Back to results
US 12,546,878 B2Granted
Detecting, tracking, and transmitting to identified objects using models in a modular system
AssigneeAnduril Industries, Inc.
InventorsSam El-Akkad, Christopher Fischer, Travis Whitaker, Bryden Pearson, Todd Berk, Thao Pham, Jon Hsu, Cameron Dart
Life of this patent
Estimating the term…
Abstract
A modular, radio frequency (“RF”) system includes one or more directional antennas and is configured with both hardware and software components to enable the RF system to monitor (e.g., detect or track signals or objects) and/or interact with (e.g., track signals or objects, or transmit signals) objects in particular directions. The RF system includes one or more machine learning models to determine, based on received signals, one or more signals to transmit.
Claims21
A computer-implemented method comprising, by one or more hardware processors executing program instructions:
- accessing or receiving, by a first RF system, detection data associated with a first object, wherein the detection data is collected or generated by one or more:
- RF systems, sensors, and devices configured to detect RF signals or objects;
- collecting, by using one or more antennas of the first RF system, RF signal data associated with the first object;
- based at least in part on the detection data and the RF signal data, identifying a first set of RF signals associated with the first object;
- identifying, by application of a machine learning model, a type of object associated with the first object;
- and
- based at least in part on the type of object, generating, by the first RF system, and causing transmission, by using the one or more antennas of the first RF system, of a second set of RF signals different from the first set of RF signals, wherein the first RF system operates in coordination with at least one other RF system, each system covering a different sector surrounding a protected area.
4 more elements
A computer-implemented method comprising, by one or more hardware processors executing program instructions:
- based on a first set of RF signals associated with a first object and an application of a machine learning model that has been trained to identify a type of object associated with the first set of RF signals and operating on an RF system, generating and causing transmission of, using a first antenna corresponding to the RF system, a second set of RF signals, wherein causing transmission includes supplying power to the first antenna, wherein the RF system operates in coordination with at least one other RF system, each system covering a different sector surrounding a protected area;
- determining, by the RF system, that the first object is moving out of an area associated with the first antenna and into an area associated with a second antenna;
- and
- based on the determination:
- reduce the power supplied to the first antenna, wherein the power supplied to the first antenna is reduced at a first rate;
- increase the power supplied to the second antenna, wherein the power supplied to the second antenna is increased at a second rate;
- and
- cause transmission, using the second antenna, of the second set of RF signals.
5 more elements
An RF system comprising:
- one or more antennas;
- a first RF module coupled to the one or more antennas, wherein the first RF module comprises a power amplifier;
- a processing module electrically connected to the first RF module, wherein the processing module comprises;
- a first one or more graphical processing units (GPUs);
- a computer readable storage medium comprising program instructions and a machine learning model, wherein the machine learning model has been trained to identify a type of object associated with a first set of RF signals;
- and
- one or more first processors that are configured to execute the program instructions to cause the RF system to:
- receive a data packet comprising software updates, wherein the software updates include one or more of:
- firmware updates corresponding to hardware components of the RF system, updates corresponding to software components utilized by the RF system, and machine learning model updates that include object detections identified by a second RF module associated with a different system, wherein the software updates include sector coverage updates that identify one or more protected areas, wherein the RF system operates in coordination with at least one other RF system, each system covering a different sector surrounding the protected area;
- and
- install the software updates to update functionality of the RF system, wherein the RF system is configured to generate and cause transmission of one or more RF signals.
8 more elements
Dependencies are inferred from the claim text.