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. 发明申请

US20080312772A1 MOTION CONTROL SYSTEM, MOTION CONTROL METHOD, AND MOTION CONTROL PROGRAM 有权
标题翻译：运动控制系统，运动控制方法和运动控制程序
公开(公告)号：US20080312772A1
公开(公告)日：2008-12-18
申请号：US12137873
申请日：2008-06-12
申请人： Tadaaki Hasegawa , Yugo Ueda , Soshi Iba , Darrin Bentivegna
发明人： Tadaaki Hasegawa , Yugo Ueda , Soshi Iba , Darrin Bentivegna
IPC分类号： G05B19/00
CPC分类号： G06N3/008 , G05B2219/40391
摘要： The present invention provides a motion control system control a motion of a second motion body by considering an environment which a human contacts and a motion mode appropriate to the environment, and an environment which a robot actually contacts. The motion mode is learned based on an idea that it is sufficient to learn only a feature part of the motion mode of the human without a necessity to learn the others. Moreover, based on an idea that it is sufficient to reproduce only the feature part of the motion mode of the human without a necessity to reproduce the others, the motion mode of the robot is controlled by using the model obtained from the learning result. Thereby, the motion mode of the robot is controlled by using the motion mode of the human as a prototype without restricting the motion mode thereof more than necessary.
摘要翻译：本发明提供一种运动控制系统，其通过考虑人体接触的环境和适合于环境的运动模式以及机器人实际接触的环境来控制第二运动体的运动。基于这样的想法来学习运动模式，即仅仅学习人的运动模式的特征部分是足够的，而不需要学习其他动作模式。此外，基于仅仅再现人的运动模式的特征部分而不需要再现其他的想法就足够了，通过使用从学习结果获得的模型来控制机器人的运动模式。因此，通过使用人的运动模式作为原型来控制机器人的运动模式，而不限制其运动模式。

2. 发明申请

US20120253514A1 REINFORCEMENT LEARNING APPARATUS, CONTROL APPARATUS, AND REINFORCEMENT LEARNING METHOD 有权
标题翻译：加强学习装置，控制装置和加固学习方法
公开(公告)号：US20120253514A1
公开(公告)日：2012-10-04
申请号：US13432094
申请日：2012-03-28
申请人： Norikazu Sugimoto , Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka
发明人： Norikazu Sugimoto , Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka
IPC分类号： G05B19/04
CPC分类号： G05B13/0265 , Y10S901/03
摘要： It is possible to perform robot motor learning in a quick and stable manner using a reinforcement learning apparatus including: a first-type environment parameter obtaining unit that obtains a value of one or more first-type environment parameters; a control parameter value calculation unit that calculates a value of one or more control parameters maximizing a reward by using the value of the one or more first-type environment parameters; a control parameter value output unit that outputs the value of the one or more control parameters to the control object; a second-type environment parameter obtaining unit that obtains a value of one or more second-type environment parameters; a virtual external force calculation unit that calculates the virtual external force by using the value of the one or more second-type environment parameters; and a virtual external force output unit that outputs the virtual external force to the control object.
摘要翻译：可以使用强化学习装置以快速且稳定的方式执行机器人电动机学习，包括：获得一个或多个第一类型环境参数的值的第一类型环境参数获取单元; 控制参数值计算单元，其通过使用所述一个或多个第一类型环境参数的值来计算使奖励最大化的一个或多个控制参数的值; 控制参数值输出单元，其将所述一个或多个控制参数的值输出到所述控制对象; 获取一个或多个第二类型环境参数的值的第二类型环境参数获取单元; 虚拟外力计算单元，其通过使用所述一个或多个第二类型环境参数的值来计算所述虚拟外力; 以及将虚拟外力输出到控制对象的虚拟外力输出单元。

3. 发明授权

US08392346B2 Reinforcement learning system 有权
标题翻译：加强学习系统
公开(公告)号：US08392346B2
公开(公告)日：2013-03-05
申请号：US12610709
申请日：2009-11-02
申请人： Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka , Norikazu Sugimoto
发明人： Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka , Norikazu Sugimoto
IPC分类号： G06F15/18 , G06N3/08
CPC分类号： G06N99/005
摘要： A reinforcement learning system (1) of the present invention utilizes a value of a first value gradient function (dV1/dt) in the learning performed by a second learning device (122), namely in evaluating a second reward (r2(t)). The first value gradient function (dV1/dt) is a temporal differential of a first value function (V1) which is defined according to a first reward (r1(t)) obtained from an environment and is served as a learning result given by a first learning device (121). An action policy which should be taken by a robot (R) to execute a task is determined based on the second reward (r2(t)).
摘要翻译：本发明的强化学习系统（1）利用由第二学习装置（122）执行的学习中的第一值梯度函数（dV1 / dt）的值，即评估第二奖励（r2（t））。第一值梯度函数（dV1 / dt）是根据从环境获得的第一奖励（r1（t））定义的第一值函数（V1）的时间微分，并且被用作由第一学习装置（121）。基于第二奖励（r2（t））确定由机器人（R）执行任务应采取的动作策略。

4. 发明授权

US07133855B2 Behavior control apparatus and method 失效
公开(公告)号：US07133855B2
公开(公告)日：2006-11-07
申请号：US10411485
申请日：2003-04-07
申请人： Yugo Ueda , Hiroshi Tsujino
发明人： Yugo Ueda , Hiroshi Tsujino
IPC分类号： G06E1/00 , G06F15/18 , G06G7/00
CPC分类号： G06N3/06 , G06N3/08
摘要： It is objective of the invention to provide a highly reliable control apparatus and method which reduces the amount of calculation required for both learning of an input/output relationship and actual control as well as prevent inappropriate outputs from being generated for inputs which have been never learned. According to one aspect of the invention, pairs of an input pattern vector for learning and a target output are distributed to a class based on the target output. Then, a correspondence between each element of the input pattern vector for learning and the target output is learned only in that class, and a distribution function is calculated for distributing a new input pattern vector for learning to that class. After the completion of this learning, the distribution function is used to determine which class a new input pattern vector detected by a sensor belongs to. Finally, an output is calculated according to the learning result of that class. Therefore, since the range of the outputs corresponding to the inputs may be limited, reliability of the control is improved.

5. 发明授权

US08886357B2 Reinforcement learning apparatus, control apparatus, and reinforcement learning method 有权
标题翻译：加强学习装置，控制装置和强化学习方法
公开(公告)号：US08886357B2
公开(公告)日：2014-11-11
申请号：US13432094
申请日：2012-03-28
申请人： Norikazu Sugimoto , Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka
发明人： Norikazu Sugimoto , Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka
IPC分类号： G06F19/00 , G05B13/02
CPC分类号： G05B13/0265 , Y10S901/03
摘要： It is possible to perform robot motor learning in a quick and stable manner using a reinforcement learning apparatus including: a first-type environment parameter obtaining unit that obtains a value of one or more first-type environment parameters; a control parameter value calculation unit that calculates a value of one or more control parameters maximizing a reward by using the value of the one or more first-type environment parameters; a control parameter value output unit that outputs the value of the one or more control parameters to the control object; a second-type environment parameter obtaining unit that obtains a value of one or more second-type environment parameters; a virtual external force calculation unit that calculates the virtual external force by using the value of the one or more second-type environment parameters; and a virtual external force output unit that outputs the virtual external force to the control object.
摘要翻译：可以使用强化学习装置以快速且稳定的方式执行机器人电动机学习，包括：获得一个或多个第一类型环境参数的值的第一类型环境参数获取单元; 控制参数值计算单元，其通过使用所述一个或多个第一类型环境参数的值来计算使奖励最大化的一个或多个控制参数的值; 控制参数值输出单元，其将所述一个或多个控制参数的值输出到所述控制对象; 获取一个或多个第二类型环境参数的值的第二类型环境参数获取单元; 虚拟外力计算单元，其通过使用所述一个或多个第二类型环境参数的值来计算所述虚拟外力; 以及将虚拟外力输出到控制对象的虚拟外力输出单元。

6. 发明授权

US08315740B2 Motion control system, motion control method, and motion control program 有权
标题翻译：运动控制系统，运动控制方法和运动控制程序
公开(公告)号：US08315740B2
公开(公告)日：2012-11-20
申请号：US12137873
申请日：2008-06-12
申请人： Tadaaki Hasegawa , Yugo Ueda , Soshi Iba , Darrin Bentivegna
发明人： Tadaaki Hasegawa , Yugo Ueda , Soshi Iba , Darrin Bentivegna
IPC分类号： G05B19/00
CPC分类号： G06N3/008 , G05B2219/40391
摘要： The present invention provides a motion control system to control a motion of a second motion body, by considering an environment which a human contacts and a motion mode appropriate to the environment, and an environment which a robot actually contacts. The motion mode is learned based on an idea that it is sufficient to learn only a feature part of the motion mode of the human without a necessity to learn the others. Moreover, based on an idea that it is sufficient to reproduce only the feature part of the motion mode of the human without a necessity to reproduce the others, the motion mode of the robot is controlled by using the model obtained from the learning result. Thereby, the motion mode of the robot is controlled by using the motion mode of the human as a prototype without restricting the motion mode thereof more than necessary.
摘要翻译：本发明提供了一种运动控制系统，其通过考虑人类接触的环境和适合于环境的运动模式以及机器人实际接触的环境来控制第二运动体的运动。基于这样的想法来学习运动模式，即仅仅学习人的运动模式的特征部分是足够的，而不需要学习其他动作模式。此外，基于仅仅再现人的运动模式的特征部分而不需要再现其他的想法就足够了，通过使用从学习结果获得的模型来控制机器人的运动模式。因此，通过使用人的运动模式作为原型来控制机器人的运动模式，而不限制其运动模式。

7. 发明申请

US20100114807A1 REINFORCEMENT LEARNING SYSTEM 有权
标题翻译：加固学习系统
公开(公告)号：US20100114807A1
公开(公告)日：2010-05-06
申请号：US12610709
申请日：2009-11-02
申请人： Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka , Norikazu Sugimoto
发明人： Yugo Ueda , Tadaaki Hasegawa , Soshi Iba , Koji Akatsuka , Norikazu Sugimoto
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： A reinforcement learning system (1) of the present invention utilizes a value of a first value gradient function (dV1/dt) in the learning performed by a second learning device (122), namely in evaluating a second reward (r2(t)). The first value gradient function (dV1/dt) is a temporal differential of a first value function (V1) which is defined according to a first reward (r1(t)) obtained from an environment and is served as a learning result given by a first learning device (121). An action policy which should be taken by a robot (R) to execute a task is determined based on the second reward (r2(t)).
摘要翻译：本发明的强化学习系统（1）利用由第二学习装置（122）执行的学习中的第一值梯度函数（dV1 / dt）的值，即评估第二奖励（r2（t））。第一值梯度函数（dV1 / dt）是根据从环境获得的第一奖励（r1（t））定义的第一值函数（V1）的时间微分，并且被用作由第一学习装置（121）。基于第二奖励（r2（t））确定由机器人（R）执行任务应采取的动作策略。

8. 发明授权

US06965694B2 Motion information recognition system 失效
标题翻译：运动信息识别系统
公开(公告)号：US06965694B2
公开(公告)日：2005-11-15
申请号：US09996307
申请日：2001-11-27
申请人： Yugo Ueda , Hiroshi Tsujino
发明人： Yugo Ueda , Hiroshi Tsujino
IPC分类号： G06K9/00 , G06T7/20 , G06K9/48
CPC分类号： G06T7/20 , G06K9/00335
摘要： A motion information recognition system takes time-series images of an object in motion and generates image vectors that are analyzed to produce a plurality of eigenvectors that are then stored. Inner product operations are performed between image vectors of a recognized object and a plurality of the stored eigenvectors for obtaining the motion information of the recognized object based on the result of said inner product operations to provide high-speed and easy motion information recognition at reduced computing cost.
摘要翻译：运动信息识别系统拍摄运动中的物体的时间序列图像，并产生被分析以产生多个特征向量然后被存储的图像矢量。在识别对象的图像向量和多个所存储的本征向量之间执行内部乘积运算，用于基于所述内部乘积运算的结果获得所识别的对象的运动信息，以在减少的计算中提供高速和容易的运动信息识别成本。

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