Search device, search method, and program

Abstract

To provide a search device, a search method and a program for quickly finding a lost moving body.SOLUTION: A search device 10 comprises: an acquisition unit 11 for acquiring, from an unmanned aerial vehicle 20 that searches for a lost moving body 30, the radio wave intensity of a radio wave dispatched from a transmitter provided to the lost moving body 30 and the position and altitude at which the radio wave is received; a generation unit 12 for arranging colors to the coordinates of a map image that corresponds to the position in accordance with the radio wave intensity, and generating a visualization graph; and an estimation unit 13 for inputting the visualization graph to an estimation model and estimating the position of the lost moving body 30.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a search device, a search method, and a program for searching for a lost moving object.

Background Art

[0002] When a drone (such as a quadcopter) is lost, for example, when the drone crashes, the battery mounted on the drone may catch fire and cause a disaster. Therefore, when the drone crashes, it is necessary to quickly find the crashed drone and prevent the occurrence of a disaster.

[0003] Patent Document 1 discloses a technique for quickly identifying the position of a drone in order to ensure safety when an abnormality occurs in the drone. According to the technique of Patent Document 1, when an abnormality such as a crash of the drone is detected, a transmitter that wirelessly outputs a signal for identifying the position of the power storage device mounted on the drone is mounted.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the technique of Patent Document 1 wirelessly outputs a signal from the transmitter, but does not disclose a method for searching for the crashed drone. Therefore, the crashed drone cannot be quickly found, and the occurrence of a disaster cannot be prevented.

[0006] As one aspect, an object is to provide a search device, a search method, and a program for quickly searching for a lost moving object.

Means for Solving the Problems

[0007] To achieve the above object, in one aspect, a search device includes an acquisition unit that acquires, from an unmanned aircraft for searching for the lost mobile object, the radio wave intensity of a radio wave transmitted from a transmitter provided in the lost mobile object, and the position and altitude at which the radio wave is received; a generation unit that generates a visualization graph by performing color coding according to the radio wave intensity on the coordinates of a map image corresponding to the position; an estimation unit that inputs the visualization graph into an estimation model to estimate the position of the lost mobile object; and is characterized by having the above.

[0008] Also, to achieve the above object, in one aspect, a search method includes a step in which a computer acquires, from an unmanned aircraft for searching for the lost mobile object, the radio wave intensity of a radio wave transmitted from a transmitter provided in the lost mobile object, and the position and altitude at which the radio wave is received (acquisition step); a step in which the computer generates a visualization graph by performing color coding according to the radio wave intensity on the coordinates of a map image corresponding to the position (generation step); a step in which the computer inputs the visualization graph to estimate the position of the lost mobile object (estimation step); and is characterized by having the above.

[0009] Furthermore, to achieve the above object, in one aspect, a search method includes a step in which a computer acquires, from an unmanned aircraft for searching for the lost mobile object, the radio wave intensity of a radio wave transmitted from a transmitter provided in the lost mobile object, and the position and altitude at which the radio wave is received (acquisition step); a step in which the computer generates a visualization graph by performing color coding according to the radio wave intensity on the coordinates of a map image corresponding to the position (generation step); a step in which the computer inputs the visualization graph to estimate the position of the lost mobile object (estimation step); and is characterized by causing the above steps to be executed.

Advantages of the Invention

[0010] On the one hand, it is possible to quickly search for the lost moving object.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Modes for Carrying Out the Invention

[0012] First, an overview will be described to facilitate the understanding of the embodiments described hereinafter. (1) When communication interruption with the unmanned aircraft occurs due to the radio wave state around the unmanned aircraft, it is only known up to the position where communication with the unmanned aircraft was possible last.

[0013] (2) Depending on the type of the unmanned aircraft, there are some cases where the operator cannot grasp the position information indicating the position where the unmanned aircraft is flying. Therefore, when the unmanned aircraft crashes at a position where it cannot be visually observed, it is not known where the unmanned aircraft has crashed.

[0014] (3) If the GNSS (Global Navigation Satellite System) receiver is damaged when the unmanned aircraft crashes, the position of the unmanned aircraft cannot be estimated.

[0015] (4) Even if the GNSS receiver is not damaged, if the unmanned aircraft crashes in the shade of trees, mountains, etc., the positioning error will increase, so it is impossible to know where the unmanned aircraft has crashed.

[0016] (5) In the position estimation using the three-point positioning by distance conversion using the radio wave intensity transmitted from the lost unmanned aircraft, the estimation error is large.

[0017] Through the processes shown in (1) to (5) above, the inventor found that the lost unmanned aircraft could not be quickly searched for by the method described above, and at the same time, derived means to solve the related problems.

[0018] That is, the inventor derived means to receive the radio wave transmitted from the lost unmanned aircraft and identify the crash position of the lost drone based on the received radio wave intensity. As a result, the lost moving object can be quickly searched for.

[0019] Hereinafter, embodiments will be described with reference to the drawings. In the drawings described below, elements having the same function or corresponding functions are denoted by the same reference numerals, and repeated descriptions thereof may be omitted.

[0020] (Embodiment) The configuration of the search device in the embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram for explaining an example of the search device.

[0021] [Device Configuration] The search device 10 includes an acquisition unit 11, a generation unit 12, and an estimation unit 13. The search device 10 is, for example, an information processing device such as a central processing unit (CPU), a programmable device such as a field-programmable gate array (FPGA), a graphics processing unit (GPU), or a circuit equipped with one or more of these, a server computer, a personal computer, or a mobile terminal. The search device 10 may also have a function to operate the unmanned aerial vehicle 20.

[0022] The acquisition unit 11 acquires the radio wave intensity of the radio wave transmitted from a transmitter provided in the lost mobile body, and the position and altitude at which the radio wave was received, from an unmanned aerial vehicle for searching the lost mobile body.

[0023] A lost mobile object is a mobile object that has become unable to communicate due to a malfunction, accident, etc. The lost mobile object has a transmitter. Examples of the mobile object include an unmanned aerial vehicle, an autonomous vehicle, an autonomous ship, a robot, and a missing person search device.

[0024] A transmitter is a device that transmits radio waves at a constant intensity at regular intervals. The transmitter is mounted on a mobile object but operates separately from the mobile object. An example of a transmitter is a beacon device.

[0025] An unmanned aerial vehicle for searching for a lost mobile object flies based on a flight route for flying over an area in a preset search area where the lost mobile object is highly likely to be present, and stores the radio wave intensity of the radio wave transmitted from the lost mobile object and the position and altitude at which the radio wave was received in a storage unit mounted on the unmanned aerial vehicle.

[0026] The generation unit 12 generates a visualized graph by coloring the coordinates of the map image corresponding to the position where the radio wave was received according to the radio wave intensity.

[0027] The visualization graph is, for example, a graph in which, for each position where radio waves are received, the inside of a circle with a preset radius centered on the coordinates of the map image corresponding to the position is colored according to the radio wave intensity. Further, the visualization graph is, for example, a graph in which, for each coordinate of the map image corresponding to the position where radio waves are received, the color is set according to the radio wave intensity, and the coordinates of the same color are connected.

[0028] The estimation unit 13 inputs the visualization graph into an estimation model to estimate the position of the lost moving object.

[0029] The estimation model is generated by machine learning using at least the visualization graph as learning data during learning. For example, the estimation model is generated using a supervised learning method in which the correct position of the lost moving object corresponding to the visualization graph is learned.

[0030] Also, it is difficult to obtain actual accident data regarding the data. Therefore, for example, a visualization graph is generated using the installation of a beacon radio wave transmitter and a moving object such as a drone equipped with a receiver for the beacon.

[0031] For example, a beacon transmitter is installed at a position where the moving object is assumed to be lost, and an unmanned aircraft that receives the radio wave is flown for an experiment. By conducting experiments in various environments in this way, information on the visualization graph and the correct position that become learning data is generated. Further, a simulation may be executed based on the measured values obtained from this experiment to generate a pseudo-visualization graph.

[0032] By doing so, data (radio wave intensity, position and altitude where the radio wave is received) for specifying the position of the lost moving object 30 is collected, and the radio wave intensity situation can be visualized using the collected data. Therefore, based on the radio wave intensity situation, the lost moving object 30 can be quickly searched for.

[0033] Also, by inputting the visualization graph visualizing the radio wave intensity situation into a model for estimating the position of the lost moving object 30, the lost moving object 30 can be quickly searched for.

[0034] [System Configuration] Using FIG. 2, the configuration of the search system in the embodiment will be described. FIG. 2 is a diagram for explaining an example of the search system.

[0035] The search system 100 shown in FIG. 2 is a system that quickly locates a lost moving object 30 using a search device 10 and an unmanned aerial vehicle 20. In the following description, for simplicity of explanation, the case where there is one unmanned aerial vehicle 20 will be described, but actually, multiple unmanned aerial vehicles 20 may be used for the search.

[0036] The data collection method in the search system 100 will be described. First, the search device 10 sets a search area 32 (circular in the example of FIG. 2) based on the lost position 31 where communication with the lost moving object 30 has been lost and the state information representing the state of the lost moving object 30 obtained before communication with the lost moving object 30 was lost.

[0037] Next, the search device 10 divides the search area 32 according to the area of the search area 32 and sets a plurality of nodes 33 (rectangles in the example of FIG. 2).

[0038] Next, before the start of the search, the search device 10 calculates an expected degree (initial expected degree) that is the initial value set for each node 33 based on the lost position 31 and the moving direction of the lost moving object 30 before communication with the lost moving object 30 was lost.

[0039] Next, the search device 10 selects nodes based on the initial expected degree and uses the selected nodes to generate a flight route for the unmanned aerial vehicle 20. For example, a flight route is generated so that the unmanned aerial vehicle 20 flies over nodes with a high expected degree. When there are multiple unmanned aerial vehicles 20, a flight route is generated for each unmanned aerial vehicle 20.

[0040] Next, the unmanned aircraft 20 flies for data collection based on the flight route in order to search for the lost moving body 30. That is, the unmanned aircraft 20 flies to receive the radio waves transmitted from the transmitter provided in the lost moving body 30. Also, the unmanned aircraft 20 measures the position and altitude at which it is flying.

[0041] Next, after the unmanned aircraft 20 completes the data collection flight based on the flight route, when the search device 10 can obtain sufficient data for identifying the position of the lost moving body 30 from the position and altitude measured by the unmanned aircraft 20 and the radio wave intensity of the received radio waves, the search device 10 causes the unmanned aircraft 20 to return to the landing point. Note that it is determined that sufficient data has been collected when the number of nodes that can receive radio waves equal to or higher than the set radio wave intensity reaches a threshold or more and the search of the nodes around that node has been completed.

[0042] On the other hand, when the search device 10 cannot obtain sufficient data for identifying the position of the lost moving body 30 by the unmanned aircraft 20, the search device 10 adjusts the expected degree set for each of the nodes 33 based on the measured position and altitude and the radio wave intensity of the received radio waves.

[0043] Thereafter, the search device 10 selects nodes based on the adjusted expected degree, generates a new flight route using the selected nodes, and causes the unmanned aircraft 20 to fly again for data collection on the new flight route.

[0044] By doing so, sufficient data for identifying the position of the lost moving body 30 can be efficiently collected. However, the data collection method is not limited to the data collection method described above.

[0045] The search device will be described in detail. Using FIG. 3, the configurations of the search device 10 and the unmanned aircraft 20 in the embodiment will be described in detail. FIG. 3 is a diagram for explaining an example of the configuration of the search system.

[0046] The search device 10 includes an acquisition unit 11, a generation unit 12, an estimation unit 13, a search processing unit 14, an output information generation unit 15, and a communication unit 16. The search device 10 is also connected to an output device 40.

[0047] First, the acquisition unit 11 acquires, during flight or after flight, data (radio wave intensity, position and altitude at which the radio wave was received) collected by the unmanned aircraft 20 via the communication unit 16. Next, the acquisition unit 11 stores the data in a storage unit (not shown). Note that the storage unit may be provided inside the search device 10 or outside the search device 10.

[0048] FIG. 4 is a diagram for explaining an example of the data structure. The data shown in FIG. 4 is information in which the position and altitude at which the radio wave was received are associated with the radio wave intensity of the received radio wave.

[0049] For example, when receiving radio waves for each node 33 on the flight route, the position where the radio wave is received is at or near the center point of the node 33 that has been flown.

[0050] Also, when receiving radio waves a plurality of times at the same node 33, the radio wave intensity of all received radio waves, the position and altitude at which the radio wave was received may be associated and stored in the storage unit.

[0051] Also, when receiving radio waves a plurality of times at the same node 33, the center position of the node 33, the highest radio wave intensity within the node 33, and the altitude corresponding to the radio wave intensity may be associated and stored in the storage unit.

[0052] Alternatively, when receiving radio waves a plurality of times at the same node 33, the center position of the node 33, the average value of the radio wave intensities received within the node 33, and the average of the altitudes may be associated and stored in the storage unit. Note that the total value, median value, mode value, etc. of the radio wave intensities may also be used.

[0053] The generation unit 12 first acquires data from the acquisition unit 11. Further, the generation unit 12 acquires a map image of the search area 32 from the storage unit. The map image is a map image including the search area 32, and position coordinates are associated therewith.

[0054] Next, the generation unit 12 corrects the radio wave intensity based on the altitude. Since the altitude at which the unmanned aircraft 20 flies is not always constant, the change in radio wave intensity due to the reception altitude (distance) is corrected.

[0055] Next, the generation unit 12 sets a circle with a preset radius with the coordinates of the map image corresponding to the position where the radio wave is received as the center point, and performs color matching according to the radio wave intensity within the set circle to generate a visualization graph (for example, a heat map, etc.) (circle drawing process).

[0056] The radius is determined according to, for example, the size of the node 33. However, the setting of the radius is not limited to the size of the node, and it may be set based on other than the size of the node.

[0057] FIG. 5 is a diagram for explaining the visualization graph generated by the circle drawing process. In the example of FIG. 5, each of the nodes 33 where the unmanned aircraft 20 has flown is a graph with color matching according to the radio wave intensity. Note that the radio wave area 34 in FIG. 5 is the area of the radio wave transmitted by the lost moving object 30.

[0058] Further, the generation unit 12 performs color matching according to the radio wave intensity for each coordinate of the map image corresponding to the position where the radio wave is received, and connects the coordinates of the same color to generate a visualization graph (for example, a contour map, etc.) (contour drawing process).

[0059] FIG. 6 is a diagram for explaining the visualization graph generated by the contour drawing process. In the example of FIG. 6, each center point of the nodes 33 where the unmanned aircraft 20 has flown is a graph with color matching according to the radio wave intensity and the coordinates of the same color are connected. Also, in the example of FIG. 6, color matching is further performed according to the radio wave intensity.

[0060] The estimation unit 13 first acquires the visualization graph from the generation unit 12. Next, the estimation unit 13 inputs the acquired visualization graph into the estimation model to estimate the position of the lost moving body 30. Note that, in addition to the visualization graph, environmental information representing the state of the terrain, plants, buildings, etc. in the search area 32 may be input into the estimation model.

[0061] The search processing unit 14 first sets the search area 32 based on the lost position 31 where communication with the lost moving body 30 has become impossible and the state information representing the state of the lost moving body 30 acquired before communication with the lost moving body 30 became impossible.

[0062] Next, the search processing unit 14 divides the search area 32 according to the area of the search area 32 and sets a plurality of nodes 33.

[0063] Next, before the start of the search, the search processing unit 14 calculates the degree of expectation (initial degree of expectation), which is the initial value set for each node 33, based on the lost position 31 and the moving direction of the lost moving body 30 before communication with the lost moving body 30 became impossible.

[0064] Next, the search processing unit 14 selects nodes based on the initial degree of expectation and generates a flight route for the unmanned aircraft 20 using the selected nodes. For example, a flight route is generated so as to fly to nodes with a high degree of expectation. When there are a plurality of unmanned aircraft 20, a flight route is generated for each unmanned aircraft 20.

[0065] In addition, after the unmanned aircraft 20 has completed the data collection flight based on the flight route, if sufficient data for identifying the position of the lost moving body 30 has been acquired, such as the position and altitude measured by the unmanned aircraft 20 and the radio wave intensity of the received radio wave, the search processing unit 14 returns the unmanned aircraft 20 to the landing point.

[0066] On the other hand, when the search processing unit 14 cannot obtain sufficient data to identify the position of the moving body 30 lost by the unmanned aircraft 20, it adjusts the degree of expectation set for each node 33 based on the measured position and altitude and the radio wave intensity of the received radio wave.

[0067] After that, the search processing unit 14 selects nodes based on the adjusted degree of expectation, and generates a new flight route using the selected nodes. Then, the unmanned aircraft 20 is made to fly again for data collection along the new flight route.

[0068] The output information generation unit 15 generates output information for displaying, for example, a visualization graph, radio wave intensity, position, and altitude, and outputs the generated output information to the output device 40. The communication unit 16 communicates with the communication unit 25 of the unmanned aircraft 20 described later.

[0069] The output device 40 acquires the output information, which has been converted into an output - capable format by the output information generation unit 15 and described later, and outputs generated images, sounds, etc. based on the output information. The output device 40 is, for example, an image display device using liquid crystal, organic EL (Electro Luminescence), or CRT (Cathode Ray Tube). Further, the image display device may be provided with a sound output device such as a speaker. Note that the output device 40 may be a printing device such as a printer.

[0070] The configuration of the unmanned aircraft will be described in detail. The unmanned aircraft 20 is an unmanned aircraft for searching for the lost moving body 30. The unmanned aircraft 20 includes a receiving unit 21, a measuring unit 22, a control unit 23, an airframe unit 24, and a communication unit 25.

[0071] When the receiving unit 21 receives radio waves transmitted from a transmitter provided in the lost moving body 30, it stores the radio wave intensity of the received radio waves in the storage unit. When the unmanned aircraft for searching receives radio waves, the measuring unit 22 measures the position and altitude at which the radio waves are received.

[0072] When a flight route for flying in an area with a high probability of the presence of the lost mobile object is set in a preset search area, the control unit 23 controls the flight mechanism unit 24 to fly the unmanned aircraft 20 for searching.

[0073] When the flight of the flight route is completed, the control unit 23 returns the unmanned aircraft 20 to a preset landing point.

[0074] The flight mechanism unit 24 is a mechanism for flying the unmanned aircraft 20. The communication unit 25 communicates with the communication unit 17 of the search device 10.

[0075] [Device Operation] Next, the operations of the search device and the unmanned aircraft in the embodiment will be described with reference to FIG. 7. FIG. 7 is a diagram for explaining an example of the operation of the search device. In the following description, the drawings will be referred to as appropriate. In the embodiment, a search method is implemented by operating the search device and the unmanned aircraft. Therefore, the description of the search method in the embodiment will be replaced with the following description of the operations of the search device and the unmanned aircraft.

[0076] First, the acquisition unit 11 acquires, from the unmanned aircraft 20 for searching for the lost mobile object 30, the radio wave intensity of the radio wave transmitted from the transmitter provided in the lost mobile object 30, and the position and altitude at which the radio wave is received (step A1).

[0077] Specifically, in step A1, the acquisition unit 11 first acquires, during or after flight, the data (radio wave intensity of the radio wave, and the position and altitude at which the radio wave is received) collected by the unmanned aircraft 20 via the communication unit 16. Next, in step A1, the acquisition unit 11 stores the data in a storage unit (not shown).

[0078] Next, the generation unit 12 colors the coordinates of the map image corresponding to the position according to the corrected radio wave intensity to generate a visualization graph (step A2).

[0079] Specifically, in step A2, the generation unit 12 first acquires data from the acquisition unit 11. Also, in step A2, the generation unit 12 acquires a map image of the search area 32 from the storage unit.

[0080] Next, in step A2, the generation unit 12 corrects the radio wave intensity based on altitude. Since the altitude at which the unmanned aircraft 20 flies is not always constant, the change in radio wave intensity due to the reception altitude (distance) is corrected.

[0081] Next, in step A2, the generation unit 12 sets a circle with a preset radius with the coordinates of the map image corresponding to the position where the radio wave is received as the center point, and performs color coding according to the radio wave intensity within the set circle to generate a visualization graph (circle drawing process).

[0082] Alternatively, in step A2, the generation unit 12 performs color coding according to the radio wave intensity for each coordinate of the map image corresponding to the position where the radio wave is received, and connects the coordinates of the same color to generate a visualization graph (contour line drawing process).

[0083] Next, the estimation unit 13 inputs the visualization graph into the estimation model to estimate the position of the lost moving object (step A3).

[0084] Specifically, in step A3, the estimation unit 13 first acquires the visualization graph from the generation unit 12. Next, in step A3, the estimation unit 13 inputs the acquired visualization graph into the estimation model and estimates the position of the lost moving object 30.

[0085] Next, the output information generation unit 15 generates output information for displaying, for example, the visualization graph, radio wave intensity, position, and altitude, and outputs the generated output information to the output device 40 (step A4).

[0086] [Effects of the Embodiment] According to the embodiment as described above, data for specifying the position of the lost mobile object 30 (the radio field strength of radio waves, the position and altitude at which the radio waves are received) is collected, and the radio field strength situation can be visualized using the collected data. Therefore, based on the radio field strength situation, the lost mobile object 30 can be quickly searched for.

[0087] [Program] The program of the search device in the embodiment may be a program that causes a computer to execute steps A1 to A4 shown in FIG. 7. By installing and executing this program on a computer, the search device and the search method in Embodiment 1 can be realized. In this case, the processor of the computer functions as the acquisition unit 11, the generation unit 12, the estimation unit 13, the search processing unit 14, and the output information generation unit 15, and performs processing.

[0088] Also, the program of the search device in the embodiment may be executed by a computer system constructed by a plurality of computers. In this case, for example, each computer may function as any one of the acquisition unit 11, the generation unit 12, the estimation unit 13, the search processing unit 14, and the output information generation unit 15.

[0089] [Physical Configuration] Here, the computer that realizes the search device will be described with reference to FIG. 8 by executing the programs in Embodiments 1 to 3. FIG. 8 is a diagram for explaining an example of a computer that realizes the search device in the embodiment.

[0090] As shown in FIG. 8, the computer 110 includes a CPU (Central Processing Unit) 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. These components are connected to each other via a bus 121 so as to be capable of data communication with each other. Note that the computer 110 may include a GPU (Graphics Processing Unit) or an FPGA (Field-Programmable Gate Array) in addition to or instead of the CPU 111.

[0091] The CPU 111 expands the programs (codes) in the present embodiment stored in the storage device 113 into the main memory 112 and executes them in a predetermined order, thereby performing various operations. The main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory). Also, the programs in the present embodiment are provided in a state stored in a computer-readable recording medium 120. Note that the programs in the present embodiment may be distributed on the Internet connected via the communication interface 117. Note that the recording medium 120 is a non-volatile recording medium.

[0092] In addition, specific examples of the storage device 113 include semiconductor storage devices such as flash memories in addition to hard disk drives. The input interface 114 mediates data transmission between the CPU 111 and input devices 118 such as a keyboard and a mouse. The display controller 115 is connected to a display device 119 and controls the display on the display device 119.

[0093] The data reader / writer 116 mediates data transmission between the CPU 111 and the recording medium 120, and executes reading of a program from the recording medium 120 and writing of the processing result in the computer 110 to the recording medium 120. The communication interface 117 mediates data transmission between the CPU 111 and another computer.

[0094] Further, specific examples of the recording medium 120 include general-purpose semiconductor memory devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic recording media such as Flexible Disk, or optical recording media such as CD-ROM (Compact Disk Read Only Memory).

[0095] Note that the search device in the embodiment can also be realized by using hardware corresponding to each part instead of a computer in which a program is installed. Further, part of the search device may be realized by a program and the remaining part may be realized by hardware.

[0096] [Supplementary Note] Regarding the above embodiments, the following supplementary notes are further disclosed. Some or all of the above-described embodiments can be expressed by (Supplementary Note 1) to (Supplementary Note 12) described below, but are not limited to the following description.

[0097] (Supplementary Note 1) An acquisition unit that acquires the radio wave intensity of radio waves transmitted from a transmitter provided in a lost mobile object, and the position and altitude at which the radio waves are received, from an unmanned aircraft for searching for the lost mobile object; A generation unit that colors a map image coordinate corresponding to the position according to the radio wave intensity and generates a visualization graph; An estimation unit that inputs the visualization graph into an estimation model and estimates the position of the lost mobile object; A search device having the above.

[0098] (Supplementary Note 2) The search device according to Supplementary Note 1, wherein the estimation unit has an estimation model for estimating the position of the lost moving object, wherein the estimation model is generated by machine learning using the visualization graph as learning data during learning, Search device.

[0099] (Supplementary Note 3) The search device according to Supplementary Note 1 or 2, wherein the generation unit generates the visualization graph by circular drawing processing that colors a circle with a preset radius centered on the coordinates of the map image corresponding to the position where the radio wave is received according to the corrected radio wave intensity, Search device.

[0100] (Supplementary Note 4) The search device according to Supplementary Note 1 or 2, wherein the generation unit colors each coordinate of the map image corresponding to the position where the radio wave is received according to the corrected radio wave intensity, and generates the visualization graph by contour drawing processing that connects coordinates of the same color, Search device.

[0101] (Supplementary Note 5) A computer An acquisition step of acquiring the radio wave intensity of a radio wave transmitted from a transmitter provided in a lost moving object, and the position and altitude where the radio wave is received, from an unmanned aerial vehicle for searching for the lost moving object; A generation step of coloring the coordinates of the map image corresponding to the position according to the radio wave intensity and generating a visualization graph; An estimation step of inputting the visualization graph into an estimation model and estimating the position of the lost moving object; Search method having.

[0102] (Supplementary Note 6) The search method according to Supplementary Note 5, wherein an estimation model is used to estimate the position of the lost moving object, The estimation model generates, by machine learning using the visualization graph as learning data during learning. Search method.

[0103] (Appendix 7) The search method according to Appendix 5 or 6, The visualization graph is generated by circular drawing processing that colors the inside of a circle with a preset radius centered on the coordinates of the map image corresponding to the position where the radio wave was received according to the corrected radio wave intensity. Search method.

[0104] (Appendix 8) The search method according to Appendix 5 or 6, The visualization graph colors according to the corrected radio wave intensity for each coordinate of the map image corresponding to the position where the radio wave was received, and is generated by contour drawing processing that connects coordinates of the same color. Search method.

[0105] (Appendix 9) On a computer An acquisition step of acquiring, from an unmanned aerial vehicle for searching for the lost mobile object, the radio wave intensity of a radio wave transmitted from a transmitter provided on the lost mobile object, the position and altitude where the radio wave was received; A generation step of generating a visualization graph by coloring according to the radio wave intensity at the coordinates of the map image corresponding to the position; An estimation step of inputting the visualization graph into an estimation model to estimate the position of the lost mobile object; A program including instructions to execute.

[0106] (Appendix 10) The program according to Appendix 9, To estimate the position of the lost mobile object, an estimation model is used, The estimation model is generated by machine learning using the visualization graph as learning data during learning. Program.

[0107] (Appendix 11) The program according to Appendix 9 or 10, wherein the visualization graph is generated by circular drawing processing that colors a circle with a preset radius centered on the coordinates of the map image corresponding to the position where the radio wave was received according to the corrected radio wave intensity. Program.

[0108] (Appendix 12) The program according to Appendix 9 or 10, wherein the visualization graph is generated by contour drawing processing that colors according to the corrected radio wave intensity for each coordinate of the map image corresponding to the position where the radio wave was received and connects the coordinates of the same color. Program.

[0109] Although the present invention has been described with reference to the embodiments above, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

Industrial Applicability

[0110] As described above, according to the present invention, a lost moving object can be quickly found. The present invention is useful in the field of searching for lost moving objects.

Explanation of Signs

[0111] 10 Search device 11 Acquisition unit 12 Generation unit 13 Estimation unit 14 Search processing unit 15 Output information generation unit 16 Communication unit 20 Unmanned aerial vehicle 21 Receiver 22 Measurement unit 23 Control unit 24 Flight mechanism unit 25 Communication unit 30 Moving object 40 Output device 100 Search System 110 Computer 111 CPU 112 Main Memory 113 Storage Device 114 Input Interface 115 Display Controller 116 Data Reader / Writer 117 Communication Interface 118 Input Device 119 Display Device 120 Recording Medium 121 Bus

Claims

**Claim 1**: Acquisition means for acquiring, from an unmanned aircraft for searching for the lost mobile object, the radio wave intensity at the position where the radio wave transmitted from the transmitter provided in the lost mobile object is received in the flight route, and the position and altitude where the radio wave is received. Generation means for correcting the radio wave intensity based on the altitude, coloring according to the corrected radio wave intensity at the coordinates of the map image corresponding to the position, and generating a visualization graph. Estimation means for inputting the visualization graph into an estimation model and estimating the position of the lost mobile object. A search device having the above. **Claim 2** The search device according to claim 1, wherein the estimation means has an estimation model for estimating the position of the lost mobile object, and the estimation model is generated by machine learning using the visualization graph as learning data during learning. Search device. **Claim 3** The search device according to claim 1 or 2, wherein the generation means generates the visualization graph by circular drawing processing of coloring within a circle with a preset radius centered on the coordinates of the map image corresponding to the position where the radio wave is received according to the corrected radio wave intensity. Search device. **Claim 4** The search device according to claim 1 or 2, wherein the generation means generates the visualization graph by contour drawing processing of coloring according to the corrected radio wave intensity for each coordinate of the map image corresponding to the position where the radio wave is received and connecting the coordinates of the same color. Search device. **Claim 5** A computer acquires, in the flight route, the radio wave intensity at the position where the radio wave transmitted from the transmitter provided in the lost mobile object is received, and the position and altitude where the radio wave is received, from an unmanned aircraft for searching for the lost mobile object, corrects the radio wave intensity based on the altitude, colors according to the corrected radio wave intensity at the coordinates of the map image corresponding to the position, and generates a visualization graph, inputs the visualization graph and estimates the position of the lost mobile object. Search method. **Claim 6** The search method according to claim 5, wherein an estimation model is used to estimate the position of the lost mobile object, and the estimation model is generated by machine learning using the visualization graph as learning data during learning. Search method. **Claim 7** The search method according to claim 5 or 6, The visualization graph is generated by a circular drawing process in which a circle with a preset radius centered on the coordinates of the map image corresponding to the position where the radio wave is received is colored according to the corrected radio wave intensity. Search method. **Claim 8** The search method according to claim 5 or 6, wherein the visualization graph is colored according to the corrected radio wave intensity for each coordinate of the map image corresponding to the position where the radio wave is received, and is generated by a contour drawing process that connects coordinates of the same color. Search method. **Claim 9** A program for a computer to cause a drone for searching for the lost mobile object to obtain the radio wave intensity at the position where the radio wave transmitted from a transmitter provided in the lost mobile object is received in a flight route, and the position and altitude where the radio wave is received, correct the radio wave intensity based on the altitude, color the coordinates of the map image corresponding to the position according to the corrected radio wave intensity, and generate a visualization graph, and input the visualization graph to estimate the position of the lost mobile object. Program including the command. **Claim 10** The program according to claim 9, wherein an estimation model is used to estimate the position of the lost mobile object, and the estimation model is generated by machine learning using the visualization graph as learning data during learning. Program.

Images