Aerocar dynamic early warning method based on adaptive control algorithm

Abstract

The invention discloses a flying car dynamic early warning method based on a self-adaptive control algorithm, which belongs to the field of flight control and comprises the following steps: S1, designing a self-adaptive interface of an early warning control system, and automatically adjusting display contents and functions of the interface according to a flight state; s2, integrating data input and voice recognition functions in the early warning control system, so that a driver user can operate through presetting and voice; s3, monitoring the flight state in real time, and dynamically analyzing the user operation habit of the driver; s4, adjusting the priority of the information displayed on the interface, highlighting the flight key information according to the current flight mode, and performing dynamic early warning; and S5, performing a driver user experience test, and optimizing the availability and response speed of the interface. Based on the modern flight control technology and the man-machine interaction concept, the invention provides the flying car dynamic early warning system and method based on the self-adaptive control algorithm, and the operation efficiency and safety of a driver user in a complex flight task can be improved.

Description

Technical Field

[0001] The present invention relates to the fields of human-computer interaction, flight control and intelligent interface design, and in particular to a flying car dynamic warning method based on an adaptive control algorithm, which aims to achieve a timely warning function by dynamically adjusting the display priority of flight information. Background Art

[0002] The rapid development of flying cars has put forward higher requirements for the design of flight control interfaces. During flight operations, the driver needs to pay attention to multiple information sources at the same time, such as navigation, flight status, and environmental changes. However, information overload and complex operating environments often lead to driver distraction, which in turn affects flight safety. If the driver cannot effectively focus on key flight information when performing tasks, it may lead to serious operational deviations.

[0003] In flight operations, the phenomenon of distraction is called the "seeing and not seeing" error. When this error occurs, the pilot's line of sight may scan important flight information or environmental threats, but due to excessive cognitive burden, the pilot fails to perceive this information and misses the critical decision-making opportunity. This phenomenon not only affects flight efficiency, but also increases the occurrence of flight accidents.

[0004] With the advancement of flying car and drone technology, the complexity of human-computer interaction is also increasing. Currently, many studies focus on the design and optimization of flight control interfaces, but there are still deficiencies in the research on real-time monitoring and intelligent adjustment of driver-user interference status, so as to improve the driver-user's attention and concentrated information processing ability during flight operations. Summary of the invention

[0005] In view of the phenomenon that the driver user's attention is distracted in a complex flight environment, the present invention provides a flying car dynamic warning method based on an adaptive control algorithm to enhance the driver user's attention to key information. By dynamically adjusting the information display priority, the control interface uses real-time flight data and driver user behavior analysis to achieve effective information management of the driver user during flight operations, providing a new solution for improving flight safety.

[0006] To achieve the above purpose, the technical solution provided by the present invention is as follows:

[0007] S1. Design an adaptive control interface layout to automatically adjust the display content according to the flight status;

[0008] S2, integrated voice recognition function, allowing the driver to choose the operation mode;

[0009] S3, real-time monitoring of flight status and environmental data, dynamic evaluation of information display priority;

[0010] S4. Adjust information display according to driver user operations to ensure that key data is displayed first;

[0011] S5. Conduct driver user experience testing, collect feedback and optimize interface design.

[0012] Preferably, in step S1:

[0013] (1) Setting information display templates according to different flight modes (such as take-off, cruise, and landing);

[0014] (2) Configure the priorities of key flight parameters, such as speed, altitude, and navigation information;

[0015] (3) Consider external environmental factors and dynamically adjust display content and format.

[0016] Preferably, in step S2, the integration of supplementation and voice recognition ensures that the driver-user can flexibly select an operation mode in a complex environment.

[0017] Preferably, in step S3, the real-time monitoring module obtains flight status data through sensors and combines it with environmental information to generate a dynamic evaluation report.

[0018] Preferably, in step S4:

[0019] (1) Analyze the driver's attention pattern based on historical operation data;

[0020] (2) Automatically optimize information display to ensure that high-priority information is in visual focus.

[0021] Preferably, in step S5, the driver user experience test will be conducted through a flight simulator to collect data to optimize the response speed and effect of the interface.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] (1) By dynamically adjusting information priority, the pilot’s concentration during flight operations can be effectively improved, reducing safety hazards caused by distraction.

[0024] (2) The design of the adaptive control interface can improve the flexibility and effectiveness of information processing based on real-time data and optimized display;

[0025] (3) The warning system of the present invention can be further integrated with an intelligent analysis system and combined with image recognition technology to achieve real-time monitoring and reminder of the driver's attention status, thereby improving flight safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions used in the embodiments of the present invention, some drawings used in the embodiments of the present invention are attached below for a brief description. For ordinary technicians in this field, other drawings can also be obtained based on these drawings without creating labor.

[0027] Figure 1 A flow chart of a method for determining the priority of a flight control interface of the present invention is proposed, showing the various steps from data collection to dynamic adjustment of information priority.

[0028] Figure 2 A schematic diagram of the real-time monitoring and driver user behavior analysis process of the present invention illustrates how to adjust the priority of information through sensors and driver user input data.

[0029] Figure 3 The schematic diagram shows the interactive interface of the present invention in different states, showing different flight parameters displayed on the interactive screen of the flying car in different flight states. In addition, there is real-time system monitoring, and when some parts of the flying car have problems, a window will pop up on the interactive interface to remind the driver or passengers to deal with it. DETAILED DESCRIPTION

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are the same as some example embodiments of the present invention, but not all of them are based on the embodiments in the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] refer to Figure 1 The present invention provides a method for determining priority of an adaptive flight control interface, comprising the following steps:

[0033] The first step is to design an adaptive interface layout. Dynamically adjust the display content according to different flight states (such as ascent, descent, cruise, and landing). In the ascent and descent stages, the system highlights navigation and speed information; in the cruise stage, it emphasizes heading and weather conditions; and in the landing stage, it prioritizes displaying altitude and low-altitude wind speed information for the landing pad. Figure 3 Drivers can set real-time feedback priorities through the prompt screen or voice commands, and the system will automatically learn and optimize the layout.

[0034] The second step is to integrate voice recognition. The pilot can select voice commands to operate during flight. Voice recognition uses natural language processing technology. The system collects microphone input in real time, analyzes the pilot's commands and adjusts the information display accordingly.

[0035] The third step is to monitor the flight status and driver user behavior in real time. Gyroscope sensors are used to collect flight parameters (such as speed, altitude, and attitude) and analyze them in combination with driver user input data. This step involves data integration and processing to ensure the accuracy and timeliness of information display.

[0036] The fourth step is to use a weighted scoring model to evaluate information priority. First, set a basic weight for each information item, such as 0.5 for navigation information and 0.3 for weather information. During the flight, real-time data updates will affect these weights. For example, under statistical conditions, the weight of weather information can be increased to 0.7. The priority calculation formula is:

[0037] Priority = ∑(information item × dynamic weight)

[0038] This ensures that critical data is always within the driver-user's line of sight.

[0039] The fifth step is to conduct a driver user experience test. Use a flight simulator to simulate different flight missions, collect priority feedback, and evaluate the effect of information priority adjustment. The test data will be used to further optimize the information display and priority calculation model.

[0040] Step 6: Use precision analysis to further optimize the display. Through the K-means precision algorithm, analyze the information attention patterns of pilots in different flight states and identify potential improvements in information display. The specific implementation steps are as follows:

[0041] Data preparation:

[0042] Collect data on the driver's attention in different states, including gaze point coordinates (x, y), gaze duration, and line of sight movement speed, to ensure data accuracy.

[0043] Set clustering parameters:

[0044] The number k is determined, usually selected based on preliminary experimental results or departmental rules. In this example, k=3 is set to display the three flight states of ascent, cruise, and landing.

[0045] Randomly select initial centers:

[0046] Randomly select k sample points from the data as the initial centers. In this example, 3 sample points are selected.

[0047] Sample distribution:

[0048] Calculate the Euclidean distance from each sample point to all k centers and assign the sample point to the nearest center. The formula is:

[0049] d(x i , c k )=(x i -c k ) 2 +(y i -c k ) 2

[0050] Based on the new evaluation results, recalculate the mean of each center:

[0051]

[0052] Repeat steps (4) and (5) until the center no longer changes or the maximum number of repetitions (such as 100) is reached. Set the convergence condition as the center change is less than 0.01:

[0053]

[0054] Generate cluster models to show attention patterns under different flight states, use visualization tools to generate scatter plots and mark state information.

[0055] Step 7: Dynamically adjust information display. The system records the operation history of the driver user and analyzes its behavioral characteristics through machine learning algorithms (such as support vector machines, random forests, etc.) to optimize the priority of information. Specifically, the system will identify the key indicators that the driver user is concerned about in different tasks based on historical data, and dynamically adjust their display priority in the interface. In order to achieve the system design of optimizing the behavioral characteristics of the driver user and adjusting the information priority through the support vector machine SVM, the key steps are as follows:

[0056] 1. Data Collection

[0057] Operation history: The system continuously monitors and records the operation history data of the driver user through the gyro sensor or flight recorder.

[0058] Combine the data from step 3.

[0059] Environmental information: In addition to the operation history, it is also necessary to record data on the flight environment, such as weather conditions, flight patterns, airspace restrictions, etc.

[0060] 2. Data Preprocessing

[0061] Feature extraction: Extract useful features from the collected operation history, such as the pilot-user’s reaction time, operation frequency, and adjustment strategies for different flight states.

[0062] 3. Model training

[0063] Behavior classification: Use machine learning algorithms such as support vector machines (SVM) to classify and model the extracted features. SVM can be used to distinguish the operational behavior characteristics of pilot users in normal flight, emergency or complex environments.

[0064] Supervised learning: Label the operation data according to different flight environments and operation results (such as efficient, suboptimal or inefficient operation) and train the SVM model to predict the optimal behavior pattern in future operations.

[0065] 4. Priority Optimization

[0066] Real-time analysis: The system analyzes the driver's operating behavior in real time based on the trained model and determines the degree of match between the current driver's operation and the historical pattern.

[0067] Dynamically adjust information display: According to the analysis results, the information priority of the display interface is adjusted. For example, in a complex environment, key information that is easy for the driver to ignore will be magnified and displayed first, while non-critical information can be reduced or even hidden to reduce information overload.

[0068] By observing gaze patterns, we can identify areas for improvement in information presentation and suggest enhancing prompts or adjusting information priorities.

[0069] Make optimization suggestions based on the analysis results, such as adjusting the way information is presented, improving attention and concentration, and ensuring that key information is effectively communicated.

[0070] Step 8: Use SPSS and other statistical software to analyze the data. Whether the interface adjustment at different stages has achieved the expected effect. For the reaction time data, first clarify the error-free reaction, then analyze the changes in information priority under different states, and analyze the differences between the test groups by retrospective analysis. Use SPSS27.0 statistical software for data analysis. The specific steps are as follows:

[0071] Collect reaction time and accuracy data to ensure data error. Record the driver user's reaction time in different task groups.

[0072] Eliminate data on incorrect responses, such as records of driver users failing to perform tasks correctly or responding incorrectly. Count and eliminate extreme data. Use the 3-times standard deviation method to calculate the mean and standard deviation of the response time, and eliminate response times that exceed the sample mean ± 3 times the standard deviation.

[0073] Univariate gradient analysis (ANOVA) was used to compare the differences in reaction time between different task groups (such as easy group, medium group and difficult group). The significance level was set at α = 0.05 to analyze whether the differences between the groups were significant.

[0074] Direct calculation of η 2 (etasquared) is used as the effect size to evaluate the size of the between-group error:

[0075]

[0076] Evaluation criteria for setting effect size: Small effect: 0.01≤η 2 ≤0.06; Medium effect: 0.06≤η 2 ≤0.14; large effect: η 2 ≥0.14.

[0077] Based on the statistical analysis results, the significant differences in reaction time between different task groups were determined. Combined with the accuracy trends of each group, the impact of task load on driver user reaction time was analyzed.

[0078] In this embodiment, the design and implementation of each step are aimed at improving the information processing ability and decision-making efficiency of the pilot user in a complex environment, and ensuring flight safety through an automated adaptive control interface.

[0079] The terms "first", "second", "third", etc. in the specification and claims of the present invention and above are used to distinguish similar objects, rather than to describe a specific order or sequential implementation. It should be understood that the numbers used can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover inclusions that do not exclude them.

[0080] The above description of the disclosed embodiments enables professionals in the field to implement or use the present invention. Various modifications to these embodiments will be cultural heritage to professionals in the field, and the general principles set forth in the paper can be implemented in the embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will be consistent with the principles and novel features disclosed in other examples herein to the widest extent.

Claims

1. A flying car dynamic warning method based on an adaptive control algorithm, characterized in that: The following steps are involved: S1. Design an adaptive interface for the early warning control system to automatically adjust the display content and functions of the interface according to the flight status; S2. Integrate data input and voice recognition functions in the early warning control system, so that the driver can operate it through presets and voice; S3, real-time monitoring of flight status and dynamic analysis of pilot user operation habits; S4. Adjust the priority of information displayed on the interface, highlight key flight information according to the current flight mode, and provide dynamic warnings; S5. Conduct driver user experience testing to optimize the usability and response speed of the interface.

2. The flying car dynamic warning method based on the adaptive control algorithm according to claim 1 is characterized in that: The layout module of the adaptive interface automatically optimizes information display according to different flight modes, and the flight modes at least include an ascent and descent mode, a cruise mode, and a landing mode.

3. The flying car dynamic warning method based on adaptive control algorithm according to claim 1, characterized in that: The modules for data input and voice recognition functions work simultaneously during a flight mission.

4. The flying car dynamic warning method based on adaptive control algorithm according to claim 1, characterized in that: The module for real-time monitoring of flight status obtains and inputs flight data through sensor data analysis.

5. The flying car dynamic warning method based on adaptive control algorithm according to claim 1, characterized in that: In emergency situations, the display priority of highlighted alarm information on the interface is increased.

6. The flying car dynamic warning method based on adaptive control algorithm according to claim 1 is characterized in that: The driver user experience testing module continuously optimizes the interface design by collecting feedback from driver users and conducting data analysis.

Images