公开(公告)号：US20220375210A1

公开(公告)日：2022-11-24

申请号：US17661041

申请日：2022-04-27

申请人： Robert Bosch GmbH

发明人： Anh Vien Ngo ,  Hanna Ziesche ,  Zohar Feldman ,  Dotan Di Castro

IPC分类号： G06V10/82 ,  G06V10/77 ,  G06V20/50 ,  B25J9/16 ,  G06N3/08

摘要： A method for controlling a robotic device. The method includes: obtaining an image, processing the image using a neural convolutional network, which generates an image in a feature space from the image, the image in the feature space, feeding the image in the feature space to a neural actor network, which generates an action parameter image, feeding the image in the feature space and the action parameter image to a neural critic network, which generates an assessment image, which defines for each pixel an assessment for the action defined by the set of action parameter values for that pixel, selecting, from multiple sets of action parameters of the action parameter image, that set of action parameter values having the highest assessment, and controlling the robot for carrying out an action according to the selected action parameter set.

公开(公告)号：US20220371185A1

公开(公告)日：2022-11-24

申请号：US17662123

申请日：2022-05-05

申请人： Robert Bosch GmbH

发明人： Alireza Ranjbar ,  Gerhard Neumann ,  Anh Vien Ngo ,  Hanna Ziesche

IPC分类号： B25J9/16 ,  G05B19/4155

摘要： A method for training a control arrangement for a controlled system. The control arrangement includes a regulation device and an actuator that operates according to a control strategy. The method includes the generation of control actions by the regulation device, each control action being generated by detecting measured variables that indicate a state of the controlled system, ascertaining a correction term for the detected measured variables by the actuator according to the control strategy, adapting the detected measured variables using the correction term for the detected measured variables, and generating the control action by supplying the adapted measured variables to the regulation device as the actual value. The method further includes training the control strategy by reinforcement learning for maximizing the gain that is achieved by the generated control actions.

公开(公告)号：US20230063799A1

公开(公告)日：2023-03-02

申请号：US17893596

申请日：2022-08-23

申请人： Robert Bosch GmbH

发明人： Anh Vien Ngo ,  Alexander Kuss ,  Hanna Ziesche ,  Miroslav Gabriel ,  Philipp Christian Schillinger ,  Zohar Feldman

IPC分类号： B25J9/16 ,  G06T7/10

摘要： A robot device, a method for training a robot control model, and a method for controlling a robot device. The method for training includes: supplying an image showing object(s), to a first and second prediction model to produce a first and second pickup prediction that has, for each pixel of the image, a first and second pickup robot configuration vector with an assigned first and second success probability; supplying the first and second pickup prediction to a blending model of the robot control model to produce a third pickup prediction that has, for each pixel of the image: a third pickup robot configuration vector that is a weighted combination of the first and second pickup robot configuration vector, and a third success probability that is a weighted combination of the first and second success probability; and training the robot control model by adapting the first and second weighting factors.