-
公开(公告)号：US11584008B1
公开(公告)日：2023-02-21
申请号：US17067525
申请日：2020-10-09
Applicant: Amazon Technologies, Inc.
Inventor： Brian C. Beckman , Leonardo Ruggiero Bachega , Brandon William Porter , Benjamin Lev Snyder , Michael Vogelsong , Corrinne Yu
IPC: B25J9/16
Abstract: A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robotic system performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.
-
公开(公告)号：US10792810B1
公开(公告)日：2020-10-06
申请号：US15842707
申请日：2017-12-14
Applicant: Amazon Technologies, Inc.
Inventor： Brian C. Beckman , Leonardo Ruggiero Bachega , Brandon William Porter , Benjamin Lev Snyder , Michael Vogelsong , Corrinne Yu
Abstract: A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robot performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.
-
公开(公告)号：US11707838B1
公开(公告)日：2023-07-25
申请号：US17167958
申请日：2021-02-04
Applicant: Amazon Technologies, Inc.
Inventor： Michael Vogelsong , Darren Ernest Canavor
IPC: B25J9/16
CPC classification number: B25J9/163 , B25J9/1671
Abstract: A machine learning system builds and uses control policies for controlling robotic performance of a task. Such control policies may be trained using targeted updates. For example, two trials identified as similar may be compared and evaluated to determine which trial achieved a greater degree of task success; a control policy update may then be generated based on identified differences between the two trials.
-
Patent Agency Ranking
公开(公告)号：US11862037B1
公开(公告)日：2024-01-02
申请号：US16453449
申请日：2019-06-26
Applicant: Amazon Technologies, Inc.
Inventor： David Lawrence Seymore , Leo Benedict Baldwin , David Heckerman , Michael Vogelsong , Maulik Majmudar
CPC classification number: G09B19/0092 , A61B5/0205 , A61B5/14517 , A61B5/14532 , A61B5/318 , A61B5/681 , A61B5/742 , G16H20/60 , A61B5/02438 , A61B2562/0204
Abstract: Systems, devices, and methods are provided for detecting and correcting eating behavior. A device may receive audio data, determine that the audio data is indicative of consumption of a product by a user. The device may determine, based on the product, a measureable attribute associated with the user. The device may receive first data associated with the measureable attribute. The device may determine that the first data exceeds a threshold. The device may generate a message for presentation.
-
5.发明授权公开(公告)号：US10766136B1
公开(公告)日：2020-09-08
申请号：US15803610
申请日：2017-11-03
Applicant: Amazon Technologies, Inc.
Inventor： Brandon William Porter , Leonardo Ruggiero Bachega , Brian C. Beckman , Benjamin Lev Snyder , Michael Vogelsong , Corrinne Yu
Abstract: A machine learning system builds and uses computer models for identifying how to evaluate the level of success reflected in a recorded observation of a task. Such computer models may be used to generate a policy for controlling a robotic system performing the task. The computer models can also be used to evaluate robotic task performance and provide feedback for recalibrating the robotic control policy.
-
公开(公告)号：US10926408B1
公开(公告)日：2021-02-23
申请号：US15870613
申请日：2018-01-12
Applicant: Amazon Technologies, Inc.
Inventor： Michael Vogelsong , Darren Ernest Canavor
IPC: B25J9/16
Abstract: A machine learning system builds and uses control policies for controlling robotic performance of a task. Such control policies may be trained using targeted updates, for example by comparing two trials to identify which represents a greater degree of task success, using this to generate updates from a reinforcement learning system, and weighting the updates based on differences between action vectors of the trials.
-
公开(公告)号：US10800040B1
公开(公告)日：2020-10-13
申请号：US15842737
申请日：2017-12-14
Applicant: Amazon Technologies, Inc.
Inventor： Brian C. Beckman , Leonardo Ruggiero Bachega , Brandon William Porter , Benjamin Lev Snyder , Michael Vogelsong , Corrinne Yu
IPC: B25J9/16
Abstract: A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robot performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.
-
8.发明授权公开(公告)号：US10766137B1
公开(公告)日：2020-09-08
申请号：US15803621
申请日：2017-11-03
Applicant: Amazon Technologies, Inc.
Inventor： Brandon William Porter , Leonardo Ruggiero Bachega , Brian C. Beckman , Benjamin Lev Snyder , Michael Vogelsong , Corrinne Yu
Abstract: A machine learning system builds and uses computer models for identifying how to evaluate the level of success reflected in a recorded observation of a task. Such computer models may be used to generate a policy for controlling a robotic system performing the task. The computer models can also be used to evaluate robotic task performance and provide feedback for recalibrating the robotic control policy.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.02 seconds)
