# US 12,761,663 B2 · Unmanned aerial vehicle control method and control apparatus, unmanned aerial vehicle, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,761,663 B2 - Document ID: US12761663B2 - Status: Granted - Kind: B2 - Application number: 18/679,257 - Filed: 2024-05-30 - Published: 2024-09-26 - Granted: 2026-10-13 - Earliest claimed: 2021-12-01 - Assignees: Sz Dji Technology Co., Ltd. - Applicants: Sz Dji Technology Co., Ltd. - Inventors: Zhiguo Zhan; Xinyu Li - Web page: https://patentgrep.com/patent/US12761663B2 ## CPC - G05D 1/617: Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards (arrangements for controlling the position or course of two or more vehicles for avoiding collisions therebetween G05D1/693; arrangements for reacting to or preventing system or operator failure G05D1/80) - B64U 20/50: Foldable or collapsible UAVs (with frangible components B64U20/30) - B64U 20/87: Mounting of imaging devices, e.g. mounting of gimbals - G05D 1/652: Take-off (delivering or retrieving payloads G05D1/667) - G06V 10/16: {using multiple overlapping images; Image stitching} - G06V 10/761: {Proximity, similarity or dissimilarity measures} - G06V 10/764: using classification, e.g. of video objects - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 10/82: using neural networks - B64U 2201/20: Remote controls - G05D 2109/254: {Flying platforms, e.g. multicopters} - G05D 2111/10: Optical signals - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - B64U: UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method for controlling a UAV includes: receiving a takeoff control command, where the takeoff control command is used to control the UAV to take off; in response to the takeoff control command, when the UAV is not equipped with the safety protection device, prohibiting the UAV from taking off, and/or when the UAV is equipped with the safety protection device, controlling the UAV to take off. This method enhances the safety and usability of the UAV. ## Claims ### Claim 1 An aircraft, comprising: a body, comprising one or more propellers; at least one storage medium storing at least one set of instructions for controlling the aircraft; and at least one processor in communication with the at least one storage medium and a sensor carried by the body, wherein during operation, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: receive a takeoff control instruction, in response to receiving the takeoff control instruction, control the sensor to turn toward a direction of the one or more propellers on the aircraft to detect installation of a safety protection device around the one or more propellers on the aircraft, and not execute the takeoff control instruction in response to the safety protection device not being installed around the one or more propellers on the aircraft; or execute the takeoff control instruction, control, after takeoff, the sensor to turn to a direction that does not face the one or more propellers on the aircraft for detection during flight, and lock the sensor in an angle range, in response to the safety protection device being installed. ### Claim 2 (depends on 1) The aircraft according to claim 1, wherein the aircraft is a foldable aircraft, and the safety protection device is not installed when the aircraft is in a folded state. ### Claim 3 (depends on 1) The aircraft according to claim 1, wherein the at least one processor executes the at least one set of instructions to further cause the aircraft to at least: in response to the takeoff control instruction, obtain environmental sensing data collected by the sensor; and determine whether the aircraft is installed with the safety protection device based on the environmental sensing data. ### Claim 4 (depends on 3) The aircraft according to claim 3, wherein to obtain the environmental sensing data collected by the sensor, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: control a gimbal of the aircraft to drive the sensor to reach a preset attitude; and obtain the environmental sensing data by the sensor in the preset attitude. ### Claim 5 (depends on 3) The aircraft according to claim 3, wherein the sensor comprises an imaging device, and to determine whether the aircraft is installed with the safety protection device based on the environmental sensing data, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: obtain a target image collected by the imaging device, wherein the target image comprises at least a part of an installation occupancy area of the safety protection device on the aircraft; and determine whether the aircraft is installed with the safety protection device based on the target image. ### Claim 6 (depends on 5) The aircraft according to claim 5, wherein to determine whether the aircraft is installed with the safety protection device based on the target image, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: obtain a reference comparison image, wherein the reference comparison image is collected by the imaging device when the aircraft is installed with the safety protection device, and the reference comparison image at least comprises the part of the installation occupancy area; determine a similarity between the reference comparison image and the target image; and determine that the aircraft is installed with the safety protection device in response to the similarity being greater than or equal to a preset similarity, or determine that the aircraft is not installed with the safety protection device in response to the similarity less than the preset similarity. ### Claim 7 (depends on 5) The aircraft according to claim 5, wherein to determine whether the aircraft is installed with the safety protection device based on the target image, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: obtain a reference comparison image library, wherein the reference comparison image library comprises a plurality of reference comparison images; determine a similarity between the target image and the plurality of reference comparison images in the reference comparison image library; and determine that the aircraft is installed with the safety protection device in response to the similarity between at least one of the plurality of reference comparison images in the reference comparison image library and the target image being greater than or equal to a preset similarity, or determine that the aircraft is not installed with the safety protection device in response to the similarity between none of the plurality of reference comparison images in the reference comparison image library and the target image being greater than or equal to the preset similarity. ### Claim 8 (depends on 5) The aircraft according to claim 5, wherein to determine whether the aircraft is installed with the safety protection device based on the target image, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: obtain a first recognition model of the safety protection device; and determine whether the aircraft is installed with the safety protection device based on the first recognition model. ### Claim 9 (depends on 8) The aircraft according to claim 8, wherein to determine whether the aircraft is installed with the safety protection device based on the first recognition model, the at least one processor executes the at least one set of instructions to-cause the aircraft to at least: input the target image into the first recognition model for recognition processing to obtain a classification label of the target image; and determine that the aircraft is installed with the safety protection device in response to the classification label being a first classification label, or determine that the aircraft is not installed with the safety protection device in response to the classification label being a second classification label. ### Claim 10 (depends on 8) The aircraft according to claim 8, wherein the first recognition model is obtained by iteratively training a neural network model based on a first sample data set, and the first sample data set comprises a plurality of positive sample data and a plurality of negative sample data; the plurality of positive sample data comprises a first sample image and a first classification label, and the first sample image contains the safety protection device; and the plurality of negative sample data comprises a second sample image and a second classification label, and the second sample image does not contain the safety protection device. ### Claim 11 (depends on 5) The aircraft according to claim 5, wherein prior to obtaining the target image collected by the imaging device, the at least one processor executes the at least one set of instructions to further cause the aircraft to at least: obtain an ambient light intensity; and obtain the target image collected by the imaging device when the ambient light intensity is greater than or equal to a preset light intensity threshold. ### Claim 12 (depends on 5) The aircraft according to claim 5, wherein to obtain the target image collected by the imaging device, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: obtain an image collected by the imaging device in a preset attitude, and determine the image as the target image; wherein an image collection range of the imaging device in the preset attitude at least partially overlaps with the installation occupancy area of the safety protection device on the aircraft. ### Claim 13 (depends on 5) The aircraft according to claim 5, wherein to obtain the target image collected by the imaging device, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: obtain a plurality of images collected by the imaging device rotating within a first rotation range; and combine the plurality of images to obtain the target image, wherein when the imaging device rotates within the first rotation range, an image collection range of the imaging device at least partially overlaps with the installation occupancy area of the safety protection device on the aircraft. ### Claim 14 (depends on 5) The aircraft according to claim 5, wherein the at least one processor executes the at least one set of instructions to further cause the aircraft to at least: after controlling the aircraft to take off, control the imaging device to rotate within a second rotation range, wherein when the imaging device rotates within the second rotation range, an image collection range of the imaging device does not overlap with the installation occupancy area of the safety protection device on the aircraft. ### Claim 15 (depends on 3) The aircraft according to claim 3, wherein the sensor comprises a radar device, and to determine whether the aircraft is installed with the safety protection device based on the environmental sensing data, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: obtain point cloud data collected by the radar device, and obtain position coordinates corresponding to an installation position of the safety protection device on the aircraft; obtain, from the point cloud data, target point cloud data matching the position coordinates, and obtain a second recognition model of the safety protection device; and determine whether the aircraft is installed with the safety protection device based on the target point cloud data and the second recognition model. ### Claim 16 (depends on 15) The aircraft according to claim 15, wherein to determine whether the aircraft is installed with the safety protection device based on the target point cloud data and the second recognition model, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: input the target point cloud data into the second recognition model for recognition processing to obtain a classification label of the target point cloud data; and determine that the aircraft is installed with the safety protection device in response to the classification label of the target point cloud data being a preset classification label, or determine that the aircraft is not installed with the safety protection device in response to the classification label of the target point cloud data not being the preset classification label. ### Claim 17 (depends on 15) The aircraft according to claim 15, wherein the second recognition model is obtained by iteratively training a neural network model based on a second sample data set, the second sample data set comprises a plurality of sample data, and the plurality of sample data comprises sample point cloud data matching the position coordinates and annotated classification labels. ### Claim 18 (depends on 1) The aircraft according to claim 1, wherein the aircraft further comprises an installation detection device to detect the safety protection device, and the at least one processor executes the at least one set of instructions to further cause the aircraft to at least: in response to the takeoff control instruction, obtain installation detection information output by the installation detection device; and determine that the aircraft is installed with the safety protection device in response to the installation detection information meeting a preset condition, or determine that the aircraft is not installed with the safety protection device in response to the installation detection information not meeting the preset condition. ### Claim 19 An aircraft, comprising: a body, including one or more propellers; at least one storage medium storing at least one set of instructions for controlling the aircraft; and at least one processor in communication with the at least one storage medium and a sensor carried by the body, wherein during operation, the at least one processor executes the at least one set of instructions to cause the aircraft to at least: receive a takeoff control instruction, in response to receiving the takeoff control instruction, control the sensor to turn toward a direction of the one or more propellers on the aircraft to detect installation of a safety protection device around the one or more propellers on the aircraft, and not determine surrounding conditions and not execute the takeoff control instruction to so as not to allow the aircraft to take off in response to the safety protection device not being installed around the one or more propellers on the aircraft; or execute the takeoff control instruction, control, after takeoff, the sensor to turn to a direction that does not face the one or more propellers on the aircraft for detection during flight, and lock the sensor in an angle range, in response to the safety protection device being installed around the one or more propellers on the aircraft. ### Claim 20 A method for control an aircraft, comprising: receiving a takeoff control instruction; in response to receiving the takeoff control instruction, controlling a sensor carried by the aircraft to turn toward a direction of one or more propellers on the aircraft to detect installation of a safety protection device around one or more propellers on the aircraft, and not executing the takeoff control instruction in response to the safety protection device not being installed around the one or more propellers on the aircraft; or executing the takeoff control instruction, controlling, after takeoff, the sensor to turn to a direction that does not face the one or more propellers on the aircraft for detection during flight, and lock the sensor in an angle range, in response to the safety protection device being installed.