公开(公告)号：US20240296662A1

公开(公告)日：2024-09-05

申请号：US18578471

申请日：2021-08-06

申请人： Siemens Corporation

发明人： Eugen Solowjow ,  Ines Ugalde Diaz ,  Yash Shahapurkar ,  Juan L. Aparicio Ojea ,  Heiko Claussen

IPC分类号： G06V10/774 ,  G06T15/20 ,  G06V10/764 ,  G06V10/776 ,  G06V20/70

CPC分类号： G06V10/774 ,  G06T15/20 ,  G06V10/764 ,  G06V10/776 ,  G06V20/70

摘要： A computer-implemented method for building an object detection module uses mesh representations of objects belonging to specified object classes of interest to render images by a physics-based simulator. Each rendered image captures a simulated environment containing objects belonging to multiple object classes of interest placed in a bin or on a table. The rendered images are generated by randomizing a set of parameters by the simulator to render a range of simulated environments. The randomized parameters include environmental and sensor-based parameters. A label is generated for each rendered image, which includes a two-dimensional representation indicative of location and object classes of objects in that rendered image frame. Each rendered image and the respective label constitute a data sample of a synthetic training dataset. A deep learning model is trained using the synthetic training dataset to output object classes from an input image of a real-world physical environment.

公开(公告)号：US20240198530A1

公开(公告)日：2024-06-20

申请号：US18557967

申请日：2021-06-25

申请人： Siemens Corporation

发明人： Ines Ugalde Diaz ,  Eugen Solowjow ,  Juan L. Aparicio Ojea ,  Martin Sehr ,  Heiko Claussen

IPC分类号： B25J9/16 ,  G06T7/73 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V20/50 ,  G06V20/70

CPC分类号： B25J9/1679 ,  B25J9/1697 ,  G06T7/73 ,  G06V10/764 ,  G06V10/811 ,  G06V10/82 ,  G06V20/50 ,  G06V20/70 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20084

摘要： In described embodiments of method for executing autonomous bin picking, a physical environment comprising a bin containing a plurality of objects is perceived by one or more sensors. Multiple artificial intelligence (AI) modules feed from the sensors to compute grasping alternatives, and in some embodiments, detected objects of interest. Grasping alternatives and their attributes are computed based on the outputs of the AI modules in a high-level sensor fusion (HLSF) module. A multi-criteria decision making (MCDM) module is used to rank the grasping alternatives and select the one that maximizes the application utility while satisfying specified constraints.

公开(公告)号：US20230359864A1

公开(公告)日：2023-11-09

申请号：US18043400

申请日：2020-08-31

申请人： Siemens Corporation ,  SIEMENS INDUSTRY, INC.

发明人： Martin Sehr ,  Eugen Solowjow ,  Wei Xi Xia ,  Shashank Tamaskar ,  Ines Ugalde Diaz ,  Heiko Claussen ,  Juan L. Aparicio Ojea

IPC分类号： G06N3/045

CPC分类号： G06N3/045 ,  G05B13/027

摘要： An edge device can be configured to perform industrial control operations within a production environment that defines a physical location. The edge device can include a plurality of neural network layers that define a deep neural network. The edge device be configured to obtain data from one or more sensors at the physical location defined by the production environment. The edge device can be further configured to perform one or more matrix operations on the data using the plurality of neural network layers so as to generate a large scale matrix computation at the physical location defined by the production environment. In some examples, the edge device can send the large scale matrix computation to a digital twin simulation model associated with the production environment, so as to update the digital twin simulation model in real time.