# US 12,183,214 B2 · System and/or method for directed aircraft perception > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,214 B2 - Document ID: US12183214B2 - Status: Granted - Kind: B2 - Application number: 18/515,836 - Filed: 2023-11-21 - Published: 2024-09-26 - Granted: 2024-12-31 - Earliest claimed: 2023-03-24 - Assignees: Merlin Labs, Inc. - Applicants: Merlin Labs, Inc. - Inventors: Matthew George; Alexander Naiman; Michael Pust; Joseph Bondaryk - Web page: https://patentgrep.com/patent/US12183214B2 ## CPC - G08G 5/80: Anti-collision systems - G08G 5/21: located onboard the aircraft - G08G 5/22: located on the ground - G08G 5/26: Transmission of traffic-related information between aircraft and ground stations - G08G 5/51: for control when on the ground, e.g. taxiing or rolling - G08G 5/723: {from the aircraft} - G08G 5/727: {from a ground station} - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract The method can include performing inference using the system; and can optionally include training the system components. The method functions to automatically interpret flight commands from a stream of air traffic control (ATC) radio communications. The method can additionally or alternatively function to train and/or update a natural language processing system based on ATC communications. Additionally, the method can include or be used in conjunction with collision avoidance and/or directed perception for traffic detection associated therewith. ## Claims ### Claim 1 A method for directed collision avoidance on an aircraft comprising: receiving a traffic advisory associated with an estimated location of an object; determining a set of camera images collected onboard the aircraft; performing an extended range search with a pretrained classifier based on the estimated location of the object, wherein the extended range search is directed by restricting an image pixel search space, within the set camera images, based on the estimated location; and performing an action based on the extended range search. ### Claim 2 (depends on 1) The method of claim 1, wherein restricting the image pixel search space comprises: restricting an ego-relative, azimuthal range of search space based on an ego-relative heading estimate for the object and a nautical distance to the estimated location. ### Claim 3 (depends on 1) The method of claim 1, wherein restricting the image pixel search space comprises: restricting an ego-relative, zenith-angle range of search space based on an ego-relative altitude estimate for the object and a nautical distance to the estimated location. ### Claim 4 (depends on 1) The method of claim 1, wherein the traffic advisory comprises a set of object information associated with the object, wherein the extended range search is based on the object information. ### Claim 5 (depends on 4) The method of claim 4, further comprising: estimating an apparent size of the object based on the object information, wherein the extended range search is based on the apparent size. ### Claim 6 (depends on 4) The method of claim 4, wherein the object information comprises an aircraft size class, wherein the pretrained classifier is an object detector which is pretrained for the aircraft size class. ### Claim 7 (depends on 1) The method of claim 1, wherein the extended range search is directed based on a set of glint returns comprising highly saturated pixels within the set of camera images. ### Claim 8 (depends on 1) The method of claim 1, wherein the set of camera images comprises a plurality of historical image frames collected prior to receipt of the traffic advisory. ### Claim 9 (depends on 8) The method of claim 8, wherein the traffic advisory comprises object movement information, wherein the extended range search of the plurality of historical image frames is based on the movement information. ### Claim 10 (depends on 1) The method of claim 1, wherein the extended range search is seeded based on the estimated location of the object. ### Claim 11 (depends on 1) The method of claim 1, further comprising: detecting the object associated with the traffic advisory based on the extended range search, wherein the action is performed based on the object detection. ### Claim 12 (depends on 11) The method of claim 11, wherein performing the action comprises determining a resolution advisory based on the object detection. ### Claim 13 (depends on 1) The method of claim 1, wherein performing the action comprises reporting negative contact based on the extended range search failing to detect the object. ### Claim 14 (depends on 1) The method of claim 1, wherein the estimated location is an ego-relative region of airspace. ### Claim 15 (depends on 1) The method of claim 1, wherein the estimated location is an ADS-B position estimate. ### Claim 16 A method for vehicle collision avoidance comprising: determining a traffic alert associated with an object; based on the traffic alert, performing a directed object detection routine with a pretrained classifier to search for the object using vehicle perception data; refining a search space of the directed object detection routine based on a set of historical traffic data; based on the directed object detection routine, locating the object associated with the traffic alert; and performing an action based on the location of the object. ### Claim 17 (depends on 16) The method of claim 16, wherein refining the search space comprises: restricting an ego-relative, azimuthal range of search space based on an ego-relative heading estimate for the object and a nautical distance to the estimated location; and restricting an ego-relative, zenith-angle range of search space based on an ego-relative altitude estimate for the object and the nautical distance to the estimated location. ### Claim 18 (depends on 16) The method of claim 16, further comprising: estimating an apparent size of the object based on traffic advisory, wherein the directed object detection routine is based on the apparent size. ### Claim 19 (depends on 16) The method of claim 16, wherein the estimated position of the object is based on aircraft position data from an Automatic Dependent Surveillance-Broadcast (ADS-B). ### Claim 20 (depends on 16) The method of claim 16, wherein the vehicle perception data comprises a plurality of historical image frames collected prior to receipt of the traffic advisory, wherein the traffic advisory comprises object movement information, wherein the search space for the plurality of historical images frames is based on the movement information.