公开(公告)号：US20160279790A1

公开(公告)日：2016-09-29

申请号：US15174858

申请日：2016-06-06

Applicant: Brain Corporation

Inventor： Philip Meier ,  Jean-Baptiste Passot ,  Borja Ibarz Gabardos ,  Patryk Laurent ,  Oleg Sinyavskiy ,  Peter O'Connor ,  Eugene Izhikevich

IPC: B25J9/16 ,  G06N99/00 ,  G06N3/00

CPC classification number: B25J9/163 ,  B25J9/1602 ,  B25J9/161 ,  B25J9/1656 ,  G05B2219/40116 ,  G05D1/0033 ,  G05D1/0088 ,  G05D2201/02 ,  G06N3/008 ,  G06N99/005 ,  Y10S901/01 ,  Y10S901/46

Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.

公开(公告)号：US20160096270A1

公开(公告)日：2016-04-07

申请号：US14542391

申请日：2014-11-14

Applicant: Brain Corporation

Inventor： Borja Ibarz Gabardos ,  Andrew Smith ,  Peter O'Connor

IPC: B25J9/16

CPC classification number: B25J9/163 ,  B25J9/1607 ,  B25J9/1666 ,  B25J9/1697 ,  G05D1/0088 ,  G05D1/0246 ,  G05D2201/02 ,  G06N3/00 ,  G06N3/008 ,  G06N3/049 ,  Y10S901/01 ,  Y10S901/03 ,  Y10S901/09 ,  Y10S901/47

Abstract: A robotic device may be operated by a learning controller comprising a feature learning configured to determine control signal based on sensory input. An input may be analyzed in order to determine occurrence of one or more features. Features in the input may be associated with the control signal during online supervised training. During training, learning process may be adapted based on training input and the predicted output. A combination of the predicted and the target output may be provided to a robotic device to execute a task. Feature determination may comprise online adaptation of input, sparse encoding transformations. Computations related to learning process adaptation and feature detection may be performed on board by the robotic device in real time thereby enabling autonomous navigation by trained robots.

Abstract translation: 机器人设备可以由包括被配置为基于感觉输入来确定控制信号的特征学习的学习控制器操作。 可以分析输入以确定一个或多个特征的发生。 输入中的特征可能与在线监督训练期间的控制信号相关联。 在训练中，学习过程可以根据训练输入和预测输出进行调整。 可以将预测和目标输出的组合提供给机器人装置以执行任务。 特征确定可以包括输入，稀疏编码变换的在线适配。 与学习过程适应和特征检测相关的计算可以由机器人设备实时执行，从而使训练有素的机器人能够进行自主导航。

公开(公告)号：US20150306761A1

公开(公告)日：2015-10-29

申请号：US14265113

申请日：2014-04-29

Applicant: Brain Corporation

Inventor： Peter O'Connor ,  Eugene Izhikevich

IPC: B25J5/00 ,  B25J9/16

CPC classification number: B25J9/1697 ,  B25J9/16 ,  G05D1/0221 ,  G05D2201/0206 ,  G05D2201/0209 ,  G06N3/008 ,  G06N3/049 ,  G06N3/084 ,  Y10S901/01 ,  Y10S901/47

Abstract: A robotic vehicle may be operated by a learning controller comprising a trainable convolutional network configured to determine control signal based on sensory input. An input network layer may be configured to transfer sensory input into a hidden layer data using a filter convolution operation. Input layer may be configured to transfer sensory input into hidden layer data using a filter convolution. Output layer may convert hidden layer data to a predicted output using data segmentation and a fully connected array of efficacies. During training, efficacy of network connections may be adapted using a measure determined based on a target output provided by a trainer and an output predicted by the network. A combination of the predicted and the target output may be provided to the vehicle to execute a task. The network adaptation may be configured using an error back propagation method. The network may comprise an input reconstruction.

Abstract translation: 机器人车辆可以由学习控制器操作，学习控制器包括被配置为基于感觉输入来确定控制信号的可训练卷积网络。 输入网络层可以被配置为使用滤波器卷积运算将感觉输入传送到隐藏层数据。 输入层可以被配置为使用滤波器卷积将感觉输入传送到隐藏层数据。 输出层可以使用数据分割和完全连接的功能阵列将隐藏层数据转换为预测输出。 在训练期间，可以使用基于由训练者提供的目标输出和由网络预测的输出确定的度量来调整网络连接的功效。 可以将预测和目标输出的组合提供给车辆以执行任务。 可以使用错误反向传播方法来配置网络适配。 网络可以包括输入重建。