IP Library Granted Patent US 11,547,088
Granted Patent B2
US 11,547,088 · App. 17/317,518 · Granted Jan 10, 2023

System and method for selecting and executing training protocols for autonomously training an animal

Inventors: Paul Mundell (San Francisco, CA); John Honchariw (San Francisco, CA); Noémie A. Guérin (San Francisco, CA); Sayli Benadikar (San Francisco, CA); Tim Genske (San Francisco, CA)
Assignee: Companion Labs, Inc.
A01K15/02G06F16/635G06V20/20G06V40/10G06V40/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,547,088
App. No.
17/317,518
Granted
Jan 10, 2023
Kind
B2
Abstract

One variation of a method for autonomously training an animal includes: loading an autonomous training protocol for the animal onto a training apparatus configured to dispense units of a primary reinforcer responsive to behaviors performed by the animal; during an autonomous training session for the animal, accessing a video feed of a working field near the training apparatus, detecting the animal in the video feed, and executing the first autonomous training protocol; calculating a training score for the autonomous training session based on behaviors performed by the animal during the autonomous training session; selecting a manual training protocol, from a set of manual training protocols, based on the training score; generating a prompt to execute the first manual training protocol with the animal during a first manual training session; and transmitting the prompt to a user associated with the animal.

Claims (97)

1. A method for training an animal, comprising:

during an initial period, loading a first autonomous training protocol onto a training apparatus;

during a first autonomous training session for the animal:

accessing a video feed recorded by an optical sensor integrated into the training apparatus and defining a field of view intersecting a working field;

detecting the animal in the video feed; and

dispensing units of a primary reinforcer via a dispenser, integrated into the training apparatus, based on behaviors performed by the animal according to the first autonomous training protocol; and

during an interim period succeeding the first autonomous training session:

calculating a first training score for the animal based on behaviors performed by the animal during the first autonomous training session; and

in response to the first training score falling below a threshold training score, selecting a first manual training protocol, from a set of manual training protocols, for execution during manual training between a user associated with the animal and the animal, based on the first training score.

2. The method of claim 1 , further comprising:

generating a prompt to execute the first manual training protocol with the animal during a first manual training session prior to a next autonomous training session for the animal; and

transmitting the prompt to a user associated with the animal.

3. The method of claim 1 , wherein selecting the first manual training protocol, from the set of manual training protocols, in response to the first training score falling below the threshold training score comprises:

accessing the set of manual training protocols comprising:

the first manual training protocol defining a first difficulty level; and

a second manual training protocol defining a second difficulty level greater than the first difficulty level; and

in response to the first training score falling below the threshold training score, selecting the first manual training protocol defining the first difficulty level.

4. The method of claim 1 , further comprising, in response to the first training score exceeding the threshold training score, selecting a second manual training protocol, from the set of training protocols, for execution during manual training between the user and the animal.

5. The method of claim 1 :

further comprising, during the first autonomous training session:

tracking a quantity of attempts of a set of commands output by the training apparatus for the animal; and

tracking a quantity of successes of the quantity of attempts for the animal; and

wherein calculating the first training score based on behaviors performed by the animal during the first autonomous training session comprises calculating the first training score based on the quantity of attempts and the quantity of successes during the first autonomous training session.

6. The method of claim 1 , further comprising:

during a second autonomous training session succeeding the first autonomous training session:

accessing a second video feed of the working field;

detecting the animal in the second video feed; and

dispensing units of the primary reinforcer based on behaviors performed by the animal according to the first autonomous training protocol; and

during a second interim period succeeding the second autonomous training session:

calculating a second training score for the second autonomous training session based on behaviors performed by the animal during the second autonomous training session; and

in response to the second training score falling below a second threshold training score, selecting a second manual training protocol, from the set of manual training protocols, for execution during manual training, based on the second training score.

7. The method of claim 6 , wherein selecting the second manual training protocol for execution during manual training based on the second training score comprises:

characterizing a difference between the first training score and the second training score for the animal; and

in response to the difference falling below a threshold difference, selecting a second manual training protocol, from the set of manual training protocols, in replacement of the first manual training protocol.

8. The method of claim 1 , further comprising, calculating an anxiety score for the animal for the first autonomous training session based on body language of the animal in the video feed.

9. The method of claim 8 , further comprising, calculating a composite training score for the first autonomous training session based on the anxiety score and the first training score.

10. The method of claim 8 , wherein calculating the anxiety score for the animal for the first autonomous training session comprises:

characterizing an anxiety level of the animal during the first autonomous training session based on body language of the animal extracted from the video feed; and

calculating the anxiety score for the animal based on the anxiety level of the animal throughout the first autonomous training session.

11. The method of claim 10 , further comprising, in response to the anxiety level exceeding a threshold anxiety level during the first autonomous training session:

selecting a first intervention action, from a set of intervention actions, configured to reduce the anxiety level during the first autonomous training session;

at the training apparatus, executing the first intervention action.

12. The method of claim 1 , further comprising:

during a second autonomous training session succeeding the first autonomous training session:

accessing a second video feed of the working field;

detecting the animal in the second video feed; and

dispensing units of the primary reinforcer based on behaviors performed by the animal according to the first autonomous training protocol;

during a second interim period succeeding the second autonomous training session:

calculating a second training score for the second autonomous training session based on behaviors performed by the animal during the second autonomous training session;

characterizing a training progression of the animal for the first autonomous training protocol based on the first training score and the second training score; and

in response to the training progression falling below a threshold training progression, amending the first manual training protocol.

13. The method of claim 1 , wherein dispensing units of the primary reinforcer based on behaviors performed by the animal comprises, during the first autonomous training session:

outputting a command;

detecting a first action of the animal in the video feed responsive to the command;

characterizing a difference between the first action and a set of actions corresponding to the command; and

in response to the difference falling below a threshold, dispensing a first unit of the primary reinforcer into the field.

14. A method for autonomously training an animal comprising:

during a first autonomous training session with the animal:

accessing a video feed recorded by an optical sensor integrated into a training apparatus and defining a field of view intersecting a working field;

detecting the animal in the video feed;

dispensing units of a primary reinforcer via a dispenser, integrated into the training apparatus, based on behaviors performed by the animal according to the first autonomous training protocol; and

tracking an anxiety level of the animal based on behaviors of the animal detected in the video feed; and

during an interim period succeeding the first autonomous training session:

calculating a composite training score for the animal based on the anxiety level and behaviors performed by the animal during the first autonomous training session; and

in response to the composite training score exceeding a threshold training score, selecting a first manual training protocol, from a set of manual training protocols, for execution during manual training between a user associated with the animal and the animal, based on the composite training score.

15. The method of claim 14 , further comprising:

generating a prompt to execute the first manual training protocol with the animal during a first manual training session preceding a next autonomous training session; and

transmitting the prompt to a user associated with the animal.

16. The method of claim 14 , wherein calculating the composite training score based on the anxiety level and behaviors performed by the animal during the first autonomous training session comprises:

calculating an anxiety score for the animal based on the anxiety level of the animal throughout the first autonomous training session;

calculating a training score for the animal based on behaviors performed by the animal during the first autonomous training session; and

calculating the composite training score based on a combination of the anxiety score and the training score.

17. The method of claim 14 , wherein tracking the anxiety level of the animal comprises:

at a first time during the first autonomous training session:

extracting a first image of the animal from the video feed captured at approximately the first time;

characterizing a first posture of the animal based on the first image; and

characterizing a first anxiety level of the animal based on the first posture; and

at a second time succeeding the first time during the first autonomous training session:

extracting a second image of the animal from the video feed captured at approximately the second time;

characterizing a second posture of the animal based on the second image; and

characterizing a second anxiety level of the animal based on the second posture.

18. The method of claim 14 , further comprising, at a first time, during the first autonomous training session, in response to the anxiety level exceeding a threshold anxiety level:

selecting a first intervention action, from a set of intervention actions, configured to reduce the anxiety level of the animal; and

at the training apparatus, executing the first intervention action at approximately the first time.

19. The method of claim 14 , further comprising:

during a second autonomous training session with the animal succeeding the first manual training session:

accessing the video feed of the working field near the training apparatus;

detecting the animal in the video feed; and

tracking a second anxiety level of the animal based on behaviors of the animal detected in the video feed; and

during a second interim period succeeding the second autonomous training session:

characterizing a difference between the anxiety level for the first autonomous training session and the second anxiety level for the second autonomous training session; and

in response to the difference falling below a threshold difference:

generating a prompt to execute a user intervention action prior to a third autonomous training session succeeding the second autonomous training session; and

transmitting the prompt to the user.

20. The method of claim 14 , wherein tracking the anxiety level of the animal during the first autonomous training session comprises, in response to dispensing a first unit of the primary reinforcer into the working field:

tracking a duration between dispensation of the first unit of the primary reinforcer and consumption of the first unit of the primary reinforcer; and

characterizing an anxiety level of the animal based on the duration.

Assignments (3)
SECURITY INTEREST Recorded Sep 17, 2026
From: SYNERGY IP HOLDINGS, LLC
To: ALTER DOMUS (US) LLC, AS COLLATERAL AGENT
Reel/Frame 076059/0617 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 24, 2026
From: VETVISION, LLC
To: SYNERGY IP HOLDINGS, LLC
Reel/Frame 075753/0155 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 18, 2022
From: MUNDELL, PAUL; HONCHARIW, JOHN; GUÉRIN, NOÉMIE A.; BENADIKAR, SAYLI; GENSKE, TIM
To: COMPANION LABS, INC.
Reel/Frame 061829/0249 →
Continuity (4)
Continuation 17146411 · Jan 11, 2021
Provisional Application 62959700 · Jan 10, 2020
Provisional Application 62959706 · Jan 10, 2020
Related Publication 20210289747A1 · Sep 23, 2021