WO2021056144A1 - 可移动平台的返航控制方法、装置及可移动平台 - Google Patents
可移动平台的返航控制方法、装置及可移动平台 Download PDFInfo
- Publication number
- WO2021056144A1 WO2021056144A1 PCT/CN2019/107300 CN2019107300W WO2021056144A1 WO 2021056144 A1 WO2021056144 A1 WO 2021056144A1 CN 2019107300 W CN2019107300 W CN 2019107300W WO 2021056144 A1 WO2021056144 A1 WO 2021056144A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- movable platform
- return
- feature point
- home
- point information
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- 230000000007 visual effect Effects 0.000 claims description 54
- 230000004927 fusion Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000001454 recorded image Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
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
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C27/00—Rotorcraft; Rotors peculiar thereto
- B64C27/04—Helicopters
- B64C27/08—Helicopters with two or more rotors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Definitions
- This application relates to the field of control technology, and in particular to a method and device for returning home control of a movable platform, and a movable platform.
- the embodiments of the present application disclose a method and device for returning home control of a movable platform, and a movable platform, which can control the movable platform to return home correctly along the original route of a flight trajectory, and ensure the safety of returning home.
- the first aspect of the embodiments of the present application discloses a return-to-home control method of a movable platform, and the method includes:
- the movable platform During the movement of the movable platform, record the waypoint information of multiple waypoints, where the waypoint information includes the position information of the movable platform and the image information collected by the movable platform;
- the movement state of the movable platform is adjusted according to the return home position to control the movable platform to return home according to the return home trajectory.
- the second aspect of the embodiments of the present application discloses a return home control device of a movable platform, including: a memory and a processor;
- the memory is used to store program instructions
- the processor is configured to execute program instructions stored in the memory, and when the program instructions are executed, the processor is configured to:
- the movable platform During the movement of the movable platform, record the waypoint information of multiple waypoints, where the waypoint information includes the position information of the movable platform and the image information collected by the movable platform;
- the movement state of the movable platform is adjusted according to the return home position to control the movable platform to return home according to the return home trajectory.
- the third aspect of the embodiments of the present application discloses a movable platform, including:
- a power system installed on the fuselage and used to provide power for the movable platform
- the fourth aspect of the embodiments of the present application discloses a computer-readable storage medium in which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented. .
- the return-to-home trajectory is generated according to the recorded position information of the movable platform during the movement process, and the movable platform is controlled to return along the return-to-home trajectory, which can improve the efficiency of generating the return-to-home trajectory; it is determined according to the image information collected by the movable platform
- the return position of the movable platform can accurately locate the position of the movable platform; in addition, the movement state of the movable platform can be adjusted according to the return position to control the movable platform to return home according to the return trajectory, which can control the movable platform along the trajectory that it has flown. Return home correctly on the same route, reduce the probability of the movable platform hitting an obstacle, and ensure the safety of the movable platform's return home.
- Fig. 1 is a schematic diagram of a movement track disclosed in an embodiment of the present application
- Fig. 2 is a schematic diagram of a return trajectory corresponding to the movement trajectory shown in Fig. 1;
- FIG. 3 is a schematic flowchart of a return-to-home control method for a movable platform disclosed in an embodiment of the present application
- FIG. 4 is a schematic diagram of an architecture flow diagram for determining a return position disclosed in an embodiment of the present application
- FIG. 5 is a schematic diagram of a position relationship between waypoints disclosed in an embodiment of the present application.
- Fig. 6 is a schematic diagram of an obstacle map and obstacle avoidance trajectory disclosed in an embodiment of the present application.
- FIG. 7 is a schematic structural diagram of a return control device of a movable platform disclosed in an embodiment of the present application.
- Fig. 8 is a schematic structural diagram of a movable platform disclosed in an embodiment of the present application.
- the movable platform In the process that the user controls the movable platform to move through the control terminal, or the movable platform moves autonomously according to the set movement trajectory, if it is detected that the movable platform satisfies the return-to-home conditions, such as obtaining the return-to-home instruction sent by the control terminal, it can be moved
- the disconnection time between the platform and the control terminal is greater than the time threshold or the difference between the remaining power of the mobile platform’s battery and the power required for the return of the mobile platform is less than or equal to the preset power threshold, the mobile platform needs to be controlled to return to the home .
- the control terminal cannot control the drone, and the drone enters an out of control state. ; At this time, the UAV can be controlled to return to a certain distance so that the UAV can resume the communication connection with the control terminal.
- an embodiment of the present application provides a return-to-home control method for a movable platform, which generates a return-to-home trajectory according to the position information of the historical waypoints of the movable platform, and controls the movable platform to follow the return-to-home trajectory according to the image information collected by the movable platform Return home to ensure the correctness and safety of the return home.
- the movable platform records the waypoint information of multiple waypoints passed by during the movement, for example, record the waypoint information of one waypoint every preset time, or record one waypoint information every preset distance of movement
- the waypoint information includes the position information of the movable platform and the image information collected by the movable platform.
- the position information is the position information of the waypoint where the movable platform is located when the image information is collected.
- the movable platform when it is detected that the return home conditions are met during the movement, the movable platform obtains the position information of multiple waypoints that the movable platform has passed before from the recorded historical waypoint information, and according to the acquired position information The position information generates a return trajectory. Control the movable platform to return home along the return track, and determine the return position of the movable platform according to the recorded image information of the movable platform during the return process, and adjust the movement state of the movable platform according to the determined return position to control The movable platform will return home according to the return track.
- the return-to-home trajectory is generated according to the recorded position information of the movable platform during the movement, and the movable platform is controlled to return along the return-to-home trajectory, which can improve the efficiency of generating the return-to-home trajectory; determine the movable platform according to the image information collected by the movable platform
- the return position of the mobile platform can accurately locate the position of the movable platform; in addition, the movement state of the movable platform can be adjusted according to the return position to control the movable platform to return home according to the return trajectory, and the movable platform can be controlled to follow the original path of the flying trajectory. Return to home, reduce the probability of the movable platform hitting an obstacle, and ensure the safety of the movable platform to return home.
- the movable platform may be a movable device such as an unmanned aerial vehicle, an unmanned vehicle, an unmanned ship, and a mobile robot.
- FIG. 3 is a schematic flowchart of a method for returning home on a movable platform according to an embodiment of the application.
- the return-to-home control method of the movable platform described in the embodiment of the present application is applied to the movable platform, and the method includes:
- the user may control the movement of the movable platform through the control terminal, or the movable platform may move autonomously according to a preset movement track.
- the movable platform When the movable platform is moving, its equipped camera captures images of the surrounding environment where the movable platform is located at multiple waypoints; acquires the images captured by the camera, and extracts the feature points of the captured images , Obtain the first feature point information; the movable platform uses the first feature point information as the image information collected by the movable platform.
- the feature point refers to a pixel point with a sharp change in the gray value of the image or a pixel point with a large curvature on the edge of the image (that is, the intersection of two edges), and the feature point can identify the subject in the image.
- Image matching can be completed through the matching of feature points.
- the movable platform can store the position information of the movable platform in the waypoint information and the image information collected by the movable platform in association.
- the movable platform saves the image information collected at a certain waypoint and the position information of the movable platform corresponding to the certain waypoint in the same file.
- the mobile platform obtains the return instruction sent by the control terminal, the time that the mobile platform is disconnected from the control terminal is greater than the time threshold, the remaining battery of the mobile platform.
- the difference between the power and the power required by the movable platform to return to home is less than or equal to the preset power threshold, and it is detected that the movable platform is malfunctioning, and the movable platform cannot pass in the preset direction, it is determined that the movable platform meets the conditions for returning to home.
- the recorded position information of the movable platform is obtained from the historical waypoint information, and the return point is determined according to the acquired position information, and a smooth trajectory is generated according to the return point.
- the smooth trajectory of is used as the return trajectory. As shown in Figure 2, the corresponding relationship between the return trajectory and the return point is shown.
- the movable platform after generating a return trajectory according to the recorded position information of the movable platform, the movable platform is controlled to return along the return trajectory.
- the positioning accuracy of the positioning device on the movable platform may be poor, and the positioning signal is weak, etc., leading to positioning deviations, causing the return position (ie actual position) of the movable platform to deviate from the return path; , It is necessary to obtain the accurate return position of the movable platform by other means.
- the image of the surrounding environment where the movable platform is located is collected through the camera configured on the movable platform; the image collected by the camera during the return process is acquired, and According to the acquired image, the target feature point information is determined in the first feature point information.
- the movable platform performs feature point extraction on the image acquired during the return journey to obtain the second feature point information; from the first feature point information, the target feature point information that matches the second feature point information is determined .
- the target feature point information may be feature point information that has the highest degree of matching with the second feature point information in the first feature point information.
- the degree of matching between the first feature point information and the second feature point information can be represented by the number of points with the same name in the feature points corresponding to the first feature point information and the feature points corresponding to the second feature point information. The larger the number, the higher the matching degree between the first feature point information and the second feature point information, and the smaller the number of points with the same name, the lower the matching degree between the first feature point information and the second feature point information.
- the visual estimated position of the movable platform is determined according to the target feature point information. Specifically, according to the position information of the movable platform corresponding to the target feature point information, that is, the position information corresponding to the target feature point information collected by the movable platform, the visual estimated position of the movable platform is determined.
- the movable platform arrives at waypoint B from waypoint A through waypoint C, and collects the image of the object in Figure 5 when passing through each waypoint; records the position information of each waypoint, and records the movable The feature point information of the feature points in the images captured by the platform at each waypoint.
- the return trajectory of the original route is waypoint B through waypoint C to waypoint A, but due to positioning deviation, the movable platform may move to waypoint D while moving along the return trajectory, and waypoint D deviates from the return trajectory;
- the movable platform also collects the image of the object in Figure 5 at waypoint D, and extracts the feature point information of the feature point from the image.
- the feature point information of the feature points in the image collected by the mobile platform at waypoint D it can be from the recorded historical feature point information, that is, the feature point information recorded during the movement of the mobile platform from waypoint A to waypoint B
- the target feature point information is determined in the, for example, the target feature point information may be collected by the movable platform at waypoint C.
- the target feature point information corresponding to the image captured by the mobile platform at waypoint C matches the feature point information corresponding to the image captured by the mobile platform at waypoint D, that is, the image captured by the mobile platform at waypoint C matches the movable
- the image collected by the platform at waypoint D has the most points with the same name.
- the visual estimated position of waypoint D can be determined according to the position information of waypoint C.
- the position information of waypoint C recorded during the movement of the movable platform from waypoint A to waypoint B can be used as the visual estimated position of waypoint D, and the position information of waypoint C can be Obtained by the positioning device on the mobile platform.
- the return position of the movable platform is determined based at least in part on the visual estimated position.
- the positioning position of the movable platform corresponding to the image collected during the process of returning the movable platform along the return trajectory is acquired, and the positioning position is obtained by positioning the positioning device configured on the movable platform; according to the vision of the movable platform Estimate the position and positioning position, and determine the return position of the movable platform. The above method is adopted to accurately locate the position of the movable platform.
- the signal strength corresponding to the positioning position is acquired, and the fusion weights corresponding to the visual estimation position and the positioning position are determined according to the signal strength.
- the fusion weight the visual estimated position and the positioning position are weighted and averaged to determine the return position of the movable platform.
- the movable platform can determine the fusion weights corresponding to the visual estimation position and the positioning position under the signal strength according to the preset mapping relationship between the signal strength and the fusion weight.
- the signal strength is strong, it indicates that the positioning accuracy of the positioning device at this time is high, and the fusion weight corresponding to the positioning position can be appropriately increased at this time; when the signal strength is weak, it indicates that the positioning accuracy of the positioning device is relatively high at this time. Low, at this time, the fusion weight of the positioning position can be appropriately reduced.
- the movable platform fuses the visual estimated position with the positioning position according to the aforementioned fusion weight to obtain the return position of the movable platform.
- the degree of matching between the target feature point information and the second feature point information is acquired, and the fusion weights respectively corresponding to the visual estimated position and the positioning position are determined according to the degree of matching.
- the visual estimated position and the positioning position are weighted and averaged to determine the return position of the movable platform.
- the movable platform can determine the fusion weights corresponding to the visual estimation position and the positioning position under the matching degree according to the preset mapping relationship between the matching degree and the fusion weight.
- the matching degree When the matching degree is high, it means that the accuracy of the visual estimated position is high, and at this time, the fusion weight corresponding to the visual estimated position can be appropriately increased; when the matching degree is low, it means that the accuracy of the visual estimated position is low. At this time, the fusion weight of the visual estimated position can be appropriately reduced.
- adjusting the moving state of the movable platform includes adjusting one or more of the moving direction, the moving track, and the moving speed of the movable platform.
- the position of the target waypoint can be determined according to the return position to control the movable platform to return to the return trajectory. For example, according to the determined return position and the position of the target waypoint, a movement trajectory is generated to control the movable After the platform moves to the position of the target waypoint along the moving track, it will continue to return home according to the return track.
- the movable platform constructs a real-time obstacle map of the environment in which the movable platform is located during the process of returning home along the return trajectory.
- the depth map of the surrounding environment where the movable platform is located is obtained through detection of the depth sensor on the movable platform, and the position and posture of the depth map detected by the depth sensor are acquired; according to the depth map and the position and position of the depth sensor Attitude, real-time construction of obstacle maps of the surrounding environment where the movable platform is located.
- a three-dimensional obstacle map within a preset range centered on the movable platform is constructed in real time, and the size corresponding to the preset range can be determined according to the detection distance of the visual sensor.
- multiple depth sensors are installed on the movable platform, and depth images can be generated in real time through each depth sensor.
- the relative position relationship between the depth sensors can be further obtained.
- the coordinate conversion relationship between the depth images generated by each depth sensor can be determined.
- the depth images generated by the depth sensors are image-spliced to obtain a three-dimensional map of the surrounding environment where the movable platform is located. Furthermore, based on the three-dimensional map, an obstacle map of the surrounding environment where the movable platform is located can be obtained.
- a single depth sensor is installed on the movable platform.
- the depth sensor can generate multiple depth images in real time during the movement of the movable platform. After obtaining the positions and attitudes of the depth sensors corresponding to the multiple depth images , It is possible to determine the coordinate conversion relationship between the multiple depth images generated by the depth sensor. Then, according to the coordinate conversion relationship, the multiple depth images generated by the depth sensor are image-spliced to obtain a three-dimensional map of the surrounding environment where the movable platform is located. Furthermore, based on the three-dimensional map, an obstacle map of the surrounding environment where the movable platform is located can be obtained.
- the depth sensor may be one or more of a binocular vision sensor, an ultrasonic sensor, a millimeter wave radar sensor, and a lidar sensor.
- the binocular vision sensor may be the same or different from the shooting device configured on the movable platform described above for capturing images.
- the binocular vision sensor can acquire the depth map of the surrounding environment where the movable platform is located, and the positioning device and the attitude sensor of the movable platform can acquire the position information and attitude information of the binocular vision sensor.
- the position information and posture information of the visual sensor obtain a three-dimensional map of the surrounding environment where the movable platform is located, and then an obstacle map of the surrounding environment where the movable platform is located can be obtained according to the three-dimensional map.
- the number of binocular vision sensors is one or more. When the number of binocular vision sensors is multiple, multiple binocular vision sensors can be installed on the front, back, left, and right sides of the movable platform, respectively.
- the movable platform is controlled to avoid the obstacle.
- the position of the obstacle is acquired according to the constructed depth map, and the probability of the movable platform hitting the obstacle is determined according to the position of the obstacle and the return trajectory; when the probability is greater than the preset value, the probability is determined according to the obstacle.
- the position of the mobile platform, the current position of the movable platform, and the return trajectory determine the obstacle avoidance trajectory; control the movable platform to move along the obstacle avoidance trajectory to avoid the obstacle, and continue to move along the return trajectory after moving along the obstacle avoidance trajectory .
- FIG. 6 shows the correspondence between obstacles, return trajectory and obstacle avoidance trajectory.
- the return trajectory is generated according to the recorded position information of the movable platform during the movement process, and the movable platform is controlled to return along the return trajectory, which not only improves the efficiency of generating the return trajectory, but also controls the movable platform to fly along
- the original path of the past trajectory is returned correctly;
- the return position of the movable platform is determined according to the image information collected by the movable platform, and the position of the movable platform can be accurately located; in addition, the movement state of the movable platform is adjusted according to the return position to control the movable
- the platform returns home according to the return trajectory, which can reduce the probability of the movable platform hitting obstacles and ensure the safety of the movable platform.
- FIG. 7 is a schematic structural diagram of a return-to-home control device for a movable platform provided by an embodiment of the application.
- the return-to-home control device of the movable platform described in the embodiment of the present application includes: a processor 701, a communication interface 702, and a memory 703.
- the processor 701, the communication interface 702, and the memory 703 may be connected through a bus or in other ways.
- the embodiment of the present application takes the connection through a bus as an example.
- the processor 701 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.
- the processor 701 may also be a multi-core CPU or a core used to implement communication identification binding in a multi-core NP.
- the processor 701 may be a hardware chip.
- the hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof.
- the PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.
- ASIC application-specific integrated circuit
- PLD programmable logic device
- CPLD complex programmable logic device
- FPGA field-programmable gate array
- GAL generic array logic
- the communication interface 702 can be used for the exchange of sending and receiving information or signaling, as well as the reception and transmission of signals.
- the memory 703 may mainly include a storage program area and a storage data area.
- the storage program area may store an operating system and a stored program required by at least one function (such as a text storage function, a location storage function, etc.); the storage data area may store Data (such as image data, text data) created according to the use of the device, etc., and may include application storage programs, etc.
- the memory 703 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
- the memory 703 is also used to store program instructions.
- the processor 701 is configured to execute program instructions stored in the memory 703, and when the program instructions are executed, the processor 701 is configured to:
- the waypoint information of multiple waypoints is recorded, the waypoint information includes the position information of the movable platform and the image information collected by the movable platform; when the movable platform When the return-to-home condition is met, the return-to-home trajectory is generated according to the position information of the movable platform recorded by the movable platform; in the process of controlling the movable platform to return along the return-to-home trajectory, according to the data collected by the movable platform
- the image information determines the home position of the movable platform; adjusts the movement state of the movable platform according to the home position to control the movable platform to return home according to the return track.
- the processor 701 before the processor 701 records the waypoint information of the multiple waypoints, the processor 701 is further configured to: obtain the images collected by the movable platform at the multiple waypoints; The movable platform performs feature point extraction on the images collected by the multiple waypoints to obtain first feature point information; and uses the first feature point information as the image information collected by the movable platform.
- the processor 701 determines the return position of the movable platform according to the image information collected by the movable platform, it is specifically configured to: acquire the process of returning the movable platform along the return trajectory According to the images collected in the process of returning home along the return trajectory of the movable platform, the target feature point information is determined in the first feature point information; the target feature point information is determined according to the target feature point information The estimated visual position of the mobile platform; the return position of the movable platform is determined at least in part based on the estimated visual position.
- the processor 701 is specifically used for determining target feature point information in the first feature point information according to the images collected during the process of returning home along the return trajectory of the movable platform: Perform feature point extraction on the images collected during the process of returning home along the return path of the movable platform to obtain second feature point information; determine in the first feature point information according to the second feature point information Target feature point information, where the target feature point information matches the second feature point information.
- the processor 701 is further configured to: associate the location information of the movable platform and the image information collected by the movable platform in the waypoint information;
- the target feature point information determines the visual estimated position of the movable platform, it is specifically used to: determine the visual estimated position of the movable platform according to the position information of the movable platform corresponding to the target feature point information .
- the processor 701 determines the return position of the movable platform at least partly according to the estimated visual position, it is specifically configured to: acquire the movable platform in the process of returning along the return trajectory The positioning position of the movable platform corresponding to the collected image; and the return position of the movable platform is determined according to the visual estimated position and the positioning position.
- the processor 701 determines the return position of the movable platform according to the visual estimated position and the positioning position, it is specifically configured to: obtain the signal strength corresponding to the positioning position, and according to the The signal strength determines the fusion weights respectively corresponding to the visual estimated position and the positioning position; the visual estimated position and the positioning position are fused according to the fusion weight to obtain the return position of the movable platform.
- the processor 701 determines the return position of the movable platform according to the visual estimated position and the positioning position, it is specifically configured to: acquire the target feature point information and the second According to the matching degree of the feature point information, the fusion weight corresponding to the visual estimation position and the positioning position is determined according to the matching degree; the visual estimation position and the positioning position are fused according to the fusion weight to obtain the Describe the return position of the movable platform.
- the movable platform satisfies the conditions for returning home, including one or more of the following: acquiring the returning home instruction sent by the control terminal; the time when the movable platform is disconnected from the controlling terminal is greater than the time threshold; so The difference between the remaining power of the battery of the movable platform and the power required for returning home of the movable platform is less than or equal to a preset power threshold.
- the processor 701 is further configured to: in the process of controlling the movable platform to return along the return track, construct an obstacle map of the environment in which the movable platform is located in real time; When the obstacle map detects that there is an obstacle around the return track, the movable platform is controlled to avoid the obstacle.
- the processor 701 when the processor 701 constructs an obstacle map of the environment in which the movable platform is located in real time, it is specifically configured to: construct an obstacle map within a preset range centered on the movable platform in real time. .
- the processor 701 when the processor 701 constructs an obstacle map of the environment in which the movable platform is located in real time, it is specifically used to: obtain a depth map of the environment in which the movable platform is located, and the depth map is determined by the The depth sensor on the movable platform is detected; the position and attitude of the depth sensor are acquired; the obstacle map of the environment in which the movable platform is located is constructed in real time according to the depth map and the position and attitude of the depth sensor .
- the processor 701 when the processor 701 adjusts the moving state of the movable platform, it is specifically configured to adjust one or more of the moving direction, the moving track, and the moving speed of the movable platform.
- the processor 701, the communication interface 702, and the memory 703 described in the embodiment of the present application can execute the implementation described in the return control method of a movable platform provided by the embodiment of the present application, and will not be omitted here. Go into details.
- the return trajectory is generated according to the recorded position information of the movable platform during the movement process, and the movable platform is controlled to return along the return trajectory, which not only improves the efficiency of generating the return trajectory, but also controls the movable platform to fly along
- the original path of the past trajectory is returned correctly;
- the return position of the movable platform is determined according to the image information collected by the movable platform, and the position of the movable platform can be accurately located; in addition, the movement state of the movable platform is adjusted according to the return position to control the movable
- the platform returns home according to the return trajectory, which can reduce the probability of the movable platform hitting obstacles and ensure the safety of the movable platform.
- the embodiment of the present invention provides a movable platform.
- the movable platform includes a fuselage 801, a power system 802, a return control device 803 of the above-mentioned movable platform, a camera 804, and a depth sensor 805.
- the power system 802 is installed on the fuselage 801 of the movable platform to provide power for the movable platform; specifically, the power system 801 may include one or more of a propeller, a motor, and an electric regulator.
- the photographing device 804 may be a visible light camera, an infrared camera, a thermal imaging camera, a depth camera, or the like.
- the depth sensor 805 may be one or more of a binocular vision sensor, an ultrasonic sensor, a millimeter wave radar sensor, and a lidar sensor.
- the camera 804 can be carried on the fuselage 801 of the movable platform through the stabilized gimbal.
- the stabilized gimbal is installed on the fuselage 801 of the movable platform, and the camera 804 is fixed on the stabilized gimbal;
- the stabilization platform can drive the camera 804 to rotate around one or more of the yaw axis, roll axis, and pitch axis, so as to adjust the posture of the camera 804 when the image is captured.
- the camera 804 can also be directly carried on the body 801 of the movable platform, and the movable platform can adjust the posture of the camera 804 when the image is taken by controlling its posture.
- the return control device 803 of the movable platform is installed on the fuselage 801 of the movable platform, and includes a processor and a memory.
- the memory is used to store program instructions
- the processor is used to execute the program instructions stored in the memory.
- the processor is used to record the waypoint information of multiple waypoints during the movement of the movable platform.
- Point information includes the position information of the movable platform and the image information collected by the movable platform; when the movable platform meets the conditions for returning home, it is generated according to the position information of the movable platform recorded by the movable platform Return home trajectory; in the process of controlling the movable platform to return home along the return home trajectory, determine the return position of the movable platform according to the image information collected by the movable platform; adjust the movable platform according to the return position
- the movement state of the platform is used to control the movable platform to return home according to the return track.
- An embodiment of the present application also provides a computer-readable storage medium in which a computer program is stored.
- the computer program is executed by a processor, the return control of the movable platform described in the above method embodiment is realized. method.
- the embodiments of the present application also provide a computer program product containing instructions, which, when run on a computer, causes the computer to execute the return-to-home control method of the movable platform described in the foregoing method embodiment.
- the program can be stored in a computer-readable storage medium, and the storage medium can include: Flash disk, read-only memory (Read-Only Memory, ROM), random access device (Random Access Memory, RAM), magnetic disk or optical disk, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mechanical Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Navigation (AREA)
Abstract
一种可移动平台的返航控制方法、装置及可移动平台，其中，该方法包括：在可移动平台的移动过程中，记录多个航点的航点信息，航点信息包括可移动平台的位置信息以及可移动平台采集的图像信息（S301）；当可移动平台满足返航条件时，根据可移动平台记录的可移动平台的位置信息生成返航轨迹（S302）；在控制可移动平台沿返航轨迹返航的过程中，根据可移动平台采集的图像信息确定可移动平台的返航位置（S303）；根据返航位置调整可移动平台的移动状态，以控制可移动平台按照返航轨迹进行返航（S304）。可控制可移动平台沿飞行过的轨迹原路正确返航，保证返航安全性。
Description
本申请涉及控制技术领域，尤其涉及一种可移动平台的返航控制方法、装置及一种可移动平台。
当可移动平台满足返航条件时，需要控制可移动平台进行返航。现有的返航方案通常利用可移动平台移动过程中定位模块记录的多个航点的位置信息计算返航路径，并控制可移动平台按照该返航路径进行返航。然而，该方案对周围环境的观测准确性并不高，会导致无人机无法正确返航；另外，当定位模块的定位信号较弱时，无人机无法准确定位，会增加无人机发生漂移的几率，从而增加撞击到障碍物的可能性，更有甚者，导致安全事故。
发明内容
本申请实施例公开了一种可移动平台的返航控制方法、装置及一种可移动平台，可控制可移动平台沿飞行过的轨迹原路正确返航，保证返航安全性。
本申请实施例第一方面公开了一种可移动平台的返航控制方法，所述方法包括：
在可移动平台的移动过程中，记录多个航点的航点信息，所述航点信息包括所述可移动平台的位置信息以及所述可移动平台采集的图像信息；
当所述可移动平台满足返航条件时，根据所述可移动平台记录的所述可移动平台的位置信息生成返航轨迹；
在控制所述可移动平台沿所述返航轨迹返航的过程中，根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置；
根据所述返航位置调整所述可移动平台的移动状态，以控制所述可移动平台按照所述返航轨迹进行返航。
本申请实施例第二方面公开了一种可移动平台的返航控制装置，包括：存储器和处理器；
所述存储器，用于存储程序指令；
所述处理器，用于执行所述存储器存储的程序指令，当所述程序指令被执行时，所述处理器用于：
在可移动平台的移动过程中，记录多个航点的航点信息，所述航点信息包括所述可移动平台的位置信息以及所述可移动平台采集的图像信息；
当所述可移动平台满足返航条件时，根据所述可移动平台记录的所述可移动平台的位置信息生成返航轨迹；
在控制所述可移动平台沿所述返航轨迹返航的过程中，根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置；
根据所述返航位置调整所述可移动平台的移动状态，以控制所述可移动平台按照所述返航轨迹进行返航。
本申请实施例第三方面公开了一种可移动平台，包括：
机身；
动力系统，安装在所述机身，用于为所述可移动平台提供动力；
如上述第二方面所述的可移动平台的返航控制装置。
本申请实施例第四方面公开了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，所述计算机程序被处理器执行时实现如上述第一方面所述方法的步骤。
在本申请实施例中，根据记录的可移动平台移动过程中的位置信息生成返航轨迹，并控制可移动平台沿返航轨迹返航，可提高生成返航轨迹的效率；根据可移动平台采集的图像信息确定可移动平台的返航位置，可准确定位可移动平台的位置；另外，根据返航位置调整可移动平台的移动状态，以控制可移动平台按照返航轨迹进行返航，可控制可移动平台沿飞行过的轨迹原路正确返航，降低可移动平台撞击到障碍物的几率，保证可移动平台的返航安全性。
为了更清楚地说明本申请实施例中的技术方案，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性的前提下， 还可以根据这些附图获得其他的附图。
图1是本申请实施例公开的一种移动轨迹的示意图；
图2是对应图1所示移动轨迹的返航轨迹的示意图；
图3是本申请实施例公开的一种可移动平台的返航控制方法的流程示意图；
图4是本申请实施例公开的一种确定返航位置的架构流程示意图；
图5是本申请实施例公开的一种航点之间的位置关系的示意图；
图6是本申请实施例公开的一种障碍物地图以及避障轨迹的示意图；
图7是本申请实施例公开的一种可移动平台的返航控制装置的结构示意图；
图8是本申请实施例公开的一种可移动平台的结构示意图。
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发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，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，都属于本发明保护的范围。
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。
在用户通过控制终端控制可移动平台移动，或者可移动平台按照设定好的移动轨迹自主移动的过程中，若检测到可移动平台满足返航条件，如获取到控制终端发送的返航指令、可移动平台与控制终端断开连接的时间大于时间阈值或者可移动平台的电池的剩余电量与所述可移动平台返航所需电量之差小于或等于预设电量阈值时，则需要控制可移动平台进行返航。
例如，在控制无人机飞行的过程中，如果由于环境、信号干扰等因素导致无人机与控制终端断开了通信连接，控制终端则无法对无人机进行控制，无人机进入失控状态；此时，可控制无人机返航一段距离，以使无人机与控制终端恢复通信连接。
现有的返航方案通常利用可移动平台移动过程中定位模块记录的多个航 点的位置信息计算返航路径，并控制可移动平台按照该返航路径进行返航。然而，该方案对周围环境的观测准确性并不高，会导致无人机无法正确返航；另外，当定位模块的定位信号较弱时，无人机无法准确定位，会增加无人机发生漂移的几率，从而增加撞击到障碍物的可能性，更有甚者，导致安全事故。
基于此，本申请实施例提供一种可移动平台的返航控制方法，根据可移动平台的历史航点的位置信息生成返航轨迹，并根据可移动平台采集的图像信息控制可移动平台沿返航轨迹进行返航，以保证返航的正确性以及安全性。
如图1所示，可移动平台在移动过程中，记录所经过的多个航点的航点信息，例如每经过预设时间记录一个航点的航点信息，或者每运动预设距离记录一个航点的航点信息。该航点信息包括可移动平台的位置信息以及可移动平台采集的图像信息，可选的，该位置信息为可移动平台采集该图像信息时所处的航点的位置信息。可选的，还可以记录可移动平台经过但未在此处采集图像信息的航点的位置信息。
如图2所示，当在移动过程中检测到满足返航条件时，可移动平台从记录的历史航点信息中获取可移动平台之前所经过的多个航点的位置信息，并根据获取到的位置信息生成返航轨迹。控制可移动平台沿该返航轨迹返航，并在返航过程中根据记录的可移动平台之前采集的图像信息确定可移动平台的返航位置，根据确定出的返航位置调整可移动平台的移动状态，以控制可移动平台按照返航轨迹进行返航。
采用上述方式，根据记录的可移动平台移动过程中的位置信息生成返航轨迹，并控制可移动平台沿返航轨迹返航，可提高生成返航轨迹的效率；根据可移动平台采集的图像信息确定可移动平台的返航位置，可准确定位可移动平台的位置；另外，根据返航位置调整可移动平台的移动状态，以控制可移动平台按照返航轨迹进行返航，可控制可移动平台沿飞行过的轨迹原路正确返航，降低可移动平台撞击到障碍物的几率，保证可移动平台的返航安全性。
本申请实施例中，可移动平台可以是无人飞行器、无人车、无人船、移动机器人等可移动设备。
请参阅图3，图3为本申请实施例提供的一种可移动平台的返航控制方法的流程示意图。本申请实施例中所描述的可移动平台的返航控制方法应用于可移 动平台，所述方法包括：
S301、在可移动平台的移动过程中，记录多个航点的航点信息，所述航点信息包括所述可移动平台的位置信息以及所述可移动平台采集的图像信息。
本申请实施例中，可以是用户通过控制终端控制可移动平台移动，也可以是可移动平台根据预设的移动轨迹自主移动。
可移动平台在移动的过程中，通过其配置的拍摄装置在多个航点处采集可移动平台所处周围环境的图像；获取拍摄装置采集到的图像，并对获取到的图像进行特征点提取，得到第一特征点信息；可移动平台将该第一特征点信息作为可移动平台采集的图像信息。在一实施例中，特征点指的是图像灰度值发生剧烈变化的像素点或者在图像边缘上曲率较大的像素点(即两个边缘的交点)，特征点能够标识图像中的拍摄对象，通过特征点的匹配能够完成图像匹配。
其中，可移动平台可以将航点信息中可移动平台的位置信息以及可移动平台采集的图像信息进行关联存储。在一实施例中，可移动平台将在某航点采集的图像信息以及该某航点对应的可移动平台的位置信息保存到同一文件中。
S302、当所述可移动平台满足返航条件时，根据所述可移动平台记录的所述可移动平台的位置信息生成返航轨迹。
本申请实施例中，若出现以下一种或多种情况：可移动平台获取到控制终端发送的返航指令、可移动平台与控制终端断开连接的时间大于时间阈值、可移动平台的电池的剩余电量与可移动平台返航所需电量之差小于或等于预设电量阈值、检测到可移动平台出现故障、可移动平台在预设方向上无法通过，则确定可移动平台满足返航条件。
当可移动平台满足返航条件时，从历史航点信息中获取记录的可移动平台的位置信息，并根据获取到的位置信息确定返航航点，根据该返航航点生成一条平滑的轨迹，将生成的平滑轨迹作为返航轨迹。如图2所示，示出了返航轨迹与返航航点的对应关系。基于记录的可移动平台的历史位置信息生成返航轨迹时，只需简单的计算处理，效率高。
S303、在控制所述可移动平台沿所述返航轨迹返航的过程中，根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置。
本申请实施例中，根据记录的可移动平台的位置信息生成返航轨迹之后， 控制可移动平台沿该返航轨迹返航。在返航过程中，可能由于可移动平台配置的定位装置的定位精准性不高、定位信号较弱等原因，导致定位偏差，使得可移动平台的返航位置(即实际位置)偏离返航轨迹；此时，需要通过其他方式获取可移动平台的准确返航位置。
如图4所示，在控制可移动平台沿该返航轨迹返航的过程中，通过可移动平台配置的拍摄装置采集可移动平台所处周围环境的图像；获取返航过程中拍摄装置采集的图像，并根据获取到的图像，在第一特征点信息中确定目标特征点信息。在一实施方式中，可移动平台对返航过程中获取到的图像进行特征点提取，得到第二特征点信息；从第一特征点信息中确定出与第二特征点信息匹配的目标特征点信息。目标特征点信息可以是第一特征点信息中与第二特征点信息匹配度最高的特征点信息。在一实施方式中，第一特征点信息与第二特征点信息的匹配度可以用第一特征点信息对应的特征点与第二特征点信息对应的特征点中同名点的数量表示，同名点的数量越多表示第一特征点信息与第二特征点信息的匹配度越高，同名点的数量越少表示第一特征点信息与第二特征点信息的匹配度越低。
进一步地，根据目标特征点信息确定可移动平台的视觉估计位置。具体地，根据目标特征点信息对应的可移动平台的位置信息，也即是可移动平台采集该目标特征点信息对应的位置信息，确定可移动平台的视觉估计位置。
如图5所示，可移动平台从航点A经航点C到达航点B，并且在经过各个航点时采集到图5中物体的图像；记录各个航点的位置信息，以及记录可移动平台在各个航点拍摄得到的图像中的特征点的特征点信息。原路返回的返航轨迹为航点B经航点C到航点A，但由于定位偏差，可能导致可移动平台在沿返航轨迹移动的过程中移动到了航点D，航点D偏离了返航轨迹；可移动平台在航点D也采集到图5中物体的图像，并从该图像中提取出了特征点的特征点信息。
根据可移动平台在航点D采集的图像中特征点的特征点信息，可以从记录的历史特征点信息，也即可移动平台从航点A运动至航点B的过程中记录的特征点信息中确定目标特征点信息，示例的，该目标特征点信息可以是可移动平台在航点C采集到的。可移动平台在航点C采集的图像对应的目标特征点信息与可移动平台在航点D采集的图像对应的特征点信息相匹配，也即可移动平台 在航点C采集的图像与可移动平台在航点D采集的图像具有最多的同名点。如此，则可以根据航点C的位置信息确定航点D的视觉估计位置。在一个实施例中，可以将可移动平台在从航点A运动至航点B的过程中记录的航点C的位置信息作为航点D的视觉估计位置，航点C的位置信息是通过可移动平台上的定位装置获取得到的。
进一步地，至少部分地根据视觉估计位置确定可移动平台的返航位置。在一实施例中，获取可移动平台沿返航轨迹返航的过程中采集的图像对应的可移动平台的定位位置，该定位位置是可移动平台配置的定位装置定位得到的；根据可移动平台的视觉估计位置和定位位置，确定可移动平台的返航位置。采用上述方式，以准确定位可移动平台的位置。
在一实施方式中，获取定位位置对应的信号强度，根据该信号强度确定视觉估计位置和定位位置分别对应的融合权重。根据该融合权重对视觉估计位置和定位位置进行加权平均，以确定可移动平台的返航位置。其中，可移动平台可根据预设的信号强度与融合权重的映射关系，确定该信号强度下视觉估计位置和定位位置分别对应的融合权重。当该信号强度较强时，表示定位装置此时的定位精准度较高，此时可以适当提高定位位置对应的融合权重；当该信号强度较弱时，表示定位装置此时的定位精准度较低，此时可以适当减小定位位置的融合权重。可移动平台按照上述融合权重将视觉估计位置与定位位置进行融合，得到可移动平台的返航位置。
在另一实施方式中，获取目标特征点信息与第二特征点信息的匹配度，根据该匹配度确定视觉估计位置和定位位置分别对应的融合权重。根据该融合权重对视觉估计位置和定位位置进行加权平均，以确定可移动平台的返航位置。其中，可移动平台可根据预设的匹配度与融合权重的映射关系，确定该匹配度下视觉估计位置和定位位置分别对应的融合权重。当该匹配度较高时，表示视觉估计位置的准确性较高，此时可以适当增加视觉估计位置对应的融合权重；当该匹配度较低时，表示视觉估计位置的准确性较低，此时可以适当降低视觉估计位置的融合权重。
S304、根据所述返航位置调整所述可移动平台的移动状态，以控制所述可移动平台按照所述返航轨迹进行返航。
本申请实施例中，调整可移动平台的移动状态包括调整可移动平台的移动方向、移动轨迹、移动速度中的一种或多种。
在一实施方式中，可根据返航位置确定目标航点的位置以控制可移动平台返回该返航轨迹，例如根据确定出的返航位置以及该目标航点的位置，生成一移动轨迹，以控制可移动平台沿该移动轨迹移动到目标航点的位置后，继续按照返航轨迹进行返航。
在其他实施例中，可移动平台在沿返航轨迹返航的过程中，实时构建可移动平台所处环境的障碍物地图。在一实施方式中，通过可移动平台上的深度传感器探测得到可移动平台所处周围环境的深度图，获取深度传感器探测该深度图的位置和姿态；根据该深度图以及该深度传感器的位置和姿态，实时构建可移动平台所处周围环境的障碍物地图。具体地，实时构建以可移动平台为中心的预设范围内的三维障碍物地图，该预设范围对应的尺寸可根据视觉传感器的探测距离确定。
在一实施方式中，可移动平台上安装有多个深度传感器，通过各深度传感器可以实时生成深度图像，在获得各深度传感器的位置和姿态以后，可以进一步得到各深度传感器之间的相对位置关系，进而能够确定由各深度传感器分别生成的深度图像之间的坐标转换关系。然后根据该坐标转换关系将由各深度传感器所生成的深度图像进行图像拼接，得到可移动平台所处周围环境的三维地图。进而根据该三维地图可得到可移动平台所处周围环境的障碍物地图。
在一实施方式中，可移动平台上安装有单个深度传感器，该深度传感器在可移动平台运动的过程中可以实时生成多个深度图像，在获得多个深度图像对应的深度传感器的位置和姿态后，能够确定由该深度传感器生成的多个深度图像之间的坐标转换关系。然后根据该坐标转换关系将由深度传感器所生成的多个深度图像进行图像拼接，得到可移动平台所处周围环境的三维地图。进而根据该三维地图可得到可移动平台所处周围环境的障碍物地图。
在一实施方式中，深度传感器可以是双目视觉传感器、超声波传感器、毫米波雷达传感器、激光雷达传感器中的一种或多种。当深度传感器为双目视觉传感器(包括第一摄像头和第二摄像头)时，该双目视觉传感器与前文所述的可移动平台配置的用于采集图像的拍摄装置可以相同，也可以不同。双目视觉 传感器可以获取可移动平台所处周围环境的深度图，可移动平台的定位装置和姿态传感器可以获取该双目视觉传感器的位置信息和姿态信息，由此可以根据该深度图以及该双目视觉传感器的位置信息和姿态信息获取可移动平台所处周围环境的三维地图，进而根据该三维地图可得到可移动平台所处周围环境的障碍物地图。其中，双目视觉传感器的数量为一个或多个。当双目视觉传感器的数量为多个时，多个双目视觉传感器可以分别安装在可移动平台的前侧，后侧，左侧，右侧等方位。
进一步地，当根据实时构建的障碍物地图检测到返航轨迹周围出现障碍物时，控制可移动平台避开该障碍物。在一实施方式中，根据构建的深度图获取该障碍物的位置，根据障碍物的位置以及返航轨迹确定可移动平台撞击到该障碍物的概率；当该概率大于预设数值时，根据障碍物的位置、可移动平台当前的位置、以及返航轨迹确定避障轨迹；控制可移动平台沿避障轨迹移动，以避开该障碍物，并在沿避障轨迹移动完成后，继续沿返航轨迹移动。请一并参阅图6，示出了障碍物、返航轨迹和避障轨迹三者之间的对应关系。
在本申请实施例中，根据记录的可移动平台移动过程中的位置信息生成返航轨迹，并控制可移动平台沿返航轨迹返航，不仅可提高生成返航轨迹的效率，还可控制可移动平台沿飞行过的轨迹原路正确返航；根据可移动平台采集的图像信息确定可移动平台的返航位置，可准确定位可移动平台的位置；另外，根据返航位置调整可移动平台的移动状态，以控制可移动平台按照返航轨迹进行返航，可降低可移动平台撞击到障碍物的几率，保证可移动平台的返航安全性。
请参阅图7，图7为本申请实施例提供的一种可移动平台的返航控制装置的结构示意图。本申请实施例中所描述的可移动平台的返航控制装置包括：处理器701、通信接口702、存储器703。其中，处理器701、通信接口702、存储器703可通过总线或其他方式连接，本申请实施例以通过总线连接为例。
处理器701可以是中央处理器(central processing unit，CPU)，网络处理器(network processor，NP)，或者CPU和NP的组合。处理器701也可以是多核CPU、或多核NP中用于实现通信标识绑定的核。
所述处理器701可以是硬件芯片。所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)或其组合。所述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，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)或其任意组合。
所述通信接口702可用于收发信息或信令的交互，以及信号的接收和传递。所述存储器703可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的存储程序(比如文字存储功能、位置存储功能等)；存储数据区可存储根据装置的使用所创建的数据(比如图像数据、文字数据)等，并可以包括应用存储程序等。此外，存储器703可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
所述存储器703还用于存储程序指令。所述处理器701，用于执行所述存储器703存储的程序指令，当所述程序指令被执行时，所述处理器701用于：
在可移动平台的移动过程中，记录多个航点的航点信息，所述航点信息包括所述可移动平台的位置信息以及所述可移动平台采集的图像信息；当所述可移动平台满足返航条件时，根据所述可移动平台记录的所述可移动平台的位置信息生成返航轨迹；在控制所述可移动平台沿所述返航轨迹返航的过程中，根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置；根据所述返航位置调整所述可移动平台的移动状态，以控制所述可移动平台按照所述返航轨迹进行返航。
本申请实施例中处理器执行的方法均从处理器的角度来描述，可以理解的是，本申请实施例中处理器要执行上述方法需要其他硬件结构的配合。本申请实施例对具体的实现过程不作详细描述和限制。
在一实施方式中，所述处理器701记录多个航点的航点信息之前，所述处理器701还用于：获取所述可移动平台在所述多个航点采集的图像；对所述可移动平台在所述多个航点采集的图像进行特征点提取，以获得第一特征点信息；将第一特征点信息作为所述可移动平台采集的图像信息。
在一实施方式中，所述处理器701根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置时，具体用于：获取所述可移动平台沿所述返航轨迹返航的过程中采集的图像；根据所述可移动平台沿所述返航轨迹返航的过 程中采集的图像，在所述第一特征点信息中确定目标特征点信息；根据所述目标特征点信息确定所述可移动平台的视觉估计位置；至少部分地根据所述视觉估计位置确定所述可移动平台的返航位置。
在一实施方式中，所述处理器701根据所述可移动平台沿所述返航轨迹返航的过程中采集的图像，在所述第一特征点信息中确定目标特征点信息时，具体用于：对所述可移动平台沿所述返航轨迹返航的过程中采集的图像进行特征点提取，以获得第二特征点信息；根据所述第二特征点信息，在所述第一特征点信息中确定目标特征点信息，所述目标特征点信息与所述第二特征点信息相匹配。
在一实施方式中，所述处理器701还用于：将所述航点信息中所述可移动平台的位置信息以及所述可移动平台采集的图像信息进行关联存储；所述处理器701根据所述目标特征点信息确定所述可移动平台的视觉估计位置时，具体用于：根据所述目标特征点信息对应的所述可移动平台的位置信息，确定所述可移动平台的视觉估计位置。
在一实施方式中，所述处理器701至少部分地根据所述视觉估计位置确定所述可移动平台的返航位置时，具体用于：获取所述可移动平台沿所述返航轨迹返航的过程中采集的图像对应的所述可移动平台的定位位置；根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置。
在一实施方式中，所述处理器701根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置时，具体用于：获取所述定位位置对应的信号强度，根据所述信号强度确定所述视觉估计位置和所述定位位置分别对应的融合权重；按照所述融合权重将所述视觉估计位置与所述定位位置进行融合，得到所述可移动平台的返航位置。
在一实施方式中，所述处理器701根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置时，具体用于：获取所述目标特征点信息与所述第二特征点信息的匹配度，根据所述匹配度确定所述视觉估计位置和所述定位位置分别对应的融合权重；按照所述融合权重将所述视觉估计位置与所述定位位置进行融合，得到所述可移动平台的返航位置。
在一实施方式中，所述可移动平台满足返航条件，包括以下一种或多种： 获取到控制终端发送的返航指令；所述可移动平台与控制终端断开连接的时间大于时间阈值；所述可移动平台的电池的剩余电量与所述可移动平台返航所需电量之差小于或等于预设电量阈值。
在一实施方式中，所述处理器701还用于：在控制所述可移动平台沿所述返航轨迹返航的过程中，实时构建所述可移动平台所处环境的障碍物地图；当根据所述障碍物地图检测到返航轨迹周围出现障碍物时，控制所述可移动平台避开所述障碍物。
在一实施方式中，所述处理器701实时构建所述可移动平台所处环境的障碍物地图时，具体用于：实时构建以所述可移动平台为中心的预设范围内的障碍物地图。
在一实施方式中，所述处理器701实时构建所述可移动平台所处环境的障碍物地图时，具体用于：获取所述可移动平台所处环境的深度图，所述深度图由所述可移动平台上的深度传感器探测得到；获取所述深度传感器的位置和姿态；根据所述深度图以及所述深度传感器的位置和姿态，实时构建所述可移动平台所处环境的障碍物地图。
在一实施方式中，所述处理器701调整所述可移动平台的移动状态时，具体用于：调整所述可移动平台的移动方向、移动轨迹、移动速度中的一种或多种。
具体实现中，本申请实施例中所描述的处理器701、通信接口702、存储器703可执行本申请实施例提供的一种可移动平台的返航控制方法中所描述的实现方式，在此不再赘述。
在本申请实施例中，根据记录的可移动平台移动过程中的位置信息生成返航轨迹，并控制可移动平台沿返航轨迹返航，不仅可提高生成返航轨迹的效率，还可控制可移动平台沿飞行过的轨迹原路正确返航；根据可移动平台采集的图像信息确定可移动平台的返航位置，可准确定位可移动平台的位置；另外，根据返航位置调整可移动平台的移动状态，以控制可移动平台按照返航轨迹进行返航，可降低可移动平台撞击到障碍物的几率，保证可移动平台的返航安全性。
基于上述可移动平台的返航控制方法及装置的描述，本发明实施例提供一种可移动平台。如图8所示，可移动平台包括机身801、动力系统802、上述 可移动平台的返航控制装置803、拍摄装置804和深度传感器805。
其中，动力系统802，安装在可移动平台的机身801上，用于为可移动平台提供动力；具体地，动力系统801可以包括螺旋桨、电机、电调中的一种或多种。拍摄装置804可以是可见光相机、红外相机、热成像相机、深度相机等。深度传感器805可以是双目视觉传感器、超声波传感器、毫米波雷达传感器、激光雷达传感器中的一种或多种。拍摄装置804可以通过增稳云台承载在可移动平台的机身801上，具体地，增稳云台安装于可移动平台的机身801上，而拍摄装置804固定在增稳云台上；增稳云台可以带动拍摄装置804绕偏航轴、横滚轴和俯仰轴中的一个或者多个轴线进行旋转，从而调整拍摄装置804拍摄图像时的姿态。另外，在某些实施例中，拍摄装置804也可以直接承载在可移动平台的机身801上，可移动平台可以通过控制自身姿态来调整拍摄装置804拍摄图像时的姿态。
可移动平台的返航控制装置803安装在可移动平台的机身801上，包括处理器和存储器。存储器用于存储程序指令，处理器用于执行存储器存储的程序指令，当程序指令被执行时，处理器用于：在可移动平台的移动过程中，记录多个航点的航点信息，所述航点信息包括所述可移动平台的位置信息以及所述可移动平台采集的图像信息；当所述可移动平台满足返航条件时，根据所述可移动平台记录的所述可移动平台的位置信息生成返航轨迹；在控制所述可移动平台沿所述返航轨迹返航的过程中，根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置；根据所述返航位置调整所述可移动平台的移动状态，以控制所述可移动平台按照所述返航轨迹进行返航。上述步骤的具体实现方式可参考前文描述，此处不再赘述。
本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，所述计算机程序被处理器执行时实现上述方法实施例所述的可移动平台的返航控制方法。
本申请实施例还提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述方法实施例所述的可移动平台的返航控制方法。
需要说明的是，对于前述的各个方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述 的动作顺序的限制，因为依据本申请，某一些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
以上对本申请实施例所提供的一种可移动平台的返航控制方法、装置及可移动平台进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。
Claims (28)
- 一种可移动平台的返航控制方法，其特征在于，所述方法包括：在可移动平台的移动过程中，记录多个航点的航点信息，所述航点信息包括所述可移动平台的位置信息以及所述可移动平台采集的图像信息；当所述可移动平台满足返航条件时，根据所述可移动平台记录的所述可移动平台的位置信息生成返航轨迹；在控制所述可移动平台沿所述返航轨迹返航的过程中，根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置；根据所述返航位置调整所述可移动平台的移动状态，以控制所述可移动平台按照所述返航轨迹进行返航。
- 根据权利要求1所述的方法，其特征在于，所述记录多个航点的航点信息之前，所述方法还包括：获取所述可移动平台在所述多个航点采集的图像；对所述可移动平台在所述多个航点采集的图像进行特征点提取，以获得第一特征点信息；将第一特征点信息作为所述可移动平台采集的图像信息。
- 根据权利要求2所述的方法，其特征在于，所述根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置，包括：获取所述可移动平台沿所述返航轨迹返航的过程中采集的图像；根据所述可移动平台沿所述返航轨迹返航的过程中采集的图像，在所述第一特征点信息中确定目标特征点信息；根据所述目标特征点信息确定所述可移动平台的视觉估计位置；至少部分地根据所述视觉估计位置确定所述可移动平台的返航位置。
- 根据权利要求3所述的方法，其特征在于，所述根据所述可移动平台沿所述返航轨迹返航的过程中采集的图像，在所述第一特征点信息中确定目标特征点信息，包括：对所述可移动平台沿所述返航轨迹返航的过程中采集的图像进行特征点提取，以获得第二特征点信息；根据所述第二特征点信息，在所述第一特征点信息中确定目标特征点信息，所述目标特征点信息与所述第二特征点信息相匹配。
- 根据权利要求3所述的方法，其特征在于，所述方法还包括：将所述航点信息中所述可移动平台的位置信息以及所述可移动平台采集的图像信息进行关联存储；所述根据所述目标特征点信息确定所述可移动平台的视觉估计位置，包括：根据所述目标特征点信息对应的所述可移动平台的位置信息，确定所述可移动平台的视觉估计位置。
- 根据权利要求4所述的方法，其特征在于，所述至少部分地根据所述视觉估计位置确定所述可移动平台的返航位置，包括：获取所述可移动平台沿所述返航轨迹返航的过程中采集的图像对应的所述可移动平台的定位位置；根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置。
- 根据权利要求6所述的方法，其特征在于，所述根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置，包括：获取所述定位位置对应的信号强度，根据所述信号强度确定所述视觉估计位置和所述定位位置分别对应的融合权重；按照所述融合权重将所述视觉估计位置与所述定位位置进行融合，得到所述可移动平台的返航位置。
- 根据权利要求6所述的方法，其特征在于，所述根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置，包括：获取所述目标特征点信息与所述第二特征点信息的匹配度，根据所述匹配度确定所述视觉估计位置和所述定位位置分别对应的融合权重；按照所述融合权重将所述视觉估计位置与所述定位位置进行融合，得到所述可移动平台的返航位置。
- 根据权利要求1所述的方法，其特征在于，所述可移动平台满足返航条件，包括以下一种或多种：获取到控制终端发送的返航指令；所述可移动平台与控制终端断开连接的时间大于时间阈值；所述可移动平台的电池的剩余电量与所述可移动平台返航所需电量之差小于或等于预设电量阈值。
- 根据权利要求1所述的方法，其特征在于，所述方法还包括：在控制所述可移动平台沿所述返航轨迹返航的过程中，实时构建所述可移动平台所处环境的障碍物地图；当根据所述障碍物地图检测到返航轨迹周围出现障碍物时，控制所述可移动平台避开所述障碍物。
- 根据权利要求10所述的方法，其特征在于，所述实时构建所述可移动平台所处环境的障碍物地图，包括：实时构建以所述可移动平台为中心的预设范围内的障碍物地图。
- 根据权利要求10所述的方法，其特征在于，所述实时构建所述可移动平台所处环境的障碍物地图，包括：获取所述可移动平台所处环境的深度图，所述深度图由所述可移动平台上的深度传感器探测得到；获取所述深度传感器的位置和姿态；根据所述深度图以及所述深度传感器的位置和姿态，实时构建所述可移动平台所处环境的障碍物地图。
- 根据权利要求1所述的方法，其特征在于，所述调整所述可移动平台的移动状态，包括：调整所述可移动平台的移动方向、移动轨迹、移动速度中的一种或多种。
- 一种可移动平台的返航控制装置，其特征在于，包括：存储器和处理器；所述存储器，用于存储程序指令；所述处理器，用于执行所述存储器存储的程序指令，当所述程序指令被执行时，所述处理器用于：在可移动平台的移动过程中，记录多个航点的航点信息，所述航点信息包括所述可移动平台的位置信息以及所述可移动平台采集的图像信息；当所述可移动平台满足返航条件时，根据所述可移动平台记录的所述可移动平台的位置信息生成返航轨迹；在控制所述可移动平台沿所述返航轨迹返航的过程中，根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置；根据所述返航位置调整所述可移动平台的移动状态，以控制所述可移动平台按照所述返航轨迹进行返航。
- 根据权利要求14所述的装置，其特征在于，所述处理器记录多个航点的航点信息之前，所述处理器还用于：获取所述可移动平台在所述多个航点采集的图像；对所述可移动平台在所述多个航点采集的图像进行特征点提取，以获得第一特征点信息；将第一特征点信息作为所述可移动平台采集的图像信息。
- 根据权利要求15所述的装置，其特征在于，所述处理器根据所述可移动平台采集的图像信息确定所述可移动平台的返航位置时，具体用于：获取所述可移动平台沿所述返航轨迹返航的过程中采集的图像；根据所述可移动平台沿所述返航轨迹返航的过程中采集的图像，在所述第 一特征点信息中确定目标特征点信息；根据所述目标特征点信息确定所述可移动平台的视觉估计位置；至少部分地根据所述视觉估计位置确定所述可移动平台的返航位置。
- 根据权利要求16所述的装置，其特征在于，所述处理器根据所述可移动平台沿所述返航轨迹返航的过程中采集的图像，在所述第一特征点信息中确定目标特征点信息时，具体用于：对所述可移动平台沿所述返航轨迹返航的过程中采集的图像进行特征点提取，以获得第二特征点信息；根据所述第二特征点信息，在所述第一特征点信息中确定目标特征点信息，所述目标特征点信息与所述第二特征点信息相匹配。
- 根据权利要求16所述的装置，其特征在于，所述处理器还用于：将所述航点信息中所述可移动平台的位置信息以及所述可移动平台采集的图像信息进行关联存储；所述处理器根据所述目标特征点信息确定所述可移动平台的视觉估计位置时，具体用于：根据所述目标特征点信息对应的所述可移动平台的位置信息，确定所述可移动平台的视觉估计位置。
- 根据权利要求17所述的装置，其特征在于，所述处理器至少部分地根据所述视觉估计位置确定所述可移动平台的返航位置时，具体用于：获取所述可移动平台沿所述返航轨迹返航的过程中采集的图像对应的所述可移动平台的定位位置；根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置。
- 根据权利要求19所述的装置，其特征在于，所述处理器根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置时，具体用于：获取所述定位位置对应的信号强度，根据所述信号强度确定所述视觉估计位置和所述定位位置分别对应的融合权重；按照所述融合权重将所述视觉估计位置与所述定位位置进行融合，得到所述可移动平台的返航位置。
- 根据权利要求19所述的装置，其特征在于，所述处理器根据所述视觉估计位置与所述定位位置，确定所述可移动平台的返航位置时，具体用于：获取所述目标特征点信息与所述第二特征点信息的匹配度，根据所述匹配度确定所述视觉估计位置和所述定位位置分别对应的融合权重；按照所述融合权重将所述视觉估计位置与所述定位位置进行融合，得到所述可移动平台的返航位置。
- 根据权利要求14所述的装置，其特征在于，所述可移动平台满足返航条件，包括以下一种或多种：获取到控制终端发送的返航指令；所述可移动平台与控制终端断开连接的时间大于时间阈值；所述可移动平台的电池的剩余电量与所述可移动平台返航所需电量之差小于或等于预设电量阈值。
- 根据权利要求14所述的装置，其特征在于，所述处理器还用于：在控制所述可移动平台沿所述返航轨迹返航的过程中，实时构建所述可移动平台所处环境的障碍物地图；当根据所述障碍物地图检测到返航轨迹周围出现障碍物时，控制所述可移动平台避开所述障碍物。
- 根据权利要求23所述的装置，其特征在于，所述处理器实时构建所述可移动平台所处环境的障碍物地图时，具体用于：实时构建以所述可移动平台为中心的预设范围内的障碍物地图。
- 根据权利要求23所述的装置，其特征在于，所述处理器实时构建所述可移动平台所处环境的障碍物地图时，具体用于：获取所述可移动平台所处环境的深度图，所述深度图由所述可移动平台上的深度传感器探测得到；获取所述深度传感器的位置和姿态；根据所述深度图以及所述深度传感器的位置和姿态，实时构建所述可移动平台所处环境的障碍物地图。
- 根据权利要求14所述的装置，其特征在于，所述处理器调整所述可移动平台的移动状态时，具体用于：调整所述可移动平台的移动方向、移动轨迹、移动速度中的一种或多种。
- 一种可移动平台，其特征在于，包括：机身；动力系统，安装在所述机身，用于为所述可移动平台提供动力；如权利要求14至26中任一项所述的可移动平台的返航控制装置。
- 一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，其特征在于：所述计算机程序被处理器执行时实现如权利要求1至13中任一项所述方法的步骤。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2019/107300 WO2021056144A1 (zh) | 2019-09-23 | 2019-09-23 | 可移动平台的返航控制方法、装置及可移动平台 |
| CN201980030309.6A CN112119361A (zh) | 2019-09-23 | 2019-09-23 | 可移动平台的返航控制方法、装置及可移动平台 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2019/107300 WO2021056144A1 (zh) | 2019-09-23 | 2019-09-23 | 可移动平台的返航控制方法、装置及可移动平台 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021056144A1 true WO2021056144A1 (zh) | 2021-04-01 |
Family
ID=73799731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/107300 WO2021056144A1 (zh) | 2019-09-23 | 2019-09-23 | 可移动平台的返航控制方法、装置及可移动平台 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112119361A (zh) |
| WO (1) | WO2021056144A1 (zh) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113050647A (zh) * | 2021-03-22 | 2021-06-29 | 苏州大学 | 自移动设备的运行控制方法及装置 |
| CN113257045A (zh) * | 2021-07-14 | 2021-08-13 | 四川腾盾科技有限公司 | 一种基于大型固定翼无人机电子围栏的无人机控制方法 |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090125223A1 (en) * | 2006-03-31 | 2009-05-14 | Higgins Robert P | Video navigation |
| CN104807456A (zh) * | 2015-04-29 | 2015-07-29 | 深圳市保千里电子有限公司 | 一种gps无信号时自动返航的方法 |
| CN106325299A (zh) * | 2016-09-13 | 2017-01-11 | 上海顺砾智能科技有限公司 | 基于视觉的无人机返航着陆方法 |
| CN106774402A (zh) * | 2016-12-28 | 2017-05-31 | 湖南省道通科技有限公司 | 对无人机进行定位的方法及装置 |
| CN106896391A (zh) * | 2017-03-14 | 2017-06-27 | 北京京东尚科信息技术有限公司 | 无人机的定位方法及装置 |
| CN107065925A (zh) * | 2017-04-01 | 2017-08-18 | 成都通甲优博科技有限责任公司 | 一种无人机返航方法及装置 |
| CN108292140A (zh) * | 2015-12-09 | 2018-07-17 | 深圳市大疆创新科技有限公司 | 用于自动返航的系统和方法 |
| CN108496129A (zh) * | 2017-04-28 | 2018-09-04 | 深圳市大疆创新科技有限公司 | 一种基于飞行器的设施检测方法及控制设备 |
| CN109388150A (zh) * | 2014-09-05 | 2019-02-26 | 深圳市大疆创新科技有限公司 | 多传感器环境地图构建 |
| CN109709973A (zh) * | 2019-01-02 | 2019-05-03 | 中国人民解放军国防科技大学 | 一种微阵列式光罗盘辅助的无人机自主返航方法 |
| CN109791414A (zh) * | 2016-09-26 | 2019-05-21 | 深圳市大疆创新科技有限公司 | 基于视觉着陆的方法和系统 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109634295B (zh) * | 2018-12-17 | 2020-12-18 | 深圳市道通智能航空技术有限公司 | 一种自动返航方法、装置和无人机 |
-
2019
- 2019-09-23 CN CN201980030309.6A patent/CN112119361A/zh active Pending
- 2019-09-23 WO PCT/CN2019/107300 patent/WO2021056144A1/zh active Application Filing
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090125223A1 (en) * | 2006-03-31 | 2009-05-14 | Higgins Robert P | Video navigation |
| CN109388150A (zh) * | 2014-09-05 | 2019-02-26 | 深圳市大疆创新科技有限公司 | 多传感器环境地图构建 |
| CN104807456A (zh) * | 2015-04-29 | 2015-07-29 | 深圳市保千里电子有限公司 | 一种gps无信号时自动返航的方法 |
| CN108292140A (zh) * | 2015-12-09 | 2018-07-17 | 深圳市大疆创新科技有限公司 | 用于自动返航的系统和方法 |
| CN106325299A (zh) * | 2016-09-13 | 2017-01-11 | 上海顺砾智能科技有限公司 | 基于视觉的无人机返航着陆方法 |
| CN109791414A (zh) * | 2016-09-26 | 2019-05-21 | 深圳市大疆创新科技有限公司 | 基于视觉着陆的方法和系统 |
| CN106774402A (zh) * | 2016-12-28 | 2017-05-31 | 湖南省道通科技有限公司 | 对无人机进行定位的方法及装置 |
| CN106896391A (zh) * | 2017-03-14 | 2017-06-27 | 北京京东尚科信息技术有限公司 | 无人机的定位方法及装置 |
| CN107065925A (zh) * | 2017-04-01 | 2017-08-18 | 成都通甲优博科技有限责任公司 | 一种无人机返航方法及装置 |
| CN108496129A (zh) * | 2017-04-28 | 2018-09-04 | 深圳市大疆创新科技有限公司 | 一种基于飞行器的设施检测方法及控制设备 |
| CN109709973A (zh) * | 2019-01-02 | 2019-05-03 | 中国人民解放军国防科技大学 | 一种微阵列式光罗盘辅助的无人机自主返航方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112119361A (zh) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11787543B2 (en) | Image space motion planning of an autonomous vehicle | |
| Barry et al. | High‐speed autonomous obstacle avoidance with pushbroom stereo | |
| US11242144B2 (en) | Aerial vehicle smart landing | |
| CN111448476B (zh) | 在无人飞行器与地面载具之间共享绘图数据的技术 | |
| CN107329490B (zh) | 无人机避障方法及无人机 | |
| CN108323190B (zh) | 一种避障方法、装置和无人机 | |
| US20190265735A1 (en) | Flight control device, unmanned aerial vehicle, flight control method, and computer-readable recording medium | |
| US20200191556A1 (en) | Distance mesurement method by an unmanned aerial vehicle (uav) and uav | |
| WO2024114209A1 (zh) | 一种无rtk信号场景下全自动无人机巡检智能路径规划方法 | |
| CN113467500B (zh) | 一种基于双目视觉的无人机非合作目标追踪系统 | |
| US9812020B2 (en) | Electronic device and unmanned aerial vehicle control method | |
| WO2021056144A1 (zh) | 可移动平台的返航控制方法、装置及可移动平台 | |
| CN112783203B (zh) | 一种基于多传感器的无人机编队保持的控制系统及方法 | |
| Springer et al. | Autonomous drone landing with fiducial markers and a gimbal-mounted camera for active tracking | |
| CN109885091B (zh) | 一种无人机自主飞行控制方法及系统 | |
| CN111247792B (zh) | 一种无人机的控制方法、无人机及计算机可读存储介质 | |
| Denuelle et al. | A sparse snapshot-based navigation strategy for UAS guidance in natural environments | |
| WO2021238743A1 (zh) | 一种无人机飞行控制方法、装置及无人机 | |
| WO2021217352A1 (zh) | 一种可移动平台的控制方法、装置及可移动平台 | |
| CN117647999A (zh) | 一种无人机控制方法、无人机及可读介质 | |
| KR101876829B1 (ko) | 소형 드론의 실내 비행제어를 위한 유도 제어 시스템 | |
| Dubey et al. | Droan-disparity-space representation for obstacle avoidance: Enabling wire mapping & avoidance | |
| US12147245B2 (en) | Method for controlling an unmanned aerial vehicle for an inspection flight to inspect an object and inspection unmanned aerial vehicle | |
| US20230073120A1 (en) | Method for Controlling an Unmanned Aerial Vehicle for an Inspection Flight to Inspect an Object and Inspection Unmanned Aerial Vehicle | |
| WO2022160101A1 (zh) | 朝向估计方法、装置、可移动平台及可读存储介质 |
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: 19947062 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: 19947062 Country of ref document: EP Kind code of ref document: A1 |