SYSTEMS AND METHODS FOR AUTONOMOUSLY SOOTHING BABIES

• US 20170340285A1
• Filed: 05/23/2017
• Published: 11/30/2017
• Est. Priority Date: 05/24/2016
• Status: Active Grant

• Current Assignee: Graco Children's Products, Inc. (Newell Brands Inc.)
• Original Assignee: Graco Children's Products, Inc. (Newell Brands Inc.)
• Inventors: Rubin, Zachary, Hondros, Bradley Keith, Ahmad, Mubeen, Steer, William Andrew, Pinkney, Justin, Smudde, Bart A., Kelly, Brian S.
• Granted Patent: US 10,238,341 B2
• Time in Patent Office: Days
• CPC Class Codes: A47D 9/057 driven by electric motors
• CPC Class Codes: A61B 2503/04 Babies, e.g. for SIDS detection
• CPC Class Codes: A61B 5/4809 Sleep detection, i.e. determining whether a subject is asleep or not
• CPC Class Codes: A61B 5/6887 mounted on external non-worn devices, e.g. non-medical devices
• CPC Class Codes: A61B 5/6891 Furniture
• CPC Class Codes: A61B 5/7405 using sound
• CPC Class Codes: A63H 33/006 Infant exercisers, e.g. for attachment to a crib
• CPC Class Codes: B62B 9/22 Devices for rocking or oscillating

Abstract

Systems and methods are disclosed for autonomously soothing babies. An example method may include receiving a first sound input from a microphone, processing the first sound input, determining a baby status based at least in part on the first sound input, determining an output action based at least in part on the baby status; and implementing the output action at the children'"'"'s apparatus.

Claims

1. A method comprising:

receiving, by a children'"'"'s apparatus comprising one or more computer processors coupled to at least one memory, a first sound input from a microphone;

processing the first sound input;

determining a baby status based at least in part on the first sound input;

determining an output action based at least in part on the baby status; and

implementing the output action at the children'"'"'s apparatus.

2. The method of claim 1, wherein processing the first sound input comprises detecting an acoustic signature of a baby'"'"'s cry using a sound processing algorithm.

3. The method of claim 2, wherein the sound processing algorithm comprises a mel frequency cepstral coefficient sound processing algorithm.

4. The method of claim 1, wherein processing the first sound input comprises:

determining a Fourier transform of the first sound input; and

determining a standard deviation of the Fourier transform;

wherein determining the baby status is based at least in part on the standard deviation.

5. The method of claim 4, further comprising:

determining a power spectral density estimate of the first sound input; and

determining a maximum value of the power spectral density estimate;

determining that the standard deviation and the maximum value are associated with the output action;

wherein determining the baby status is based at least in part on the maximum value.

6. The method of claim 1, wherein the baby status is an uncomfortable baby status, the method further comprising:

determining an operational mode of the device; and

determining an active device setting modification profile using the operational mode;

wherein determining the output action comprises selecting an output action using the active device setting modification profile.

7. The method of claim 1, wherein determining the baby status comprises selecting the baby status from one of:

a crying status, a whining status, a babbling status, a laughing status, or a non-baby status.

8. The method of claim 1, wherein determining the output action comprises adjusting a swing speed, adjusting a vibration intensity, or adjusting a sound output volume.

9. The method of claim 1, wherein the first sound input is a discrete segment of sound data or streaming sound data.

10. The method of claim 1, further comprising:

determining that the baby status is a soothed baby status; and

implementing a post-soothing device setting modification.

11. The method of claim 1, wherein the baby status is a first baby status and the output action is a first output action, the method further comprising:

receiving a second sound input;

processing the second sound input;

determining a second baby status based at least in part on the second sound input;

determining that the second baby status is different than the first baby status; and

determining a second output action based at least in part on the second baby status.

12. The method of claim 1, further comprising:

detecting a motion; and

determining an amount of motion;

wherein determining the output action is based at least in part on the amount of motion.

13. An apparatus comprising:

a baby supporting portion; and

one or more processors configured to execute computer-executable instructions to;

receive a first sound input;

process the first sound input;

determine a baby status based at least in part on the first sound input; and

determine an output action based at least in part on the baby status.

14. The apparatus of claim 13, wherein the controller is configured to determine the output action by adjusting a swing speed, adjusting a vibration intensity, or adjusting a sound output volume.

15. The apparatus of claim 13, wherein the baby status is a first baby status and the output action is a first output action, and wherein the controller is further configured to:

receive a second sound input;

process the second sound input;

determine a second baby status based at least in part on the second sound input;

determine that the second baby status is different than the first sound input; and

determine a second output action based at least in part on the second baby status.

16. The apparatus of claim 13, further comprising at least one of:

a swing apparatus, a vibration motor, one or more light sources, or one or more speakers.

17. The apparatus of claim 13, further comprising a motion sensor, wherein the controller is further configured to:

detect a motion; and

determine an amount of motion;

wherein the controller is configured to determine the output action is based at least in part on the amount of motion.

18. A method comprising:

determining, by one or more computer processors coupled to at least one memory, that a baby is crying based at least in part on detected sound from a microphone;

determining a soothing response action hierarchy comprising a plurality of response actions;

determining that a first response action of the plurality of response actions has been implemented;

implementing a second response action of the plurality of response actions; and

determining that the baby is not crying after a predetermined time interval has elapsed.

19. The method of claim 18, further comprising:

receiving the detected sound; and

processing the detected sound to generate sound data;

wherein determining that the baby is crying based at least in part on the detected sound comprises comparing the sound data to one or more data files in a sound database.

20. The method of claim 18, further comprising:

determining that the second response action was more effective than the first response action; and

updating the soothing response action hierarchy to prioritize the second response action over the first response action.