公开(公告)号：US20190118375A1

公开(公告)日：2019-04-25

申请号：US16230478

申请日：2018-12-21

Applicant: X DEVELOPMENT LLC

Inventor： Seyed Mohammad Khansari Zadeh

IPC: B25J9/16 ,  G05B19/423 ,  B25J13/08

CPC classification number: B25J9/163 ,  B25J9/1664 ,  B25J13/088 ,  G05B19/423 ,  G05B2219/40465 ,  G05B2219/40471 ,  G05B2219/40474 ,  Y10S901/04

Abstract: Generating a robot control policy that regulates both motion control and interaction with an environment and/or includes a learned potential function and/or dissipative field. Some implementations relate to resampling temporally distributed data points to generate spatially distributed data points, and generating the control policy using the spatially distributed data points. Some implementations additionally or alternatively relate to automatically determining a potential gradient for data points, and generating the control policy using the automatically determined potential gradient. Some implementations additionally or alternatively relate to determining and assigning a prior weight to each of the data points of multiple groups, and generating the control policy using the weights. Some implementations additionally or alternatively relate to defining and using non-uniform smoothness parameters at each data point, defining and using d parameters for stiffness and/or damping at each data point, and/or obviating the need to utilize virtual data points in generating the control policy.

公开(公告)号：US20180222045A1

公开(公告)日：2018-08-09

申请号：US15428916

申请日：2017-02-09

Applicant: X DEVELOPMENT LLC

Inventor： Seyed Mohammad Khansari Zadeh

IPC: B25J9/16 ,  B25J13/08

CPC classification number: B25J9/163 ,  B25J9/1664 ,  B25J13/088 ,  G05B19/423 ,  G05B2219/40465 ,  G05B2219/40471 ,  G05B2219/40474 ,  Y10S901/04

Abstract: Generating a robot control policy that regulates both motion control and interaction with an environment and/or includes a learned potential function and/or dissipative field. Some implementations relate to resampling temporally distributed data points to generate spatially distributed data points, and generating the control policy using the spatially distributed data points. Some implementations additionally or alternatively relate to automatically determining a potential gradient for data points, and generating the control policy using the automatically determined potential gradient. Some implementations additionally or alternatively relate to determining and assigning a prior weight to each of the data points of multiple groups, and generating the control policy using the weights. Some implementations additionally or alternatively relate to defining and using non-uniform smoothness parameters at each data point, defining and using d parameters for stiffness and/or damping at each data point, and/or obviating the need to utilize virtual data points in generating the control policy.

公开(公告)号：US20210229276A1

公开(公告)日：2021-07-29

申请号：US17230628

申请日：2021-04-14

Applicant: X Development LLC

Inventor： Seyed Mohammad Khansari Zadeh ,  Mrinal Kalakrishnan ,  Paul Wohlhart

IPC: B25J9/16 ,  G06N20/00 ,  G06N5/04

Abstract: Training and/or use of a machine learning model for placement of an object secured by an end effector of a robot. A trained machine learning model can be used to process: (1) a current image, captured by a vision component of a robot, that captures an end effector securing an object; (2) a candidate end effector action that defines a candidate motion of the end effector; and (3) a target placement input that indicates a target placement location for the object. Based on the processing, a prediction can be generated that indicates likelihood of successful placement of the object in the target placement location with application of the motion defined by the candidate end effector action. At many iterations, the candidate end effector action with the highest probability is selected and control commands provided to cause the end effector to move in conformance with the corresponding end effector action. When at least one release criteria is satisfied, control commands can be provided to cause the end effector to release the object, thereby leading to the object being placed in the target placement location.

公开(公告)号：US20210078167A1

公开(公告)日：2021-03-18

申请号：US16886545

申请日：2020-05-28

Applicant: X Development LLC

Inventor： Seyed Mohammad Khansari Zadeh ,  Daniel Kappler ,  Jianlan Luo ,  Jeffrey Bingham ,  Mrinal Kalakrishnan

IPC: B25J9/16 ,  B25J15/00 ,  G06T7/70 ,  G06K9/00 ,  G06T7/50 ,  G06T7/90

Abstract: Generating and utilizing action image(s) that represent a candidate pose (e.g., a candidate end effector pose), in determining whether to utilize the candidate pose in performance of a robotic task. The action image(s) and corresponding current image(s) can be processed, using a trained critic network, to generate a value that indicates a probability of success of the robotic task if component(s) of the robot are traversed to the particular pose. When the value satisfies one or more conditions (e.g., satisfies a threshold), the robot can be controlled to cause the component(s) to traverse to the particular pose in performing the robotic task.

公开(公告)号：US10391632B2

公开(公告)日：2019-08-27

申请号：US16230478

申请日：2018-12-21

Applicant: X DEVELOPMENT LLC

Inventor： Seyed Mohammad Khansari Zadeh

IPC: B25J9/16 ,  G05B19/423 ,  B25J13/08

Abstract: Generating a robot control policy that regulates both motion control and interaction with an environment and/or includes a learned potential function and/or dissipative field. Some implementations relate to resampling temporally distributed data points to generate spatially distributed data points, and generating the control policy using the spatially distributed data points. Some implementations additionally or alternatively relate to automatically determining a potential gradient for data points, and generating the control policy using the automatically determined potential gradient. Some implementations additionally or alternatively relate to determining and assigning a prior weight to each of the data points of multiple groups, and generating the control policy using the weights. Some implementations additionally or alternatively relate to defining and using non-uniform smoothness parameters at each data point, defining and using d parameters for stiffness and/or damping at each data point, and/or obviating the need to utilize virtual data points in generating the control policy.

公开(公告)号：US20230150126A1

公开(公告)日：2023-05-18

申请号：US18097153

申请日：2023-01-13

Applicant: X Development LLC

Inventor： Seyed Mohammad Khansari Zadeh

IPC: B25J9/16 ,  B25J13/08 ,  G05B19/423

CPC classification number: B25J9/163 ,  B25J9/1664 ,  B25J13/088 ,  G05B19/423 ,  Y10S901/04 ,  G05B2219/40465 ,  G05B2219/40471 ,  G05B2219/40474

Abstract: Generating a robot control policy that regulates both motion control and interaction with an environment and/or includes a learned potential function and/or dissipative field. Some implementations relate to resampling temporally distributed data points to generate spatially distributed data points, and generating the control policy using the spatially distributed data points. Some implementations additionally or alternatively relate to automatically determining a potential gradient for data points, and generating the control policy using the automatically determined potential gradient. Some implementations additionally or alternatively relate to determining and assigning a prior weight to each of the data points of multiple groups, and generating the control policy using the weights. Some implementations additionally or alternatively relate to defining and using non-uniform smoothness parameters at each data point, defining and using d parameters for stiffness and/or damping at each data point, and/or obviating the need to utilize virtual data points in generating the control policy.

公开(公告)号：US11607802B2

公开(公告)日：2023-03-21

申请号：US16886545

申请日：2020-05-28

Applicant: X Development LLC

Inventor： Seyed Mohammad Khansari Zadeh ,  Daniel Kappler ,  Jianlan Luo ,  Jeffrey Bingham ,  Mrinal Kalakrishnan

IPC: B25J9/16 ,  B25J15/00 ,  G06T7/70 ,  G06K9/00 ,  G06T7/50 ,  G06T7/90 ,  G06V20/10

Abstract: Generating and utilizing action image(s) that represent a candidate pose (e.g., a candidate end effector pose), in determining whether to utilize the candidate pose in performance of a robotic task. The action image(s) and corresponding current image(s) can be processed, using a trained critic network, to generate a value that indicates a probability of success of the robotic task if component(s) of the robot are traversed to the particular pose. When the value satisfies one or more conditions (e.g., satisfies a threshold), the robot can be controlled to cause the component(s) to traverse to the particular pose in performing the robotic task.

公开(公告)号：US20220410380A1

公开(公告)日：2022-12-29

申请号：US17843288

申请日：2022-06-17

Applicant: X Development LLC

Inventor： Yao Lu ,  Mengyuan Yan ,  Seyed Mohammad Khansari Zadeh ,  Alexander Herzog ,  Eric Jang ,  Karol Hausman ,  Yevgen Chebotar ,  Sergey Levine ,  Alexander Irpan

IPC: B25J9/16

Abstract: Utilizing an initial set of offline positive-only robotic demonstration data for pre-training an actor network and a critic network for robotic control, followed by further training of the networks based on online robotic episodes that utilize the network(s). Implementations enable the actor network to be effectively pre-trained, while mitigating occurrences of and/or the extent of forgetting when further trained based on episode data. Implementations additionally or alternatively enable the actor network to be trained to a given degree of effectiveness in fewer training steps. In various implementations, one or more adaptation techniques are utilized in performing the robotic episodes and/or in performing the robotic training. The adaptation techniques can each, individually, result in one or more corresponding advantages and, when used in any combination, the corresponding advantages can accumulate. The adaptation techniques include Positive Sample Filtering, Adaptive Exploration, Using Max Q Values, and Using the Actor in CEM.

公开(公告)号：US10207404B2

公开(公告)日：2019-02-19

申请号：US15428916

申请日：2017-02-09

Applicant: X DEVELOPMENT LLC

Inventor： Seyed Mohammad Khansari Zadeh

IPC: B25J9/16 ,  B25J13/08 ,  G05B19/423

Abstract: Generating a robot control policy that regulates both motion control and interaction with an environment and/or includes a learned potential function and/or dissipative field. Some implementations relate to resampling temporally distributed data points to generate spatially distributed data points, and generating the control policy using the spatially distributed data points. Some implementations additionally or alternatively relate to automatically determining a potential gradient for data points, and generating the control policy using the automatically determined potential gradient. Some implementations additionally or alternatively relate to determining and assigning a prior weight to each of the data points of multiple groups, and generating the control policy using the weights. Some implementations additionally or alternatively relate to defining and using non-uniform smoothness parameters at each data point, defining and using d parameters for stiffness and/or damping at each data point, and/or obviating the need to utilize virtual data points in generating the control policy.

公开(公告)号：US11607807B2

公开(公告)日：2023-03-21

申请号：US17230628

申请日：2021-04-14

Applicant: X Development LLC

Inventor： Seyed Mohammad Khansari Zadeh ,  Mrinal Kalakrishnan ,  Paul Wohlhart

IPC: B25J9/16 ,  G06N5/04 ,  G06N20/00 ,  G06N5/046

Abstract: Training and/or use of a machine learning model for placement of an object secured by an end effector of a robot. A trained machine learning model can be used to process: (1) a current image, captured by a vision component of a robot, that captures an end effector securing an object; (2) a candidate end effector action that defines a candidate motion of the end effector; and (3) a target placement input that indicates a target placement location for the object. Based on the processing, a prediction can be generated that indicates likelihood of successful placement of the object in the target placement location with application of the motion defined by the candidate end effector action. At many iterations, the candidate end effector action with the highest probability is selected and control commands provided to cause the end effector to move in conformance with the corresponding end effector action. When at least one release criteria is satisfied, control commands can be provided to cause the end effector to release the object, thereby leading to the object being placed in the target placement location.