Marek P Michalowski

US Patent:

20200174460, Jun 4, 2020

Filed:

Dec 6, 2019

Appl. No.:

16/705445

Inventors:

- Mountain View CA, US
Eli Reekmans - San Francisco CA, US
Stoyan Gaydarov - Burlingame CA, US
Marek Michalowski - San Francisco CA, US
Michael Beardsworth - San Francisco CA, US
Ryan Butterfoss - San Francisco CA, US
Ytai Ben-Tsvi - Sunnyvale CA, US

International Classification:

G05B 19/418

Abstract:

Disclosed herein is a worksite automation process that involves: generating a first sequence of tasks to build the product according to a model. The process further involves causing one or more robotic devices to build the product by beginning to execute the first sequence of tasks. Further, during the execution of the first sequence of tasks, performing a buildability analysis to determine a feasibility of completing the product by executing the first sequence of tasks. Based on the analysis, determining that it is not feasible to complete the product by executing the first sequence of tasks, and in response, generating a second sequence of tasks to complete the product according to the model. Then, causing the one or more robotic devices to continue building the product by beginning to execute the second sequence of tasks.

US Patent:

20190308321, Oct 10, 2019

Filed:

Apr 24, 2019

Appl. No.:

16/392761

Inventors:

- Mountain View CA, US
Marek Michalowski - San Francisco CA, US
Michael Beardsworth - San Francisco CA, US

International Classification:

B25J 9/16

Abstract:

Described herein are methods and systems to establish a pre-build relationship in a model that specifies a first parameter for a first feature of a structure and a second parameter for a second feature of the structure. In particular, a computing system may receive data specifying a pre-build relationship that defines a build value of the first parameter in terms of a post-build observed value of the second parameter. During production of the structure, the computing system may determine the post-build observed value of the second parameter and, based on the determined post-build observed value, may determine the build value of the first parameter in accordance with the pre-build relationship. After determining the build value, the computing system may then transmit, to a robotic system, an instruction associated with production of the first feature by the robotic system, with that instruction specifying the determined build value of the first parameter.

US Patent:

20190184555, Jun 20, 2019

Filed:

Jan 18, 2019

Appl. No.:

16/251175

Inventors:

- Mountain View CA, US
Anthony Jules - Oakland CA, US
Marek Michalowski - San Francisco CA, US
Kendra Byrne - Mountain View CA, US
Jonathan Proto - San Francisco CA, US
Brandon Kruysman - San Francisco CA, US
Eli Reekmans - San Francisco CA, US

International Classification:

B25J 9/16
G05B 17/02
E04G 21/22
B25J 13/08

Abstract:

A robotic system includes one or more end-effectors that combine, according to a production process, at least one object and structure(s) at a production site. Sensor(s) generate, from the production site, sensor data relating to the production process. A control system stores specifications for the production process based on a model of the production site and/or the at least one object. The control system: receives, from the sensor(s), the sensor data; determines, from the sensor data, properties of at least one of: the production site or the at least one object; determines difference(s) between the properties and the model; determine(s) adjustment(s) to the production process based on the difference(s); and sends, for the end-effector(s), instruction(s) for combining the at least one object and the structure(s) based on the specifications and the one or more adjustments to the production process.

US Patent:

20180348742, Dec 6, 2018

Filed:

Jun 1, 2017

Appl. No.:

15/611777

Inventors:

- Mountain View CA, US
Eli Reekmans - San Francisco CA, US
Stoyan Gaydarov - San Francisco CA, US
Marek Michalowski - San Francisco CA, US
Michael Beardsworth - San Francisco CA, US
Ryan Butterfoss - San Francisco CA, US
Ytai Ben-Tsvi - Sunnyvale CA, US

International Classification:

G05B 19/418

Abstract:

Disclosed herein is a worksite automation process that involves: generating a first sequence of tasks to build the product according to a model. The process further involves causing one or more robotic devices to build the product by beginning to execute the first sequence of tasks. Further, during the execution of the first sequence of tasks, performing a buildability analysis to determine a feasibility of completing the product by executing the first sequence of tasks. Based on the analysis, determining that it is not feasible to complete the product by executing the first sequence of tasks, and in response, generating a second sequence of tasks to complete the product according to the model. Then, causing the one or more robotic devices to continue building the product by beginning to execute the second sequence of tasks.

US Patent:

20180290305, Oct 11, 2018

Filed:

Apr 7, 2017

Appl. No.:

15/481909

Inventors:

- Mountain View CA, US
Marek Michalowski - San Francisco CA, US
Michael Beardsworth - San Francisco CA, US

International Classification:

B25J 9/16

Abstract:

Described herein are methods and systems to establish a pre-build relationship in a model that specifies a first parameter for a first feature of a structure and a second parameter for a second feature of the structure. In particular, a computing system may receive data specifying a pre-build relationship that defines a build value of the first parameter in terms of a post-build observed value of the second parameter. During production of the structure, the computing system may determine the post-build observed value of the second parameter and, based on the determined post-build observed value, may determine the build value of the first parameter in accordance with the pre-build relationship. After determining the build value, the computing system may then transmit, to a robotic system, an instruction associated with production of the first feature by the robotic system, with that instruction specifying the determined build value of the first parameter.

US Patent:

20180029227, Feb 1, 2018

Filed:

Jul 28, 2016

Appl. No.:

15/222583

Inventors:

- Mountain View CA, US
Anthony Jules - Oakland CA, US
Marek Michalowski - San Francisco CA, US
Kendra Byrne - San Francisco CA, US
Jonathan Proto - San Francisco CA, US
Brandon Kruysman - San Francisco CA, US
Eli Reekmans - San Francisco CA, US

International Classification:

B25J 9/16
B25J 13/08
G05B 17/02

Abstract:

A robotic system includes one or more end-effectors that combine, according to a production process, at least one object and structure(s) at a production site. Sensor(s) generate, from the production site, sensor data relating to the production process. A control system stores specifications for the production process based on a model of the production site and/or the at least one object. The control system: receives, from the sensor(s), the sensor data; determines, from the sensor data, properties of at least one of: the production site or the at least one object; determines difference(s) between the properties and the model; determine(s) adjustment(s) to the production process based on the difference(s); and sends, for the end-effector(s), instruction(s) for combining the at least one object and the structure(s) based on the specifications and the one or more adjustments to the production process.

US Patent:

20180029235, Feb 1, 2018

Filed:

Jul 28, 2016

Appl. No.:

15/222568

Inventors:

- Mountain View CA, US
Anthony Jules - Oakland CA, US
Marek Michalowski - San Francisco CA, US
Kendra Byrne - San Francisco CA, US
Jonathan Proto - San Francisco CA, US
Brandon Kruysman - San Francisco CA, US
Eli Reekmans - San Francisco CA, US
Matthew Bitterman - San Francisco CA, US
Michael Scott Beardsworth - San Francisco CA, US

International Classification:

B25J 9/16
G05B 17/02
G05B 19/4063

Abstract:

A robotic system includes end-effector(s) that combine a plurality of objects in a production process. The system includes sensor(s) that obtain measurement(s) relating to a combination of a first object and one or more other objects during the production process. The system includes a control system communicatively coupled to the sensor(s). The control system stores specifications relating to the combination of the plurality of objects. The control system receives the measurement(s) from the sensor(s), determines a difference based on the measurement(s) and the specifications, determines adjustment(s) to the production process based on the determined difference, and sends, for the end-effector(s), instruction(s) based on the specifications and the one or more adjustment(s). The end-effector(s) combine a second object with the first object and the one or more objects based on the specifications and the one or more adjustment(s).