Systems and methods for scalable edge-based microcontrollers
Embodiments described herein provide for the leveraging of edge-based resources (e.g., processing, memory, storage, and/or other resources of one or more Multi-Access/Mobile Edge Computing devices (“MECs”), such as MECs associated with a radio access network (“RAN”) of a wireless network) to process data from and/or provide instructions to microcontroller devices, System on Chip (“SoC”) devices, configurable logic boards, Internet of Things (“IoT”) devices, and/or other types of devices or systems. For example, embodiments described herein may provide for the creation and configuration of logical devices or systems based on one or more microcontrollers, SoC devices, etc., edge-based processing of sensor data and/or other types of data received or generated by the microcontrollers, SoC devices, etc., and the generation of instructions to control physical devices communicatively coupled to the microcontrollers, SoC devices, etc.
1. A device, comprising:
one or more processors configured to:
maintain, by a Multi-Access/Mobile Edge Computing device (“MEC”), a plurality of input models that each include respective sensor data values;
maintain, by the MEC, a plurality of output models that each include one or more actions to perform;
maintain, by the MEC, information associating respective input models, of the plurality of input models, to respective output models of the plurality of output models;
receive, by the MEC, via one or more wireless networks, input data from one or more edge-controlled systems, wherein a particular edge-controlled system of the one or more edge-controlled system includes one or more controllers, wherein the received input data is based on sensor data collected by one or more sensors that are communicatively coupled to the one or more controllers;
compare, by the MEC, the input data to the plurality of input models that are each based on respective sensor data values;
select, by the MEC and based on the comparing, a particular input model from the plurality of input models;
identify, by the MEC and based on the information associating respective input models to respective output models, a particular output model associated with the particular input model, wherein the one or more actions associated with the particular output model include a plurality of output instructions to actuate one or more devices connected to the one or more controllers; and
provide, by the MEC, via the one or more wireless networks, the plurality of output instructions to the particular edge-controlled system, wherein the particular edge-controlled system generates a set of electrical signals based on the plurality of output instructions and provides the set of electrical signals to actuate the one or more devices connected to the one or more controllers.
2. The device of claim 1 , wherein the one or more wireless networks include a radio access network (“RAN”), and wherein the input data is received by the MEC from a base station of the RAN without the input data traversing a core network that is communicatively coupled to the RAN.
3. The device of claim 1 , wherein the one or more devices connected to the one or more edge-controlled systems include one or more motors, wherein actuating the one or more devices includes actuating the one or more motors.
4. The device of claim 1 , wherein the plurality of output instructions include instructions to actuate one or more logical systems, wherein the particular edge-controlled system generates the set of electrical signals to actuate the one or more connected devices based on the instructions to actuate the one or more logical systems.
5. The device of claim 1 , wherein the one or more processors are further configured to:
receive feedback data from the particular edge-controlled system after providing the output instructions to the particular edge-controlled system; and
modify the output model based on the feedback data.
6. The device of claim 1 , wherein the one or more processors are further configured to:
receive feedback data from the particular edge-controlled system after providing the output instructions to the particular edge-controlled system; and
modify an association between the output model and at least one of the first input model or the second input model based on the feedback data.
7. The device of claim 1 , wherein the sensor data values are collected by one or more sensors associated with the edge-controlled system, wherein the one or more sensors include at least one of:
an accelerometer,
a gyroscope, or
a Light Detection and Ranging (“LIDAR”) sensor.
8. A non-transitory computer-readable medium, storing a plurality of processor-executable instructions to:
maintain, by a Multi-Access/Mobile Edge Computing device (“MEC”), a plurality of input models that each include respective sensor data values;
maintain, by the MEC, a plurality of output models that each include one or more actions to perform;
maintain, by the MEC, information associating respective input models, of the plurality of input models, to respective output models of the plurality of output models;
receive, by the MEC, via one or more wireless networks, input data from one or more edge-controlled systems, wherein a particular edge-controlled system of the one or more edge-controlled system includes one or more controllers, wherein the received input data is based on sensor data collected by one or more sensors that are communicatively coupled to the one or more controllers;
compare, by the MEC, the input data to the plurality of input models that are each based on respective sensor data values;
select, by the MEC and based on the comparing, a particular input model from the plurality of input models;
identify, by the MEC and based on the information associating respective input models to respective output models, a particular output model associated with the particular input model, wherein the one or more actions associated with the particular output model include a plurality of output instructions to actuate one or more devices connected to the one or more controllers; and
provide, by the MEC, via the one or more wireless networks, the plurality of output instructions to the particular edge-controlled system, wherein the particular edge-controlled system generates a set of electrical signals based on the plurality of output instructions and provides the set of electrical signals to actuate the one or more devices connected to the one or more controllers.
9. The non-transitory computer-readable medium of claim 8 , wherein the one or more wireless networks include a radio access network (“RAN”), and wherein the input data is received by the MEC from a base station of the RAN without the input data traversing a core network that is communicatively coupled to the RAN.
10. The non-transitory computer-readable medium of claim 8 , wherein the one or more devices connected to the one or more edge-controlled systems include one or more motors, wherein actuating the one or more devices includes actuating the one or more motors.
11. The non-transitory computer-readable medium of claim 8 , wherein the plurality of output instructions include instructions to actuate one or more logical systems, wherein the particular edge-controlled system generates the set of electrical signals to actuate the one or more connected devices based on the instructions to actuate the one or more logical systems.
12. The non-transitory computer-readable medium of claim 8 , wherein the plurality of processor-executable instructions further include processor-executable instructions to:
receive feedback data from the particular edge-controlled system after providing the output instructions to the particular edge-controlled system; and
modify the output model based on the feedback data.
13. The non-transitory computer-readable medium of claim 8 , wherein the plurality of processor-executable instructions further include processor-executable instructions to:
receive feedback data from the particular edge-controlled system after providing the output instructions to the particular edge-controlled system; and
modify an association between the output model and at least one of the first input model or the second input model based on the feedback data.
14. A method, comprising:
maintaining, by a Multi-Access/Mobile Edge Computing device (“MEC”), a plurality of input models that each include respective sensor data values;
maintaining, by the MEC, a plurality of output models that each include one or more actions to perform;
maintaining, by the MEC, information associating respective input models, of the plurality of input models, to respective output models of the plurality of output models;
receiving, by the MEC, via one or more wireless networks, input data from one or more edge-controlled systems, wherein a particular edge-controlled system of the one or more edge-controlled system includes one or more controllers, wherein the received input data is based on sensor data collected by one or more sensors that are communicatively coupled to the one or more controllers;
comparing, by the MEC, the input data to the plurality of input models that are each based on respective sensor data values;
selecting, by the MEC and based on the comparing, a particular input model from the plurality of input models;
identifying, by the MEC and based on the information associating respective input models to respective output models, a particular output model associated with the particular input model, wherein the one or more actions associated with the particular output model include a plurality of output instructions to actuate one or more devices connected to the one or more controllers; and
providing, by the MEC, via the one or more wireless networks, the plurality of output instructions to the particular edge-controlled system, wherein the particular edge-controlled system generates a set of electrical signals based on the plurality of output instructions and provides the set of electrical signals to actuate the one or more devices connected to the one or more controllers.
15. The method of claim 14 , wherein the one or more wireless networks include a radio access network (“RAN”), and wherein the input data is received by the MEC from a base station of the RAN without the input data traversing a core network that is communicatively coupled to the RAN.
16. The method of claim 14 , wherein the one or more devices connected to the one or more edge-controlled systems include one or more motors, wherein actuating the one or more devices includes actuating the one or more motors.
17. The method of claim 14 , wherein the plurality of output instructions include instructions to actuate one or more logical systems, wherein the particular edge-controlled system generates the set of electrical signals to actuate the one or more connected devices based on the instructions to actuate the one or more logical systems.
18. The method of claim 14 , the method further comprising:
receiving feedback data from the particular edge-controlled system after providing the output instructions to the particular edge-controlled system; and
modifying the output model based on the feedback data.
19. The method of claim 14 , the method further comprising:
receiving feedback data from the particular edge-controlled system after providing the output instructions to the particular edge-controlled system; and
modifying an association between the output model and at least one of the first input model or the second input model based on the feedback data.
20. The method of claim 14 , wherein the sensor data values are collected by one or more sensors associated with the edge-controlled system, wherein the one or more sensors include at least one of:
an accelerometer,
a gyroscope, or
a Light Detection and Ranging (“LIDAR”) sensor.