Tremor detecting and rendering in virtual reality
Systems and methods are provided for measuring and identifying real-world tremors in order to calculate and display an anti-tremor in a virtual reality world. A system may identify a tremor in a body part, such as hands, and measure the tremor movement from, e.g., body sensors, to calculate an opposite movement and animate virtual hands performing the reverse tremor motion. Depicting inverse motions, such as an anti-tremor, may be used in a few ways to therapeutically train and exercise patients to better control their tremors. Providing a visual cue may help a patient interrupt the movement, as well as provide possibilities for therapy or training muscle memory and stimulating nerve and neuron recovery. By displaying an anti-tremor with virtual hands, a VR system may be used to help train or exercise body parts experiencing tremors.
1. A method for detecting and rendering tremors in a virtual reality environment, the method comprising:
receiving raw sensor data;
filtering the raw sensor data to generate filtered position and orientation data;
determining whether the filtered position and orientation data describes a tremor comprising a tremor frequency and a tremor amplitude;
in response to determining the filtered position and orientation data describes the tremor, calculating an anti-tremor based on the filtered position and orientation data; and
rendering an avatar based on the anti-tremor, wherein the avatar is displayed in the virtual reality environment in motion due to the anti-tremor, and wherein the anti-tremor comprises an anti-tremor frequency equal to the tremor frequency and an anti-tremor amplitude that is opposite in amplitude to the tremor amplitude.
2. The method of claim 1 , wherein the determining uses a trained machine learning model to determine whether the filtered position and orientation data comprises data describing the tremor.
3. The method of claim 2 , wherein the trained machine learning model is trained to receive position and orientation data and output a determination whether the filtered position and orientation data comprises data describing the tremor.
4. The method of claim 2 , wherein the trained machine learning model is trained to receive position and orientation data and output which portion of the filtered position and orientation data comprises data describing the tremor.
5. The method of claim 1 , wherein the determining uses a data analytics technique to determine whether the filtered position and orientation data comprises data describing the tremor.
6. The method of claim 5 , wherein using the data analytics technique comprises processing position and orientation data to identify at least one of the following: oscillation, rotation, rhythm, pattern, and change in acceleration.
7. The method of claim 1 , wherein calculating an anti-tremor comprises performing at least one of the following to the data describing the tremor: inverting, translating, transposing, transforming, and scaling.
8. The method of claim 1 , wherein calculating an anti-tremor comprises:
establishing a neutral position based on the filtered position and orientation data;
defining a coordinate system based on the neutral position;
determining a tremor vector in the coordinate system based on the filtered position and orientation data describing the tremor; and
determining an anti-tremor vector based on a reflection of the tremor vector over the neutral position in the coordinate system.
9. The method of claim 1 , wherein calculating an anti-tremor comprises:
determining tremor rotation data based on the filtered position and orientation data describing the tremor; and
determining anti-tremor vector rotation data based on inverting tremor rotation data.
10. The method of claim 1 , wherein filtering comprises using at least one of the following: a feature extraction technique, a noise-reduction technique, signal processing, transforming, and normalizing.
11. The method of claim 1 , wherein rendering the avatar based on the anti-tremor comprises:
substituting the filtered position and orientation data describing the tremor with data describing the anti-tremor; and
rendering the avatar based on the filtered position and orientation data with the substituted data describing the anti-tremor.
12. The method of claim 1 , wherein receiving raw sensor data is received wirelessly.
13. The method of claim 1 , wherein receiving raw sensor data is received from a plurality of sensors placed on a patient's body.
14. The method of claim 1 , wherein filtering the raw sensor data is performed by a plurality of sensors placed on a patient's body.
15. The method of claim 1 , wherein rendering the avatar is performed in near real time with receiving the raw sensor data.
16. A system of detecting and rendering tremors in a virtual reality environment, the system comprising:
a receiver configured to receive raw sensor data;
processing circuitry configured to:
filter the raw sensor data to generate filtered position and orientation data;
determine whether the filtered position and orientation data describes a tremor comprising a tremor frequency and a tremor amplitude;
in response to determining the filtered position and orientation data describes the tremor, calculate an anti-tremor based on the filtered position and orientation data; and
render an avatar based on the anti-tremor, wherein the avatar is displayed in the virtual reality environment in motion due to the anti-tremor, and wherein the anti-tremor comprises an anti-tremor frequency equal to the tremor frequency and an anti-tremor amplitude that is opposite in amplitude to the tremor amplitude.
17. The system of claim 16 , wherein the processing circuitry is further configured to determine using a trained machine learning model to determine whether the filtered position and orientation data comprises data describing the tremor.
18. The system of claim 17 , wherein the trained machine learning model is trained to receive position and orientation data and output a determination whether the filtered position and orientation data comprises data describing the tremor.
19. The system of claim 17 , wherein the trained machine learning model is trained to receive position and orientation data and output which portion of the filtered position and orientation data comprises data describing the tremor.
20. The system of claim 16 , wherein the processing circuitry is further configured to determine using a data analytics technique to determine whether the filtered position and orientation data comprises data describing the tremor.