Man-machine interaction method for unmanned aerial vehicle autonomous operation system

Abstract

The invention discloses a man-machine interaction method for an unmanned aerial vehicle autonomous operation system. The man-machine interaction method comprises the steps that S1, inspection items before an unmanned aerial vehicle flies are divided into logic stages according to an operation process; s2, setting a basic weight for each inspection item, and screening key items; s3, the system communicates with an unmanned aerial vehicle sensor in real time, parameter data is collected and compared with an expected reference value, and when a detection result has deviation, the weight of a corresponding inspection item is increased; and S4, automatically acquiring and checking the inspection items which do not need to be manually confirmed by the background through a sensor interface, and completing confirmation of all key items. Weights are set according to various inspection tasks, dynamic adjustment is carried out according to security levels, historical data and task types, key items which really need to be manually confirmed and operated in the current stage are screened out by setting a threshold value, and other items are automatically inspected or omitted in the background. And autonomous operation, remote management, batch flight control or group unmanned aerial vehicle operation of a large-scale unmanned aerial vehicle scene are supported.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a human-computer interaction method for an autonomous UAV operating system. Background Technology

[0002] With the rapid development of drone applications (such as logistics transportation, emergency rescue, surveying and inspection and military reconnaissance), the pre-flight inspection and operation of drones are becoming increasingly complex. Traditional drone operation inspection methods have the following defects and shortcomings: (1) Before the drone flies, the operator often needs to check each item on the paper or electronic list provided by the manufacturer, such as battery power, GPS signal, servo and motor status, propeller fixation, communication link, flight control system version check, etc. The number of inspection items can reach dozens to hundreds, and the operator must complete them within a limited time. The work is tedious and easy to miss; (2) The drone operator may need to issue instructions quickly within a limited time, such as route adjustment, camera angle switching, payload delivery, etc., to complete high-precision input in a short time. However, the traditional touch control method is not reliable enough in a high dynamic environment.

[0003] In recent years, some drones have been equipped with ground station tablets or mobile apps to digitize checklists. While these solutions reduce the inefficiency of paper records, they are essentially still linear "item-by-item check-in" presentations, with a large amount of non-critical data occupying the interface space, making it difficult for users to quickly locate key issues. Some high-end drones already support collecting data such as battery voltage, motor speed, and GPS accuracy through sensors and comparing it with system standards. However, current systems typically only automatically collect and prompt data, still displaying all check items with equal weight, without significantly highlighting key steps and safety-sensitive data, making it difficult to support truly unmanned operation or large-scale drone swarm operations. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a human-computer interaction method for an autonomous operation system of unmanned aerial vehicles.

[0005] The objective of this invention is achieved through the following technical solution: a human-computer interaction method for an autonomous operation system of an unmanned aerial vehicle (UAV), comprising the following steps:

[0006] S1: Divide the pre-flight inspection items for drones according to the operational process. One logical stage;

[0007] S2: Assign basic weights to each inspection item and filter out key items;

[0008] S3: The system communicates with the drone's sensors in real time to collect parameter data. and the expected reference value By comparison, when discrepancies are found in the test results, the weight of the corresponding test item is increased.

[0009] ;

[0010] in, Based on the weights, This is the amplification factor.

[0011] when Greater than the threshold When this happens, the system will elevate this item to a critical item;

[0012] S4: The background automatically acquires and verifies inspection items that do not require manual confirmation through the sensor interface, and completes the confirmation of all key items.

[0013] Preferably, in step S1, the set of pre-flight inspection items for the drone is denoted as... It is divided into the following categories according to the operation process: One logical stage:

[0014] .

[0015] The present invention has the following advantages: The present invention sets weights for each inspection task and dynamically adjusts them according to the security level, historical data and task type. By setting thresholds, the key items that truly require manual confirmation and operation at the current stage are selected, while the remaining items are automatically checked in the background or omitted. This supports autonomous operation, remote management, batch flight control or swarm drone operations in large-scale drone scenarios. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the human-computer interaction method for an autonomous unmanned aerial vehicle (UAV) system. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0018] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0021] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are only used for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. In addition, the terms "first," "second," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0023] In this embodiment, as Figure 1 As shown, a human-computer interaction method for an autonomous operation system of an unmanned aerial vehicle (UAV) includes the following steps:

[0024] S1: Divide the pre-flight inspection items for drones according to the operational process. A logical stage; specifically, the set of pre-flight inspection items for the drone is denoted as... It is divided into the following categories according to the operation process: One logical stage:

[0025] ;

[0026] Each stage is displayed on the tablet interface only in small font as a prompt text, for example: The current stage is... At this stage, key items need to be identified. item.

[0027] S2: Assign basic weights to each inspection item and filter key items; specifically, for each inspection item... Set basic weights Its value is determined by flight safety level and historical accident data statistics. The key set of terms here is... ,in, The preset threshold is dynamically adjusted by the system based on the drone's mission scenario. The value is 0.8. In this embodiment, the system only sets... The items within the interface are displayed through interactive controls (buttons, input boxes, or selection boxes), while other low-weight inspection items are automatically compared or omitted by the background. In other words, the inspection items at each stage only focus on displaying key operation items to the human-machine interface, effectively avoiding information overload under the traditional full linear checklist, enabling operators to quickly locate and complete key inspections, and greatly improving the convenience and accuracy of manual operation.

[0028] S3: The system communicates with the drone's sensors in real time to collect parameter data. and the expected reference value By comparison, when discrepancies are found in the test results, the weight of the corresponding test item is increased.

[0029] ;

[0030] in, Based on the weights, This is the amplification factor. The value is 0.5~1.5;

[0031] when Greater than the threshold When this happens, the system will elevate the item to a critical item, meaning the check item will automatically be moved from the background to the displayed item and highlighted. For example, the expected battery voltage value... It is 24.0V, parameter data 22.5V, initial weight It is 0.75. If it is 1, then for:

[0032] ,

[0033] at this time If the value is greater than 0.8, the system will display this item as a critical item and require operator confirmation. This means that by employing a weighted allocation and dynamic threshold adjustment mechanism for inspection items, the system automatically identifies the core inspection items that truly impact flight safety at each stage. Only important parameters with weights exceeding the threshold are presented through interactive methods such as buttons and input boxes, while the remaining data is automatically verified in the background. This significantly reduces safety risks caused by human error. Furthermore, by utilizing real-time sensor data input and anomaly amplification coefficient formulas, the system automatically increases the operational priority of critical parameters if deviations occur, highlighting key areas on the interface and providing alarm prompts. This ensures that critical hidden dangers are exposed immediately, enhancing safety control.

[0034] S4: The backend automatically acquires and verifies inspection items that do not require manual confirmation via sensor interfaces, completing the confirmation of all key items. Specifically, it checks the set... For inspection items that do not require manual confirmation, the backend automatically acquires and verifies data through sensor interfaces. When all key items... Only after confirmation can the process proceed to the next stage to ensure a safe closed loop. If any required fields are ignored, the system will lock the current stage and display the message "Not yet completed".

[0035] Example 1: Taking a certain type of long-endurance fixed-wing UAV as an example, applied to long-distance emergency patrol missions, this UAV requires a pre-flight check covering power supply, fuel, control surfaces, navigation, communication, aerodynamics, and mission parameters. The operator must check each item on a paper or electronic list, which is prone to overlooking key points and is time-consuming. The check items are shown in Table 1.

[0036] Table 1

[0037]

[0038] The information for each sub-item is stored in the system database, and each item has a preset initial weight value. ,

[0039] Weight allocation: The system uses weights to determine whether each item is a "key item". The initial weights are as follows (taking stage 3 as an example), as shown in Table 2.

[0040] Table 2

[0041]

[0042] The system automatically filters out those with a weight greater than or equal to The items, as the set of key items for this stage. .

[0043] Dynamic weight adjustment: For example, during the fuel detection phase, the system acquires the measured values ​​from the fuel sensor. =18.5L, expected value =23.0L, initial weight =0.74, abnormal amplification factor =1.2, at this time:

[0044] ;

[0045] because This item will be automatically highlighted on the current key item screen, and a warning will pop up: "Insufficient fuel, please check if you want to add fuel."

[0046] Interactive Experience: The stage switching area only uses small text to indicate the current stage (e.g., "Stage 4 / 6"); each stage has a maximum of 2-4 buttons / input boxes displaying the "key items" that need to be operated. For example, in the "Control Surface Feedback" interface, there are only 3 buttons: "Elevator Action Feedback," "Aileron Action Feedback," and "Rudder Action Feedback," with the rest automatically detected in the background; numerical types (e.g., "Current Fuel Level") are input boxes with color indicators (green for normal, red for warning); Boolean types (e.g., "Is the Wing Lock Locked?") are confirmation buttons, with a forced highlight warning when there is an abnormality.

[0047] Background process control and data management: Automatically acquires real-time data from various sensor interfaces and synchronizes it to the database background. Only the "key items" on the interface need to be operated. After all are confirmed, the process can proceed to the next stage. Otherwise, the process is locked. All manual or automatic operation processes generate logs, and abnormal items are stored in the database for later traceability.

[0048] Comparison of results and operation: The traditional method requires manual confirmation of 36 items one by one, taking about 13 minutes on the first operation, with a high probability of missed detections; After applying this invention, each stage has ≤4 operation items, requiring a total of 15 manual operations; the rest are completed automatically by sensors and the system backend, taking about 6 minutes in total, improving efficiency by about 54%. Real-time magnification and automatic highlighting of key item anomalies significantly reduce the risk of operational omissions and flight accidents, supporting subsequent one-to-many management of batch drones (swarm flights), with each drone requiring only one round of manual operation on a tablet, saving labor and providing high visibility.

[0049] In summary, this application, implemented in a modular form, can be widely integrated into ground stations or airborne intelligent management units of various UAVs, facilitating the promotion and deployment of various types of UAVs (rotor-wing, fixed-wing, compound-wing, etc.) and adapting to multiple scenarios such as single-aircraft, swarm flight, and remote autonomous operation and maintenance. Compared with traditional manual operation methods, this invention significantly reduces the number of manual interaction operations and pre-flight preparation time, achieving an efficiency improvement of more than 50%, while greatly reducing the probability of missing key inspection items, thus achieving both efficient management and flight safety.

[0050] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A human-computer interaction method for an autonomous operation system of an unmanned aerial vehicle (UAV), characterized in that: Includes the following steps: S1: Divide the pre-flight inspection items for drones according to the operational process. One logical stage; S2: Assign basic weights to each inspection item and filter out key items; S3: The system communicates with the drone's sensors in real time to collect parameter data. and the expected reference value By comparison, when discrepancies are found in the test results, the weight of the corresponding test item is increased. ； in, Based on the weights, This is the amplification factor. when Greater than the threshold When this happens, the system will elevate this item to a critical item; S4: The background automatically acquires and verifies inspection items that do not require manual confirmation through the sensor interface, and completes the confirmation of all key items.

2. The human-computer interaction method for an autonomous unmanned aerial vehicle (UAV) system according to claim 1, characterized in that: In step S1, the set of pre-flight inspection items for the drone is denoted as... It is divided into the following categories according to the operation process: One logical stage: 。

Images