# US 9,519,049 B1 · Processing unknown radar emitters > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 9,519,049 B1 - Document ID: US9519049B1 - Status: Granted - Kind: B1 - Application number: 14/501,115 - Filed: 2014-09-30 - Granted: 2016-12-13 - Earliest claimed: 2014-09-30 - Assignees: Raytheon Company - Applicants: Raytheon Company - Inventors: Shubha Kadambe; Alexander Niechayev; Ted Y. Lumanlan - Web page: https://patentgrep.com/patent/US9519049B1 ## CPC - G01S 7/021: {Auxiliary means for detecting or identifying radar signals or the like, e.g. radar jamming signals} - G01S 7/02: of systems according to group G01S13/00 - G01S 7/022: {Road traffic radar detectors} - 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 ## Abstract Methods and apparatus to receive radar pulses, process the received pulses using weighted finite state machine to learn a model of an unknown emitter generating the received radar pulses, and estimate a state/function of the unknown emitter based on the received radar pulses using the learned model, and predict the next state/function of the unknown emitter based on the received radar pulses and applying maximum likelihood estimation. ## Claims ### Claim 1 A method, comprising: receiving radar pulses from an unknown radar emitter at an input of a radar warning system; processing the received pulses using a weighted finite state machine implemented in the radar warning system to learn a model of the unknown radar emitter; storing the learned model in memory on the radar warning system; estimating, using a computer processor on the radar warning system, a state/function of the unknown radar emitter based on the received radar pulses using the stored learned model; and automatically building finite state machines using finite state transducers based on instructions stored in the memory. ### Claim 2 (depends on 1) The method according to claim 1, further including determining weights for the weighted finite state machine using expectation-maximization processing. ### Claim 3 (depends on 1) The method according to claim 1, further including estimating a mode of the unknown emitter as search or track from the received pulses. ### Claim 4 (depends on 1) The method according to claim 1, further including predicting a next state for the unknown emitter from a current estimated state of the unknown emitter. ### Claim 5 (depends on 1) The method according to claim 1, further including interleaving the received pulses based on adaptive stochastic weights. ### Claim 6 (depends on 1) The method according to claim 1, further including performing parsing, tracking and association of emitters. ### Claim 7 (depends on 1) The method according to claim 1, further including using human speech recognition/text processing to process the received pulses where a radar language comprises pulse sequences, which are analogous to speech phonemes, waveform sequences, which are analogous to words in human speech, and phrases, which are analogous to phrases in human speech, and states, which are analogous to a sentence in human speech. ### Claim 8 (depends on 7) The method according to claim 7, further including estimating a state/function of the unknown emitter from combinations of the received pulses. ### Claim 9 An article, comprising: a non-transitory computer readable medium having instructions stored thereon such that in response to the instructions executed by a processor, the processor performs steps which enable the processor to: receive radar pulses from an unknown radar emitter at an input of a radar warning system; process the received pulses using a weighted finite state machine implemented in the radar warning system to learn a model of the unknown radar emitter; store the learned model in memory on the radar warning system; estimate a state/function of the unknown radar emitter based on the received radar pulses using the stored learned model; and automatically build finite state machines using finite state transducers based on instructions stored in the memory. ### Claim 10 (depends on 9) The article according to claim 9, wherein in response to the instructions executed by the processor, the processor further performs steps which enable the processor to determine weights for the weighted finite state machine using expectation-maximization processing. ### Claim 11 (depends on 9) The article according to claim 9, wherein in response to the instructions executed by the processor, the processor further performs steps which enable the processor to estimate a mode of the unknown emitter as search or track from the received pulses. ### Claim 12 (depends on 9) The article according to claim 9, wherein in response to the instructions executed by the processor, the processor further performs steps which enable the processor to predict a next state for the unknown emitter from a current estimated state of the unknown emitter. ### Claim 13 (depends on 9) The article according to claim 9, wherein in response to the instructions executed by the processor, the processor further performs steps which enable the processor to interleave the received pulses based on adaptive stochastic weights. ### Claim 14 (depends on 9) The article according to claim 9, wherein in response to the instructions executed by the processor, the processor further performs steps which enable the processor to perform parsing, tracking and association of emitters. ### Claim 15 (depends on 9) The article according to claim 9, wherein in response to the instructions executed by the processor, the processor further performs steps which enable the processor to use human speech recognition/text processing to process the received pulses where a radar language comprises pulse sequences, which are analogous to speech phonemes, waveform sequences, which are analogous to words in human speech, and phrases, which are analogous to phrases in human speech, and states, which are analogous to a sentence in human speech. ### Claim 16 (depends on 15) The article according to claim 15, wherein in response to the instructions executed by the processor, the processor further performs steps which enable the processor to estimate a state/function of the unknown emitter from combinations of the received pulses. ### Claim 17 A radar warning system, comprising: a memory; and a processor coupled to the memory, the processor and the memory configured to: receive radar pulses from an unknown radar emitter; process the received radar pulses using a weighted finite state machine implemented in the radar warning system to learn a model of the unknown radar emitter; store the learned model in the memory; estimate, using the processor, a state/function of the unknown radar emitter based on the received radar pulses using the stored learned model; and automatically build finite state machines using-finite state transducers based on instructions stored in the memory. ### Claim 18 (depends on 17) The system according to claim 17, wherein the processor and the memory are further configured to determine weights for the weighted finite state machine using expectation-maximization processing.