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

US11679496B2 Robot controller that controls robot, learned model, method of controlling robot, and storage medium 有权
公开(公告)号：US11679496B2
公开(公告)日：2023-06-20
申请号：US17106785
申请日：2020-11-30
申请人： CANON KABUSHIKI KAISHA
发明人： Shigeru Toriihara , Yuki Wada
IPC分类号： B25J9/16 , G05B19/4155 , G06N3/063
CPC分类号： B25J9/161 , B25J9/163 , B25J9/1697 , G05B19/4155 , G06N3/063 , G05B2219/39284
摘要： A robot controller that controls a robot by automatically obtaining a controller capable of suitably controlling a wide range of robots. An image is acquired from an image capturing apparatus that photographs an environment including the robot. The robot is driven based on an output result obtained by inputting the image to a neural network. The neural network is updated according to a reward generated in a case where a plurality of virtual images photographed while changing an environmental condition of a virtual environment generated by virtualizing the environment and a state of a virtual robot are input to the neural network, and a policy of the virtual robot, which is output from the neural network, satisfies a predetermined condition.

2. 发明授权

US12051013B2 Learning device, learning method, and program therefor for shorten time in generating appropriate teacher data 有权
公开(公告)号：US12051013B2
公开(公告)日：2024-07-30
申请号：US16968606
申请日：2019-03-05
申请人： OMRON Corporation
发明人： Takashi Fujii , Yuki Ueyama , Yasuaki Abe , Nobuyuki Sakatani , Kazuhiko Imatake
IPC分类号： G06N7/04 , B25J9/16 , B25J15/02 , G05B13/02 , G06N3/06 , G06N3/08 , G06N20/00
CPC分类号： G06N7/046 , B25J9/161 , B25J9/163 , B25J15/02 , G05B13/0265 , G06N3/06 , G06N3/08 , G06N7/04 , G06N20/00 , G05B2219/39284
摘要： This learning device provides a learned model to an adjuster including the learned model learned to output a predetermined compensation amount to a controller based on parameters of an object to be processed, in a system including the controller outputting a command value obtained by compensating a target value based on a compensation amount; and a control object performing a predetermined process on the object and outputting a control variable as a response to the command value. The learning device includes: a learning part generating candidate compensation amounts based on operation data including a target value, command value and control variable, learning with the generated candidate compensation amounts and the parameters of the object as teacher data, and generating or updating the learned model; and a setting part providing, to the adjuster, the generated or updated learned model.

3. 发明申请

US20040148268A1 Artificial multiped and motion controller therefor 审中-公开
标题翻译：人造乘法和运动控制器
公开(公告)号：US20040148268A1
公开(公告)日：2004-07-29
申请号：US10469372
申请日：2004-03-12
发明人： Torsten Reil
IPC分类号： G06F019/00
CPC分类号： B25J9/161 , B62D57/032 , G05B2219/39273 , G05B2219/39284
摘要： An artificial multiped is constructed (either in simulation or embodied) in such a way that its natural body dynamics allow the lower part of each leg to swing naturally under the influence of gravity. The upper part of each leg is actively actuated in the sagittal plane. The necessary input to drive the above-mentioned actuators is derived from a neural network controller. The latter is arranged as two bi-directionally coupled chains of neural oscillators, the number of which equals twice that of the legs to be actuated. Parameter optimisation of the controllers is achieved by evolutionary computation in the form of a genetic algorithm.
摘要翻译：人造乘法器（仿真或体现）被构造成使得其自然的身体动力学允许每个腿的下部在重力的影响下自然地摆动。每个腿的上部在矢状平面中被主动地致动。驱动上述致动器的必要输入源自神经网络控制器。后者被布置为两个双向耦合的神经振荡器链，其数量等于要被致动的腿的数量的两倍。控制器的参数优化是通过遗传算法形式的进化计算来实现的。

4. 发明授权

US07685081B2 Bipedal walking simulation 有权
标题翻译：双扣步行模拟
公开(公告)号：US07685081B2
公开(公告)日：2010-03-23
申请号：US12122608
申请日：2008-05-16
申请人： Torsten Reil
发明人： Torsten Reil
IPC分类号： G06F15/18
CPC分类号： B25J9/161 , B62D57/032 , G05B2219/39273 , G05B2219/39284
摘要： An artificial multiped is constructed (either in simulation or embodied) in such a way that its natural body dynamics allow the lower part of each leg to swing naturally under the influence of gravity. The upper part of each leg is actively actuated in the sagittal plane. The necessary input to drive the above-mentioned actuators is derived from a neural network controller. The latter is arranged as two bi-directionally coupled chains of neural oscillators, the number of which equals twice that of the legs to be actuated. Parameter optimisation of the controllers is achieved by evolutionary computation in the form of a genetic algorithm.
摘要翻译：人造乘法器（仿真或体现）被构造成使得其自然的身体动力学允许每个腿的下部在重力的影响下自然地摆动。每个腿的上部在矢状平面中被主动地致动。驱动上述致动器的必要输入源自神经网络控制器。后者被布置为两个双向耦合的神经振荡器链，其数量等于要被致动的腿的数量的两倍。控制器的参数优化是通过遗传算法形式的进化计算来实现的。

5. 发明申请

US20080275831A1 Bipedal Walking Simulation 有权
标题翻译：双手步行模拟
公开(公告)号：US20080275831A1
公开(公告)日：2008-11-06
申请号：US12122608
申请日：2008-05-16
申请人： Torsten Reil
发明人： Torsten Reil
IPC分类号： G06F15/18
CPC分类号： B25J9/161 , B62D57/032 , G05B2219/39273 , G05B2219/39284
摘要： An artificial multiped is constructed (either in simulation or embodied) in such a way that its natural body dynamics allow the lower part of each leg to swing naturally under the influence of gravity. The upper part of each leg is actively actuated in the sagittal plane. The necessary input to drive the above-mentioned actuators is derived from a neural network controller. The latter is arranged as two bi-directionally coupled chains of neural oscillators, the number of which equals twice that of the legs to be actuated. Parameter optimisation of the controllers is achieved by evolutionary computation in the form of a genetic algorithm.
摘要翻译：人造乘法器（仿真或体现）被构造成使得其自然的身体动力学允许每个腿的下部在重力的影响下自然地摆动。每个腿的上部在矢状平面中被主动地致动。驱动上述致动器的必要输入源自神经网络控制器。后者被布置为神经振荡器的两个双向耦合的链，其数量等于要被致动的腿的数量的两倍。控制器的参数优化是通过遗传算法形式的进化计算来实现的。

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