System and method for estimating position of flying vehicle

Abstract

To provide a system for estimating the position of a flying vehicle and a method for estimating the position of a flying vehicle, with which the estimation accuracy of a current position of a flying vehicle is improved so that the flying vehicle can fly stably for a long time.SOLUTION: A system 20 for estimating the position of a flying vehicle estimates a current position of a current flying vehicle 10 by executing a machine learning algorithm N, using time series data related to the flying vehicle 10 flying in a predetermined flight zone as input values. The machine learning algorithm N is composed of an input cross-attention layer C1, a self-attention layer S, and an output cross-attention layer C2, and uses first array data D1 as time series data being the input values. Further, the machine learning algorithm has a function for generating second array data D2 by reconstructing the first array data D1 based on a prescribed weighting factor.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a system and method for estimating the position of an aircraft, and more particularly to a system and method for estimating the position of an aircraft that improves the accuracy of estimating the current position of the aircraft and enables the aircraft to fly stably for a long period of time. [Background technology]

[0002] In order to ensure safety during autonomous flight, unmanned aerial vehicles such as unmanned airplanes and drones need to acquire their current position in real time during flight. To acquire the current position of an unmanned aerial vehicle, for example, a method is adopted in which a GPS device mounted on the unmanned aerial vehicle receives a GPS signal sent from an artificial satellite, or a method is adopted in which a flight route from a starting point is calculated by synthesizing a vector of a travel distance and a direction for each subdivision point based on an inertial navigation device such as an acceleration sensor or a gyro sensor mounted on the unmanned aerial vehicle.

[0003] However, GPS devices cannot obtain stable position information in environments where GPS signals are difficult to receive, such as under bridges or inside buildings. Inertial navigation systems also have a large accumulation of errors over the distance traveled, limiting the flight distance over which they can maintain safe flight.

[0004] Therefore, to fly an unmanned aerial vehicle safely for a long time in such an environment, a human must visually monitor the unmanned aerial vehicle during flight. Also, when autonomous flight or automatic control is difficult, it is necessary to switch to manual remote control to assist the flight. However, human monitoring and control imposes a heavy burden and can cause serious accidents due to oversight or piloting errors caused by human error. Therefore, various technologies have been proposed to enable the accurate current position of an unmanned aerial vehicle to be obtained.

[0005] For example, Patent Document 1 discloses a system that grasps the current flight position based on an object captured by an imaging device mounted on an unmanned aerial vehicle. Specifically, a reference object captured at a reference position and a measured object captured at a measured position are compared, and the current position of the aircraft is estimated by detecting the three-dimensional displacement of the measured position from the reference position based on the two-dimensional position deviation and the three-dimensional angle deviation. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent Publication No. 2020-176961 Summary of the Invention [Problem to be solved by the invention]

[0007] According to Patent Document 1, it is possible to determine the aircraft's flight position even in environments where GPS signals are difficult to receive, and since there are no errors associated with the distance traveled, as occurs with inertial navigation systems, it is possible to always stably determine the aircraft's position even during long flights.

[0008] However, when acquiring the flight position of the drone based on the image captured by the imaging device, calculations for image processing are required, which increases the calculation load and time, and accordingly increases the battery consumption of the drone, limiting the flight time.

[0009] The present invention has been devised in consideration of the above points, and aims to provide an aircraft position estimation system and aircraft position estimation method that improve the estimation accuracy of the current position of an aircraft, and enable the aircraft to fly stably for long periods of time. [Means for solving the problem]

[0010] In order to achieve the above-mentioned objective, the aircraft position estimation system of the present invention comprises a communication unit capable of receiving time series data regarding an aircraft flying in a specified area via wireless communication, and an estimation unit that estimates the current flight position of the aircraft by executing a specified machine learning algorithm using the time series data received by the communication unit as input values.

[0011] Here, by providing a communication unit capable of receiving time series data regarding an aircraft flying in a specified area via wireless communication, it is possible to receive time series data indicating the flight status of the aircraft via wireless communication.

[0012] In addition, by providing an estimation unit that estimates the current flight position of the aircraft by executing a predetermined machine learning algorithm using the time series data received by the communication unit as input values, the current position of the aircraft can be accurately determined with little computational load based on past learned data.

[0013] In addition, when the estimation unit generates sequence data by reconstructing the time series data based on a predetermined weighting coefficient, the estimation unit can reconstruct the time series data as sequence data that requires attention for estimating the current position of the aircraft.

[0014] In addition, when the estimation unit has an input layer that generates first sequence data in which input values ​​are compressed based on a predetermined weighting coefficient, the input values ​​can be compressed into sequence data in which features are extracted from the time series data of the aircraft, so there is no need to calculate interactions between all times in the time series data, and the amount of memory and calculation required for calculation can be reduced.

[0015] Furthermore, when the estimation unit has an intermediate layer that reconstructs the first sequence data to generate the second sequence data, the estimation unit can further optimize noteworthy time series data among the first sequence data compressed in the input layer. More specifically, the estimation unit can learn correlations between time series data included in the first sequence data and reconstruct the time series data into highly correlated time series data.

[0016] Furthermore, when the estimation unit has an output layer that converts the second array data into output values ​​of the same size as the input values, the estimation unit can output the time series data compressed in the input layer as time series data that is the same size as the input values ​​and that is characterized by learning. Then, the current position of the flying object can be accurately estimated based on the time series data output by the output layer.

[0017] In addition, when the input layer and the output layer each perform a cross-attention process using the cross-attention mechanism once, the input layer can first compress the input value to data of a predetermined size to reduce the computational load of the machine learning algorithm, and the output layer can output the learned data by the machine learning algorithm as time-series data of the original size.

[0018] In addition, when the intermediate layer performs self-attention processing using a self-attention mechanism multiple times, the intermediate layer can optimize the time series data by repeating the self-attention processing and capture the characteristic data necessary to estimate the current position of the aircraft, thereby improving the accuracy of estimating the current position of the aircraft.

[0019] In addition, when the input layer generates the first array data by mapping a byte array based on the input value with a latent array having a smaller number of data than the byte array, the input layer can compress the time series data into array data characterized based on the latent array determined by random numbers.

[0020] In addition, when the wireless communication is of the LPWA (Low power wide area) type, LPWA is a long-distance data communication method with low power consumption, so battery consumption when sending and receiving data with the aircraft is low, and the flight time and distance of the aircraft can be extended.

[0021] Furthermore, if the time series data includes the roll angle, pitch angle, yaw angle, and altitude of the aircraft, the current position of the aircraft can be accurately estimated based on these parameters.

[0022] In addition, when the machine learning algorithm is a perceiver or a transformer, it can learn long-term dependencies for long-term time-series data without being affected by past learning data. Furthermore, by adopting a perceiver, it is possible to reduce the computation load.

[0023] In order to achieve the above-mentioned object, the position estimation method for an aircraft of the present invention comprises the steps of receiving time series data regarding an aircraft flying in a specified area via wireless communication, and estimating the current position of the aircraft by executing a specified machine learning algorithm using the received time series data as input values.

[0024] Through the above steps, the time series data of the aircraft can be used as input values, and the current position of the aircraft can be accurately determined based on the learned data with a small computational load.

[0025] Furthermore, the present position of the aircraft is compared with a predetermined flight route, and if the present position of the aircraft deviates from the flight route, the aircraft is controlled autonomously or by an external control signal to return to the flight route, thereby enabling the aircraft to always fly along the correct flight route. Effect of the Invention

[0026] The aircraft position estimation system and aircraft position estimation method according to the present invention improve the accuracy of estimating the current position of the aircraft, enabling the aircraft to fly stably for long periods of time. [Brief description of the drawings]

[0027] [Figure 1] 1 is a schematic diagram of an entire network configuration including an aircraft position estimation system according to an embodiment of the present invention. [Diagram 2] 2 is a block diagram showing the hardware configuration of an aircraft according to an embodiment of the present invention. FIG. [Diagram 3] FIG. 2 is a block diagram showing a hardware configuration of an estimation unit according to the embodiment of the present invention. [Figure 4] FIG. 1 is a schematic diagram of a machine learning model applied in a location estimation system. [Diagram 5] 3 is a flow chart showing a position estimation flow of an aircraft according to an embodiment of the present invention. [Figure 6] In an embodiment of the present invention, (a) is an autopilot program for an aircraft, and (b) is time-series data acquired by the aircraft. [Figure 7] 13 is a result of outputting arguments for an autopilot program from time-series data in an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] Hereinafter, a position estimation system for an aircraft and a position estimation method for an aircraft according to an embodiment of the present invention will be described in detail with reference to the drawings etc. for the purpose of understanding the present invention.

[0029] 1 is a schematic diagram of an entire network configuration according to an embodiment of the present invention. In this embodiment, an aircraft 10 flies within an LPWA (Low power wide area) network, and the aircraft 10 and a position estimation system 20 can communicate with each other through a network 40 via an LPWA gateway 30.

[0030] An LPWA network is a network that uses specific low-power radio stations as base stations, and standards such as SIGFOX, LoRa (LoRa WAN), Wi-Fi HaLow, Wi-SUN, RPMA, Flexnet, IM920, Cat.M1, and Cat.NB1 can be applied as appropriate.

[0031] The communication method between the aircraft 10 and the position estimation system 20 is not necessarily limited to LPWA, and may be appropriately selected from known communication methods. However, LPWA is a long-distance data communication method with low power consumption, and since the battery consumption of the aircraft 10 is small when transmitting and receiving data between the aircraft 10 and the position estimation system 20, the flight time and flight distance of the aircraft 10 can be extended.

[0032] [Flying object] The flying object 10 of this embodiment is an unmanned flying object that flies by remote control or automatic piloting, such as a drone, a multicopter, an unmanned aerial vehicle, etc. As shown in the block diagram of FIG. 2, the flying object 10 is composed of a communication unit 11, a data processing unit 12, a sensor unit 13, and a flight control unit 14.

[0033] The communication unit 11 has the function of connecting the aircraft 10 to an LPWA network and transmitting and receiving data and control signals to and from the position estimation system 20 via the network 40.

[0034] The sensor unit 13 is a sensor for detecting the flight state of the flying object 10, and mainly includes a roll sensor 131 for measuring angular velocity in the roll direction, a pitch sensor 132 for measuring angular velocity in the pitch direction, a yaw sensor 133 for measuring angular velocity in the yaw direction, and an altitude sensor 134 for measuring altitude, and while the flying object 10 is flying, the sensor unit 13 measures time series data related to the flight of the flying object 10. The time series data measured by the sensor unit 13 is input to the data processing unit 12, where various processes are executed and the data is output from the communication unit 11 to the position estimation system 20.

[0035] The flight control unit 14 outputs a control signal to the power mechanism of the aircraft 10 in order to fly the aircraft 10 according to a predetermined flight route. In addition, in the event of an abnormal situation in which the aircraft 10 needs to make an emergency landing due to a system failure or a cyber attack, or in the event that the aircraft 10 deviates from the flight route and needs to be returned to the correct flight route, the flight control unit 14 has a function of outputting a control signal to the power mechanism based on an external control signal.

[0036] [Location Estimation System] The position estimation system 20 has a function of estimating the current position of the aircraft 10 based on time series data related to flight transmitted from the aircraft 10 flying in the flight area. The position estimation system 20 is composed of a computer device having a CPU, memory, etc., and as shown in the block diagram of Fig. 3, is composed of a communication unit 21 that receives radio waves, an estimation unit 22 that estimates the current position of the aircraft 10 based on a machine learning model using the time series data of the aircraft received by the communication unit 21 as input values, and a learning unit 23 that learns the machine learning model based on teacher data stored in a memory unit 24.

[0037] The machine learning model N applied in the estimation unit 22 of an embodiment of the present invention is a mathematical model that predicts the current position of the aircraft 10 using the time series data of the aircraft 10 as input values, and specifically, the machine learning model uses a perceiver.

[0038] Here, the machine learning model N applied in the estimation unit 22 is not necessarily limited to a perceiver, but can be appropriately selected from known machine learning models such as a long short-term memory model (LSTM), a convolutional neural network (CNN), or a transformer.

[0039] However, when using time series data of the aircraft 10 as input values ​​as in the present invention, it is possible that the flight direction of the aircraft 10 may change after a long period of time has passed, so it is preferable to select a machine learning model that can capture long-term dependencies and has a low computational load.

[0040] In this regard, LSTM is heavily influenced by the past, so it cannot capture long-term dependencies, resulting in large errors in output values, and the amount of calculation required is also enormous, requiring a large amount of memory. CNN also captures local events and is not suitable for capturing long-term dependencies. On the other hand, transformers are less likely to produce errors like LSTM and CNN, but they calculate all interactions in the input time series data, so they require a large amount of memory and calculations when dealing with long-term time series data.

[0041] In contrast, the basic concept of the machine learning model of the Perceiver is similar to that of the Transformer, but since the Perceiver calculates the interactions of compressed time series data, it does not require a large amount of memory or calculation compared to the Transformer even if the time series data becomes long. Therefore, it is preferable to apply the Perceiver from the viewpoint of capturing long-term dependencies and reducing the calculation load.

[0042] 4 is a schematic diagram for explaining the machine learning model N applied in the embodiment of the present invention. The machine learning model N has a function of using time series data measured by the sensor unit 13 of the aircraft 10 as input values, reconstructing this time series data based on a predetermined weighting coefficient to generate sequence data, and is composed of an input cross attention layer C1 which is an input layer, a self attention layer S which is an intermediate layer, and an output cross attention layer C2 which is an output layer.

[0043] The input cross-attention layer C1 is an input layer in which a known cross-attention mechanism is executed, and functions as an encoder that encodes input data. As described above, the input cross-attention layer C1 receives time-series data measured by the sensor unit 13 of the aircraft 10 as input values. This time-series data is data arranged in a time series obtained by extracting data from a certain time interval using a window function. In this embodiment, for example, 30-minute time-series data can be expressed as 18,000 x 37 matrix data.

[0044] When time series data is input to the input cross attention layer C1, the interaction of the time series data is calculated based on the latent array L (abstract array data consisting of random numbers in which the features of the time series data are embedded) to extract features of the time series data. The input cross attention layer C1 repeatedly extracts time series data and stores it in the latent array L as necessary, thereby learning the latent array L. In this embodiment, this latent array L is 256 x 128 matrix data, but the size of the latent array L can be changed as appropriate.

[0045] Then, the first sequence data D1 is generated, which is compressed in a predetermined manner based on the extracted feature amount. That is, the time-series data consisting of a predetermined byte sequence is mapped with a latent sequence L having a smaller number of data than the byte sequence, thereby generating the first sequence data D1 in which the time-series data is compressed.

[0046] The self-attention layer S is an intermediate layer where a known self-attention mechanism is executed, and further optimally encodes the data to be focused on among the first array data D1. Specifically, the interaction of the first array data D1 is calculated, and weighting coefficients are calculated based on the similarity between which parts need to be strengthened to obtain correct output data, and the optimal solution is derived as the weighted average.

[0047] Then, the second sequence data D2 is generated by optimizing the first sequence data D1 in the self-attention layer S. Note that in order to estimate the current position of the flying object 10, it is necessary to calculate the moving direction of the flying object 10 and the flight distance from the starting point. As a result of self-attention, the correlation between the time series data of the starting point and the end point of the traveling direction of the flying object 10 is generally high.

[0048] The output cross-attention layer C2 is an output layer in which a known cross-attention mechanism is executed like the input cross-attention layer C1, and functions as a decoder that outputs the second array data D2 generated in the self-attention layer S as output data of the original size. That is, the output cross-attention layer C2 decodes the second array data D2 in which the features obtained by learning are emphasized, to the same size as the time-series data that is the input value.

[0049] In the embodiment of the present invention, the cross-attention processing in the input cross-attention layer C1 and the output cross-attention layer C2 is performed once each, and the self-attention processing in the self-attention layer S is performed 12 times.

[0050] The number of times each calculation process is performed is not necessarily limited to the above. In particular, the number of times the process is performed in the self-attention mechanism for capturing features in time-series data can be changed as appropriate depending on the type and size of the time-series data from which features should be captured.

[0051] The learning unit 23 learns the machine learning model using the teacher data. Specifically, the weighting coefficients in the machine learning model are repeatedly updated by, for example, a known backpropagation method, so that the difference between the output value of the machine learning model and the actual measured value of the output parameter is reduced using a large amount of teacher data. As a result, the machine learning model is learned, and a trained machine learning model is generated. Information on the trained machine learning model (such as the model structure and weighting coefficients) is stored in the storage unit 24 in the position estimation system 20, and is used as the machine learning model in the estimation unit 22 from the next time onwards.

[0052] Next, a flow of estimating the position of the flying object 10 executed by the position estimation system 20 will be described with reference to FIG.

[0053] First, when the position estimation system 20 receives time series data acquired by the sensor unit 13 of the aircraft 10, the estimation unit 22 calculates the features of the time series data from the interactions of the time series data based on the latent array L in the input cross-attention layer C1 (STEP 1), and generates first array data D1 that has been compressed to a predetermined size (STEP 2).

[0054] Next, the first sequence data D1 is input to the self-attention layer S, and the self-attention mechanism is executed (STEP 3). In the calculation in this self-attention layer, as described above, the interaction of the first sequence data D1 is calculated, a weighting coefficient based on the similarity is calculated, and an optimal solution is derived as the weighted average. Then, the second sequence data D2 is generated by optimizing the first sequence data D1 (STEP 4).

[0055] The second array data D2 generated in STEP 4 is decoded in the output cross-attention layer C2 to the same size as the time-series data of the input values ​​(STEP 5), and the current position of the aircraft 10 is estimated based on the output data.

[0056] The current position of the flying body 10 estimated by the estimation unit 22 is then compared with the predetermined flight route, and if the current position of the flying body 10 is flying along the flight route, no special instructions are given to the flying body 10, allowing it to continue flying as is. On the other hand, if the flying body 10 has deviated from the flight route, a control signal is sent to the flying body 10 to return to the flight route. Having received the control signal, the flying body 10 outputs a control signal from the flight control unit 14 to the power mechanism of the flying body 10, allowing the flying body 10 to autonomously return to the flight route.

[0057] Next, an embodiment of the present invention will be described. First, Fig. 6(a) shows a Python program for automatic control of the aircraft 10. This program shows that (1) it rises 5 meters after takeoff, (2) it remains stationary for 10 seconds, and then (3) it moves west at a speed of 5 meters per second for 2 seconds.

[0058] Figure 6(b) shows time series data measured by the aircraft 10 that flew according to this program. In this embodiment, in order to estimate the current position of the aircraft 10, a perceiver is used as a machine learning model to infer the values ​​of arguments of the autopilot program from the time series data. To this end, the output of the machine learning model in Figure 4 is configured to be a multivariate linear regression model.

[0059] Figure 7 shows the results of outputting arguments for an autopilot program from time-series data using the Hugging Face perceiver code. The values ​​enclosed in white frames are the correct value (top) and the calculated result (bottom). We can see that the error in the calculated result is a few percent.

[0060] As described above, the aircraft position estimation system and aircraft position estimation method to which the present invention is applied improves the estimation accuracy of the aircraft's current position, enabling the aircraft to fly stably for long periods of time. [Explanation of symbols]

[0061] 10 Flying Objects 11 Communications Department 12 Data Processing Section 13 Sensor section 131 Roll sensor 132 Pitch Sensor 133 Yaw sensor 134 Altitude Sensor 14 Flight control unit 20 Location Estimation System 21 Communications Department 22 Estimation part 23 Learning Department 24 Memory section 30 LPWA Gateway 40 Network N Machine Learning Models D1 First array data D2 Second array data L latent array C1 Input Cross Attention Layer C2 Output Cross Attention Layer S Self-attention layer

Claims

1. A communication unit capable of receiving time series data related to an aircraft flying in a predetermined area via wireless communication; and an estimation unit that estimates a current flight position of the aircraft by executing a predetermined machine learning algorithm using the time series data received by the communication unit as an input value. Aircraft position estimation system.

2. The estimation unit is The time series data is reconstructed based on a predetermined weighting coefficient to generate sequence data. The position estimation system for an air vehicle according to claim 1 .

3. The estimation unit is an input layer that generates first array data by compressing the input values ​​based on a predetermined weighting coefficient; an intermediate layer that reconstructs the first sequence data to generate second sequence data; an output layer that converts the second array data into an output value having the same size as the input value; 3. The position estimation system for an aircraft according to claim 1 or 2.

4. The input layer and the output layer each perform a cross-attention process using a cross-attention mechanism once; The intermediate layer performs a self-attention process using a self-attention mechanism multiple times. The position estimation system for an aircraft according to claim 3 .

5. The input layer generates the first array data by mapping a byte array based on the input value with a latent array having a smaller number of data than the byte array. The position estimation system for an aircraft according to claim 3 .

6. The wireless communication is a low power wide area (LPWA) system.

3. The position estimation system for an aircraft according to claim 1 or 2.

7. The time series data includes a roll angle, a pitch angle, a yaw angle, and an altitude of the aircraft.

3. The position estimation system for an aircraft according to claim 1 or 2.

8. The machine learning algorithm is a perceiver or a transformer.

3. The position estimation system for an aircraft according to claim 1 or 2.

9. receiving time series data relating to an aircraft flying in a predetermined area via wireless communication; and executing a predetermined machine learning algorithm using the received time series data as an input value to estimate a current position of the aircraft. A method for estimating the position of an aircraft.

10. The step of estimating a current position of the flying object includes: generating first array data by compressing the input values ​​based on a predetermined weighting coefficient; reconstructing the first sequence data to generate second sequence data; converting the second array data into an output value having the same size as the input value; The method for estimating the position of an aircraft according to claim 9.

11. the step of generating the first array data and the step of converting the first array data into an output value are each performed once by a cross-attention process using a cross-attention mechanism; the step of generating the second array data includes performing a self-attention process using a self-attention mechanism a plurality of times; The method for estimating the position of an aircraft according to claim 10.

12. The step of generating the first array data includes: Mapping a byte array determined by the input value with a latent array that has a smaller number of data than the byte array. The method for estimating the position of an aircraft according to claim 9 or 10.

13. Comparing the current position of the aircraft with a predetermined flight route; and when the current position of the flying object deviates from the flight route, controlling the flying object by autonomous control or by an external control signal so as to return to the flight route. The method for estimating the position of an aircraft according to claim 9 or 10.

Images