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

US4990838A Movement trajectory generating method of a dynamical system 失效
标题翻译：动力系统的运动轨迹生成方法
公开(公告)号：US4990838A
公开(公告)日：1991-02-05
申请号：US462531
申请日：1990-01-03
申请人： Mitsuo Kawato , Yoshiharu Maeda , Yoji Uno , Ryoji Suzuki
发明人： Mitsuo Kawato , Yoshiharu Maeda , Yoji Uno , Ryoji Suzuki
IPC分类号： B25J9/22 , B25J9/16 , B25J9/18 , G01D21/00 , G05B13/00 , G05B13/02 , G05B19/41 , G06F15/18 , G06N3/00 , G06N3/04 , G06N99/00
CPC分类号： G05B19/41 , B25J9/161 , G06N3/0454 , G05B2219/33027 , G05B2219/42155 , G05B2219/49157
摘要： A movement trajectory generating system of a dynamical system uses neural network units (1, 2, 3) including cascade connection of a first layer (11, 21, 31), a second layer (12, 22, 32), a third layer (13, 23, 33) and a fourth layer (14, 24, 34), to learn a vector field of differential equations indicating forward dynamics of a controlled object (4). Conditions concerning trajectories of a final point and a via-point of movement of the controlled object and locations of obstacles are given from a motor center (5). While smoothness of movement is ensured by couplings of electric synapses using errors with respect to those conditions as total energy, least dissipation of energy is attained, whereby trajectory formation and control input for realizing the trajectory are obtained simultaneously.

2. 发明申请

US20120035765A1 BRAIN INFORMATION OUTPUT APPARATUS, ROBOT, AND BRAIN INFORMATION OUTPUT METHOD 有权
标题翻译：脑信息输出装置，机器人和脑信息输出方法
公开(公告)号：US20120035765A1
公开(公告)日：2012-02-09
申请号：US13202784
申请日：2010-02-22
申请人： Masaaki Sato , Takahito Tamagawa , Okito Yamashita , Yusuke Takeda , Mitsuo Kawato , Kentaro Yamada , Masahiro Kimura , Akihiro Toda , Tatsuya Okabe
发明人： Masaaki Sato , Takahito Tamagawa , Okito Yamashita , Yusuke Takeda , Mitsuo Kawato , Kentaro Yamada , Masahiro Kimura , Akihiro Toda , Tatsuya Okabe
IPC分类号： G06F19/00 , G05B15/00 , A61B5/00
CPC分类号： B25J13/00 , A61B5/0042 , A61B5/0059 , A61B5/0073 , A61B5/0476 , A61B5/055 , A61B5/4064 , A61B5/6814 , G06F3/015 , G06N99/005
摘要： A brain information output apparatus includes an intention determination information storage unit in which two or more pieces of intention determination information can be stored, with each intention determination information including a pair of an intention identifier, and a learning feature amount group including one or more feature amounts extracted from second learning data that is obtained by converting first learning data into intracerebral brain activity data, the first leaning data being acquired from the outside of the cranium of a user when the user performs a trial according to one intention; a first brain activity data acquiring unit that acquires first brain activity data from the outside of the cranium of a user; a second brain activity data acquiring unit that converts the first brain activity data to intracerebral brain activity data, and acquires second brain activity data; a feature amount group acquiring unit that acquires, from the second brain activity data, an input feature amount group including one or more feature amounts; an intention identifier acquiring unit that acquires an intention identifier corresponding to the input feature amount group based on the two or more pieces of intention determination information; and an intention identifier output unit that outputs the intention identifier.
摘要翻译：大脑信息输出装置包括意图确定信息存储单元，其中可以存储两个或多个意图确定信息，每个意图确定信息包括一对意图标识符和包括一个或多个特征的学习特征量组通过将第一学习数据转换为大脑脑活动数据而获得的第二学习数据提取的量，当用户根据一种意图进行试验时，从用户头颅的外部获取第一倾斜数据; 第一脑活动数据获取单元，从用户的头颅的外部获取第一脑活动数据; 第二大脑活动数据获取单元，将第一脑活动数据转换为大脑脑活动数据，并获取第二大脑活动数据; 特征量组获取单元，从第二大脑活动数据获取包括一个或多个特征量的输入特征量组; 意图标识符获取单元，基于所述两个或多个意图确定信息来获取与所述输入特征量组相对应的意图识别符; 以及输出意图标识符的意图标识符输出单元。

3. 发明申请

US20050113973A1 Robot and attitude control method of robot 有权
标题翻译：机器人的机器人和姿态控制方法
公开(公告)号：US20050113973A1
公开(公告)日：2005-05-26
申请号：US10922907
申请日：2004-08-23
申请人： Gen Endo , Mitsuo Kawato , Gordon Cheng , Jun Nakanishi , Jun Morimoto
发明人： Gen Endo , Mitsuo Kawato , Gordon Cheng , Jun Nakanishi , Jun Morimoto
IPC分类号： B25J5/00 , B25J9/16 , B25J13/08 , B62D57/032 , G06F19/00
CPC分类号： B62D57/032 , B25J9/161 , B25J13/08
摘要： The motion of the movable sections of the robot is taken for a periodic motion so that the attitude of the robot can be stably controlled in a broad sense of the word by regulating the transfer of the movable sections. More specifically, one or more than one phase generators are used for the robot system and one of the plurality of controllers is selected depending on the generated phase. Then, the controller controls the drive of the movable sections according to continuous phase information. Additionally, the actual phase is estimated from the physical system and the frequency and the phase of the phase generator are regulated by using the estimated value, while the physical phase and the phase generator of the robot system are subjected to mutual entrainment so that consequently, it is possible to control the motion of the robot by effectively using the dynamics of the robot.
摘要翻译：机器人的可移动部分的运动被采取周期性的运动，使得通过调节可移动部分的转移，能够以广义的方式将机器人的姿态稳定地控制。更具体地，一个或多于一个的相位发生器用于机器人系统，并且根据生成的相位选择多个控制器之一。然后，控制器根据连续相位信息控制可动部分的驱动。另外，从物理系统估计实际相位，并且通过使用估计值来调节相位发生器的频率和相位，同时机器人系统的物理相位和相位发生器受到相互夹带，可以通过有效地利用机器人的动力来控制机器人的运动。

4. 发明授权

US06529887B1 Agent learning machine 失效
标题翻译：代理学习机
公开(公告)号：US06529887B1
公开(公告)日：2003-03-04
申请号：US09508850
申请日：2000-05-18
申请人： Kenji Doya , Mitsuo Kawato
发明人： Kenji Doya , Mitsuo Kawato
IPC分类号： G06F1518
CPC分类号： G06N99/005 , G05B13/0265 , G05B13/048
摘要： The invention provides a novel highly-adaptive agent learning machine comprising a plurality of learning modules each having a set of reinforcement learning system which works on an environment and determines an action output for maximizing a reward provided as a result thereof and an environment predicting system which predicts a change in the environment, wherein a responsibility signal is calculated such that the smaller a prediction error of the environment predicting system of each of the learning modules, the larger the value thereof, and the action output by the reinforcement learning system is weighted in proportion to the responsibility signal, thereby providing an action with regard to the environment. The machine switches and combines actions optimum to various states or operational modes of an environment without using any specific teacher signal and performs behavior learning flexibly without using any prior knowledge.
摘要翻译：本发明提供了一种新颖的高度适应性学习机器，其包括多个学习模块，每个学习模块具有一组在环境上工作的加强学习系统，并确定用于最大化作为其结果提供的奖励的动作输出和环境预测系统，预测环境变化，其中计算责任信号，使得每个学习模块的环境预测系统的预测误差越小，加强学习系统输出的动作越小，加强学习系统的动作的加权越小与责任信号成比例，从而对环境采取行动。机器可以切换和组合最适合环境的各种状态或操作模式的操作，而不使用任何特定的教师信号，并且可以灵活地执行行为学习，而无需使用任何先前的知识。

5. 发明授权

US08868174B2 Brain information output apparatus, robot, and brain information output method 有权
标题翻译：脑信息输出设备，机器人和大脑信息输出方法
公开(公告)号：US08868174B2
公开(公告)日：2014-10-21
申请号：US13202784
申请日：2010-02-22
申请人： Masaaki Sato , Takahito Tamagawa , Okito Yamashita , Yusuke Takeda , Mitsuo Kawato , Kentaro Yamada , Masahiro Kimura , Akihiro Toda , Tatsuya Okabe
发明人： Masaaki Sato , Takahito Tamagawa , Okito Yamashita , Yusuke Takeda , Mitsuo Kawato , Kentaro Yamada , Masahiro Kimura , Akihiro Toda , Tatsuya Okabe
IPC分类号： A61B5/04 , B25J13/00 , G06F3/01 , G06N99/00 , A61B5/0476 , A61B5/00 , A61B5/055
CPC分类号： B25J13/00 , A61B5/0042 , A61B5/0059 , A61B5/0073 , A61B5/0476 , A61B5/055 , A61B5/4064 , A61B5/6814 , G06F3/015 , G06N99/005
摘要： A brain information output apparatus includes an intention determination information storage unit in which two or more pieces of intention determination information can be stored, with each intention determination information including a pair of an intention identifier, and a learning feature amount group including one or more feature amounts extracted from second learning data that is obtained by converting first learning data into intracerebral brain activity data, the first leaning data being acquired from the outside of the cranium of a user when the user performs a trial according to one intention; a first brain activity data acquiring unit that acquires first brain activity data from the outside of the cranium of a user; a second brain activity data acquiring unit that converts the first brain activity data to intracerebral brain activity data, and acquires second brain activity data; a feature amount group acquiring unit that acquires, from the second brain activity data, an input feature amount group including one or more feature amounts; an intention identifier acquiring unit that acquires an intention identifier corresponding to the input feature amount group based on the two or more pieces of intention determination information; and an intention identifier output unit that outputs the intention identifier.
摘要翻译：大脑信息输出装置包括意图确定信息存储单元，其中可以存储两个或多个意图确定信息，每个意图确定信息包括一对意图标识符和包括一个或多个特征的学习特征量组通过将第一学习数据转换为大脑脑活动数据而获得的第二学习数据提取的量，当用户根据一种意图进行试验时，从用户头颅的外部获取第一倾斜数据; 第一脑活动数据获取单元，从用户的头颅的外部获取第一脑活动数据; 第二大脑活动数据获取单元，将第一脑活动数据转换为大脑脑活动数据，并获取第二大脑活动数据; 特征量组获取单元，从第二大脑活动数据获取包括一个或多个特征量的输入特征量组; 意图标识符获取单元，基于所述两个或多个意图确定信息来获取与所述输入特征量组相对应的意图识别符; 以及输出意图标识符的意图标识符输出单元。

6. 发明授权

US07657345B2 Robot and attitude control method of robot 有权
标题翻译：机器人的机器人和姿态控制方法
公开(公告)号：US07657345B2
公开(公告)日：2010-02-02
申请号：US10922907
申请日：2004-08-23
申请人： Gen Endo , Mitsuo Kawato , Gordon Cheng , Jun Nakanishi , Jun Morimoto
发明人： Gen Endo , Mitsuo Kawato , Gordon Cheng , Jun Nakanishi , Jun Morimoto
IPC分类号： B25J9/10 , G06F15/00 , G05B19/18 , G05B19/04
CPC分类号： B62D57/032 , B25J9/161 , B25J13/08
摘要： The motion of the movable sections of the robot is taken for a periodic motion so that the attitude of the robot can be stably controlled in a broad sense of the word by regulating the transfer of the movable sections. More specifically, one or more than one phase generators are used for the robot system and one of the plurality of controllers is selected depending on the generated phase. Then, the controller controls the drive of the movable sections according to continuous phase information. Additionally, the actual phase is estimated from the physical system and the frequency and the phase of the phase generator are regulated by using the estimated value, while the physical phase and the phase generator of the robot system are subjected to mutual entrainment so that consequently, it is possible to control the motion of the robot by effectively using the dynamics of the robot.
摘要翻译：机器人的可移动部分的运动被采取周期性的运动，使得通过调节可移动部分的转移，能够以广义的方式将机器人的姿态稳定地控制。更具体地，一个或多于一个的相位发生器用于机器人系统，并且根据生成的相位选择多个控制器之一。然后，控制器根据连续相位信息控制可动部分的驱动。另外，从物理系统估计实际相位，并且通过使用估计值来调节相位发生器的频率和相位，同时机器人系统的物理相位和相位发生器受到相互夹带，可以通过有效地利用机器人的动力来控制机器人的运动。

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