Cluster-based sensor assignment

Patent metadata

Field	Value
Publication number	US-2021294444-A1
Application number	US-202117342126-A
Country	US
Kind code	A1
Filing date	Jun 8, 2021
Priority date	Jun 14, 2019
Publication date	Sep 23, 2021
Grant date	—

Abstract

The logic of a handheld controller system may use a clustering algorithm to determine which sensors of a touch sensor array, such as capacitive pads, to assign to individual fingers of a user's hand. The clustering algorithm disclosed herein allows for dynamically determining the controller configuration on-the-fly for a given user. An example process includes receiving data generated by a plurality of sensors of a touch sensor array of the handheld controller, generating a covariance matrix that indicates correlations between pairs of sensors, determining a plurality of feature vectors based at least in part on the covariance matrix, each feature vector corresponding to an individual sensor and describing that sensor's correlation(s) with one or more other sensors, clustering the feature vectors using a clustering algorithm, and configuring the touch sensor array according to a controller configuration that assigns sensors to respective fingers of a hand.

First claim

What is claimed is:

1 . A method comprising:
receiving data generated by a plurality of sensors distributed on a handle of a handheld controller; clustering, based at least in part on the data, a plurality of feature vectors, each feature vector corresponding to a sensor of the plurality of sensors and describing a correlation between the sensor and one or more other sensors of the plurality of sensors; and assigning, based at least in part on the clustering, at least a first subset of the plurality of sensors to a first group that corresponds to a first finger of a hand and a second subset of the plurality of sensors to a second group that corresponds to a second finger of the hand.

2 . The method of claim 1 , wherein:
the plurality of sensors are distributed on the handle in rows of sensors, the rows oriented substantially horizontally on the handle; the first subset of the plurality of sensors comprises at least some sensors in one or more first rows of the rows; and the second subset of the plurality of sensors comprises at least some sensors in one or more second rows of the rows.

3 . The method of claim 1 , wherein:
the first finger corresponds to a middle finger; the second finger corresponds to a ring finger; and the assigning further comprises assigning a third subset of the plurality of sensors to a third group that corresponds to a pinky finger.

4 . The method of claim 3 , wherein the assigning further comprises assigning a fourth subset of the plurality of sensors to a fourth group that corresponds to a non-finger group.

5 . The method of claim 1 , wherein the clustering of the plurality of feature vectors comprises assigning each feature vector of the plurality of feature vectors to one of a first cluster that correspond to the first group or a second cluster that corresponds to the second group.

6 . The method of claim 1 , further comprising determining the plurality of feature vectors based at least in part on a covariance matrix that indicates correlations between pairs of sensors of the plurality of sensors.

7 . The method of claim 6 , wherein the covariance matrix is a n×d covariance matrix, where n is a number of the plurality of sensors, and where d is less than n.

8 . A system comprising:
a controller having a plurality of sensors spread about a handle of the controller; one or more processors; and memory storing computer-executable instructions that, when executed by the one or more processors, cause performance of operations comprising:
receiving data generated by the plurality of sensors;
clustering, based at least in part on the data, a plurality of feature vectors, each feature vector corresponding to a sensor of the plurality of sensors and describing a correlation between the sensor and one or more other sensors of the plurality of sensors; and
assigning, based at least in part on the clustering, at least a first subset of the plurality of sensors to a first group that corresponds to a first finger of a hand and a second subset of the plurality of sensors to a second group that corresponds to a second finger of the hand.

9 . The system of claim 8 , wherein:
the plurality of sensors are spread about the handle in rows of sensors, the rows oriented substantially horizontally on the handle; the first subset of the plurality of sensors comprises at least some sensors in one or more first rows of the rows; and the second subset of the plurality of sensors comprises at least some sensors in one or more second rows of the rows.

10 . The system of claim 8 , wherein:
the first finger corresponds to a middle finger; the second finger corresponds to a ring finger; and the assigning further comprises assigning a third subset of the plurality of sensors to a third group that corresponds to a pinky finger.

11 . The system of claim 10 , wherein the assigning further comprises assigning a fourth subset of the plurality of sensors to a fourth group that corresponds to a non-finger group.

12 . The system of claim 8 , wherein the operations further comprise, after the assigning:
receiving additional data generated by the plurality of sensors; and providing the additional data to an application to generate image data corresponding to the hand.

13 . The system of claim 8 , further comprising determining the plurality of feature vectors based at least in part on a covariance matrix that indicates correlations between pairs of sensors of the plurality of sensors.

14 . One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
receiving data generated by a plurality of sensors distributed on a handle of a handheld controller; clustering, based at least in part on the data, a plurality of feature vectors, each feature vector corresponding to a sensor of the plurality of sensors and describing a correlation between the sensor and one or more other sensors of the plurality of sensors; and assigning, based at least in part on the clustering, at least a first subset of the plurality of sensors to a first group that corresponds to a first finger of a hand and a second subset of the plurality of sensors to a second group that corresponds to a second finger of the hand.

15 . The one or more non-transitory computer-readable media of claim 14 , wherein:
the plurality of sensors are distributed on the handle in rows of sensors, the rows oriented substantially horizontally on the handle; the first subset of the plurality of sensors comprises at least some sensors in one or more first rows of the rows; and the second subset of the plurality of sensors comprises at least some sensors in one or more second rows of the rows.

16 . The one or more non-transitory computer-readable media of claim 14 , wherein:
the first finger corresponds to a middle finger; the second finger corresponds to a ring finger; and the assigning further comprises assigning a third subset of the plurality of sensors to a third group that corresponds to a pinky finger.

17 . The one or more non-transitory computer-readable media of claim 16 , wherein the assigning further comprises assigning a fourth subset of the plurality of sensors to a fourth group that corresponds to a non-finger group.

18 . The one or more non-transitory computer-readable media of claim 14 , wherein the acts further comprise, after the assigning:
receiving additional data generated by the plurality of sensors; and providing the additional data to an application to generate image data corresponding to the hand.

19 . The one or more non-transitory computer-readable media of claim 14 , further comprising determining the plurality of feature vectors based at least in part on a covariance matrix that indicates correlations between pairs of sensors of the plurality of sensors.

20 . The one or more non-transitory computer-readable media of claim 19 , wherein the covariance matrix is a n×d covariance matrix, where n is a number of the plurality of sensors, and where d is less than n.

Assignees

• Valve Corp

Inventors

• Nietfeld Scott Douglas

Classifications

• G06F18/23213

  with fixed number of clusters, e.g. K-means clustering · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title

• A63F13/67

  adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use · CPC title

• G06F3/044 Primary

  by capacitive means · CPC title

• A63F13/214

  for locating contacts on a surface, e.g. floor mats or touch pads · CPC title