Determining causal models for controlling environments

Patent metadata

Field	Value
Publication number	US-12386322-B2
Application number	US-202318512437-A
Country	US
Kind code	B2
Filing date	Nov 17, 2023
Priority date	Mar 15, 2019
Publication date	Aug 12, 2025
Grant date	Aug 12, 2025

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes identifying a procedural instance; determining a temporal extent for the procedural instance based on temporal extent parameters for the one or more entities in the procedural instance; selecting control settings for the procedural instance; monitoring environment responses to the control settings that are received for the one or more entities; determining which of the environment responses to attribute to the procedural instance in a causal model; and adjusting, based at least in part on the environment responses that are attributed to the procedural instance, the temporal extent parameters for the one or more entities.

First claim

What is claimed is:

1. A method comprising repeatedly performing the following:
identifying a procedural instance, wherein the procedural instance is a segment of the environment to which control settings are to be applied and that includes one or more entities for which environment responses are received;
determining a temporal extent for the procedural instance based on temporal extent parameters for the one or more entities in the procedural instance;
selecting control settings for the procedural instance;
monitoring environment responses to the control settings that are received for the one or more entities;
determining, based on a time window that is defined by the temporal extent for the procedural instance, which of the environment responses to attribute to the procedural instance in a causal model that identifies, for each controllable element, causal relationships between possible settings for the controllable element and a performance metric that measures a performance of the control system in controlling the environment; and
adjusting, based at least in part on the environment responses that are attributed to the procedural instance, the temporal extent parameters for the one or more entities.

2. The method of claim 1 , wherein identifying the procedural instance comprises:
determining, for each of a plurality of entities in the environment, a respective spatial extent based on a set of spatial extent parameters for the entity; and
generating one or more procedural instances that each include one or more of the entities in the environment based on the respective spatial extents for the entities.

3. The method of claim 1 , wherein determining, based on a time window that is defined by the temporal extent for the procedural instance, which of the environment responses to attribute to the procedural instance comprises:
determining to attribute each environment response that is received during a specified portion of the time window to the procedural instance.

4. The method of claim 1 , wherein the temporal extent parameters define a range of possible temporal extents and a respective probability for each of the possible temporal extents, and wherein determining the temporal extent comprises sampling the temporal extent from the range of possible temporal extents in accordance with the probabilities.

5. The method of claim 4 , wherein adjusting the temporal extent parameters comprises adjusting the probabilities for the possible temporal extents.

6. The method of claim 5 , wherein adjusting the probabilities for the possible temporal extents comprises:
adjusting the probabilities based on a difference measure that measures system performance between (i) procedural instances for which the control settings are selected using the causal model and (ii) environment instances for which control settings are selected using baseline probabilities that are independent of the causal model.

7. The method of claim 6 , wherein adjusting the probabilities comprises:
updating, based at least in part on the environment responses that are attributed to the procedural instance, a second causal model that measures causal effects between possible values of the temporal extent and the difference in system performance; and
mapping the updated second causal model to updated probabilities for the possible values.

8. The method of claim 4 , wherein adjusting the temporal extent parameters comprises adjusting the range of possible temporal extents.

9. The method of claim 1 , wherein different controllable elements have different temporal extent parameters, and different environment responses are attributed to the procedural instance for different controllable elements.

10. The method of claim 1 , wherein different entities in the environment have different temporal extent parameters.

11. The method of claim 1 , wherein different entities in the environment have the same temporal extent parameters.

12. At least one non-transitory computer-readable medium storing instructions that, when executed, configure at least one processor for repeatedly performing the following:
identifying a procedural instance, wherein the procedural instance is a segment of the environment to which control settings are to be applied and that includes one or more entities for which environment responses are received;
determining a temporal extent for the procedural instance based on temporal extent parameters for the one or more entities in the procedural instance;
selecting control settings for the procedural instance;
monitoring environment responses to the control settings that are received for the one or more entities;
determining, based on a time window that is defined by the temporal extent for the procedural instance, which of the environment responses to attribute to the procedural instance in a causal model that identifies, for each controllable element, causal relationships between possible settings for the controllable element and a performance metric that measures a performance of the control system in controlling the environment; and
adjusting, based at least in part on the environment responses that are attributed to the procedural instance, the temporal extent parameters for the one or more entities.

13. The at least one non-transitory computer-readable medium of claim 12 , wherein identifying the procedural instance comprises:
determining, for each of a plurality of entities in the environment, a respective spatial extent based on a set of spatial extent parameters for the entity; and
generating one or more procedural instances that each include one or more of the entities in the environment based on the respective spatial extents for the entities.

14. The at least one non-transitory computer-readable medium of claim 12 , wherein determining, based on a time window that is defined by the temporal extent for the procedural instance, which of the environment responses to attribute to the procedural instance comprises:
determining to attribute each environment response that is received during a specified portion of the time window to the procedural instance.

15. The at least one non-transitory computer-readable medium of claim 12 , wherein the temporal extent parameters define a range of possible temporal extents and a respective probability for each of the possible temporal extents, and wherein determining the temporal extent comprises sampling the temporal extent from the range of possible temporal extents in accordance with the probabilities.

16. The at least one non-transitory computer-readable medium of claim 15 , wherein adjusting the temporal extent parameters comprises adjusting the probabilities for the possible temporal extents.

17. The at least one non-transitory computer-readable medium of claim 16 , wherein adjusting the probabilities for the possible temporal extents comprises:
adjusting the probabilities based on a difference measure that measures system performance between (i) procedural instances for which the control settings are selected using the causal model and (ii) environment instances for which control settings are selected using baseline probabilities that are independent of the causal model.

18. The at least one non-transitory computer-readable medium of claim 15 , wherein adjusting the temporal extent parameters comprises adjusting the range of possible temporal extents.

19. At least one system comprising:
at least one computing device comprising one or more processors; and
at least one memory coupled to at least one

Assignees

• 3M Innovative Properties Company

Inventors

• Brooks Brian E
• Benoit Gilles J
• Olson Peter O
• Olson Tyler W
• Nayar Himanshu
• Arsenault Frederick J
• Johnson Nicholas A

Classifications

• G05B23/0248

  Causal models, e.g. fault tree; digraphs; qualitative physics · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F18/2193

  based on specific statistical tests · CPC title

• G05B13/021

  in which a variable is automatically adjusted to optimise the performance · CPC title

• B60W40/105

  Speed · CPC title