WO2022011533A1 - 一种运动控制方法、控制设备、可移动平台及存储介质 - Google Patents

一种运动控制方法、控制设备、可移动平台及存储介质 Download PDF

Info

Publication number
WO2022011533A1
WO2022011533A1 PCT/CN2020/101791 CN2020101791W WO2022011533A1 WO 2022011533 A1 WO2022011533 A1 WO 2022011533A1 CN 2020101791 W CN2020101791 W CN 2020101791W WO 2022011533 A1 WO2022011533 A1 WO 2022011533A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
target
pixel
movable platform
motion control
Prior art date
Application number
PCT/CN2020/101791
Other languages
English (en)
French (fr)
Inventor
张东烁
原文智
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2020/101791 priority Critical patent/WO2022011533A1/zh
Publication of WO2022011533A1 publication Critical patent/WO2022011533A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/12—Target-seeking control

Definitions

  • the present application relates to the field of electronic technology, and in particular, to a motion control method, a control device, a movable platform and a storage medium.
  • motion control plays a very important role.
  • the motion control of the movable platform can be realized by means of assisted positioning and navigation technology, so that the movement of the movable platform is more stable and safe.
  • the commonly used robot-assisted positioning and navigation technologies include visual-assisted positioning and navigation, ultrasonic-assisted positioning and navigation, lighthouse-assisted positioning and navigation, and laser-assisted positioning and navigation.
  • vision-assisted positioning and navigation technology is commonly used to assist positioning and navigation of robots.
  • the richer the texture of the image the better, which has the problem of large amount of image data processing and high hardware requirements.
  • the embodiments of the present application provide a motion control method, a control device, a movable platform and a storage medium, which can realize navigation motion control based on images at low cost.
  • an embodiment of the present application provides a motion control method, the method is applied to a control device for controlling a movable platform, a photographing device is provided on the movable platform, and a lens of the photographing device is provided There is a filter for filtering the light of the target wavelength, the photographing device follows the movement of the movable platform, and the method includes:
  • the motion control instruction is used to control the power assembly to drive the movable platform to move toward the target direction, and after the movable platform moves toward the target direction, the target light spot in the second image captured by the photographing device
  • the second pixel location in the second image is close to the desired image location relative to the first pixel location.
  • an embodiment of the present application provides a movable platform, the movable platform includes a control device, a storage device, a photographing device, and a power assembly, and a lens of the photographing device is provided with a filter for filtering light of a target wavelength ;
  • the storage device for storing computer programs
  • the control device invokes the computer program for acquiring a first image obtained by photographing the target environment by the photographing device; determines the target light spot from the first image, and determines that the target light spot is in the first image.
  • a first pixel position on an image according to the first pixel position and the desired image position, a motion control instruction is generated, and a motion control instruction is sent to the connected power assembly; the motion control instruction is used to control the power assembly to drive the
  • the movable platform moves toward the target direction, and after the movable platform moves toward the target direction, the second pixel position of the target light spot in the second image captured by the photographing device is relative to the first pixel position in the second image. Pixel position, close to the desired image position.
  • an embodiment of the present application provides a control device, the control device includes a memory and a processor, wherein:
  • the memory for storing computer programs
  • the processor invokes a computer program for:
  • the motion control instruction is used to control the power assembly to drive the movable platform to move toward the target direction, and after the movable platform moves toward the target direction, the target light spot in the second image captured by the photographing device
  • the second pixel location in the second image is close to the desired image location relative to the first pixel location.
  • an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program is adapted to be loaded by a processor and execute the motion described in the first aspect above Control Method.
  • a filter that can filter the light of the target wavelength is set on the camera lens of the movable platform, so that the captured image only includes the light spot corresponding to the target wavelength, which is simple and easy to analyze the image.
  • the amount of image processing is greatly reduced, the computational efficiency is improved, and the precision of motion control for the movable platform is improved.
  • FIG. 1A is a schematic diagram of a motion control scene provided by an embodiment of the present invention.
  • FIG. 1B is a schematic diagram of another motion control scenario provided by an embodiment of the present invention.
  • FIG. 2 is a schematic structural diagram of a movable platform provided by an embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of a PID controller provided by an embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of a motion control method provided by an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of an image captured by a capturing device with a filter provided by an embodiment of the present invention
  • FIG. 6 is a schematic diagram of an image analysis provided by an embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of a movable platform according to an embodiment of the present invention.
  • FIG. 8 is a schematic structural composition diagram of a control device provided by an embodiment of the present invention.
  • the photographing device is mounted on a movable platform, and a filter is set on the lens of the photographing device. Due to the existence of the filter, the photographing device can only photograph the light source whose wavelength is the target wavelength. related images.
  • the first image is obtained by the photographing device, and the first image is obtained by photographing the surrounding environment of the movable platform.
  • a light source capable of emitting light of the target wavelength is arranged in the surrounding environment of the movable platform, so that the movable platform can
  • the light source in the surrounding environment is used as a navigation target and moves toward the light source; after the first image is obtained, the target light spot is determined from the first image, and the first pixel position of the target light spot on the first image is determined; According to the first pixel position and the desired image position, a motion control instruction is generated, and a motion control instruction is sent to the power assembly of the mobile platform; the motion control instruction is used to control the power assembly to drive the movable platform to move toward the target direction, that is, the direction of the light source.
  • the desired image position may be the middle position of the image, so during the movement of the movable platform, the target light spot in the image needs to be always in the center of the image, so that the movable platform can be used for motion control.
  • the movement of the movable platform is continuously controlled, so that the movable platform always moves toward the position of the light source corresponding to the target light spot.
  • FIG. 1A is a schematic diagram of a motion control scene provided by an embodiment of the present invention.
  • the devices in this scenario include: a dart robot 110 and a light-emitting device 120 .
  • the light-emitting device 120 may be an infrared light-emitting diode (Light Emitting Diode, LED), a laser light-emitting diode, etc., capable of emitting light of a specified wavelength.
  • LED Light Emitting Diode
  • a laser light-emitting diode etc.
  • a shooting device is installed on the body of the dart robot 110, the shooting device includes a camera, and the camera is also provided with a filter, and the camera in the dart robot 110 can monitor the environment around the dart robot 110. Shooting is performed to obtain an image. Due to the existence of the filter, the camera can only capture the image containing the target light spot, and the target light spot is obtained by the camera shooting the light-emitting device 120 .
  • the present application can be applied to a scene in which the dart robot 110 seeks a target, and the dart robot 110 is controlled to move toward the light-emitting device 120 to achieve target seeking.
  • a control device is installed on the body of the dart robot 110. The control device can control the movement of the dart robot 110 by controlling the power components provided on the dart robot 110. The control device controls the dart robot 110 to emit light in the target environment by controlling the power components.
  • the device 120 moves, and the position where the light emitting device 120 is located is the position of the "target" or is near the position of the "target”.
  • the dart robot 110 flies towards the light-emitting device 120 and takes a picture of the target environment.
  • the flying direction of the dart robot 110 is continuously adjusted to ensure that the target light spot is in the middle of the image or the designated image position.
  • the dart robot 110 may be thrown from a user's hand toward the light-emitting device, or may be launched toward the light-emitting device from a movable platform, such as a competitive robot, into the target environment.
  • the first spot of the target light spot is.
  • the power component is continuously controlled to drive the dart robot 110 to move, and the second pixel position on the next image is higher than the first pixel position. approach the desired image position. In this way, it can be ensured that the dart robot 110 "centers on the bull's-eye".
  • the light-emitting device 120 can also move all the time to become a “moving target”.
  • the dart robot 110 also continuously controls the movement of the dart robot 110 based on the first pixel position of the target light spot in the captured image to ensure subsequent The second pixel position on the image is closer to the desired image position than the first pixel position, and functions such as tracking, following, and navigation of the light-emitting device 120 corresponding to the target light spot are implemented.
  • the movement control of the movable platform based on the photographing device, the light-emitting device, and the filter can also be in the scenario of multi-robot coordinated motion, in which a light-emitting device is set on one robot, and one or more other robots are based on the photographing device.
  • the photographed target light spot is controlled by motion to ensure the coordinated movement with the robot with the light-emitting device.
  • the robot with the photographing device moves to the left
  • the robot with the photographing device is based on the light emitted by the light-emitting device.
  • the corresponding target light spot can also follow the control robot to move to the left.
  • FIG. 1B is a schematic diagram of another motion control scenario provided by an embodiment of the present invention.
  • the devices in this scenario include: Robot A 100 and Robot B 200.
  • the body of the robot A 100 includes a control device 101
  • the body of the robot B 200 includes a light-emitting device 202 .
  • the body of the robot armour 100 is provided with a photographing device, and the lens of the photographing device is provided with a filter for filtering the light of the target wavelength, and the photographing device follows the movement of the robot armour 100 .
  • the light-emitting device 202 carried on the robot B 200 emits light of the target wavelength, and the photographing device captures the environment in which the robot A 100 is located to obtain a first image, which is installed in the robot A 100 or remotely established with the robot A 100 is a control device that has a communication connection 101 Acquire a first image, and determine a first pixel position of a target light spot in the first image in the first image.
  • the filter Due to the existence of the filter, the light generated or reflected by objects other than the target wavelength is removed during the shooting process of the shooting device, and the obtained first image only contains the light corresponding to the light emitted by the light-emitting device 202 on the body of Robot B 200. Target light spot.
  • the control device 101 sends a motion control instruction to the power component of the robot A 100, and the motion control instruction is used to control the motion component to drive the robot A 100 to move toward the target direction, or the motion control instruction is used to control the motion component to drive the robot A 100 to move in the target direction.
  • Move on the target plane 300 so that the robot A 100 and the robot B 200 walk toward each other in the direction corresponding to the target plane 300 , and the target plane 300 is perpendicular to the connection line between the robot A 100 and the robot B 200 .
  • the robot A 100 when the robot A 100 is in the following mode of following the robot 200, the robot A 100 moves toward the target direction (that is, toward the robot B 200). In this case, the robot A 100 and the robot 200 form a following In the system, the two move at the same speed, so as to achieve the purpose of the robot A 100 following the robot 200 without the possibility of collision.
  • the control device 101 can control the power components of the robot A 100 according to the control conditions.
  • the control The condition is set according to the requirement to ensure that the second pixel position of the target light spot in the second image captured by the camera is close to the desired image position relative to the first pixel position, and the first pixel position is Refers to the position of the target cursor point on any image (for example, the first image) before the second image is captured.
  • the desired image position refers to the position of the center of the image.
  • the target light spot moves towards the robot B 200, and finally realizes the docking between the robot A 100 and the robot B 200.
  • the movement speed of robot B 200 is 0 or less than the movement speed of robot A 100.
  • the scenario in which two robots are docked can be It is the scene of docking charging.
  • the control device 101 cannot When the light emitted by the light-emitting device 202 on the robot A 100 plays the role of target guidance, the light-emitting device 202 is connected with the charging device of the robot B 200 to realize the charging process of the light-emitting device 202 through the power supply of the robot B 200 operation.
  • FIG. 2 is a schematic structural diagram of a movable platform provided by an embodiment of the present invention.
  • the movable platform 200 may at least include: a control device 210 , a photographing device 220 , and a power assembly 230 .
  • the photographing device 220 includes a camera 221 and a filter 222 ;
  • the power assembly 230 includes a steering gear 231 and a directional wing 232 .
  • the photographing device 220 sends the first image to the control device 210, wherein the target environment is provided with a light source capable of emitting light of the target wavelength; the control device 210 according to The first image generation motion control instruction is sent to the power component 230, wherein the motion control instruction is generated according to the first pixel position and the desired image position, and the first pixel position is the target light spot in the first image on the first image. Position; the power component 230 drives the steering gear 231 and the directional wings 232 of the movable platform according to the motion control instructions to make the movable platform 200 move toward the target direction.
  • the power component 230 may also be a component corresponding to a rotary-wing drone.
  • the movable platform 200 is a four-rotor, hexa-rotor, octa-rotor, etc. rotary-wing drone, and the power component 230 includes electronic speed regulation. engine, motor and propeller.
  • control device 210 mentioned in the embodiment of the present invention may be formed based on the proportional-integral-derivative (Proportion Integration Differentiation, PID) controller in FIG. 3 .
  • PID Proportion Integration Differentiation
  • FIG. 3 The structure of a PID controller is briefly described in .
  • the PID controller 211 can compare the collected data to a reference value, and then use this difference to calculate a new input value that is intended to allow the system data to reach or maintain the reference value.
  • the PID controller 211 can perform motion control on the movable platform 200 according to the target light spot in the image captured by the photographing device 220, and according to the pixel position of the target light spot in the image and the desired image position, specifically to make the movement of the movable platform 200 in the image.
  • the target light spot is always in the center of the image, so that the movable platform 200 can be used as a target guide, and the movement trajectory of the movable platform 200 can be continuously corrected, and the movable platform 200 can move toward the target with the desired image position as a reference. directional movement.
  • the control device 210 can control the movable platform 200 according to pre-programmed instructions.
  • control device may be a remote controller, for example, a terminal device such as a mobile phone, a personal computer, a smart wearable device, etc. that can remotely control a mobile platform such as an aircraft and a robot mentioned above, and the control device and the mobile platform
  • the connection can be established by means of radio frequency, Bluetooth, infrared, Wi-Fi, 4G/5G and other mobile communications.
  • FIG. 4 is a schematic flowchart of a motion control method provided by an embodiment of the present invention.
  • the motion control method is applied to a control device that controls a movable platform.
  • a photographing device is provided on the movable platform.
  • the lens of the device is provided with a filter for filtering the light of the target wavelength, the photographing device moves with the movable platform, and the method includes but is not limited to the steps described in S401 to S403 below.
  • the movable platform 200 may be an unmanned aerial vehicle, an unmanned ship, an unmanned vehicle, a sweeping robot, an Automated Guided Vehicle (AGV) car, a dart robot, etc.
  • the invention is not limited to this.
  • the photographing device is used to photograph images or videos during the movement of the movable platform, and may specifically be various types of cameras.
  • the control device provided by the embodiment of the present invention may be directly mounted on the body of the movable platform, or may be mounted on the body of the movable platform in other ways.
  • the axis pan/tilt is mounted on the body of the movable platform, which is not limited in the embodiment of the present invention.
  • the control device may be formed based on a proportional-integral-derivative PID controller, and the PID-based controller includes a PID outer loop and a PID inner loop; the PID outer loop is used to control the target light spot in the first image toward the direction of the target light spot.
  • the motion control process is performed according to the desired image position; the PID inner loop is used to control the speed when the power component drives the movable platform to move; the motion control instruction is based on the PID outer loop and PID inner loop generated.
  • S401 Acquire a first image obtained by photographing a target environment by a photographing device.
  • a light source capable of emitting light with a target wavelength is set in the target environment, and the target light spot determined from the first image refers to: the light source in the target environment after being photographed by the photographing device provided with the filter. Image points on the resulting image.
  • the photographing device can obtain environmental images one by one based on a monocular camera, or can obtain clearer environmental images one by one after performing image combination optimization based on a binocular camera or a multi-eye camera.
  • Each lens of the photographing device is provided with a filter for filtering the light of the target wavelength.
  • the lens of the photographing device can be a grayscale camera or a color camera, and the filter can include an infrared filter, an ultraviolet filter, or a laser filter. , or visible filters, etc. In this way, the light other than the light of the target wavelength in the target environment can be filtered out, and only one target light spot appears in the captured image for image processing, which greatly reduces the difficulty in the image processing process.
  • the lens of the photographing device is a grayscale camera
  • the light source set in the target environment that can emit light with the target wavelength is an infrared LED lamp
  • the target wavelength is set to 100 microns
  • the filter is an infrared filter, which can filter out
  • the filter can filter and capture light up to 100 microns.
  • the infrared LED light is fixed at a certain position in the target environment, and the light emitted from this position can be captured by the camera.
  • FIG. 5 is a schematic diagram of an image captured by a photographing device with a filter provided by an embodiment of the present invention. As shown in the figure, the image only contains white light spots, and the white light spots are It is obtained by photographing the infrared light emitted by the infrared LED light for the photographing device.
  • the movable platform may further include a pan/tilt, and the photographing device is fixed on the body of the movable platform through the pan/tilt, so that when the movable platform shakes, the photographing device also shakes. It affects the shooting effect and affects the accurate determination of the pixel positions of the subsequent target light spots.
  • the gimbal especially the three-axis gimbal, can better ensure that the camera is less affected by jitter;
  • the control device detects the movable platform by using an inertial sensor and/or a gyroscope and control the attitude of the gimbal according to the change of the detected attitude of the movable platform to offset the influence of the shaking of the movable platform on the stability of the camera, so that the shooting device is always in a stable state and captures clear and accurate environmental images. .
  • S402 Determine the target light spot from the first image, and determine the first pixel position of the target light spot on the first image.
  • the expression form of the pixel position may be pixel coordinates
  • the target light spot is determined from the first image
  • the first pixel position of the target light spot on the first image may be based on the pixel value of each pixel on the image. to be sure.
  • the target light spot is an image point on an image obtained by a photographing device provided with a filter to photograph a light source in a target environment.
  • the color value of each pixel can be traversed, and when the color value is greater than a predetermined threshold, it can be determined that the pixels in this part of the area are the target light The pixel point corresponding to the spot, and then the position of the pixel point at the center of this part of the area is taken as the first pixel position.
  • the pixel point analysis is ended, and the position of the one or more pixel points is used to determine the first pixel position, that is, the control device performs image analysis on the first image, and obtains the image of the first image.
  • the row pixel coordinate value and the column pixel coordinate value and then determine the first pixel position of the target light spot on the first image according to the row pixel coordinate value and the column pixel coordinate value.
  • the determining the first pixel position of the target light spot on the first image may include: the control device may perform statistical analysis on the pixel sum of the lines of the first image to obtain the first image pixel position.
  • the control device may perform statistical analysis on the pixel sum of the lines of the first image to obtain the first image pixel position.
  • Each row pixel sum, the row pixel sum greater than the first preset threshold in each row pixel sum is taken as the target row pixel sum, and the row pixel coordinate value is determined according to the target row pixel sum; the first image is calculated by the column pixel sum.
  • each column pixel sum of the first image uses the column pixel sum greater than the second preset threshold in each column pixel sum as the target column pixel sum, and determine the column pixel coordinate value according to the target column pixel sum;
  • the row pixel coordinate value and the column pixel coordinate value determine the first pixel location.
  • control device may specifically perform Blob analysis on the first image, and the Blob analysis is to extract and mark the connected domain of the binary image after the foreground and background of the image are separated. That is, the image is binarized (that is, the gray value of the pixel in the image is set to 0 or 255, that is, the process of presenting an obvious black and white effect for the entire image).
  • Each marked blob represents a foreground target, and then some relevant features of the blob can be calculated to facilitate the determination of the first pixel position.
  • the control device performs statistical analysis on the pixel sum of the lines after scanning the first image, and obtains the pixel sum of each line of the first image, assuming that they are respectively x 1 , x 2 , . . . , x n , and x 1 , x 2, ..., and the row of pixels x n pixels as a target row is greater than a first predetermined threshold value and, for the assumed target pixel and x 1, x 2, x 3, according to x 1, x 2, x 3 , determine the row pixel coordinate value of x, for example, randomly select or take the intermediate value x 2 ; do a statistical analysis of the pixel sum of the first image to obtain the pixel sum of each column of the first image, assuming that they are y 1 and y 2 respectively , ..., y m , take the column pixel sum of y 1 , y 2 , ..., y m greater than the second preset threshold as the target column pixel sum,
  • S403 Generate a motion control instruction according to the first pixel position and the desired image position, and issue a motion control instruction to the connected power components.
  • the motion control instruction is used to control the power component to drive the movable platform to move toward the target direction.
  • the second pixel position of the target light spot in the second image captured by the camera is in the second image.
  • the position of the target light spot in a certain image may be far from the desired image position compared with the position of the target light spot in the previously captured image, but in fact, In the motion control command sent for a certain image, the motion trajectory is still corrected as much as possible to ensure that the movable platform is moving towards the light source.
  • the reason for this phenomenon may be due to calculation errors, or external environment such as strong wind, or ground shaking It is caused by some factors that affect the movement of the movable platform.
  • the desired image position is determined according to the image center position area of the image captured by the photographing device.
  • the desired image position may also be determined according to the position set by the user.
  • the control device can present a user interface to the user, the user interface can include a preview interface for displaying the captured image, and can determine the desired image position according to the user's click, double-click, slide and other operations .
  • the power component includes a steering gear and a steering wing.
  • the steering gear and the steering wing provide the power required to adjust the running direction of the movable platform, and the steering gear can adjust the rotation axis of the steering wing by adjusting the steering gear.
  • the rotation angle of the camera can be used to compensate the shooting angle of the shooting device, and the shaking of the shooting device can be prevented or reduced by a suitable buffer mechanism.
  • the movable platform can be set by the user to move toward the light source capable of emitting light of the target wavelength, that is, the aforementioned light-emitting device, and the photographing direction of the photographing device is always on the movable platform.
  • the front such as when a dart robot is fired, is fired towards the light-emitting device.
  • the photographing device can also be rotated on the movable platform.
  • the movable platform moves, such as the aforementioned robot A
  • the camera of the photographing device is rotated to capture an image of the environment. Once the currently photographed image is found If the target light spot is included in the image, the image can be used as the first image, and the corresponding steps can be started, and the motion control of the movable platform can be completed with the target light spot as a reference.
  • the control device when the control device generates the motion control instruction, if an obstacle is detected, the obstacle avoidance assistance instruction is preferentially generated, and the movement to avoid the obstacle is the priority control method.
  • the control device may guide obstacle avoidance based on the motion control instruction at the same time, and the generated obstacle avoidance control instruction combines the movement direction controlled by the motion control instruction.
  • the movable platform can move based on the obstacle avoidance assistance instruction and the motion control instruction, so that the movable platform can avoid obstacles while moving toward the target direction, and ensure the safe movement of the movable platform.
  • the movable platform stores map information of the current environment, when the control device detects that the distance between the current position and the obstacle is less than a predetermined distance, or predicts that the current speed will hit the obstacle within a predetermined time , or when it is detected that the distance between the current position and the obstacle is less than the predetermined distance, and the current speed direction of the movable platform is facing the obstacle, the control device starts to execute the operation of generating the obstacle avoidance assistance instruction.
  • the map information of the current environment stored on the movable platform may be downloaded from a server, or acquired based on detection data of sensors on the movable platform.
  • the sensor may include a vision sensor (eg binocular camera, monocular camera) and/or a distance sensor (eg TOF camera, lidar).
  • the map information may be acquired by the dart robot based on the detection data of the sensor in the same target hunting or in different target hunting times.
  • a filter that can filter the light of the target wavelength is set on the camera lens of the movable platform, so that the captured image only includes the light spot corresponding to the target wavelength, which is simple and easy to analyze the image.
  • the amount of image processing is greatly reduced, the computational efficiency is improved, and the precision of motion control for the movable platform is improved.
  • An embodiment of the present invention provides a movable platform, which can be an unmanned aerial vehicle, an unmanned ship, an unmanned car, a robot, etc., wherein the robot can be a sweeping robot, a dart robot, a missile robot, an AGV car, etc. .
  • FIG. 7 is a schematic structural diagram of a movable platform provided by an embodiment of the present invention.
  • FIG. 7 is described by taking an unmanned aerial vehicle as an example. As shown in FIG.
  • the movable platform includes a control device 701 and a storage device 702 , and also includes a photographing device 703 and a power assembly 704 , and a filter for filtering the light of the target wavelength is set on the lens of the photographing device 703 .
  • the movable platform may also include other structures, such as a main body rack, a power supply, a communication interface, and the like.
  • control device 701 may specifically be a dedicated remote controller for controlling a movable platform, or may be a smartphone, a smart phone, a remote control device that can be used to remotely control a movable platform such as a drone, an unmanned vehicle, etc. Tablet PCs, smart wearable devices and other smart terminals.
  • the storage device 702 may include a volatile memory (volatile memory), such as random-access memory (RAM); the storage device 702 may also include a non-volatile memory (non-volatile memory), such as a flash memory. Flash memory (flash memory), solid-state drive (solid-state drive, SSD), etc.; the storage device 702 may also include a combination of the above-mentioned types of memory.
  • volatile memory volatile memory
  • non-volatile memory such as a flash memory.
  • flash memory flash memory
  • solid-state drive solid-state drive, SSD
  • the storage device 702 may also include a combination of the above-mentioned types of memory.
  • the control device 701 may be a central processing unit (CPU).
  • the control device 701 may further include a hardware chip.
  • the above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or the like.
  • the above-mentioned PLD may be a field-programmable gate array (FPGA), a general-purpose array logic (generic array logic, GAL), or the like.
  • the control device 701 is configured to acquire a first image obtained by photographing a target environment by a photographing device; determine the target light spot from the first image, and determine the first pixel position of the target light spot on the first image; According to the first pixel position and the desired image position, a motion control instruction is generated, and a motion control instruction is sent to the connected power assembly; the motion control instruction is used to control the power assembly to drive the movable platform to move toward the target direction, and when the movable platform After moving in the target direction, the second pixel position of the target light spot in the second image captured by the photographing device is close to the desired image position relative to the first pixel position.
  • the target environment is provided with a light source capable of emitting light of the target wavelength
  • the target light spot determined from the first image refers to: the photographing device with the filter set shoots the target environment image points on the resulting image after the light source in .
  • control device 701 is configured to perform statistical analysis on the sum of pixels of lines in the first image to obtain the sum of pixels of each line of the first image;
  • the row pixel sum is used as the target row pixel sum, and the row pixel coordinate value is determined according to the target row pixel sum;
  • the statistical analysis of the column pixel sum is performed on the first image, and each column pixel sum of the first image is obtained;
  • the column pixel sum greater than the second preset threshold is used as the target column pixel sum, and the column pixel coordinate value is determined according to the target column pixel sum;
  • the first pixel position is determined according to the row pixel coordinate value and the column pixel coordinate value.
  • the desired image position is determined according to the image center position area of the image captured by the capturing device.
  • control device 701 is constructed based on a proportional-integral-derivative PID controller.
  • the proportional-integral-derivative-based PID controller includes a PID outer loop and a PID inner loop; the PID outer loop is used to perform motion control processing on the target light spot in the first image toward the desired image position; the PID inner loop uses It is used to control the speed when the power component drives the movable platform to move; the motion control instructions are generated according to the PID outer loop and the PID inner loop.
  • the filters include: infrared filters, or ultraviolet filters, or laser filters, or visible filters.
  • the power components 704 controlled by the motion control instructions include: a steering gear and a steering wing.
  • control device in the embodiment of the present invention, reference may be made to the description of the related content in the foregoing embodiment, which is not repeated here.
  • a filter that can filter the light of the target wavelength is set on the camera lens of the movable platform, so that the captured image only includes the light spot corresponding to the target wavelength, which is simple and easy to analyze the image.
  • the amount of image processing is greatly reduced, the computational efficiency is improved, and the accuracy of motion control for the movable platform is improved.
  • FIG. 8 it is a schematic structural composition diagram of a control device according to an embodiment of the present invention.
  • the control device in the embodiment of the present invention includes a processor 801 and a memory 802; the control device may also include an input interface 803, an output interface 804.
  • the input interface 803 may be some user interface, or a data interface, or a communication interface.
  • the output interface 804 may be some network interfaces, communication interfaces, etc., capable of sending out data.
  • the memory 802 may include volatile memory (volatile memory), such as RAM; the memory 802 may also include non-volatile memory (non-volatile memory), such as flash memory, SSD, etc.; the memory 802 may also include the above-mentioned types. combination of memory.
  • the processor 801 may be a CPU.
  • the processor 801 may further include a hardware chip.
  • the above-mentioned hardware chip can be ASIC, PLD, etc.
  • the above-mentioned PLD may be an FPGA, a GAL, or the like.
  • the control device in the embodiment of the present invention is mainly used to control a movable platform, a photographing device is arranged on the movable platform, and a filter for filtering light of a target wavelength is arranged on the lens of the photographing device, and the The photographing device moves with the movable platform.
  • the memory 802 is used to store a computer program; the processor 801 is used to call the program code to perform the following steps:
  • the motion control instruction is used to control the power component to drive the movable platform to move toward the target direction. After the movable platform moves toward the target direction, the second pixel position of the target light spot in the second image captured by the camera is in the second image. Approach the desired image position relative to the first pixel position.
  • the target environment is provided with a light source capable of emitting light of the target wavelength
  • the target light spot determined from the first image refers to: the photographing device with the filter set shoots the target environment image points on the resulting image after the light source in .
  • the processor 801 is configured to perform the following steps:
  • the first pixel position is determined according to the row pixel coordinate value and the column pixel coordinate value.
  • the desired image position is determined according to an image center position area of the image captured by the capturing device.
  • the filters include: infrared filters, or ultraviolet filters, or laser filters, or visible filters.
  • the power components controlled by the motion control instructions include: the steering gear and the directional wings of the movable platform.
  • control device in the embodiment of the present invention, reference may be made to the description of the related content in the foregoing embodiment, which is not repeated here.
  • a filter that can filter the light of the target wavelength is set on the camera lens of the movable platform, so that the captured image only includes the light spot corresponding to the target wavelength, which is simple and easy to analyze the image.
  • the amount of image processing is greatly reduced, the computational efficiency is improved, and the precision of motion control for the movable platform is improved.
  • the embodiment of the present application further provides a readable storage medium, where the readable storage medium stores a computer program, and when the computer program is executed by the processor, it can be used to implement the description in the embodiment corresponding to FIG. 4 of the embodiment of the present application The motion control method is not repeated here.
  • the above-mentioned software functional unit is stored in a storage medium, and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute the methods described in the various embodiments of the present invention. some steps.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Studio Devices (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种运动控制方法、控制设备、可移动平台及存储介质，其中该方法包括：获取由拍摄装置拍摄目标环境得到的第一图像(S401)；从第一图像中确定出目标光斑点，并确定目标光斑点在第一图像上的第一像素位置(S402)；根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令(S403)。在可移动平台运动的过程中，可以实现对可移动平台进行实时地运动控制，降低图像处理过程中的难度，提高了对可移动平台进行运动控制的精度。

Description

一种运动控制方法、控制设备、可移动平台及存储介质 技术领域
本申请涉及电子技术领域，尤其涉及一种运动控制方法、控制设备、可移动平台及存储介质。
背景技术
随着科学的进步与技术的发展，诸如无人机、可移动的机器人、甚至自动驾驶汽车等可移动平台的应用场景也越来越广泛。在可移动平台的众多应用场景中，运动控制扮演着十分重要的角色，可以借助辅助定位导航技术等来实现可移动平台的运动控制，使可移动平台的运动更加稳定、安全。目前，常用的机器人辅助定位导航技术包括视觉辅助定位导航、超声波辅助定位导航、灯塔辅助定位导航、激光辅助定位导航等。
目前常用的是视觉辅助定位导航技术对机器人进行辅助定位导航，但视觉辅助过程中，需要图像的纹理越丰富越好，这就存在图像数据处理量大，对硬件要求较高的问题。
发明内容
本申请实施例提供了一种运动控制方法、控制设备、可移动平台及存储介质，可低成本地基于图像实现导航运动控制。
第一方面，本申请实施例提供一种运动控制方法，所述方法应用于对可移动平台进行控制的控制设备上，所述可移动平台上设置有拍摄装置，所述拍摄装置的镜头上设置有过滤目标波长的光线的滤波片，所述拍摄装置是跟随所述可移动平台运动的，所述方法包括：
获取由拍摄装置拍摄目标环境得到的第一图像；
从所述第一图像中确定出目标光斑点，并确定所述目标光斑点在所述第一图像上的第一像素位置；
根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；
所述运动控制指令用于控制所述动力组件带动所述可移动平台朝向目标方向运动，在所述可移动平台向目标方向运动后，所述拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近所述期望图像位置。
第二方面，本申请实施例提供一种可移动平台，所述可移动平台包括控制设备、存储装置、拍摄装置以及动力组件，所述拍摄装置的镜头上设置有过滤目标波长的光线的滤波片；
所述存储装置，用于存储计算机程序；
所述控制设备，调用所述计算机程序，用于获取由拍摄装置拍摄目标环境得到的第一图像；从所述第一图像中确定出目标光斑点，并确定所述目标光斑点在所述第一图像上的第一像素位置；根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；所述运动控制指令用于控制所述动力组件带动所述可移动平台朝向目标方向运动，在所述可移动平台向目标方向运动后，所述拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近所述期望图像位置。
第三方面，本申请实施例提供一种控制设备，所述控制设备包括存储器和处理器，其中：
所述存储器，用于存储计算机程序；
所述处理器，调用计算机程序，用于：
获取由拍摄装置拍摄目标环境得到的第一图像；
从所述第一图像中确定出目标光斑点，并确定所述目标光斑点在所述第一图像上的第一像素位置；
根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；
所述运动控制指令用于控制所述动力组件带动所述可移动平台朝向目标方向运动，在所述可移动平台向目标方向运动后，所述拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近所述期望图像位置。
第四方面，本申请实施例提供一种计算机可读存储介质，所述计算机可读 存储介质存储有计算机程序，所述计算机程序适于由处理器加载并执行如上述第一方面所述的运动控制方法。
在本发明实施例中，通过对可移动平台上的拍摄装置镜头设置的可以过滤目标波长的光线的滤波片，使得拍摄得到的图像中仅仅包括该目标波长所对应光斑，在图像分析时简单易行，图像处理量大幅降低，提高了计算效率，进而提高了对可移动平台进行运动控制的精度。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1A是本发明实施例提供的一种运动控制场景示意图；
图1B是本发明实施例提供的另一种运动控制场景示意图；
图2是本发明实施例提供的一种可移动平台的结构示意图；
图3是本发明实施例提供的一种PID控制器的结构示意图；
图4是本发明实施例提供的一种运动控制方法的流程示意图；
图5是本发明实施例提供的一种由带滤波片的拍摄装置拍摄到的图像的示意图；
图6是本发明实施例提供的一种图像分析的示意图；
图7是本发明实施例提供的一种可移动平台的结构示意图；
图8是本发明实施例提供的一种控制设备的结构组成示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
在本申请中，拍摄装置搭载在可移动平台上，并且该拍摄装置的镜头上设 置了滤波片，由于该滤波片的存在，拍摄装置只能够拍摄到发出的光线的波长为目标波长的光源的相关图像。由拍摄装置来获取第一图像，第一图像是由拍摄装置拍摄可移动平台周围环境得到的，在可移动平台周围环境中设置有能够发出目标波长的光线的光源，以便于可移动平台能够将周围环境中的该光源作为导航目标，朝向该光源移动；在得到第一图像后，再从第一图像中确定出目标光斑点，并确定目标光斑点在第一图像上的第一像素位置；根据第一像素位置与期望图像位置，生成运动控制指令，并向移动平台的动力组件发出运动控制指令；运动控制指令用于控制动力组件带动可移动平台朝向目标方向也即光源的方向移动，该期望的图像位置可能是图像的中间位置，那么在可移动平台运动过程中，需要使图像中的目标光斑点始终处于图像的正中央位置，这样就可以对可移动平台起到运动控制的作用，不断控制可移动平台的运动，使得可移动平台始终朝着目标光斑点所对应的光源的位置运动。
下面结合附图，对本发明的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。
请参见图1A，是本发明实施例提供的一种运动控制场景示意图。该场景下的设备包括：飞镖机器人110、发光设备120。其中，发光设备120可以为红外发光二极管(Light Emitting Diode，LED)、激光发光二极管等，能够发射指定波长的光线。
在本发明实施例中，飞镖机器人110机身上安装有拍摄装置，该拍摄装置包括摄像头，并且该摄像头上还设置有滤光片，通过飞镖机器人110中的摄像头可以对飞镖机器人110周围的环境进行拍摄，得到图像，由于滤波片的存在，摄像头只能捕捉到包含目标光斑点的图像，该目标光斑点是摄像头拍摄发光设备120而得到的。
本申请可以应用到飞镖机器人110寻靶的场景中，控制飞镖机器人110朝向发光设备120运动实现寻靶。飞镖机器人110机身上安装有控制设备，控制设备可以通过控制飞镖机器人110上设置的动力组件来控制飞镖机器人110的运动，控制设备通过控制动力组件来控制飞镖机器人110朝着目标环境中的发光设备120移动，发光设备120所处的位置即为“靶”的位置或者在“靶”的位置附近。飞镖机器人110在飞行之初，朝向发光设备120飞行并对目标环境 进行拍摄，因为滤波片的存在，只会捕捉到所述发光设备120发出的光线，拍摄的图像中仅仅包括发光设备120所发出光线对应的目标光斑点，基于目标光斑点在图像的实时位置，不断调整飞镖机器人110的飞行方向，确保目标光斑点在图像的中间位置或者指定图像位置即可。
飞镖机器人110可能从某个用户手中朝向发光设备掷出，也可能从一个可移动平台例如竞技机器人上朝向发光设备发射到目标环境中，在初次根据拍摄装置拍摄到的图像中目标光斑点的第一像素位置后，为了将目标光斑点置于图像的期望图像位置，比如图像中心点位置，持续控制动力组件带动飞镖机器人110运动，在下一图像上的第二像素位置相对于第一像素位置更接近所述期望图像位置。如此可以保证飞镖机器人110“正中靶心”。在另一个实施例中，发光设备120也可以一直移动，成为一个“移动靶”，飞镖机器人110同样基于拍摄到的图像中目标光斑点的第一像素位置，持续控制飞镖机器人110运动，确保后续图像上的第二像素位置相比于第一像素位置更接近期望图像位置，实现对目标光斑点所对应的发光设备120的跟踪、跟随、导航等功能。
基于拍摄装置、发光设备、滤波片来进行可移动平台的移动控制还可以是在多机器人协调运动的场景中，在该场景中，一个机器人上设置发光设备、一个或者多个其他机器人基于拍摄装置拍摄的目标光斑点，进行运动控制，以确保和带有发光设备的机器人协同运动，例如带发光设备的机器人向左运动时，带拍摄装置的机器人基于拍摄到的所述发光设备所发出的光线对应的目标光斑点，也可以跟着控制机器人向左运动。请参见图1B，是本发明实施例提供的另一种运动控制场景示意图。该场景下的设备包括：机器人甲100以及机器人乙200。其中，机器人甲100机身上包含控制设备101，机器人乙200机身上包含发光设备202。
机器人甲100机身上设置有拍摄装置，拍摄装置的镜头上设置有过滤目标波长的光线的滤波片，拍摄装置是跟随机器人甲100运动的。承载在机器人乙200上的发光设备202发出目标波长的光线，拍摄装置拍摄机器人甲100所处的环境得到第一图像，设置于机器人甲100内或者远程与机器人甲100建立有通信连接的控制设备101获取第一图像，并确定第一图像中的目标光斑点在第一图像中的第一像素位置。由于滤波片的存在，拍摄装置拍摄过程中去掉了除 目标波长以外的其他物体产生或反射的光线，得到的第一图像上只包含机器人乙200机身上的发光设备202发出的光线所对应的目标光斑点。
控制设备101向机器人甲100的动力组件发出运动控制指令，该运动控制指令用于控制运动组件带动机器人甲100朝着目标方向进行移动，或该运动控制指令用于控制运动组件带动机器人甲100在目标平面300上移动，使得机器人甲100与机器人乙200在目标平面300所对应的方向上相向而行，该目标平面300与机器人甲100和机器人乙200之间的连线相垂直。
在一个实施例中，机器人甲100可以处于跟随机器人200的跟随模式时，机器人甲100朝向目标方向(也即朝向机器人乙200)的方向运动，在此情况下机器人甲100和机器人200形成的跟随系统中，两者的运动速度相同，以此达到机器人甲100跟随机器人200的目的、且不会存在相撞的可能。
为了保证机器人甲100能够相对准确地跟踪机器人乙200，控制设备101可以根据控制条件来对机器人甲100的动力组件进行控制，对于先后拍摄得到的第一图像和第二图像而言，所述控制条件是根据保证拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近期望图像位置的要求设置的，所述第一像素位置是指在拍摄得到第二图像之前的任意图像(例如第一图像)上目标光标点的位置。另外，在一个实施例中，所述期望图像位置是指图像的正中央的位置。
在其他一些实施例中，还可以存在机器人甲100与机器人乙200对接的场景，机器人乙200处于静止或者慢速移动的状态，机器人甲100则基于机器人乙200的发光设备202所发射的光线对应的目标光斑点，朝向机器人乙200移动，最终实现机器人甲100与机器人乙200的对接。两个机器人对接的场景下具体实现可参考前一实施例跟随场景的具体描述，区别仅在于，机器人乙200的运动速度为0或者小于机器人甲100的运动速度，两个机器人对接的场景例如可以是对接充电的场景。
在一个实施例中，在机器人甲100朝向机器人乙200运动的过程中，若承载在机器人乙200机身上的发光设备202处于没电状态时，即控制设备101不能够根据承载在机器人乙200上的发光设备202发出的光线对机器人甲100起到目标指引的作用时，将发光设备202与机器人乙200的充电设备进行连接， 以通过机器人乙200的供电电源实现对发光设备202进行充电处理的操作。
可以理解的是，本发明实施例描述的可移动平台的结构示意图是为了更加清楚的说明本发明实施例的技术方案，并不构成对于本发明实施例提供的技术方案的限定，本领域普通技术人员可知，随着系统架构的演变和新业务场景的出现，本发明实施例提供的技术方案对于类似的技术问题，同样适用。
请参见图2，图2本发明实施例提供的一种可移动平台的结构示意图。如图2所示，可移动平台200至少可以包括：控制设备210、拍摄装置220、动力组件230。其中，拍摄装置220包括摄像头221和滤波片222；动力组件230包括舵机231和方向翼232。
在一个实施例中，拍摄装置220对目标环境进行拍摄得到第一图像后，将第一图像发给控制设备210，其中，目标环境中设置有能够发出目标波长的光线的光源；控制设备210根据第一图像生成运动控制指令发给动力组件230，其中，运动控制指令是根据第一像素位置和期望图像位置生成的，第一像素位置为第一图像中的目标光斑点在第一图像上的位置；动力组件230根据运动控制指令带动可移动平台的舵机231和方向翼232以使得可移动平台200朝向目标方向运动。在可移动平台200向目标方向运动后，拍摄装置220拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近期望图像位置，期望图像位置是根据所述拍摄装置拍摄到的图像中心位置区域确定的。在其他实施例中，动力组件230还可以是旋翼无人机对应的组件，比如可移动平台200是四旋翼、六旋翼、八旋翼等等的旋翼无人机，动力组件230即包括电子调速器、电机和螺旋桨。
在一个实施例中，本发明实施例提及的控制设备210可以是基于图3中的比例-积分-微分(Proportion Integration Differentiation，PID)控制器组成的，具体结构请参见图3，在图3中简要描述了一种PID控制器的结构。PID控制器211可以把收集到的数据与参考值进行比较，然后把这个差别用于计算新的输入值，这个新的输入值的目的是可以让系统的数据达到或者保持在参考值。具体可以为PID控制器211根据拍摄装置220拍摄得到的图像中的目标光斑点，根据目标光斑点在图像中的像素位置与期望图像位置，对可移动平台200进行运动控制，具体为使得图像中的目标光斑点始终处于图像的正中央，这样就可 以对可移动平台200起到目标指引的作用，不断修正可移动平台200的运动轨迹，以期望图像位置为参考让可移动平台200朝着目标方向运动。应理解，控制设备210可以按照预先编好的程序指令对可移动平台200进行控制。
在另一个实施例中，控制设备可以为遥控器，例如能够远程控制飞行器、上述提及的机器人等可移动平台的手机、个人电脑、智能可穿戴设备等终端设备，控制设备与可移动平台之间可以通过射频、蓝牙、红外、Wi-Fi、4G/5G等移动通信等方式建立连接。
基于以上的描述，下面对本发明实施例提供的运动控制方法的具体流程进一步进行说明。请参见图4，图4是本发明实施例提供的一种运动控制方法的流程示意图，该运动控制方法应用于对可移动平台进行控制的控制设备上，可移动平台上设置有拍摄装置，拍摄装置的镜头上设置有过滤目标波长的光线的滤波片，拍摄装置是跟随可移动平台运动的，该方法包括但不限于如下S401到S403所描述的步骤。
需要说明的是，本发明实施例中，可移动平台200可以为无人机、无人船、无人汽车、扫地机器人，自动引导运输(Automated Guided Vehicle，AGV)小车、飞镖机器人等等，本发明对此不作限定。拍摄装置用于在可移动平台的运动过程中进行图像或者视频拍摄，具体可以是各种类型的摄像机。另外，本发明实施例所提供的控制设备可以直接搭载于可移动平台的机身上，也可通过其他方式搭载于可移动平台的机身上，例如拍摄装置可以通过单轴、双轴或多轴云台搭载在可移动平台的机身上，本发明实施例对此不作限定。该控制设备可以是基于比例积分微分PID控制器构成的，而所述基于PID控制器包括PID外环和PID内环；所述PID外环用于对所述第一图像中的目标光斑点朝着所述期望图像位置进行运动控制处理；所述PID内环用于对所述动力组件带动所述可移动平台运动时的速度进行控制处理；所述运动控制指令是根据所述PID外环和PID内环生成的。
S401：获取由拍摄装置拍摄目标环境得到的第一图像。目标环境中设置有能够发出目标波长的光线的光源，而从所述第一图像中确定出的目标光斑点是指：设置了滤波片的所述拍摄装置拍摄目标环境中的所述光源后所得到的图像上的图像点。
拍摄装置可以基于单目摄像头得到一张一张的环境图像，也可以基于双目摄像头或多目摄像头进行图像组合优化后得到一张一张更加清晰的环境图像。拍摄装置的各镜头上设置有过滤目标波长的光线的滤波片，拍摄装置的镜头可以是灰度摄像头，也可以是彩色摄像头，滤波片可以包括红外滤波片、或者紫外滤波片、或者激光滤波片、或者可见滤波片等。通过这种方式，可以将目标环境中的除目标波长的光线以外的其它光线过滤掉，拍摄得到的图像中仅出现一个目标光斑点进行图像处理，极大地降低了图像处理过程中的难度。
举例来说，当拍摄装置的镜头为灰度摄像头、目标环境中设置的能够发出目标波长的光线的光源为红外LED灯时，设置目标波长为100微米，滤波片为红外滤波片，能够过滤掉目标环境中除红外光线以外的其它光线，且该滤波片能够过滤捕捉到100微米的光线。红外LED灯固定于目标环境中的某个位置，在此位置下发出的光线可以被拍摄装置捕捉到。
红外LED灯发出红外光，拍摄装置对目标环境进行拍摄，拍摄装置的镜头上设置的滤波片对目标环境中除红外光以外的光线都过滤掉，则拍摄装置获取到的第一图像为只包含该100微米的红外LED灯所对应目标光斑点的图像。如图5所示，图5是本发明实施例提供的一种由带滤波片的拍摄装置拍摄到的图像的示意图，如图所示，该图像中只包含白色光斑点，该白色光斑点即为拍摄装置拍摄红外LED灯发出的红外光线得到的。
在一个实施例中，可移动平台中还可以包括云台，拍摄装置是通过云台固定在可移动平台的机身上的，如此可以避免在可移动平台发生抖动时，拍摄装置也随之抖动而影响拍摄效果以及影响后续的目标光斑点的像素位置的准确确定。一方面，云台特别是三轴云台能够较好地确保拍摄装置收到的抖动影响较小，另一方面，在一个实施例中，控制设备利用惯性传感器和/或陀螺仪检测可移动平台的姿态，并根据检测到的可移动平台的姿态的变化来控制云台的姿态，以抵消可移动平台的抖动对摄像头稳定性的影响，使得拍摄装置始终处于稳定状态，拍摄清晰准确的环境图像。
S402：从第一图像中确定出目标光斑点，并确定目标光斑点在所述第一图像上的第一像素位置。像素位置的表现形式可以为像素坐标，从第一图像中确定出目标光斑点，所述目标光斑点在所述第一图像上的第一像素位置可以是根 据图像上每个像素点的像素值来确定的。如前述，目标光斑点为设置了滤波片的拍摄装置拍摄目标环境中的光源后所得到的图像上的图像点。
在一个实施例中，由于第一图像中实际仅包括目标光斑点，则可以遍历每一个像素点的颜色值，当颜色值大于预定的阈值时，即可确定这部分区域的像素点为目标光斑点对应的像素点，进而将这部分区域的中心位置像素点的位置作为第一像素位置。
在一个实施例中，可以不必对全部像素点进行遍历，而只需要依次对某一行的像素点、某个一列的像素点进行颜色值的判断，一旦检测到一个或者多个(比如50个)像素点的颜色值大于预设的阈值，则结束像素点分析，以该一个或者多个像素点的位置来确定第一像素位置，即控制设备对第一图像进行图像分析，得到第一图像的行像素坐标值和列像素坐标值，再根据行像素坐标值和列像素坐标值，确定目标光斑点在第一图像上的第一像素位置。
在一个实施例中，所述确定所述目标光斑点在所述第一图像上的第一像素位置可以包括：控制设备可以对第一图像做行的像素和的统计分析，得到第一图像的各个行像素和，将各个行像素和中大于第一预设阈值的行像素和作为目标行像素和，根据目标行像素和，确定行像素坐标值；对第一图像做列的像素和的统计分析，得到第一图像的各个列像素和，将各个列像素和中大于第二预设阈值的列像素和作为目标列像素和，根据目标列像素和，确定列像素坐标值；最后再根据所述行像素坐标值和列像素坐标值确定第一像素位置。
在一个实施例中，控制设备具体可以是对第一图像进行Blob分析，Blob分析就是对图像的前景和背景分离后的二值图像，进行连通域提取和标记。即将图像进行二值化(就是指将图像中的像素点的灰度值设置为0或255，即将整个图像呈现出明显的黑白效果的过程)。标记完成的每一个Blob都代表一个前景目标，然后就可以计算Blob的一些相关特征，以便于确定所述第一像素位置。
举例来说，控制设备对第一图像扫描后做行的像素和的统计分析，得到第一图像的各个行像素和，假设分别为x 1，x 2，...,x n，将x 1，x 2，...,x n中大于第一预设阈值的行像素和作为目标行像素和，假设目标像素和为x 1，x 2，x 3，根据x 1，x 2，x 3，确定行像素坐标值为x，比如随机选取或者取中间值x 2；对第一图像做列的像 素和的统计分析，得到第一图像的各个列像素和，假设分别为y 1，y 2，...,y m，将y 1，y 2，...,y m中大于第二预设阈值的列像素和作为目标列像素和，假设目标像素和为y 1，y 2，y 3，根据目标列像素和，确定列像素坐标值为y，比如随机选取或者取中间值y 2。最终得到目标光斑点的像素坐标为(x，y)。
S403：根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令。运动控制指令用于控制动力组件带动可移动平台朝向目标方向运动，在可移动平台向目标方向运动后，拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近期望图像位置。也就是说，不断修正可移动平台的运动朝向，始终尽量将目标光斑点置于图像中心位置，确保可移动平台朝向光源或者说发光设备移动。需要说明的是，在实际图像中，在移动过程中可能存在某个图像中目标光斑点的位置相较于之前拍摄的图像的目标光斑点的位置，远离期望图像位置的情况，但实际上，在针对该某一个图像而发送的运动控制指令仍然是尽量修正运动轨迹，确保可移动平台正对光源运动的，导致这一现象的原因可能是因为计算误差、或者外部环境比如强风、或者地面抖动等某些影响可移动平台移动的因素造成的。
在一个实施例中，期望图像位置是根据拍摄装置所拍摄图像的图像中心位置区域确定的，当然，期望图像位置还可以是根据用户设置的位置来确定，当拍摄到第一图像或者第一图像之前的某个图像时，控制设备可以向用户呈现一个用户界面，该用户界面上可以包括用于显示拍摄到的图像的预览界面，并且能够根据用户的点击、双击、滑动等操作确定期望图像位置。
在一个实施例中，对于固定翼无人机而言，动力组件包括舵机和方向翼，舵机和方向翼提供调整可移动平台运行方向所需动力，舵机可通过调整方向翼的转动轴的转动角度来对拍摄装置的拍摄角度进行补偿，并可通过适当的缓冲机构来防止或减小拍摄装置的抖动。
需要说明的是，本发明实施例中可移动平台可以一开始就被用户设置是朝向能够发射目标波长的光线的光源即前述提及的发光设备前进的，拍摄装置的拍摄朝向始终处于可移动平台前方，比如飞镖机器人被发射的时候，就是朝向发光设备发射的。在其他一些实施例中，拍摄装置也可以在可移动平台上旋转， 当可移动平台移动过程中，比如前述提及机器人甲，通过旋转拍摄装置的摄像头，捕捉环境图像，一旦发现当前拍摄的图像中包括目标光斑点，则可以将该图像作为第一图像，开始执行相应的步骤，以目标光斑点作为参考，完成对可移动平台的运动控制。
在一个实施例中，控制设备在生成运动控制指令时，如果检测到有障碍物，则优先生成避障辅助指令，以避开障碍物移动为优先控制方式。当然，在一个实施例中，控制设备可以同时基于运动控制指令来指导避障，生成的避障控制指令结合了运动控制指令控制的运动方向。可移动平台可以基于该避障辅助指令和运动控制指令来移动，可以使得可移动平台在朝向目标方向运动的同时可避开障碍物，保障可移动平台的安全移动。
本发明实施例中，生成避障辅助指令的触发方式有多种。在一个实施例中，可移动平台存储有当前环境的地图信息，当控制设备检测到当前位置与障碍物的距离小于预定距离时，或者预测到以当前的速度在预定时间内会撞上障碍物时，或者检测到当前位置与障碍物的距离小于预定距离，且可移动平台的当前速度方向朝向障碍物时，控制设备开始执行生成避障辅助指令的操作。
其中，可移动平台所存储的当前环境的地图信息可以是从服务器上下载的，或者是基于可移动平台上的传感器的探测数据所获取的。其中，该传感器可以包括视觉传感器(例如双目相机、单目相机)和/或距离传感器(例如TOF相机、激光雷达)。例如，在可移动平台为飞镖机器人的实施例中，该地图信息可以是飞镖机器人基于传感器在同一次寻靶或者在不同次寻靶中的探测数据所获取的。
在本发明实施例中，通过对可移动平台上的拍摄装置镜头设置的可以过滤目标波长的光线的滤波片，使得拍摄得到的图像中仅仅包括该目标波长所对应光斑，在图像分析时简单易行，图像处理量大幅降低，提高了计算效率，进而提高了对可移动平台进行运动控制的精度。
本发明实施例提供一种可移动平台，该可移动平台可以是无人飞行器、无人船、无人汽车以及机器人等，其中，机器人具体可以为扫地机器人、飞镖机器人、导弹机器人、AGV小车等。请参见图7，是本发明实施例提供的可移动平台的结构示意图，图7是以无人机为例进行说明的，如图7所示，该可移 动平台包括控制设备701、存储装置702，并且还包括拍摄装置703和动力组件704，拍摄装置703的镜头上设置有过滤目标波长的光线的滤波片。当然，所述可移动平台还可以包括其他结构，比如主体机架、电源、通信接口等。
在其他实施例中，所述控制设备701具体可以是一个用于控制可移动平台的专用遥控器，也可以是可用于对无人机、无人汽车等可移动平台进行遥控控制的智能手机、平板电脑、智能可穿戴设备等等智能终端。
所述存储装置702可包括易失性存储器(volatile memory)，如随机存取存储器(random-access memory，RAM)；存储装置702也可以包括非易失性存储器(non-volatile memory)，例如快闪存储器(flash memory)，固态硬盘(solid-state drive，SSD)等；存储装置702还可以包括上述种类的存储器的组合。
所述控制设备701可以是中央处理器(central processing unit，CPU)。所述控制设备701还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)等。上述PLD可以是现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)等。
所述控制设备701，用于获取由拍摄装置拍摄目标环境得到的第一图像；从第一图像中确定出目标光斑点，并确定目标光斑点在所述第一图像上的第一像素位置；根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；运动控制指令用于控制所述动力组件带动可移动平台朝向目标方向运动，在可移动平台向目标方向运动后，所述拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近期望图像位置。
在一个实施例中，所述目标环境中设置有能够发出目标波长的光线的光源，从所述第一图像中确定出的目标光斑点是指：设置了滤波片的所述拍摄装置拍摄目标环境中的所述光源后所得到的图像上的图像点。
在一个实施例中，所述控制设备701，用于对第一图像做行的像素和的统计分析，得到第一图像的各个行像素和；将各个行像素和中大于第一预设阈值 的行像素和作为目标行像素和，根据目标行像素和，确定行像素坐标值；对第一图像做列的像素和的统计分析，得到第一图像的各个列像素和；将各个列像素和中大于第二预设阈值的列像素和作为目标列像素和，根据目标列像素和，确定列像素坐标值；根据行像素坐标值和列像素坐标值确定第一像素位置。
在一个实施例中，期望图像位置是根据拍摄装置所拍摄图像的图像中心位置区域确定的。
在一个实施例中，控制设备701为基于比例积分微分PID控制器构成的。
在一个实施例中，基于比例积分微分PID控制器包括PID外环和PID内环；PID外环用于对第一图像中的目标光斑点朝着期望图像位置进行运动控制处理；PID内环用于对动力组件带动可移动平台运动时的速度进行控制处理；运动控制指令是根据PID外环和PID内环生成的。
在一个实施例中，滤波片包括：红外滤波片、或者紫外滤波片、或者激光滤波片、或者可见滤波片。
在一个实施例中，运动控制指令所控制的动力组件704包括：舵机和方向翼。
本发明实施例中所述控制设备的具体实现可参考前述实施例中相关内容的描述，在此不赘述。
在本发明实施例中，通过对可移动平台上的拍摄装置镜头设置的可以过滤目标波长的光线的滤波片，使得拍摄得到的图像中仅仅包括该目标波长所对应光斑，在图像分析时简单易行，图像处理量大幅降低，提高了计算效率，进而提高了对可移动平台进行运动控制的精度。
再请参见图8，是本发明实施例的一种控制设备的结构组成示意图，本发明实施例的所述控制设备包括处理器801和存储器802；所述控制设备还可以包括输入接口803、输出接口804。所述输入接口803可以是一些用户接口，或者数据接口，或者通信接口。所述输出接口804可以是一些网络接口、通信接口等，能够向外发出数据。
所述存储器802可包括易失性存储器(volatile memory)，如RAM；存储器802也可以包括非易失性存储器(non-volatile memory)，例如flash memory，SSD等；存储器802还可以包括上述种类的存储器的组合。所述处理器801 可以是CPU。所述处理器801还可以进一步包括硬件芯片。上述硬件芯片可以是ASIC，PLD等。上述PLD可以是FPGA，GAL等。
本发明实施例的所述控制设备主要用于对可移动平台进行控制，所述可移动平台上设置有拍摄装置，所述拍摄装置的镜头上设置有过滤目标波长的光线的滤波片，所述拍摄装置是跟随所述可移动平台运动的。
在一个实施例中，存储器802，用于存储计算机程序；处理器801，调用所述程序代码，用于执行如下步骤：
获取由拍摄装置拍摄目标环境得到的第一图像；
从第一图像中确定出目标光斑点，并确定目标光斑点在第一图像上的第一像素位置；
根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；
运动控制指令用于控制动力组件带动可移动平台朝向目标方向运动，在可移动平台向目标方向运动后，拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近期望图像位置。
在一个实施例中，所述目标环境中设置有能够发出目标波长的光线的光源，从所述第一图像中确定出的目标光斑点是指：设置了滤波片的所述拍摄装置拍摄目标环境中的所述光源后所得到的图像上的图像点。
在一个实施例中，所述处理器801，用于执行如下步骤：
对所述第一图像做行的像素和的统计分析，得到所述第一图像的各个行像素和；
将各个所述行像素和中大于第一预设阈值的行像素和作为目标行像素和，根据所述目标行像素和，确定行像素坐标值；
对所述第一图像做列的像素和的统计分析，得到所述第一图像的各个列像素和；
将各个所述列像素和中大于第二预设阈值的列像素和作为目标列像素和，根据所述目标列像素和，确定列像素坐标值；
根据所述行像素坐标值和列像素坐标值确定第一像素位置。
在一个实施例中，所述期望图像位置是根据所述拍摄装置所拍摄图像的图 像中心位置区域确定的。
在一个实施例中，所述滤波片包括：红外滤波片、或者紫外滤波片、或者激光滤波片、或者可见滤波片。
在一个实施例中，所述运动控制指令所控制的动力组件包括：所述可移动平台的舵机和方向翼。
本发明实施例中所述控制设备的具体实现可参考前述实施例中相关内容的描述，在此不赘述。
在本发明实施例中，通过对可移动平台上的拍摄装置镜头设置的可以过滤目标波长的光线的滤波片，使得拍摄得到的图像中仅仅包括该目标波长所对应光斑，在图像分析时简单易行，图像处理量大幅降低，提高了计算效率，进而提高了对可移动平台进行运动控制的精度。
本申请实施例还提供一种可读存储介质，所述可读存储介质存储有计算机程序，所述计算机程序被处理器执行时，可以用于实现本申请实施例图4所对应实施例中描述的运动控制方法，在此不再赘述。
上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所揭露的仅为本发明的部分实施例而已，当然不能以此来限定本发明之权利范围，本领域普通技术人员可以理解实现上述实施例的全部或部分流程，并依本发明权利要求所作的等同变化，仍属于发明所涵盖的范围。

Claims (23)

  1. 一种运动控制方法，其特征在于，应用于对可移动平台进行控制的控制设备上，所述可移动平台上设置有拍摄装置，所述拍摄装置的镜头上设置有过滤目标波长的光线的滤波片，所述拍摄装置是跟随所述可移动平台运动的，所述方法包括：
    获取由拍摄装置拍摄目标环境得到的第一图像；
    从所述第一图像中确定出目标光斑点，并确定所述目标光斑点在所述第一图像上的第一像素位置；
    根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；
    所述运动控制指令用于控制所述动力组件带动所述可移动平台朝向目标方向运动，在所述可移动平台向目标方向运动后，所述拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近所述期望图像位置。
  2. 如权利要求1所述的方法，其特征在于，所述目标环境中设置有能够发出目标波长的光线的光源，从所述第一图像中确定出的目标光斑点是指：设置了滤波片的所述拍摄装置拍摄目标环境中的所述光源后所得到的图像上的图像点。
  3. 如权利要求1所述的方法，其特征在于，所述确定所述目标光斑点在所述第一图像上的第一像素位置，包括：
    对所述第一图像做行的像素和的统计分析，得到所述第一图像的各个行像素和；
    将各个所述行像素和中大于第一预设阈值的行像素和作为目标行像素和，根据所述目标行像素和，确定行像素坐标值；
    对所述第一图像做列的像素和的统计分析，得到所述第一图像的各个列像素和；
    将各个所述列像素和中大于第二预设阈值的列像素和作为目标列像素和，根据所述目标列像素和，确定列像素坐标值；
    根据所述行像素坐标值和列像素坐标值确定第一像素位置。
  4. 如权利要求1所述的方法，其特征在于，所述期望图像位置是根据所述拍摄装置所拍摄图像的图像中心位置区域确定的。
  5. 如权利要求1所述的方法，其特征在于，所述控制设备为基于比例积分微分PID控制器构成的。
  6. 如权利要求5所述的方法，其特征在于，
    所述基于PID控制器包括PID外环和PID内环；
    所述PID外环用于对所述第一图像中的目标光斑点朝着所述期望图像位置进行运动控制处理；所述PID内环用于对所述动力组件带动所述可移动平台运动时的速度进行控制处理；
    所述运动控制指令是根据所述PID外环和PID内环生成的。
  7. 如权利要求1所述的方法，其特征在于，所述滤波片包括：红外滤波片、或者紫外滤波片、或者激光滤波片、或者可见滤波片。
  8. 如权利要求1-7任一项所述的方法，其特征在于，所述运动控制指令所控制的动力组件包括：所述可移动平台的舵机和方向翼。
  9. 一种可移动平台，其特征在于，所述可移动平台包括控制设备、存储装置、拍摄装置以及动力组件，所述拍摄装置的镜头上设置有过滤目标波长的光线的滤波片；
    所述存储装置，用于存储计算机程序；
    所述控制设备，调用所述计算机程序，用于获取由拍摄装置拍摄目标环境得到的第一图像；从所述第一图像中确定出目标光斑点，并确定所述目标光斑 点在所述第一图像上的第一像素位置；根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；所述运动控制指令用于控制所述动力组件带动所述可移动平台朝向目标方向运动，在所述可移动平台向目标方向运动后，所述拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近所述期望图像位置。
  10. 如权利要求9所述的可移动平台，其特征在于，所述目标环境中设置有能够发出目标波长的光线的光源；所述控制设备，用于设置了滤波片的所述拍摄装置拍摄目标环境中的所述光源后所得到的图像上的图像点。
  11. 如权利要求9所述的可移动平台，其特征在于，所述控制设备，用于对所述第一图像做行的像素和的统计分析，得到所述第一图像的各个行像素和；将各个所述行像素和中大于第一预设阈值的行像素和作为目标行像素和，根据所述目标行像素和，确定行像素坐标值；对所述第一图像做列的像素和的统计分析，得到所述第一图像的各个列像素和；将各个所述列像素和中大于第二预设阈值的列像素和作为目标列像素和，根据所述目标列像素和，确定列像素坐标值；根据所述行像素坐标值和列像素坐标值确定第一像素位置。
  12. 如权利要求9所述的可移动平台，其特征在于，所述期望图像位置是根据所述拍摄装置拍摄到的图像中心位置区域确定的。
  13. 如权利要求9所述的可移动平台，其特征在于，所述控制设备为基于比例积分微分PID控制器构成的。
  14. 如权利要求13所述的可移动平台，其特征在于，
    所述基于PID控制器包括PID外环和PID内环；
    所述PID外环用于对所述第一图像中的目标光斑点朝着所述期望图像位置进行运动控制处理；所述PID内环用于对所述动力组件带动所述可移动平台运动时的速度进行控制处理；
    所述运动控制指令是根据所述PID外环和PID内环生成的。
  15. 如权利要求9所述的可移动平台，其特征在于，所述滤波片包括：红外滤波片、或者紫外滤波片、或者激光滤波片、或者可见滤波片。
  16. 如权利要求9-15任一项所述的可移动平台，其特征在于，所述动力组件包括：所述可移动平台的舵机和方向翼。
  17. 一种控制设备，其特征在于，包括存储器和处理器；
    所述存储器，用于存储程序代码；
    所述处理器，调用所述程序代码，用于执行如下步骤：
    获取由拍摄装置拍摄目标环境得到的第一图像；
    从所述第一图像中确定出目标光斑点，并确定所述目标光斑点在所述第一图像上的第一像素位置；
    根据第一像素位置和期望图像位置，生成运动控制指令，并向已连接的动力组件发出运动控制指令；
    所述运动控制指令用于控制所述动力组件带动所述可移动平台朝向目标方向运动，在所述可移动平台向目标方向运动后，所述拍摄装置拍摄得到的第二图像中的目标光斑点在第二图像中的第二像素位置相对于第一像素位置，接近所述期望图像位置。
  18. 如权利要求17所述的控制设备，其特征在于，所述目标环境中设置有能够发出目标波长的光线的光源，从所述第一图像中确定出的目标光斑点是指：设置了滤波片的所述拍摄装置拍摄目标环境中的所述光源后所得到的图像上的图像点。
  19. 如权利要求17所述的控制设备，其特征在于，所述处理器，用于执行如下步骤：
    对所述第一图像做行的像素和的统计分析，得到所述第一图像的各个行像 素和；
    将各个所述行像素和中大于第一预设阈值的行像素和作为目标行像素和，根据所述目标行像素和，确定行像素坐标值；
    对所述第一图像做列的像素和的统计分析，得到所述第一图像的各个列像素和；
    将各个所述列像素和中大于第二预设阈值的列像素和作为目标列像素和，根据所述目标列像素和，确定列像素坐标值；
    根据所述行像素坐标值和列像素坐标值确定第一像素位置。
  20. 如权利要求17所述的控制设备，其特征在于，所述期望图像位置是根据所述拍摄装置所拍摄图像的图像中心位置区域确定的。
  21. 如权利要求17所述的控制设备，其特征在于，所述滤波片包括：红外滤波片、或者紫外滤波片、或者激光滤波片、或者可见滤波片。
  22. 如权利要求17所述的控制设备，其特征在于，所述运动控制指令所控制的动力组件包括：所述可移动平台的舵机和方向翼。
  23. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机程序，所述计算机程序在被执行时，实现如权利要求1-4任一项所述的运动控制方法。
PCT/CN2020/101791 2020-07-14 2020-07-14 一种运动控制方法、控制设备、可移动平台及存储介质 WO2022011533A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/101791 WO2022011533A1 (zh) 2020-07-14 2020-07-14 一种运动控制方法、控制设备、可移动平台及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/101791 WO2022011533A1 (zh) 2020-07-14 2020-07-14 一种运动控制方法、控制设备、可移动平台及存储介质

Publications (1)

Publication Number Publication Date
WO2022011533A1 true WO2022011533A1 (zh) 2022-01-20

Family

ID=79554396

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/101791 WO2022011533A1 (zh) 2020-07-14 2020-07-14 一种运动控制方法、控制设备、可移动平台及存储介质

Country Status (1)

Country Link
WO (1) WO2022011533A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107202982A (zh) * 2017-05-22 2017-09-26 徐泽宇 一种基于无人机位姿计算的信标布置及图像处理方法
CN107985556A (zh) * 2017-11-29 2018-05-04 天津聚飞创新科技有限公司 无人机悬停系统及方法
CN108010080A (zh) * 2017-11-29 2018-05-08 天津聚飞创新科技有限公司 无人机跟踪系统及方法
CN108001694A (zh) * 2017-11-29 2018-05-08 天津聚飞创新科技有限公司 无人机降落系统及方法
US20190332127A1 (en) * 2017-07-03 2019-10-31 Skydio, Inc. Detecting optical discrepancies in captured images

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107202982A (zh) * 2017-05-22 2017-09-26 徐泽宇 一种基于无人机位姿计算的信标布置及图像处理方法
US20190332127A1 (en) * 2017-07-03 2019-10-31 Skydio, Inc. Detecting optical discrepancies in captured images
CN107985556A (zh) * 2017-11-29 2018-05-04 天津聚飞创新科技有限公司 无人机悬停系统及方法
CN108010080A (zh) * 2017-11-29 2018-05-08 天津聚飞创新科技有限公司 无人机跟踪系统及方法
CN108001694A (zh) * 2017-11-29 2018-05-08 天津聚飞创新科技有限公司 无人机降落系统及方法

Similar Documents

Publication Publication Date Title
US11797009B2 (en) Unmanned aerial image capture platform
US11604479B2 (en) Methods and system for vision-based landing
Barry et al. High‐speed autonomous obstacle avoidance with pushbroom stereo
US11073389B2 (en) Hover control
WO2019113966A1 (zh) 一种避障方法、装置和无人机
CN108235815B (zh) 摄像控制装置、摄像装置、摄像系统、移动体、摄像控制方法及介质
US20190243356A1 (en) Method for controlling flight of an aircraft, device, and aircraft
CN110622091A (zh) 云台的控制方法、装置、系统、计算机存储介质及无人机
WO2020233682A1 (zh) 一种自主环绕拍摄方法、装置以及无人机
WO2021098453A1 (zh) 目标跟踪方法及无人飞行器
WO2019128275A1 (zh) 一种拍摄控制方法、装置及飞行器
WO2019227333A1 (zh) 集体照拍摄方法和装置
WO2020154942A1 (zh) 无人机的控制方法和无人机
CN113795805A (zh) 无人机的飞行控制方法和无人机
WO2020135447A1 (zh) 一种目标距离估计方法、装置及无人机
WO2022193081A1 (zh) 无人机的控制方法、装置及无人机
US20210105411A1 (en) Determination device, photographing system, movable body, composite system, determination method, and program
WO2020225979A1 (ja) 情報処理装置、情報処理方法、プログラム、及び情報処理システム
WO2022011533A1 (zh) 一种运动控制方法、控制设备、可移动平台及存储介质
CN110291013B (zh) 云台的控制方法、云台及无人飞行器
CN112292712A (zh) 装置、摄像装置、移动体、方法以及程序
US20220046177A1 (en) Control device, camera device, movable object, control method, and program
WO2022000211A1 (zh) 拍摄系统的控制方法、设备、及可移动平台、存储介质
WO2021238743A1 (zh) 一种无人机飞行控制方法、装置及无人机
US11265456B2 (en) Control device, photographing device, mobile object, control method, and program for image acquisition

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20944898

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20944898

Country of ref document: EP

Kind code of ref document: A1