Component connection verification device and method

Patent metadata

Field	Value
Publication number	US-11954252-B2
Application number	US-202117169315-A
Country	US
Kind code	B2
Filing date	Feb 5, 2021
Priority date	Feb 27, 2020
Publication date	Apr 9, 2024
Grant date	Apr 9, 2024

Abstract

A device for verifying the connection of components by a gripper, wherein connecting two or more components produces a connection sound. The device comprises a plurality of audio sensors, a fastener for securing the plurality of audio sensors at different positions on the gripper, and a controller. The controller comprises an input for receiving the audio signals from the plurality of audio sensors, a neural network for isolating the connection sound from the audio signals received from the plurality of audio sensors using independent component analysis based on training audio data obtained from audio signals received during a plurality of training connections made in a controlled environment; and an output for indicating a desired connection status based on the isolated connection sound.

First claim

What is claimed is:

1. A device for verifying a connection of components connected by a gripper, the device comprising:
a plurality of audio sensors configured to generate audio signals in response to detecting sounds, the sounds including background noise and a connection sound produced by two or more components being connected together;
a fastener configured to secure the plurality of audio sensors at different positions on the gripper; and
a controller comprising:
a controller input configured to receive the audio signals from the plurality of audio sensors;
a neural network configured to isolate the connection sound from the background noise in the audio signals received from the plurality of audio sensors using independent component analysis that is independent of relative positions of the plurality of audio sensors to each other and to the two or more components and is based on training audio data obtained from audio signals received during a plurality of training connections made in a controlled environment, wherein the independent component analysis by the neural network comprises an analysis of differences in phase delay and composition between the audio signals received from at least two of the plurality of audio sensors based on differences identified by the training audio data; and
an output interface configured to indicate that a desired connection status has been achieved based on the isolated connection sound.

2. The device according to claim 1 , wherein the neural network applies a cocktail party algorithm to isolate individual human voices from the background noise.

3. The device according to claim 1 , wherein the gripper is one of a user's hand or a robotic manipulator.

4. The device according to claim 1 , wherein:
the plurality of audio sensors comprises first and second audio sensors located at first and second positions on the gripper when secured by the fastener; and
the first and second positions are located such that, in use, both the first and second audio sensors simultaneously contact at least one of the two or more components when held by the gripper during their connection.

5. The device according to claim 1 , wherein the neural network comprises further training audio data obtained from audio signals received during a different plurality of training connections made by connecting a different two or more components in a controlled environment.

6. The device according to claim 1 , wherein the output interface comprises an audio output for connection to a speaker for outputting the isolated connection sound.

7. The device according to claim 1 , wherein the controller is further configured to compare the isolated connection sound to a profile associated with a desired connection sound for identifying when the desired connection status has been achieved.

8. The device according to claim 1 , wherein the output interface comprises a visual indicator.

9. The device according to claim 1 , wherein the output interface comprises an indicator for indicating a poor connection status based on the isolated connection sound.

10. The device according to claim 1 , further comprising a storage for storing a log of the connection status of components connected by a user.

11. The device according to claim 1 , wherein the fastener is a glove that is wearable by a user's hand.

12. The device according to claim 1 , wherein the two or more components are electronic connectors.

13. A method for verifying a connection of components connected by a gripper, the method comprising:
securing a plurality of audio sensors at different positions on the gripper using a fastener, the audio sensors configured to generate audio signals based on background noise and a connection sound produced by two or more components being connected together;
receiving the audio signals from the plurality of audio sensors to a controller input as the two or more components are connected using the gripper;
isolating the connection sound from the background noise in the audio signals received from the plurality of audio sensors by a neural network using independent component analysis that is independent of relative positions of the plurality of audio sensors to each other and to the two or more components and is based on training audio data obtained from audio signals received during a plurality of training connections made in a controlled environment, wherein using the independent component analysis by the neural network comprises analysing differences in phase delay and composition between the audio signals received from at least two of the plurality of audio sensors based on differences identified by the training audio data; and

outputting a signal indicating that a desired connection status has been achieved based on the isolated connection sound.

14. The method according to claim 13 , wherein the isolating of the connection sound includes isolating individual human voices from the ambient noise.

15. The method according to claim 13 , further comprising comparing the isolated connection sound to a profile associated with a desired connection sound for identifying when the desired connection status has been achieved.

16. A method for training a device to verify a connection of components connected by a gripper, the method comprising:
securing a plurality of audio sensors at different positions on the gripper using a fastener;
establishing a first controlled environment with low ambient noise;
performing a first sequence of training connections under the first controlled environment in which two or more components are connected to a desired connection status using the gripper, wherein connecting the two or more components produces a connection sound;
receiving first audio signals from the plurality of audio sensors to a controller input during the first sequence of training connections;
establishing a second controlled environment in which ambient noise corresponds to a usage environment;
performing a second sequence of training connections under the second controlled environment in which two or more components are connected to a desired connection status using the gripper;
receiving second audio signals from the plurality of audio sensors to a controller input during the second sequence of training connections; and
processing, by a neural network, the first and second audio signals received from the plurality of audio sensors during the first and second sequences of training connections, respectively, using independent component analysis, wherein the processing, by the neural network, of the first and second audio signals includes isolating the connection sound from the ambient noise based on differences in phase delay and signal composition between audio signals in the first and second audio signals to produce training audio data.

17. The method according to claim 16 , wherein the differences in phase delay and signal composition between the audio signals in the first and second audio signals are dependent on relative positions of each controller input to respective sources of each connection sound.

Assignees

• Aptiv Technologies AG

Inventors

• Szelest Marcin
• Skruch Pawel

Classifications

• G06F3/014 Primary

  Hand-worn input/output arrangements, e.g. data gloves · CPC title

• A41D19/0027

  Measuring instruments, e.g. watch, thermometer · CPC title

• G01H1/00

  Measuring {characteristics of} vibrations in solids by using direct conduction to the detector (G01H9/00, G01H11/00 take precedence) · CPC title

• G09B5/065

  Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems · CPC title

• G10L21/0208

  Noise filtering · CPC title