
CPC分类号： G06N99/005 , G06N3/0445 , G06N3/0454 , G06N3/084
摘要： A learning apparatus includes a storage unit configured to store a network formed by a plurality of nodes each holding dynamics; a learning unit configured to learn the dynamics of the network in a self-organizing manner on the basis of observed time-series data; a winner-node determiner configured to determine a winner node, the winner node being a node having dynamics that best match the time-series data; and a weight determiner configured to determine learning weights for the dynamics held by the individual nodes according to distances of the individual nodes from the winner node. The learning unit is configured to learn the dynamics of the network in a self-organizing manner by degrees corresponding to the learning weights.
摘要翻译：学习装置包括：存储单元，被配置为存储由保持动态的多个节点形成的网络; 学习单元，被配置为基于观察到的时间序列数据以自组织的方式学习网络的动态; 获胜者节点确定器，被配置为确定胜者节点，胜者节点是具有与时间序列数据最佳匹配的动态的节点; 以及权重确定器，被配置为根据各个节点与胜利者节点的距离来确定由各个节点保持的动态的学习权重。学习单元被配置为以自组织的方式以对应于学习权重的度学习网络的动态。

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