公开(公告)号：US20230010651A1

公开(公告)日：2023-01-12

申请号：US17772656

申请日：2019-10-29

Applicant: Biao ZHANG ,  ABB Schweiz AG

Inventor： Biao Zhang ,  Saumya Sharma ,  Yixin Liu ,  Jianjun Wang ,  Jorge Vidal-Ribas ,  Jordi Artigas ,  Ramon Casanelles

IPC: G06N3/08 ,  G06N3/04

Abstract: A system and method for collecting data regarding operation of a robot using, at least in part, responses from a first operation model to an input of sensed data from a plurality of sensors. The collected data can be used to optimize the first operation model to generate a second operation model. While the first operation model is being optimized, a train data-driven model that utilizes an end-to-end learning approach can be generated that is based, at least in part, on the collected data. Both the second operation model and the train data-driven model can be evaluated, and, based on such evaluation, a determination can be made as to whether the train data-driven model is reliable. Moreover, based on a comparison of the models, one of the second operation model and the train data-driven model can be selected for validation, and if validated, used in the operation of the robot.

公开(公告)号：US20220402136A1

公开(公告)日：2022-12-22

申请号：US17772365

申请日：2019-10-29

Applicant: Biao Zhang ,  ABB Schweiz AG

Inventor： Biao Zhang ,  Saumya Sharma ,  Yixin Liu ,  Jianjun Wang ,  Will Eakins ,  Andrew Salm ,  Yun Hsuan Su ,  Jorge Vidal-Ribas ,  Ramon Casanelles ,  Jordi Artigas

IPC: B25J9/16 ,  B25J13/08

Abstract: A system and method for determining performance of a robot. In one form the robot is constructed as you assembling automotive workpieces onto an automobile assembly. In one form the robot accomplishes the task of assembling an automotive workpiece onto the automotive assembly by using vision feedback and force feedback. The vision feedback can use any number of features perform its function. Such features can include an artificial feature such as but not limited to a QR code, as well as a natural feature such as a portion of the workpiece or automotive assembly. In one embodiment the robot is capable of detecting a collision event and assessing the severity of the collision event. In another embodiment the robot is capable of evaluating its performance by attracting a performance metric against a performance threshold, and comparing a sensor fusion output with a sensor fusion output reference.

公开(公告)号：US20210339397A1

公开(公告)日：2021-11-04

申请号：US16864798

申请日：2020-05-01

Applicant: ABB Schweiz AG

Inventor： Biao Zhang ,  Saumya Sharma ,  Yixin Liu ,  Jianjun Wang ,  Will Eakins ,  Andrew M. Salm ,  Yun Hsuan Su ,  Jorge Vidal-Ribas ,  Jordi Artigas ,  Ramon Casanelles

IPC: B25J9/16

Abstract: A robotic assembly operation is provided for assembling a second part to a first part. During setup of the assembly operation, control parameters and a control scheme are set and changed by simulating the operation and testing whether performance requirements are met. A dry run may be performed thereafter, and test data may be collected after running the simulation to determine if the performance requirements are satisfied during the dry run. During production, production data may also be collected and control parameters may be tuned when changes occur during production in order to maintain stable assembly.

公开(公告)号：US20210323164A1

公开(公告)日：2021-10-21

申请号：US16851946

申请日：2020-04-17

Applicant: ABB Schweiz AG

Inventor： Biao Zhang ,  Jianjun Wang ,  Yixin Liu ,  Saumya Sharma ,  Jorge Vidal-Ribas ,  Jordi Artigas ,  Ramon Casanelles

IPC: B25J9/16 ,  B25J13/08

Abstract: A system and method that automatically resolves conflicts among sensor information in a sensor fusion robot system. Such methods can accommodate converging ambiguous and divergent sensor information in a manner that can allow continued, and relatively accurate, robotic operations. The processes can include handling sensor conflict via sensor prioritization, including, but not limited, prioritization based on the particular stage or segment of the assembly operation when the conflict occurs, overriding sensor data that exceeds a threshold value, and/or prioritization based on evaluations of recent sensor performance, predictions, system configuration, and/or historical information. The processes can include responding to sensor conflicts through comparisons of the accuracy of workpiece location predictions from different sensors during different assembly stages in connection with arriving at a determination of which sensor(s) is providing accurate and reliable predictions.