Robotic workspace layout planning

Patent metadata

Field	Value
Publication number	US-11209798-B1
Application number	US-201916265123-A
Country	US
Kind code	B1
Filing date	Feb 1, 2019
Priority date	Feb 1, 2019
Publication date	Dec 28, 2021
Grant date	Dec 28, 2021

Abstract

This specification describes systems, methods, devices, and other techniques for planning workspaces for automated fabrication processes. A computing system facilitates planning by receiving a set of parameters for planning a layout of a workspace for an automated fabrication process, and generating a plurality of candidate workspace layouts, including selecting, for each candidate workspace layout, (i) one or more robots for performing tasks in the automated fabrication process and (ii) corresponding locations for the one or more robots within the workspace. The system determines an optimal workspace layout based on the plurality of candidate workspace layouts, generates a workspace layout specification for the optimal workspace layout, and provides the workspace layout specification to one or more second computing systems.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving, by a first computing system, a set of parameters for planning a layout of a workspace for an automated fabrication process;
generating, by the first computing system, a plurality of candidate workspace layouts, including implementing a decision tree that branches according to variations in the plurality of candidate workspace layouts, wherein:
(i) each internal node of the decision tree represents a partially defined candidate workspace layout,
(ii) sibling nodes of the decision tree represent alternative candidate workspace layouts that differ from each other in at least one dimension, and
(iii) at least some of the plurality of candidate workspace layouts identify one or more robots for performing tasks in the automated fabrication process and corresponding locations for the one or more robots within the workspace;

selecting, by the first computing system and from among the plurality of candidate workspace layouts, an optimal workspace layout, wherein the optimal workspace layout is selected based on the optimal workspace layout optimizing an objective function that evaluates the plurality of candidate workspace layouts;
generating, by the first computing system, a workspace layout specification for the optimal workspace layout; and
directing a particular robot to move to a particular location in the workspace according to the workspace layout specification, thereby causing the particular robot to move to the particular location.

2. The computer-implemented method of claim 1 , comprising using the workspace layout specification to configure the workspace according to the optimal workspace layout.

3. The computer-implemented method of claim 1 , wherein generating the workspace layout specification comprises generating a computer-aided design (CAD) file storing data representing the optimal workspace layout.

4. The computer-implemented method of claim 1 , wherein the workspace comprises factory floor space that has been allocated for the automated fabrication process, and the automated fabrication process comprises a manufacturing process.

5. The computer-implemented method of claim 1 , wherein the set of parameters for planning the layout of the workspace comprises: product design parameters that describe a physical design of a product of the automated fabrication process; and environmental parameters that describe physical attributes of the workspace.

6. The computer-implemented method of claim 5 , wherein the set of parameters for planning the layout of the workspace further comprises resource parameters that describe a catalog of available resources for implementing the automated process and corresponding costs for use of the resources.

7. The computer-implemented method of claim 5 , wherein the set of parameters for planning the layout of the workspace further comprises process parameters that describe tasks to be performed in the automated fabrication process.

8. The computer-implemented method of claim 1 , wherein the objective function is programmed to at least one of promote selection of similar resources to implement the automated fabrication process or penalize selection of dissimilar resources to implement the automated fabrication process.

9. The computer-implemented method of claim 1 , wherein generating the plurality of candidate workspace layouts further includes, for at least one of the candidate workspace layouts, selecting one or more sensors and corresponding locations for the one or more sensors in the workspace, the one or more sensors configured to monitor execution of the automated fabrication process.

10. The computer-implemented method of claim 1 , wherein generating the plurality of candidate workspace layouts comprises spatially discretizing the workspace and determining locations for the one or more robots in the workspace that correspond to discretized points.

11. The computer-implemented method of claim 1 , wherein each leaf node in the decision tree represents a fully defined candidate workspace layout.

12. The computer-implemented method of claim 1 , comprising systematically traversing the decision tree to determine the optimal workspace layout, including at each internal node, following a path through a particular child node of the internal node that best optimizes an objective function among multiple child nodes of the internal node.

13. The computer-implemented method of claim 1 , wherein the first computing system is configured to iteratively generate nodes along the decision tree and to incrementally traverse the decision tree along a path that optimizes the objective function.

14. The computer-implemented method of claim 1 , wherein generating the plurality of candidate workspace layouts comprises selecting, from a set of alternative candidate workspace layouts, the plurality of candidate workspace layouts as a representative subset of candidate workspace layouts, and wherein determining the optimal workspace layout comprises evaluating the candidate workspace layouts to the exclusion of other workspace layouts from the set of alternative candidate workspace layouts that are not part of the representative subset.

15. One or more non-transitory computer-readable media having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving, by a first computing system, a set of parameters for planning a layout of a workspace for an automated fabrication process;
generating, by the first computing system, a plurality of candidate workspace layouts, including implementing a decision tree that branches according to variations in the plurality of candidate workspace layouts, wherein:
(i) each internal node of the decision tree represents a partially defined candidate workspace layout,
(ii) sibling nodes of the decision tree represent alternative candidate workspace layouts that differ from each other in at least one dimension, and
(iii) at least some of the plurality of candidate workspace layouts identify one or more robots for performing tasks in the automated fabrication process and corresponding locations for the one or more robots within the workspace;

selecting, by the first computing system and from among the plurality of candidate workspace layouts, an optimal workspace layout, wherein the optimal workspace layout is selected based on the optimal workspace layout optimizing an objective function that evaluates the plurality of candidate workspace layouts;
generating, by the first computing system, a workspace layout specification for the optimal workspace layout; and
directing a particular robot to move to a particular location in the workspace according to the workspace layout specification, thereby causing the particular robot to move to the particular location.

16. The computer-readable media of claim 15 , wherein the operations comprise using the workspace layout specification to configure the workspace according to the optimal workspace layout.

17. A system, comprising:
one or more processing devices; and
one or more computer-readable media having instructions stored thereon that, when executed by the one or more processing devices, cause performance of operations comprising:
receiving a set of parameters for planning a layout of a workspace for an automated fabrication process;
generating a plurality of candidate workspace layouts, including implementing a decision tree that branches according to variations in the plurality of candidate workspace layouts, wh

Assignees

• Intrinsic Innovation Llc

Inventors

• Michalowski Marek
• Beardsworth Michael

Classifications

• Y02P90/02

  Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS] · CPC title

• G05B2219/31054

  Planning, layout of assembly system · CPC title

• G05B2219/32085

  Layout of factory, facility, cell, production system planning · CPC title

• G05B19/4188 Primary

  characterised by CIM planning or realisation · CPC title

• G05B2219/50391

  Robot · CPC title