# US 11,906,657 B2 · System and method for drone and object classification > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,906,657 B2 - Document ID: US11906657B2 - Status: Granted - Kind: B2 - Application number: 16/589,678 - Filed: 2019-10-01 - Published: 2020-04-02 - Granted: 2024-02-20 - Earliest claimed: 2018-10-02 - Assignees: Fortem Technologies, Inc. - Applicants: Fortem Technologies, Inc. - Inventors: David Preece; Mikko Valimaki; Mitchell Kay Oldroyd; Adam Eugene Robertson; Bryan Alan Davis; Matthew Elliott Argyle; David Thimm; James David Mackie - Web page: https://patentgrep.com/patent/US11906657B2 ## CPC - G01S 7/415: {Identification of targets based on measurements of movement associated with the target} - G01S 13/86: Combinations of radar systems with non-radar systems, e.g. sonar, direction finder - G01S 13/862: {Combination of radar systems with sonar systems} - G01S 13/865: {Combination of radar systems with lidar systems} - G01S 13/867: {Combination of radar systems with cameras} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - B64U 10/10: Rotorcrafts - B64U 2101/31: for surveillance - B64U 2101/64: for parcel delivery or retrieval - G01S 7/417: {involving the use of neural networks} - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - B64U: UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR ## Abstract A method and system device provides a unique object identification process by obtaining information from one or more of radar signals, infrared signals, optical signals, audio signals, and other signals. The method includes continuously receiving object data at the device, applying by a machine learning system, a set of parameters to process the object identification and confidence level, and outputting or updating the object identification, confidence level, and actionable recommendations. The radar data includes a Doppler signature having a wrapped signal due to a sampling rate of the radar system. The Doppler signature is used to train the machine learning system to identify drone types. ## Claims ### Claim 1 A method comprising: transmitting, from a device, a radar signal to a flying object, wherein the flying object comprises at least one rotary blade which enables the flying object to fly; receiving, at the device, a reflected signal from the flying object, the reflected signal comprising a doppler signature caused by rotating movement of the at least one rotary blade; and classifying the flying object by applying a machine learning algorithm to the reflected signal to yield a classification, wherein the machine learning algorithm is trained utilizing a respective doppler signature based on a respective rotating movement for each respective at least one rotary blade for each of a plurality of flying objects, wherein the respective rotating movement includes a first part in which the respective at least one rotary blade is moving towards the device and a second part in which the respective at least one rotary blade is moving away from the device. ### Claim 2 (depends on 1) The method of claim 1, wherein the radar signal comprises frequencies between 30 MHz and 300 GHz. ### Claim 3 (depends on 1) The method of claim 1, further comprising: receiving at the device an infrared signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal and the infrared signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled infrared signals. ### Claim 4 (depends on 1) The method of claim 1, further comprising: receiving at the device an audio signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal and the audio signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled audio signals. ### Claim 5 (depends on 1) The method of claim 1, further comprising: receiving at the device an optical signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal and the optical signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled optical signals. ### Claim 6 (depends on 1) The method of claim 1, further comprising: receiving at the device an audio signal associated with the flying object; receiving at the device an infrared signal associated with the flying object; receiving at the device an optical signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal, the infrared signal, the audio signal and the optical signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled audio signals, labeled infrared signals labeled optical signals. ### Claim 7 (depends on 1) The method of claim 1, further comprising: determining, by the machine learning algorithm, a moving pattern associated with the flying object based on one or more of the reflected signal, an audio signal associated with the flying object, an infrared signal associated with the flying object and an optical signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the moving pattern to yield the classification, wherein the machine learning algorithm is trained utilizing labeled moving patterns. ### Claim 8 (depends on 7) The method of claim 7, wherein the moving pattern comprises one of patterns of flying objects or patterns of movement of ground-based objects. ### Claim 9 (depends on 7) The method of claim 7, wherein the moving pattern is based at least in part on moving patterns associated with a group of flying objects. ### Claim 10 (depends on 1) The method of claim 1, further comprising: determining, by the machine learning algorithm, a payload being carried by the flying object based on one or more of the reflected signal, an audio signal associated with the flying object, an infrared signal associated with the flying object and an optical signal associated with the flying object to yield a payload classification, wherein the machine learning algorithm is trained utilizing labeled payloads. ### Claim 11 (depends on 1) The method of claim 1, further comprising: transmitting an instruction, based on the classification, to an aerial vehicle scheduling and routing module. ### Claim 12 (depends on 1) The method of claim 1, further comprising: deploying, based on the classification, an aerial vehicle to engage with the flying object. ### Claim 13 A system comprising: a processor; and a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising: transmitting a radar signal from a device to a flying object; receiving at the device a reflected signal from the flying object, the reflected signal comprising a Doppler signature associated with a rotary movement of at least one rotary blade on the flying object, wherein the rotary movement comprises a first part in which the at least one rotary blade is moving towards the system and a second part in which the at least one rotary blade is moving away from the system; and classifying the flying object by applying a machine learning algorithm to the reflected signal to yield a classification, wherein the machine learning algorithm is trained utilizing labeled reflected radar signals. ### Claim 14 (depends on 13) The system of claim 13, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising: receiving at the device an infrared signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal and the infrared signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled infrared signals. ### Claim 15 (depends on 13) The system of claim 13, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising: receiving at the device an audio signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal and the audio signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled audio signals. ### Claim 16 (depends on 13) The system of claim 13, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising: receiving at the device an optical signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal and the optical signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled optical signals. ### Claim 17 (depends on 13) The system of claim 13, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising: receiving at the device an audio signal associated with the flying object; receiving at the device an infrared signal associated with the flying object; receiving at the device an optical signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the reflected signal, the audio signal, the infrared signal and the optical signal to yield the classification, wherein the machine learning algorithm is trained utilizing labeled radar signals, labeled audio signals, labeled infrared signals and labeled optical signals. ### Claim 18 (depends on 13) The system of claim 13, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising: determining, by the machine learning algorithm, a moving pattern associated with the flying object based on one or more of the reflected signal associated with the flying object, an audio signal associated with the flying object, an infrared signal associated with the flying object and an optical signal associated with the flying object; and classifying the flying object by applying the machine learning algorithm to the moving pattern to yield the classification, wherein the machine learning algorithm is trained utilizing labeled moving patterns. ### Claim 19 A system comprising: a radar component that transmits a radar signal and receives a reflected radar signal from a flying object, the reflected radar signal comprising a Doppler signature of the flying object, wherein the Doppler signature of the flying object is based on a first part in which a rotary blade of the flying object is moving towards the system and a second part in which the rotary blade is moving away from the system; an infrared receiving component that receives an emitted infrared signal from the flying object; a microphone that receives an audible signal generated by the flying object; a camera that receives an optical signal associated with the flying object; and a machine learning module that receives signals comprising the reflected radar signal, the emitted infrared signal, the audible signal, and the optical signal, and utilizes the signals to yield a classification of the flying object.