Unmanned aerial vehicle dynamic platform landing guiding method and system based on GNSS and visual identification

Abstract

The invention discloses an unmanned aerial vehicle dynamic platform landing guidance method and system based on GNSS and visual identification, and relates to unmanned aerial vehicle landing guidance, and the method comprises the steps: obtaining GNSS information of an unmanned aerial vehicle and a dynamic platform, setting a navigation positioning error evaluation model, and calculating a first relative position error between the GNSS-based unmanned aerial vehicle and the dynamic platform; visual information of the AprilTag on the dynamic platform is obtained, a visual positioning error evaluation model is set, and a second relative position error between the AprilTag-based unmanned aerial vehicle and the dynamic platform is calculated; infrared information of infrared equipment on the unmanned aerial vehicle is obtained, an infrared positioning error evaluation model is set, a third relative position error between the unmanned aerial vehicle based on the infrared equipment and the dynamic platform is calculated, and the infrared information comprises the temperature, the environment temperature, the environment humidity and the airflow speed of the dynamic platform; adjusting the unmanned aerial vehicle according to the first relative position error, the second relative position error and the third relative position error so as to complete landing guidance.

Description

Technical Field

[0001] The present invention belongs to the technical field of UAV landing guidance, and more specifically, relates to a method and system for guiding the landing of a UAV on a dynamic platform based on GNSS and visual recognition. Background Art

[0002] With the wide application of UAV technology, how to ensure the safe landing of UAVs in complex environments has become an important research topic. Traditional UAV landing guidance methods mostly rely on static platforms or single sensors, such as GNSS or visual recognition technology. However, these methods often face problems such as insufficient positioning accuracy and difficulty in recognition in dynamic platforms, bad weather, or complex environments. Therefore, there is an urgent need for a new landing guidance method that combines multiple technologies to ensure the safe landing of UAVs under different conditions. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes a method for guiding the landing of a UAV on a dynamic platform based on GNSS and visual recognition, including:

[0004] Obtain the GNSS information of the UAV and the dynamic platform, and set up a navigation positioning error evaluation model to calculate the first relative position error between the UAV and the dynamic platform based on GNSS, where the GNSS information includes: the position of the UAV, the position of the dynamic platform, the speed of the UAV, and the acceleration of the UAV;

[0005] Obtain the visual information of the AprilTag on the dynamic platform, and set up a visual positioning error evaluation model to calculate the second relative position error between the UAV and the dynamic platform based on the AprilTag, where the visual information includes: the position of the AprilTag, the tilt angle of the dynamic platform, and the rotational angular velocity of the dynamic platform;

[0006] Obtain the infrared information of the infrared device on the UAV, and set up an infrared positioning error evaluation model to calculate the third relative position error between the UAV and the dynamic platform based on the infrared device, where the infrared information includes: the temperature of the dynamic platform, the ambient temperature, the ambient humidity, and the air flow velocity;

[0007] Adjust the UAV according to the first relative position error, the second relative position error, and the third relative position error, so as to complete the landing guidance.

[0008] Further, the navigation positioning error evaluation model includes:

[0009]

[0010] where, ∈ platform$(t)$ is the first relative position error between the GNSS-based drone and the dynamic platform at time $t$, $P$ u $(t)$ is the position of the drone at time $t$, $P$ p $(t)$ is the position of the dynamic platform at time $t$, $\alpha$ is the first adjustment factor of the relative position error evaluation model, $\beta$ is the second adjustment factor of the relative position error evaluation model, $t$ 0 is the starting time, $\gamma$ is the third adjustment factor of the relative position error evaluation model, $\eta$ is the fourth adjustment factor of the relative position error evaluation model, $V$ u $(t)$ is the velocity of the drone at time $t$, $K$ is the fifth adjustment factor of the relative position error evaluation model, $a$ u $(t)$ is the acceleration of the drone at time $t$.

[0011] Furthermore, the visual positioning error evaluation model includes:

[0012]

[0013] where $\delta$ vis $(t)$ is the second relative position error between the AprilTag-based drone and the dynamic platform at time $t$, $\varphi$ is the first adjustment factor of the visual recognition error evaluation model, $P$ tag $(t)$ is the position of the AprilTag at time $t$, $\delta''$ is the second adjustment factor of the visual recognition error evaluation model, $\theta$ is the third adjustment factor of the visual recognition error evaluation model, $\gamma''$ is the fourth adjustment factor of the visual recognition error evaluation model, $\lambda$ 1 is the fifth adjustment factor of the visual recognition error evaluation model, $\theta$ p $(t)$ is the tilt angle of the dynamic platform at time $t$, $\alpha'$ is the sixth adjustment factor of the visual recognition error evaluation model, $\lambda$ 2 is the seventh adjustment factor of the visual recognition error evaluation model, $\omega$ p $(t)$ is the rotational angular velocity of the dynamic platform at time $t$, $\beta'$ is the eighth adjustment factor of the visual recognition error evaluation model.

[0014] Furthermore, the infrared positioning error evaluation model includes:

[0015] $Q$ IR $(t)=\alpha''\cdot|T$ tag $(t)-T$ env $(t)|$ δ′ $\cdot\exp(-\gamma'\cdot||P$ u $(t)-P$ p $(t)||)\cdot(1+\lambda$ 3 $\cdot H$ env $(t)+\lambda$ 4 $\cdot||V$ air $(t)||)$

[0016] Among them, Q IR (t) is the third relative position error between the drone based on the infrared device and the dynamic platform at time t, α″ is the first adjustment factor of the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor of the infrared positioning error evaluation model, γ′ is the third adjustment factor of the infrared positioning error evaluation model, λ 3 is the fourth adjustment factor of the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ 4 is the fifth adjustment factor of the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

[0017] Furthermore, it also includes setting a target optimization function L for the relative error, and by adjusting the GNSS, AprilTag, and infrared device, making the value of the target optimization function L of the relative error the smallest to achieve the purpose of minimizing the error.

[0018] Furthermore, the target optimization function L of the relative error includes:

[0019]

[0020] Among them, λ 5 is the first adjustment factor of the target optimization function L of the relative error, γ″′ is the second adjustment factor of the target optimization function L of the relative error, λ 6 is the third adjustment factor of the target optimization function L of the relative error, β″′ is the fourth adjustment factor of the target optimization function L of the relative error.

[0021] The present invention also proposes a drone dynamic platform landing guidance system based on GNSS and visual recognition, including:

[0022] A navigation error calculation module, configured to obtain the GNSS information of the drone and the dynamic platform, and set a navigation positioning error evaluation model to calculate the first relative position error between the drone based on GNSS and the dynamic platform. Among them, the GNSS information includes: the position of the drone, the position of the dynamic platform, the speed of the drone, and the acceleration of the drone;

[0023] A visual error calculation module, which is used to obtain the visual information of the AprilTag on the dynamic platform, set up a visual positioning error evaluation model, and calculate the second relative position error between the drone and the dynamic platform based on the AprilTag. Wherein, the visual information includes: the position of the AprilTag, the tilt angle of the dynamic platform, and the rotational angular velocity of the dynamic platform;

[0024] An infrared error calculation module, which is used to obtain the infrared information of the infrared device on the drone, set up an infrared positioning error evaluation model, and calculate the third relative position error between the drone and the dynamic platform based on the infrared device. Wherein, the infrared information includes: the temperature of the dynamic platform, the ambient temperature, the ambient humidity, and the air flow velocity;

[0025] A guidance module, which is used to adjust the drone according to the first relative position error, the second relative position error, and the third relative position error, so as to complete the landing guidance.

[0026] Furthermore, the navigation positioning error evaluation model includes:

[0027]

[0028] Wherein, ∈ platform (t) is the first relative position error between the drone and the dynamic platform based on GNSS at time t, P u (t) is the position of the drone at time t, P p (t) is the position of the dynamic platform at time t, α is the first adjustment factor of the relative position error evaluation model, β is the second adjustment factor of the relative position error evaluation model, t 0 is the starting time, γ is the third adjustment factor of the relative position error evaluation model, η is the fourth adjustment factor of the relative position error evaluation model, V u (t) is the speed of the drone at time t, κ is the fifth adjustment factor of the relative position error evaluation model, a u (t) is the acceleration of the drone at time t.

[0029] Furthermore, the visual positioning error evaluation model includes:

[0030]

[0031] Wherein, δ vis (t) is the second relative position error between the drone and the dynamic platform based on the AprilTag at time t, φ is the first adjustment factor of the visual recognition error evaluation model, P tag(t) is the position of the AprilTag at time t, δ″ is the second adjustment factor of the visual recognition error evaluation model, θ is the third adjustment factor of the visual recognition error evaluation model, γ″ is the fourth adjustment factor of the visual recognition error evaluation model, λ 1 is the fifth adjustment factor of the visual recognition error evaluation model, θ p (t) is the tilt angle of the dynamic platform at time t, α′ is the sixth adjustment factor of the visual recognition error evaluation model, λ 2 is the seventh adjustment factor of the visual recognition error evaluation model, ω p (t) is the rotational angular velocity of the dynamic platform at time t, β′ is the eighth adjustment factor of the visual recognition error evaluation model.

[0032] Furthermore, the infrared positioning error evaluation model includes:

[0033] Q IR (t) = α″·|T tag (t) - T env (t)| δ′ ·exp(-γ′·||P u (t) - P p (t)||)·(1 + λ 3 ·H env (t) + λ 4 ·||V air (t)||)

[0034] where Q IR (t) is the third relative position error between the drone and the dynamic platform based on the infrared device at time t, α″ is the first adjustment factor of the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor of the infrared positioning error evaluation model, γ′ is the third adjustment factor of the infrared positioning error evaluation model, λ 3 is the fourth adjustment factor of the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ 4 is the fifth adjustment factor of the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

[0035] As Figure 3 and Figure 4 shown, generally speaking, compared with the prior art by the above technical solutions conceived by the present invention, the following beneficial effects are achieved:

[0036] The present invention combines GNSS information, visual information, and infrared information, and sets up corresponding models to calculate the relative position error, thereby enabling precise landing guidance for drones. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flowchart of the method according to Embodiment 1 of the present invention;

[0038] Figure 2 is a system structure diagram of Embodiment 2 of the present invention;

[0039] Figure 3 is an effect diagram of the present invention;

[0040] Figure 4 is a schematic diagram of the unmanned takeoff and landing of the present invention.

[0041] Reference Signs:

[0042] 1. Drone 2. Takeoff and Landing Platform

[0043] 3. Guidance Mark 4. Six-Degree-of-Freedom Wave Compensation Device

[0044] 5. Ship Deck DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to better understand the above technical solutions, the following will describe the above technical solutions in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0046] The method provided by the present invention can be implemented in the following terminal environment. The terminal may include one or more of the following components: a processor, a storage medium, and a display screen. Among them, the storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiments.

[0047] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts within the entire terminal, and by running or executing instructions, programs, code sets, or instruction sets stored in the storage medium, and by calling data stored in the storage medium, it executes various functions of the terminal and processes data.

[0048] The storage medium may include a random access memory (RAM), and may also include a read-only memory (ROM). The storage medium can be used to store instructions, programs, codes, code sets, or instructions.

[0049] The display screen is used to display the user interfaces of various application programs.

[0050] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be elaborated here.

[0051] Embodiment 1

[0052] As Figure 1 shown, an embodiment of the present invention provides a method for guiding the landing of a UAV dynamic platform based on GNSS and visual recognition, including:

[0053] Step 101, obtain the GNSS information of the UAV and the dynamic platform (GNSS is the Global Navigation Satellite System), and set a navigation positioning error evaluation model to calculate the first relative position error between the UAV and the dynamic platform based on GNSS. Among them, the GNSS information includes: the position of the UAV, the position of the dynamic platform, the speed of the UAV, and the acceleration of the UAV;

[0054] Specifically, the navigation positioning error evaluation model includes:

[0055]

[0056] wherein, ∈ platform (t) is the first relative position error between the UAV and the dynamic platform based on GNSS at time t, P u (t) is the position of the UAV at time t, P p (t) is the position of the dynamic platform at time t, α is the first adjustment factor of the relative position error evaluation model, β is the second adjustment factor of the relative position error evaluation model, t 0 is the starting time, γ is the third adjustment factor of the relative position error evaluation model, η is the fourth adjustment factor of the relative position error evaluation model, V u (t) is the speed of the UAV at time t, κ is the fifth adjustment factor of the relative position error evaluation model, a u (t) is the acceleration of the UAV at time t.

[0057] Step 102: Obtain the visual information of the AprilTag (a type of visual recognition marker, similar to a QR code or barcode, mainly used in computer vision systems to assist the system in positioning, tracking, or augmented reality applications) on the dynamic platform, and set up a visual positioning error evaluation model to calculate the second relative position error between the drone and the dynamic platform based on the AprilTag. Among them, the visual information includes: the position of the AprilTag, the tilt angle of the dynamic platform, and the rotational angular velocity of the dynamic platform;

[0058] Specifically, the visual positioning error evaluation model includes:

[0059]

[0060] Among them, δ vis (t) is the second relative position error between the drone and the dynamic platform based on the AprilTag at time t, φ is the first adjustment factor of the visual recognition error evaluation model, P tag (t) is the position of the AprilTag at time t, δ ″ is the second adjustment factor of the visual recognition error evaluation model, θ is the third adjustment factor of the visual recognition error evaluation model, γ″ is the fourth adjustment factor of the visual recognition error evaluation model, λ 1 is the fifth adjustment factor of the visual recognition error evaluation model, θ p (t) is the tilt angle of the dynamic platform at time t, α′ is the sixth adjustment factor of the visual recognition error evaluation model, λ 2 is the seventh adjustment factor of the visual recognition error evaluation model, ω p (t) is the rotational angular velocity of the dynamic platform at time t, β′ is the eighth adjustment factor of the visual recognition error evaluation model.

[0061] Step 103: Obtain the infrared information of the infrared device on the drone, and set up an infrared positioning error evaluation model to calculate the third relative position error between the drone and the dynamic platform based on the infrared device. Among them, the infrared information includes: the temperature of the dynamic platform, the ambient temperature, the ambient humidity, and the air flow velocity;

[0062] Specifically, the infrared positioning error evaluation model includes:

[0063] Q IR (t) = α″·|T tag (t) - T env (t)| δ′ ·exp(-γ′·||P u (t) - P p (t)||)·(1 + λ 3 ·Henv (t) + λ 4 · ||V air (t) ||)

[0064] Wherein, Q IR (t) is the third relative position error between the UAV based on the infrared device and the dynamic platform at time t, α″ is the first adjustment factor of the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor of the infrared positioning error evaluation model, γ′ is the third adjustment factor of the infrared positioning error evaluation model, λ 3 is the fourth adjustment factor of the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ 4 is the fifth adjustment factor of the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

[0065] Step 104: Adjust the UAV according to the first relative position error, the second relative position error and the third relative position error, so as to complete the landing guidance.

[0066] Specifically, it further includes setting a target optimization function L for the relative error, and by adjusting GNSS, AprilTag and the infrared device, making the value of the target optimization function L of the relative error minimum, so as to achieve the purpose of minimizing the error.

[0067] Specifically, the target optimization function L of the relative error includes:

[0068]

[0069] Wherein, λ 5 is the first adjustment factor of the target optimization function L of the relative error, γ″′ is the second adjustment factor of the target optimization function L of the relative error, λ 6 is the third adjustment factor of the target optimization function L of the relative error, β″′ is the fourth adjustment factor of the target optimization function L of the relative error.

[0070] The following is an example of this embodiment, as follows:

[0071] 1. Starting state: The UAV takes off;

[0072] 2. GNSS positioning information transmission: Transmit the GNSS position of the movable vehicle (such as the takeoff and landing platform) to the UAV in real time through wireless communication;

[0073] 3. UAV Return: The UAV flies near the takeoff and landing platform according to the received GNSS position information, which ensures the initial landing position accuracy;

[0074] 4. Visual Recognition Stage: First, judge the weather condition:

[0075] Good weather: Use the visible light camera, that is, the UAV scans the takeoff and landing platform through the on-board visible light camera, identifies the specific AprilTag on the takeoff and landing platform, calculates the position error between the UAV and the platform through the visual positioning error evaluation model, and performs position correction;

[0076] Bad weather / Insufficient light: Use the infrared camera, that is, the on-board infrared camera takes over for identification and positioning. The metal AprilTag is heated to increase the infrared feature difference, and the temperature control device ensures the constant temperature of the AprilTag to improve the infrared image quality and recognition accuracy.

[0077] 5. Precise Landing:

[0078] Based on the relative position after visual recognition, the UAV lands safely and precisely on the takeoff and landing platform in a predetermined attitude.

[0079] Embodiment 2

[0080] As Figure 2 shown, the embodiment of the present invention also provides a UAV dynamic platform landing guidance system based on GNSS and visual recognition, including:

[0081] Calculation of Navigation Error Module, used to obtain the GNSS information of the UAV and the dynamic platform, and set the navigation positioning error evaluation model to calculate the first relative position error between the UAV and the dynamic platform based on GNSS, where the GNSS information includes: the position of the UAV, the position of the dynamic platform, the speed of the UAV, and the acceleration of the UAV;

[0082] Specifically, the navigation positioning error evaluation model includes:

[0083]

[0084] Where, ∈ platform (t) is the first relative position error between the UAV and the dynamic platform based on GNSS at time t, P u (t) is the position of the UAV at time t, P p (t) is the position of the dynamic platform at time t, α is the first adjustment factor of the relative position error evaluation model, β is the second adjustment factor of the relative position error evaluation model, t 0 is the starting time, γ is the third adjustment factor of the relative position error evaluation model, η is the fourth adjustment factor of the relative position error evaluation model, Vu (t) is the speed of the UAV at time t, K is the fifth adjustment factor of the relative position error evaluation model, a u (t) is the acceleration of the UAV at time t.

[0085] The visual error calculation module is used to obtain the visual information of the AprilTag on the dynamic platform, and set the visual positioning error evaluation model to calculate the second relative position error between the UAV and the dynamic platform based on the AprilTag. Among them, the visual information includes: the position of the AprilTag, the tilt angle of the dynamic platform, and the rotational angular velocity of the dynamic platform;

[0086] Specifically, the visual positioning error evaluation model includes:

[0087]

[0088] Among them, δ vis (t) is the second relative position error between the UAV and the dynamic platform based on the AprilTag at time t, φ is the first adjustment factor of the visual recognition error evaluation model, P tag (t) is the position of the AprilTag at time t, δ ″ is the second adjustment factor of the visual recognition error evaluation model, θ is the third adjustment factor of the visual recognition error evaluation model, γ″ is the fourth adjustment factor of the visual recognition error evaluation model, λ 1 is the fifth adjustment factor of the visual recognition error evaluation model, θ p (t) is the tilt angle of the dynamic platform at time t, α′ is the sixth adjustment factor of the visual recognition error evaluation model, λ 2 is the seventh adjustment factor of the visual recognition error evaluation model, ω p (t) is the rotational angular velocity of the dynamic platform at time t, β′ is the eighth adjustment factor of the visual recognition error evaluation model.

[0089] The infrared error calculation module is used to obtain the infrared information of the infrared device on the UAV, and set the infrared positioning error evaluation model to calculate the third relative position error between the UAV and the dynamic platform based on the infrared device. Among them, the infrared information includes: the temperature of the dynamic platform, the ambient temperature, the ambient humidity, and the air flow velocity;

[0090] Specifically, the infrared positioning error evaluation model includes:

[0091] Q IR (t) = α″·|T tag (t) - T env (t)| δ′ ·exp(-γ′·||P u (t) - Pp (t)||)·(1 + λ 3 ·H env (t)+λ 4 ·||V air (t)||)

[0092] Where Q IR (t) is the third relative position error between the drone based on the infrared device and the dynamic platform at time t, α″ is the first adjustment factor of the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor of the infrared positioning error evaluation model, γ′ is the third adjustment factor of the infrared positioning error evaluation model, λ 3 is the fourth adjustment factor of the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ 4 is the fifth adjustment factor of the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

[0093] The guiding module is used to adjust the drone according to the first relative position error, the second relative position error and the third relative position error, so as to complete the landing guidance.

[0094] Specifically, it further includes setting a target optimization function L of the relative error, and by adjusting GNSS, AprilTag and the infrared device, the value of the target optimization function L of the relative error is minimized to achieve the purpose of minimizing the error.

[0095] Specifically, the target optimization function L of the relative error includes:

[0096]

[0097] Where λ 5 is the first adjustment factor of the target optimization function L of the relative error, γ″′ is the second adjustment factor of the target optimization function L of the relative error, λ 6 is the third adjustment factor of the target optimization function L of the relative error, β″′ is the fourth adjustment factor of the target optimization function L of the relative error.

[0098] Embodiment 3

[0099] The embodiment of the present invention also proposes a storage medium storing multiple instructions, and the instructions are used to implement the method for guiding the landing of a drone dynamic platform based on GNSS and visual recognition.

[0100] Optionally, in this embodiment, the above storage medium may be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0101] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: Step 101, obtain the GNSS information of the drone and the dynamic platform, set up a navigation positioning error evaluation model, and calculate the first relative position error between the drone and the dynamic platform based on GNSS, where the GNSS information includes: the position of the drone, the position of the dynamic platform, the speed of the drone, and the acceleration of the drone;

[0102] Specifically, the navigation positioning error evaluation model includes:

[0103]

[0104] where ∈ platform (t) is the first relative position error between the drone and the dynamic platform based on GNSS at time t, P u (t) is the position of the drone at time t, P p (t) is the position of the dynamic platform at time t, α is the first adjustment factor of the relative position error evaluation model, β is the second adjustment factor of the relative position error evaluation model, t 0 is the starting time, γ is the third adjustment factor of the relative position error evaluation model, η is the fourth adjustment factor of the relative position error evaluation model, V u (t) is the speed of the drone at time t, K is the fifth adjustment factor of the relative position error evaluation model, a u (t) is the acceleration of the drone at time t.

[0105] Step 102, obtain the visual information of the AprilTag on the dynamic platform, set up a visual positioning error evaluation model, and calculate the second relative position error between the drone and the dynamic platform based on AprilTag, where the visual information includes: the position of the AprilTag, the tilt angle of the dynamic platform, and the rotational angular velocity of the dynamic platform;

[0106] Specifically, the visual positioning error evaluation model includes:

[0107]

[0108] where δ vis ( t ) is the second relative position error between the drone and the dynamic platform based on AprilTag at time t, φ is the first adjustment factor of the visual recognition error evaluation model, P tag(t) is the position of the AprilTag at time t, δ″ is the second adjustment factor of the visual recognition error evaluation model, θ is the third adjustment factor of the visual recognition error evaluation model, γ″ is the fourth adjustment factor of the visual recognition error evaluation model, λ 1 is the fifth adjustment factor of the visual recognition error evaluation model, θ p (t) is the tilt angle of the dynamic platform at time t, α′ is the sixth adjustment factor of the visual recognition error evaluation model, λ 2 is the seventh adjustment factor of the visual recognition error evaluation model, ω p (t) is the rotational angular velocity of the dynamic platform at time t, β′ is the eighth adjustment factor of the visual recognition error evaluation model.

[0109] Step 103: Obtain the infrared information of the infrared device on the drone, set up an infrared positioning error evaluation model, and calculate the third relative position error between the drone and the dynamic platform based on the infrared device. Among them, the infrared information includes: the temperature of the dynamic platform, the ambient temperature, the ambient humidity, and the air flow velocity;

[0110] Specifically, the infrared positioning error evaluation model includes:

[0111] Q IR (t) = α″·|T tag (t) - T env (t)| δ′ ·exp(-γ′·||P u (t) - P p (t)||)·(1 + λ 3 ·H env (t) + λ 4 ·||V air (t)||)

[0112] Among them, Q IR (t) is the third relative position error between the drone and the dynamic platform based on the infrared device at time t, α″ is the first adjustment factor of the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor of the infrared positioning error evaluation model, γ′ is the third adjustment factor of the infrared positioning error evaluation model, λ 3 is the fourth adjustment factor of the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ 4 is the fifth adjustment factor of the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

[0113] Step 104: Adjust the drone according to the first relative position error, the second relative position error, and the third relative position error, thereby completing the landing guidance.

[0114] Specifically, it further includes setting a target optimization function L for the relative error. By adjusting the GNSS, AprilTag, and infrared device, the value of the target optimization function L of the relative error is minimized to achieve the purpose of minimizing the error.

[0115] Specifically, the target optimization function L of the relative error includes:

[0116]

[0117] where λ 5 is the first adjustment factor of the target optimization function L of the relative error, γ″′ is the second adjustment factor of the target optimization function L of the relative error, λ 6 is the third adjustment factor of the target optimization function L of the relative error, and β″′ is the fourth adjustment factor of the target optimization function L of the relative error.

[0118] Embodiment 4

[0119] The embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the method for guiding the landing of a drone dynamic platform based on GNSS and visual recognition.

[0120] Specifically, the electronic equipment in this embodiment can be a computer terminal, and the computer terminal can include: one or more processors, and a storage medium.

[0121] Among them, the storage medium can be used to store software programs and modules, such as the method for guiding the landing of a drone dynamic platform based on GNSS and visual recognition in the embodiment of the present invention, and the corresponding program instructions / modules. The processor runs the software programs and modules stored in the storage medium to perform various functional applications and data processing, that is, to implement the above-mentioned method for guiding the landing of a drone dynamic platform based on GNSS and visual recognition. The storage medium can include a high-speed random storage medium, and can also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium can further include a storage medium remotely set relative to the processor, and these remote storage media can be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and their combinations.

[0122] The processor can execute the following steps by transmitting the information stored in the storage medium by the system call and the application program: Step 101, obtain the GNSS information of the drone and the dynamic platform, set up a navigation positioning error evaluation model, and calculate the first relative position error between the drone and the dynamic platform based on GNSS. Among them, the GNSS information includes: the position of the drone, the position of the dynamic platform, the speed of the drone, and the acceleration of the drone.

[0123] Specifically, the navigation positioning error evaluation model includes:

[0124]

[0125] Among them, ∈ platform $(t)$ is the first relative position error between the drone and the dynamic platform based on GNSS at time $t$, $P$ u $(t)$ is the position of the drone at time $t$, $P$ p $(t)$ is the position of the dynamic platform at time $t$, $\alpha$ is the first adjustment factor of the relative position error evaluation model, $\beta$ is the second adjustment factor of the relative position error evaluation model, $t$ 0 is the starting time, $\gamma$ is the third adjustment factor of the relative position error evaluation model, $\eta$ is the fourth adjustment factor of the relative position error evaluation model, $V$ u $(t)$ is the speed of the drone at time $t$, $\kappa$ is the fifth adjustment factor of the relative position error evaluation model, $a$ u $(t)$ is the acceleration of the drone at time $t$.

[0126] Step 102, obtain the visual information of the AprilTag on the dynamic platform, set up a visual positioning error evaluation model, and calculate the second relative position error between the drone and the dynamic platform based on the AprilTag. Among them, the visual information includes: the position of the AprilTag, the tilt angle of the dynamic platform, and the rotational angular velocity of the dynamic platform.

[0127] Specifically, the visual positioning error evaluation model includes:

[0128]

[0129] Among them, $\delta$ vis $(t)$ is the second relative position error between the drone and the dynamic platform based on the AprilTag at time $t$, $\varphi$ is the first adjustment factor of the visual recognition error evaluation model, $P$ tag $(t)$ is the position of the AprilTag at time $t$, $\delta''$ is the second adjustment factor of the visual recognition error evaluation model, $\theta$ is the third adjustment factor of the visual recognition error evaluation model, $\gamma''$ is the fourth adjustment factor of the visual recognition error evaluation model, $\lambda$ 1is the fifth adjustment factor for the visual recognition error evaluation model, θ p (t) is the tilt angle of the dynamic platform at time t, α′ is the sixth adjustment factor for the visual recognition error evaluation model, λ 2 is the seventh adjustment factor for the visual recognition error evaluation model, ω p (t) is the rotational angular velocity of the dynamic platform at time t, β′ is the eighth adjustment factor for the visual recognition error evaluation model.

[0130] Step 103: Obtain the infrared information of the infrared device on the drone, set up an infrared positioning error evaluation model, and calculate the third relative position error between the drone and the dynamic platform based on the infrared device. Among them, the infrared information includes: the temperature of the dynamic platform, the ambient temperature, the ambient humidity, and the air flow velocity;

[0131] Specifically, the infrared positioning error evaluation model includes:

[0132] Q IR (t) = α″·|T tag (t) - T env (t)| δ′ ·exp(-γ′·||P u (t) - P p (t)||)·(1 + λ 3 ·H env (t) + λ 4 ·||V air (t)||)

[0133] Among them, Q IR (t) is the third relative position error between the drone and the dynamic platform based on the infrared device at time t, α″ is the first adjustment factor for the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor for the infrared positioning error evaluation model, γ′ is the third adjustment factor for the infrared positioning error evaluation model, λ 3 is the fourth adjustment factor for the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ 4 is the fifth adjustment factor for the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

[0134] Step 104: Adjust the drone according to the first relative position error, the second relative position error, and the third relative position error, so as to complete the landing guidance.

[0135] Specifically, it further includes setting a target optimization function L for relative error. By adjusting GNSS, AprilTag, and infrared devices, the value of the target optimization function L of the relative error is minimized to achieve the purpose of minimizing the error.

[0136] Specifically, the target optimization function L of the relative error includes:

[0137]

[0138] where λ 5 is the first adjustment factor of the target optimization function L of the relative error, γ″′ is the second adjustment factor of the target optimization function L of the relative error, λ 6 is the third adjustment factor of the target optimization function L of the relative error, and β″′ is the fourth adjustment factor of the target optimization function L of the relative error.

[0139] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0140] In the above embodiments of the present invention, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0141] In several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0142] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0144] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, read-only storage media (ROM, Read-Only Memory), random access storage media (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs.

[0145] Obviously, the above embodiments are merely examples given for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or variations can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or variations derived therefrom are still within the protection scope of the present invention.

Claims

1. A method for guiding the landing of a UAV dynamic platform based on GNSS and visual recognition, characterized in that: include: Acquire GNSS information of the UAV and the dynamic platform, set a navigation positioning error evaluation model, and calculate a first relative position error between the UAV and the dynamic platform based on GNSS, wherein the GNSS information includes: the position of the UAV, the position of the dynamic platform, the speed of the UAV, and the acceleration of the UAV; Obtain visual information of AprilTag on the dynamic platform, set up a visual positioning error evaluation model, and calculate the second relative position error between the AprilTag-based UAV and the dynamic platform, wherein the visual information includes: the position of AprilTag, the tilt angle of the dynamic platform, and the rotation angular velocity of the dynamic platform; Acquire infrared information of the infrared device on the UAV, set up an infrared positioning error evaluation model, and calculate the third relative position error between the UAV based on the infrared device and the dynamic platform, wherein the infrared information includes: temperature, ambient temperature, ambient humidity and airflow velocity of the dynamic platform; The UAV is adjusted according to the first relative position error, the second relative position error and the third relative position error, thereby completing landing guidance.

2. A method for guiding the landing of a UAV dynamic platform based on GNSS and visual recognition as claimed in claim 1, characterized in that: The navigation positioning error evaluation model includes: Among them, ∈ platform (t) is the first relative position error between the GNSS-based UAV and the dynamic platform at time t, P u (t) is the position of the UAV at time t, P p (t) is the position of the dynamic platform at time t, α is the first adjustment factor of the relative position error evaluation model, β is the second adjustment factor of the relative position error evaluation model, t0 is the starting time, γ is the third adjustment factor of the relative position error evaluation model, η is the fourth adjustment factor of the relative position error evaluation model, V u (t) is the speed of the UAV at time t, κ is the fifth adjustment factor of the relative position error evaluation model, and a u (t) is the acceleration of the UAV at time t.

3. A method for guiding the landing of a UAV dynamic platform based on GNSS and visual recognition as claimed in claim 2, characterized in that: The visual positioning error evaluation model includes: Among them, δ vis (t) is the second relative position error between the UAV based on AprilTag and the dynamic platform at time t, φ is the first adjustment factor of the visual recognition error evaluation model, P tag (t) is the position of AprilTag at time t, δ″ is the second adjustment factor of the visual recognition error evaluation model, θ is the third adjustment factor of the visual recognition error evaluation model, γ″ is the fourth adjustment factor of the visual recognition error evaluation model, λ1 is the fifth adjustment factor of the visual recognition error evaluation model, θ p (t) is the tilt angle of the dynamic platform at time t, α′ is the sixth adjustment factor of the visual recognition error evaluation model, λ2 is the seventh adjustment factor of the visual recognition error evaluation model, ω p (t) is the rotation angular velocity of the dynamic platform at time t, and β′ is the eighth adjustment factor of the visual recognition error evaluation model.

4. The method for guiding the landing of a UAV dynamic platform based on GNSS and visual recognition as claimed in claim 3, characterized in that: The infrared positioning error evaluation model includes: Q IR (t)=α″·|T tag (t)-T env (t)| δ′ ·exp(-γ′·||P u (t)-P p (t)||)·(1+λ3·H env (t)+λ4·||V air (t)||) Among them, Q IR (t) is the third relative position error between the UAV based on infrared equipment and the dynamic platform at time t, α″ is the first adjustment factor of the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor of the infrared positioning error evaluation model, γ′ is the third adjustment factor of the infrared positioning error evaluation model, λ3 is the fourth adjustment factor of the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ4 is the fifth adjustment factor of the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

5. The method for guiding the landing of a UAV dynamic platform based on GNSS and visual recognition as claimed in claim 4, characterized in that: It also includes setting a target optimization function L of the relative error, and minimizing the value of the target optimization function L of the relative error by adjusting the GNSS, AprilTag and infrared equipment to achieve the purpose of minimizing the error.

6. The method for guiding the landing of a UAV dynamic platform based on GNSS and visual recognition as claimed in claim 5, characterized in that: The objective optimization function L of the relative error includes: Among them, λ5 is the first adjustment factor of the target optimization function L of the relative error, γ″′ is the second adjustment factor of the target optimization function L of the relative error, λ6 is the third adjustment factor of the target optimization function L of the relative error, and β″′ is the fourth adjustment factor of the target optimization function L of the relative error.

7. A UAV dynamic platform landing guidance system based on GNSS and visual recognition, characterized in that: include: A navigation error calculation module is used to obtain GNSS information of the UAV and the dynamic platform, and set a navigation positioning error evaluation model to calculate a first relative position error between the UAV and the dynamic platform based on GNSS, wherein the GNSS information includes: the position of the UAV, the position of the dynamic platform, the speed of the UAV and the acceleration of the UAV; A visual error calculation module is used to obtain the visual information of AprilTag on the dynamic platform, set a visual positioning error evaluation model, and calculate the second relative position error between the UAV based on AprilTag and the dynamic platform, wherein the visual information includes: the position of AprilTag, the tilt angle of the dynamic platform, and the rotation angular velocity of the dynamic platform; The infrared error calculation module is used to obtain the infrared information of the infrared device on the UAV, set the infrared positioning error evaluation model, and calculate the third relative position error between the UAV and the dynamic platform based on the infrared device, wherein the infrared information includes: the temperature of the dynamic platform, the ambient temperature, the ambient humidity and the airflow velocity; The guidance module is used to adjust the UAV according to the first relative position error, the second relative position error and the third relative position error, so as to complete the landing guidance.

8. The unmanned aerial vehicle dynamic platform landing guidance system based on GNSS and visual recognition as claimed in claim 7, characterized in that: The navigation positioning error evaluation model includes: Among them, ∈ platform (t) is the first relative position error between the GNSS-based UAV and the dynamic platform at time t, P u (t) is the position of the UAV at time t, P p (t) is the position of the dynamic platform at time t, α is the first adjustment factor of the relative position error evaluation model, β is the second adjustment factor of the relative position error evaluation model, t0 is the starting time, γ is the third adjustment factor of the relative position error evaluation model, η is the fourth adjustment factor of the relative position error evaluation model, V u (t) is the speed of the UAV at time t, κ is the fifth adjustment factor of the relative position error evaluation model, and a u (t) is the acceleration of the UAV at time t.

9. The unmanned aerial vehicle dynamic platform landing guidance system based on GNSS and visual recognition as claimed in claim 8, characterized in that: The visual positioning error evaluation model includes: Among them, δ vis (t) is the second relative position error between the UAV based on AprilTag and the dynamic platform at time t, φ is the first adjustment factor of the visual recognition error evaluation model, P tag (t) is the position of AprilTag at time t, δ″ is the second adjustment factor of the visual recognition error evaluation model, θ is the third adjustment factor of the visual recognition error evaluation model, γ″ is the fourth adjustment factor of the visual recognition error evaluation model, λ1 is the fifth adjustment factor of the visual recognition error evaluation model, θ p (t) is the tilt angle of the dynamic platform at time t, α′ is the sixth adjustment factor of the visual recognition error evaluation model, λ2 is the seventh adjustment factor of the visual recognition error evaluation model, ω p (t) is the rotation angular velocity of the dynamic platform at time t, and β′ is the eighth adjustment factor of the visual recognition error evaluation model.

10. The unmanned aerial vehicle dynamic platform landing guidance system based on GNSS and visual recognition as claimed in claim 9, characterized in that: The infrared positioning error evaluation model includes: Q IR (t)=α″·|T tag (t)-T env (t)| δ′ ·exp(-γ′·||P u (t)-P p (t)||)·(1+λ3·H env (t)+λ4·||V air (t)||) Among them, Q IR (t) is the third relative position error between the UAV based on infrared equipment and the dynamic platform at time t, α" is the first adjustment factor of the infrared positioning error evaluation model, T tag (t) is the temperature of the dynamic platform at time t, T env (t) is the ambient temperature at time t, δ′ is the second adjustment factor of the infrared positioning error evaluation model, γ′ is the third adjustment factor of the infrared positioning error evaluation model, λ3 is the fourth adjustment factor of the infrared positioning error evaluation model, H env (t) is the ambient humidity at time t, λ4 is the fifth adjustment factor of the infrared positioning error evaluation model, V air (t) is the air flow velocity at time t.

Images