WEARABLE CONTROLLER FOR WRIST
A wrist-worn computer interface including a sensor for measuring wrist tendon forces corresponding to specific finger motions including a linear array of cantilevered piezoelectric sensors configured to emit electric currents upon pressure from the wrist tendons on the tip of the piezoelectric sensors, a processing module configured for converting the electric currents generated upon pressure from wrist tendons into signals and for processing the signals to identify one or more specific finger motions, and a flexible PCB connecting the piezoelectric sensors to the processing module. A controller module is configured to cause one or more computing devices to automatically execute one or more specific commands corresponding to one or more of the specific finger motions.
1 . A wrist-worn sensor for measuring wrist tendon forces corresponding to specific finger motions comprising:
a. an array of cantilever piezoelectric sensors wherein the piezoelectric sensors emit electric currents generated upon pressure from wrist tendons on the tip of the piezoelectric sensors;
b. a processing module configured for converting the electric currents generated upon pressure from wrist tendons into signals and for processing the signals for identification of one or more specific finger motions;
c. a flexible PCB connecting the array of cantilever piezoelectric sensors to the processing module.
2 . The wrist-worn sensor of claim 1 wherein the array of piezoelectric sensors is configured to have a spatial resolution of less than 2 mm.
3 . The wrist-worn sensor of claim 1 wherein the cantilever sensors are configured in a linear array.
4 . The wrist-worn sensor of claim 3 wherein the linear array comprises four piezo-electric sensors with partially overlapping sensor areas.
5 . The wrist worn sensor of claim 3 where the array of cantilever piezoelectric sensors is positioned proximally to a wearer's Flexor Carpi Ulnaris Tendon, Flexor Digitorum Profundus Tendon and Flexor Digitorum Superficialis Tendon.
6 . The wrist worn sensor of claim 3 where the array of cantilever piezoelectric sensors is configured to optimally capture the tension applied to each tendon in the wrist.
7 . The wrist-worn sensor of claim 1 wherein the sensors are positioned at an angle greater than 10 degrees relative to the flexible PCB.
8 . The wrist-worn sensor of claim 1 wherein the piezoelectric sensors are embedded in an elastomeric material.
9 . The piezo-electric sensors of claim 8 wherein the elastomeric material is selected from the list consisting of silicone rubber, polymer foam and polymer elastomer.
10 . The piezo-electric sensors of claim 8 wherein the elastomeric material filters out low amplitude high frequency signals.
11 . A computer interface, comprising the wrist-worn sensor of claim 1 and a controller module configured to cause one or more computing devices to automatically execute one or more specific commands upon identification of one or more of the specific finger motions.
12 . The wrist-worn computer interface of claim 11 , wherein the computer interface communicates wirelessly with one or more computing devices.
13 . The wrist-worn computer interface of claim 11 further comprising a button placed in in contact with a user's wrist so as to be triggered by the user flexing the wrist and causing the activation of the device from a sleeping, power-saving mode to an active acquisition mode.
14 . A process for detecting specific finger movements based on wrist-tendon forces, the process comprising the steps of:
a. sensing one or more electric signals produced by an array of cantilever piezoelectric sensors generated upon pressure of wrist tendons applied to the tip of the sensors;
b. extracting a set of characteristic features from the electric signal produced by the array of cantilever piezoelectric sensors;
c. feeding the characteristic features to a trained classifier;
d. identifying one or more specific finger gestures associated with specific classes of the trained classifier; and
e. automatically directing one or more computing devices to execute one or more commands corresponding to one or more of the identified finger gestures.
15 . The process of claim 14 further comprising the step of performing an initial calibration of the sensors which evaluates gesture generated signals associated with a subset of user finger gestures to determine expected signals during the finger-gesture identification step.
16 . The process of claim 14 further comprising the step of calibrating the controller by automatically identifying the parameters needed to run a software program installed in the module or in one or more external computing devices, the software program receiving the signals and identifying the parameter for the training following a protocol of specific finger gestures.
17 . The process of claim 14 , wherein the feature extraction step further comprises the steps of considering all electric signals coming from the sensors during each finger movement and gesture, band-pass filtering said signals to limit the data to a predetermined amount, and analyzing the signals by means of a feature extractor.
18 . The process of claim 14 , wherein the feature extraction step analyzes the signals in order to obtain a set of features describing the signals to be compared with other signal features coming from other finger movements and gestures.
19 . The process of claim 14 , wherein the features are selected from the list consisting of time domain features and frequency domain features.
20 . The process of claim 14 further comprising a step of disabling one or more of the sensors during rest.