Maritime search and rescue route planning method, device and program product

Abstract

The application provides a maritime search and rescue path planning method, device and program product, the method comprising: S1, receiving position information of a search and rescue signal, and establishing a two-dimensional grid map of a region where the position information is located; S2, quantifying sea water flow information and maritime environment information in the two-dimensional grid map into corresponding grade values, accumulating the two grade values to obtain a comprehensive environment influence value of the two-dimensional grid, and dividing the two-dimensional grid map into search and rescue regions with different priorities according to a predetermined corresponding relationship; S3, planning a search and rescue path according to the priorities by using a corresponding search and rescue path planning algorithm; S4, after an unmanned ship carrying a UAV reaches the position of the search and rescue signal, carrying out search and rescue according to the search and rescue path; and S5, when a target detected by the UAV is greater than a predetermined detection confidence, the unmanned ship reaches the position of the target to carry out secondary confirmation. By using the above technical scheme, the efficiency and success rate of maritime search and rescue are significantly improved, and the performance is outstanding in a complex environment in the middle and far seas.

Description

Technical Field

[0001] The present invention relates to the field of maritime rescue technology, and in particular to a maritime search and rescue path planning method, device and program product. Background Art

[0002] Traditional drone-based maritime search and rescue solutions are limited by their limited endurance and are unable to cope with search and rescue missions in the middle and distant seas. In addition, the complex and changeable weather at sea can easily lead to false alarms or missed detections, reducing the efficiency and accuracy of search and rescue. Moreover, current drone path planning strategies mainly focus on full coverage of the search and rescue area, while ignoring the impact of maritime environmental factors such as wind direction and ocean currents on the target's movement trajectory. Traditional planning methods do not specifically consider the particularity of maritime search and rescue scenarios, resulting in low search and rescue efficiency in actual operations and an inability to effectively track the target's position that changes over time.

[0003] In recent years, advances in unmanned technology have enabled drones and unmanned ships to be used in mid- and long-distance sea search and rescue. Drones, with their high maneuverability and wide sensing range, have obvious advantages in rapid search and coverage of large sea areas. However, their endurance and wind resistance are limited. Although unmanned ships have strong endurance and can perform missions deep into mid- and long-distance seas, their relatively limited sensing capabilities make it difficult for them to independently complete accurate search and rescue in complex environments. Therefore, a new method for maritime search and rescue is needed to reduce the probability of false alarms and improve detection accuracy. Summary of the Invention

[0004] The embodiments of the present invention provide a method, device and program product for maritime search and rescue path planning, which aim to improve the efficiency and success rate of maritime search and rescue in complex environments in medium and long-distance sea areas by combining the advantages of drones and unmanned ships.

[0005] In order to achieve the above object, on the one hand, a method for maritime search and rescue path planning is provided, the method comprising the following steps:

[0006] S1, receiving the location information of the search and rescue signal, establishing a two-dimensional grid map of the search and rescue area where the location information is located, and marking the area to be searched and rescued in the two-dimensional grid map according to map information;

[0007] S2, according to a pre-set quantization method, quantize the seawater flow information in the area to be searched and rescued and the marine environment information in the area to be searched and rescued into corresponding seawater flow level values ​​and marine environment level values, accumulate the seawater flow level values ​​and the marine environment information level values ​​of the two-dimensional grid in the area to be searched and rescued to obtain the comprehensive environmental impact value of the two-dimensional grid in the area to be searched and rescued, and divide the two-dimensional grid in the area to be searched and rescued into search and rescue areas of different priorities according to the corresponding relationship between the pre-set comprehensive environmental impact value and the search and rescue area priority, wherein the search and rescue areas of different priorities include: a first-level search and rescue area, a second-level search and rescue area and a third-level search and rescue area; wherein the seawater flow information includes seawater flow velocity; and the seawater environment information includes wind force;

[0008] S3, planning a search and rescue path using a corresponding search and rescue path planning algorithm according to the priority of the search and rescue area; wherein, the maximum probability path planning algorithm is used for the first-level search and rescue area, and the area coverage path planning algorithm combined with A* is used for the second-level search and rescue area and the third-level search and rescue area;

[0009] S4, after the unmanned boat carrying the drone arrives at the location of the search and rescue signal, searching and rescuing the area to be searched and rescued according to the search and rescue path planned by the search and rescue path planning algorithm;

[0010] S5. When the target detected by the drone is greater than the preset drone detection confidence level, the unmanned boat arrives at the location of the target for secondary confirmation. If the unmanned boat confirms that the target is the target to be searched and rescued, it tracks the target to be searched and rescued and sends the location of the target to be searched and rescued to the rescue center in real time; wherein, the drone detection confidence level is pre-set according to different weather conditions.

[0011] Preferably, in the maritime search and rescue path planning method, the UAV detection confidence is related to the sea wind speed, visibility and sea temperature.

[0012] Preferably, in the maritime search and rescue path planning method, in step S1:

[0013] The scope of the search and rescue area is: a square search and rescue area with a side length of R and a starting center point at the location of the search and rescue signal, wherein the side length R represents the maximum distance that the drone or drone group can effectively search;

[0014] The two-dimensional grid is established with the longitude and latitude of the location of the search and rescue signal as the coordinate origin and the effective detection range of the drone as the size, wherein the effective detection range of the drone is related to the visibility of the drone, and the visibility of the drone is affected by weather factors at sea;

[0015] The step S1 further includes: marking the unnecessary search areas in the two-dimensional grid map according to map information; the unnecessary search areas include islands and land.

[0016] Preferably, in the maritime search and rescue path planning method, in step S2:

[0017] The seawater flow information and the seawater environment information are both quantified into a multi-level scale, wherein the multi-level scale includes positive values, negative values, and / or zero values, wherein a negative value in the multi-level scale indicates a direction downstream or downwind of the search and rescue starting point; a positive value in the multi-level scale indicates an upstream or upwind direction of the search and rescue starting point; and a zero value in the multi-level scale indicates no seawater flow or wind force;

[0018] The corresponding relationship between the comprehensive environmental impact value and the search and rescue area priority is:

[0019] When the magnitude of the comprehensive environmental impact value indicates that the corresponding area is affected by the downwind direction and the downstream seawater flow, and satisfies a predetermined first condition, the corresponding area is a first-level search and rescue area;

[0020] When the magnitude of the comprehensive environmental impact value indicates that the seawater flow and wind force impact on the corresponding area meets the predetermined second condition, the corresponding area is a secondary search and rescue area;

[0021] When the magnitude of the comprehensive environmental impact value indicates that the impact of the upward wind direction and the impact of the seawater flow in the upstream direction meet the predetermined third condition, the corresponding area is a third-level search and rescue area.

[0022] Preferably, in the maritime search and rescue path planning method, in step S3:

[0023] The maximum probability planning algorithm for the first-level search and rescue area is as follows: based on the search and rescue starting point, eight two-dimensional grids are searched around the search and rescue starting point, using the formula Min{s1 s2…s8}, where s1 to s8 represent the two-dimensional grids around the search and rescue starting point; when the priority of a two-dimensional grid around the search and rescue starting point is a first-level search and rescue area and the comprehensive environmental impact value of the two-dimensional grid is the smallest, the two-dimensional grid is selected as the next search and rescue point, and the searched two-dimensional grid is marked as searched;

[0024] For the secondary search and rescue areas and the tertiary search and rescue areas, different strategies are adopted according to the search and rescue capabilities of the UAV and combined with the A* area coverage path planning algorithm.

[0025] Preferably, in the maritime search and rescue path planning method, step S3 comprises:

[0026] If the unmanned boat carries only one drone and the drone's search and rescue capability meets the requirements, after the drone completes the search of the primary search and rescue area, it will search the secondary and tertiary search and rescue areas, with priority given to the secondary search and rescue area.

[0027] If the unmanned boat carries two drones and the search and rescue capabilities of the two drones meet the requirements, one drone is assigned to search and rescue the first-level search and rescue area, and the other drone is assigned to search and rescue the second-level search and rescue area and the third-level search and rescue area, among which the second-level search and rescue area is searched first;

[0028] If the unmanned boat carries three drones and the search and rescue capabilities of the three drones meet the requirements, one drone will be allocated to each of the first-level search and rescue area, the second-level search and rescue area, and the third-level search and rescue area for search and rescue.

[0029] Preferably, in the maritime search and rescue path planning method, in step S4:

[0030] The unmanned boat includes a drone take-off and landing module, a communication module, a charging and storage module, and a controlled module. The drone take-off and landing module is used to control the take-off and landing of the drone; the communication module is used to maintain communication between the unmanned boat and the drone and the search and rescue center; the charging and storage module is used to charge the drone; and the controlled module is used for remote control of the unmanned boat.

[0031] The UAV includes a multimodal perception module, a communication module, a flight control module and a computing and processing module, wherein the multimodal perception module is used for the UAV to search and rescue under different environmental conditions; the communication module is used to maintain communication between the UAV and the unmanned boat; the flight control module is used to control the flight of the UAV; and the computing and processing module is used to determine whether the acquired perception information is a search and rescue target.

[0032] Preferably, in the maritime search and rescue path planning method, in step S5, the step of setting the UAV detection confidence level according to different weather conditions includes:

[0033] If the weather condition is good and meets the pre-set conditions, then when the UAV detection confidence level is greater than a first confidence level threshold, it is considered a suspicious target;

[0034] If the weather condition is normal weather that meets the pre-set conditions, then when the UAV detection confidence level is greater than a second confidence level threshold, it is considered a suspicious target;

[0035] If the weather condition is severe weather that meets the pre-set conditions, then when the UAV detection confidence level is greater than a third confidence level threshold, it is considered a suspicious target;

[0036] The first confidence threshold is greater than the second confidence threshold, and the second confidence threshold is greater than the third confidence threshold.

[0037] In another aspect, a device for maritime search and rescue path planning is provided, comprising a memory and a processor, the memory storing at least one program, the at least one program being executed by the processor to implement the steps of the maritime search and rescue path planning method according to any one of the above.

[0038] In yet another aspect, a computer program product is provided, comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the maritime search and rescue path planning method according to any one of the above.

[0039] The above technical solutions have the following technical effects:

[0040] The technical solution of the embodiment of the present application is targeted at the characteristics of maritime search and rescue, considers the influence of maritime environmental factors when planning the path of the unmanned aerial vehicle, divides the search and rescue area to be searched into different priority levels in combination with the sea flow information and sea environment information of the search and rescue area to be searched, and uses different search and rescue strategies for the search and rescue areas of different priority levels by using the two-dimensional grid method, thereby improving the search and rescue efficiency.

[0041] In a further embodiment, a multi-level search and rescue strategy is implemented by the number and search and rescue capability of the unmanned aerial vehicles on the unmanned ship. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A flowchart of a maritime search and rescue path planning method according to an embodiment of the present application;

[0043] Figure 2 A two-dimensional grid diagram of a search and rescue area in a maritime search and rescue path planning method according to another embodiment of the present application;

[0044] Figure 3 A two-dimensional grid assignment diagram in a maritime search and rescue path planning method according to another embodiment of the present application;

[0045] Figure 4A two-dimensional grid diagram of a primary search and rescue area in a method for maritime search and rescue path planning according to another embodiment of the present invention;

[0046] Figure 5 FIG2 is a diagram of a device for maritime search and rescue path planning according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] To further illustrate various embodiments, the present invention is provided with accompanying drawings. These drawings form part of the present disclosure and are primarily used to illustrate the embodiments and, in conjunction with the relevant description in the specification, to explain the operating principles of the embodiments. By referring to these drawings, one of ordinary skill in the art will understand other possible embodiments and the advantages of the present invention. The components in the figures are not drawn to scale, and similar reference numerals are generally used to represent similar components.

[0048] The present invention will now be further described with reference to the accompanying drawings and specific embodiments.

[0049] Example 1:

[0050] In order to improve the efficiency and success rate of maritime search and rescue in complex environments in the ocean, this embodiment provides a maritime search and rescue path planning method. Figure 1 This is a flow chart of a method for planning a maritime search and rescue path according to an embodiment of the present invention. Figure 1 As shown, the maritime search and rescue path planning method includes the following steps:

[0051] S1, receiving the location information of the search and rescue signal, creating a two-dimensional grid map of the search and rescue area where the location information is located, and marking the area to be searched and rescued in the two-dimensional grid map according to the map information;

[0052] S2, according to a pre-set quantization method, quantize the seawater flow information in the area to be searched and rescued and the marine environment information in the area to be searched and rescued into corresponding seawater flow level values ​​and marine environment level values, accumulate the seawater flow level values ​​and the marine environment information level values ​​of the two-dimensional grid in the area to be searched and rescued to obtain the comprehensive environmental impact value of the two-dimensional grid in the area to be searched and rescued, and divide the two-dimensional grid in the area to be searched and rescued into search and rescue areas of different priorities according to the corresponding relationship between the pre-set comprehensive environmental impact value and the search and rescue area priority, wherein the search and rescue areas of different priorities include: a first-level search and rescue area, a second-level search and rescue area, and a third-level search and rescue area; wherein the seawater flow information includes seawater flow velocity; the seawater environment information includes wind force; in a specific implementation, the seawater flow level includes the seawater flow velocity level, and the marine environment level includes the wind force level;

[0053] S3, a corresponding search and rescue path planning algorithm is adopted according to the priority of the search and rescue area to plan a search and rescue path; wherein, the maximum probability path planning algorithm is adopted for the first-level search and rescue area, and the A* combined area coverage path planning algorithm is adopted for the second-level search and rescue area and the third-level search and rescue area;

[0054] S4, after the unmanned ship carries the unmanned aerial vehicle to the position of the search signal, the search and rescue area is searched according to the search and rescue path planned by the search and rescue path planning algorithm;

[0055] S5, when the target detected by the unmanned aerial vehicle is greater than the pre-set unmanned aerial vehicle detection confidence, the unmanned ship arrives at the position of the target for secondary confirmation, and if the unmanned ship confirms that the target is the target to be searched, the target to be searched is tracked and the position of the target to be searched is sent to the rescue center in real time; wherein, the unmanned aerial vehicle detection confidence is pre-set according to different weather conditions.

[0056] Embodiment two:

[0057] This embodiment is aimed at the characteristics of maritime search and rescue, considers the influence of marine environmental factors when planning the path of the unmanned aerial vehicle, adopts different search and rescue strategies for different levels of search and rescue areas, and at the same time, uses the unmanned ship to detect the suspicious target twice, effectively reduces the missed detection rate and improves the rescue efficiency. The method of this embodiment includes the following steps:

[0058] Step one, receive the position information of the search signal, initialize the search area grid map, establish the two-dimensional grid map of the search area, and import the seawater flow information and marine environment information to establish a dynamic grid.

[0059] Among them, Figure 2 It is another embodiment of the two-dimensional grid map of the search area in the maritime search and rescue path planning method of the present application. As shown in Figure 2 The range includes a square search area with the search information as the starting point and the side length R, wherein the side length R represents the farthest distance that the unmanned aerial vehicle or the unmanned aerial vehicle group can effectively search under the condition of fully mobilizing the sensors and communication equipment of the unmanned aerial vehicle, and considering the energy consumption of the unmanned aerial vehicle and the required time for safe return;

[0060] The two-dimensional grid takes the latitude and longitude of the position of the search signal as the coordinate origin, and the effective detection range of the unmanned aerial vehicle as the size, wherein the effective detection range of the unmanned aerial vehicle is related to the visibility of the unmanned aerial vehicle, and the visibility of the unmanned aerial vehicle is affected by the marine weather factors. In a specific implementation, the effective detection range of the unmanned aerial vehicle is determined by the following formula: r[n]=f(W_3), wherein f() is a function expression, n represents this event, and W_3 represents the visibility of the unmanned aerial vehicle. In a specific implementation, when the visibility of the unmanned aerial vehicle is 20 meters, the grid side length r is 40 meters.

[0061] The two-dimensional grid is marked according to the map information, wherein islands, land and other areas are marked as areas that do not require search and rescue, and other areas are marked as areas to be searched and rescued.

[0062] Step 2: Divide the search and rescue area priority levels, convert the seawater flow information and the marine environment information into level values, accumulate the seawater flow level values ​​and the marine environment information level values ​​to obtain a comprehensive environmental impact value, and divide the two-dimensional grid in the search and rescue area into search and rescue areas of different priorities based on the pre-set correspondence between the obtained comprehensive environmental impact value and the search and rescue area priority.

[0063] In a specific implementation, the seawater flow information is the seawater flow velocity, and the seawater environment information is the wind force. The seawater flow information and the seawater environment information are both quantified into a multi-level scale, wherein the multi-level scale includes positive values, negative values ​​and / or zero values, and negative values ​​in the multi-level scale represent downstream or downwind directions toward the search and rescue starting point; positive values ​​in the multi-level scale represent upstream or upwind directions toward the search and rescue starting point, and zero values ​​in the multi-level scale represent no obvious seawater flow or wind force. In a specific implementation, the above-mentioned multi-level scale is a corresponding level; such as the wind force level indicating the magnitude of the wind force impact, and the seawater velocity level indicating the impact of seawater flow. In a specific implementation, the multi-level scale is determined by the following formula:

[0064] S[n]=f(W_1,W_2)

[0065] Among them, f() is a function expression, n represents the event, W_1 represents the seawater flow velocity, and W_2 represents the offshore wind speed.

[0066] The corresponding relationship between the comprehensive environmental impact value and the search and rescue area priority is:

[0067] When the magnitude of the comprehensive environmental impact value indicates that the corresponding area is affected by the downwind direction and the downstream seawater flow, which satisfies a predetermined first condition, the corresponding area is a first-level search and rescue area. In a specific implementation, when the search and rescue area is affected by the downwind direction and the downstream seawater flow, which satisfies the predetermined first condition, it indicates that the area is affected by a relatively strong downwind direction and the downstream seawater flow.

[0068] When the magnitude of the comprehensive environmental impact value indicates that the impact of seawater flow and wind force on the corresponding area meets the predetermined second condition, the corresponding area is a secondary search and rescue area. In a specific implementation, when the impact of downwind influence and downstream seawater flow on the search and rescue area meets the predetermined second condition, it means that the impact of seawater flow and wind force on the area is small or not significantly affected.

[0069] When the magnitude of the comprehensive environmental impact value indicates that the impact of the upward wind and the upstream seawater flow satisfies a predetermined third condition, the corresponding area is a level 3 search and rescue area. In one specific implementation, when the impact of the upward wind and the upstream seawater flow on the search and rescue area meets the predetermined third condition, it indicates that the area is subject to relatively strong upward wind and upstream seawater flow.

[0070] In one specific implementation, wind speed levels are categorized as -2, -1, 0, 1, and 2, with negative values ​​assigned to downwind directions and positive values ​​assigned to upwind directions from the search and rescue starting point, with zero representing no wind. Seawater flow velocity levels are categorized as -2, -1, 0, 1, and 2, with negative values ​​assigned to downstream directions and positive values ​​assigned to upstream directions from the search and rescue starting point, with zero representing no flow. The combined environmental impact value of the wind speed level and seawater flow velocity level ranges from -4 to 4, and the two-dimensional grid is assigned a value based on this combined environmental impact value.

[0071] In a specific implementation, Figure 3 Schematic diagram of two-dimensional grid assignment in the maritime search and rescue path planning method of this embodiment. Figure 3 As shown, with the center as the search and rescue starting point, the wind direction is from southwest to northeast, the wind force level is 2, the water flow is eastward, and the seawater flow velocity is 1. When the wind direction is downwind of the search and rescue starting point, the wind force level is -2, the seawater flow direction is downstream of the search and rescue starting point, and the seawater flow velocity is -1, the corresponding comprehensive value is -3, and the corresponding area is a first-level search and rescue area; when the wind direction is downwind of the search and rescue starting point, the wind force is -2, the seawater flow direction is upstream of the search and rescue starting point, and the seawater flow velocity is 1, the corresponding comprehensive value is 1, and the corresponding area is a second-level search and rescue area; when the wind direction is upwind of the search and rescue starting point, the wind force is 2, the seawater flow direction is upstream of the search and rescue starting point, and the seawater flow velocity is 1, the corresponding comprehensive value is 3, and the corresponding area is a third-level search and rescue area.

[0072] Figure 4 FIG2 is a two-dimensional grid diagram of a primary search and rescue area in a method for planning a maritime search and rescue path according to another embodiment of the present invention. Figure 4 As shown, in one implementation, the corresponding relationship between the comprehensive environmental impact value and the search and rescue area priority is:

[0073] The first-level search and rescue area is affected by strong downwind or downstream seawater flow. Preferably, the comprehensive environmental impact value of the first-level search and rescue area is -4, -3, or -2;

[0074] The secondary search and rescue area indicates that the impact of seawater flow or wind force is small or no significant impact. Preferably, the comprehensive environmental impact value of the secondary search and rescue area is -1, 0, or 1;

[0075] The third-level search and rescue area indicates that it is affected by strong upward wind or upstream seawater flow. Preferably, the comprehensive environmental impact value of the third-level search and rescue range is 2, 3, or 4.

[0076] Step three: The unmanned boat carries the drone to the location of the search and rescue signal.

[0077] Preferably, the unmanned boat includes a drone take-off and landing module, a communication module, a charging and storage module, and a controlled module, wherein the drone take-off and landing module is used to control the take-off and landing of the drone; the communication module is used to maintain communication between the unmanned boat and the drone and the search and rescue center; the charging and storage module is used to charge the drone; and the controlled module is used for remote control of the unmanned boat;

[0078] Preferably, the UAV includes a multimodal perception module, a communication module, a flight control module and a computing and processing module, wherein the multimodal perception module is used for search and rescue of the UAV under different environmental conditions; the communication module is used to maintain communication between the UAV and the unmanned boat; the flight control module is used to control the flight of the UAV; and the computing and processing module is used to determine whether the acquired perception information is a search and rescue target.

[0079] Step 4: Different UAV search and rescue path planning methods are used according to the divided area levels. The maximum probability planning algorithm is used for the priority area, and the area coverage path planning algorithm combined with A* is used for the secondary priority area.

[0080] Among them, the maximum probability planning algorithm is used for the first-level search and rescue area. According to the position of the starting grid point, the two-dimensional grid that is the first-level search and rescue area and has the smallest comprehensive environmental impact value among the eight surrounding two-dimensional grids is found as the next search and rescue area, and the searched two-dimensional grids are marked as searched; for the second-level and third-level search and rescue areas, the area coverage path planning algorithm combined with A* is used, and different strategies are adopted according to the carried UAVs and their search and rescue capabilities.

[0081] Preferably, if the unmanned vessel carries only one drone and the drone's search and rescue capabilities meet the requirements, after the search of the primary search and rescue area is completed, the secondary and tertiary search and rescue areas are searched. The secondary search and rescue area is given a greater weight than the tertiary search and rescue area, and the secondary search and rescue area is searched first.

[0082] Preferably, if the unmanned vessel carries two drones and their search and rescue capabilities meet the requirements, one drone is assigned to search the primary search and rescue area. The other drone searches the secondary and tertiary search and rescue areas. The secondary search and rescue area is given a higher weight than the tertiary search and rescue area, giving priority to the secondary search and rescue area.

[0083] Preferably, if the unmanned ship carries three unmanned aerial vehicles and the unmanned aerial vehicle search and rescue capability meets the requirements, each level of search and rescue area is allocated an unmanned aerial vehicle, and the second level of search and rescue area and the third level of search and rescue area are additionally weighted.

[0084] Step five, different unmanned aerial vehicle detection confidence is set according to different weather conditions, when the target detected by the unmanned aerial vehicle is greater than the set confidence, the unmanned ship reaches the target position for secondary confirmation, if the target is confirmed to be a target to be searched and rescued, the target is tracked and the real-time position of the target is sent to the rescue center, wherein the unmanned aerial vehicle detection confidence is related to the sea wind speed, the unmanned aerial vehicle visibility and the sea temperature.

[0085] In a specific implementation, the unmanned aerial vehicle detection confidence is determined by the following formula: T[n]=f(W_2,W_3,W_4), wherein f() is a function expression, n represents this event, W_2 represents the sea wind speed, W_3 represents the unmanned aerial vehicle visibility, and W_4 represents the sea temperature.

[0086] In a specific implementation, when the sea wind speed is 5 level gale, the unmanned aerial vehicle visibility is 40 meters, and the sea temperature is 18℃, the unmanned aerial vehicle detection confidence is 40%.

[0087] Wherein, the weather condition is good weather meeting the pre-set condition, when the unmanned aerial vehicle detection confidence is greater than the first confidence threshold, it is considered to be a suspicious target, preferably, the first confidence is greater than 80%;

[0088] If the weather condition is general weather meeting the pre-set condition, when the unmanned aerial vehicle detection confidence is greater than the second confidence threshold, it is considered to be a suspicious target, preferably, the second confidence is greater than 60%;

[0089] If the weather condition is bad weather meeting the pre-set condition, when the unmanned aerial vehicle detection confidence is greater than the third confidence threshold, it is considered to be a suspicious target, preferably, the third confidence is greater than 40%;

[0090] The first confidence threshold is greater than the second confidence threshold, and the second confidence threshold is greater than the third confidence threshold.

[0091] In a specific implementation, the good weather is that the unmanned aerial vehicle visibility is greater than 100 meters and the sea wind speed is less than 3 level; the general weather is that the unmanned aerial vehicle visibility is greater than 50 meters and less than 100 meters, and the sea wind speed is greater than 3 level and less than 5 level; and the bad weather is that the unmanned aerial vehicle visibility is less than 50 meters and the sea wind speed is greater than 5 level.

[0092] Embodiment three:

[0093] The application also provides a device for planning a search and rescue path at sea, such as Figure 5As shown, the device includes a processor 501, a memory 502, a bus 503, and a computer program stored in the memory 502 and executable on the processor 501. The processor 501 includes one or more processing cores. The memory 502 is connected to the processor 501 via the bus 503. The memory 502 is used to store program instructions. When the processor executes the computer program, the steps in the above-mentioned method embodiment of the first embodiment of the present invention are implemented.

[0094] Furthermore, as an executable solution, the device for planning the maritime search and rescue route can be a computer unit, which can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer unit may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the composition structure of the above-mentioned computer unit is merely an example of a computer unit and does not constitute a limitation on the computer unit. The computer unit may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the computer unit may also include input and output devices, network access devices, buses, etc., which are not limited in the embodiments of the present invention.

[0095] Furthermore, as an executable solution, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer unit and connects various parts of the entire computer unit using various interfaces and lines.

[0096] The memory can be used to store the computer programs and / or modules, and the processor implements the various functions of the computer unit by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created based on the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0097] Example 4:

[0098] The present invention also provides a computer program product, comprising a computer program, which implements the steps of the method described above when executed by a processor.

[0099] Although the present invention has been particularly shown and described in conjunction with preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made to the present invention without departing from the spirit and scope of the invention as defined in the appended claims, and all such changes are within the scope of protection of the present invention.

Claims

1. A method for planning a maritime search and rescue path, characterized in that: include: S1, receiving the location information of the search and rescue signal, establishing a two-dimensional grid map of the search and rescue area where the location information is located, and marking the area to be searched and rescued in the two-dimensional grid map according to map information; S2, according to a preset quantization method, quantize the seawater flow information in the area to be searched and rescued and the marine environment information in the area to be searched and rescued into corresponding seawater flow level values ​​and marine environment level values, accumulate the seawater flow level values ​​and the marine environment level values ​​of the two-dimensional grid in the area to be searched and rescued to obtain the comprehensive environmental impact value of the two-dimensional grid in the area to be searched and rescued, and divide the two-dimensional grid in the area to be searched and rescued into search and rescue areas of different priorities according to the corresponding relationship between the preset comprehensive environmental impact value and the search and rescue area priority, wherein the search and rescue areas of different priorities include: a first-level search and rescue area, a second-level search and rescue area and a third-level search and rescue area; wherein the seawater flow information includes seawater flow velocity; and the marine environment information includes wind force; S3, planning a search and rescue path using a corresponding search and rescue path planning algorithm according to the priority of the search and rescue area; wherein, the maximum probability path planning algorithm is used for the first-level search and rescue area, and the area coverage path planning algorithm combined with A* is used for the second-level search and rescue area and the third-level search and rescue area; S4, after the unmanned boat carrying the drone arrives at the location of the search and rescue signal, searching and rescuing the area to be searched and rescued according to the search and rescue path planned by the search and rescue path planning algorithm; S5. When the target detected by the drone is greater than the preset drone detection confidence level, the unmanned boat arrives at the location of the target for secondary confirmation. If the unmanned boat confirms that the target is the target to be searched and rescued, it tracks the target to be searched and rescued and sends the location of the target to be searched and rescued to the rescue center in real time; wherein, the drone detection confidence level is pre-set according to different weather conditions.

2. The method for maritime search and rescue path planning according to claim 1, characterized in that: The drone detection confidence is related to sea wind speed, visibility and sea temperature.

3. The method for maritime search and rescue path planning according to claim 1, wherein: In the step S1: The scope of the search and rescue area is: a square search and rescue area with a side length of R and a starting center point at the location of the search and rescue signal, wherein the side length R represents the maximum distance that the drone or drone group can effectively search; The two-dimensional grid is established with the longitude and latitude of the location of the search and rescue signal as the coordinate origin and the effective detection range of the drone as the size, wherein the effective detection range of the drone is related to the visibility of the drone, and the visibility of the drone is affected by weather factors at sea; The step S1 further includes: marking the unnecessary search areas in the two-dimensional grid map according to map information; the unnecessary search areas include islands and land.

4. The method for maritime search and rescue path planning according to claim 3, characterized in that: In the step S2: The seawater flow information and the marine environment information are both quantified into a multi-level scale, wherein the multi-level scale includes positive values, negative values, and / or zero values, wherein a negative value in the multi-level scale indicates a direction downstream or downwind of the search and rescue starting point; a positive value in the multi-level scale indicates an upstream or upwind direction of the search and rescue starting point; and a zero value in the multi-level scale indicates no seawater flow or wind force; The corresponding relationship between the comprehensive environmental impact value and the search and rescue area priority is: When the magnitude of the comprehensive environmental impact value indicates that the corresponding area is affected by the downwind direction and the downstream seawater flow and satisfies a predetermined first condition, the corresponding area is a first-level search and rescue area; When the magnitude of the comprehensive environmental impact value indicates that the seawater flow and wind force impact on the corresponding area meets the predetermined second condition, the corresponding area is a secondary search and rescue area; When the magnitude of the comprehensive environmental impact value indicates that the impact of the upward wind direction and the impact of the seawater flow in the upstream direction meet the predetermined third condition, the corresponding area is a third-level search and rescue area.

5. The method for maritime search and rescue path planning according to claim 4, characterized in that: In the step S3: The maximum probability planning algorithm for the first-level search and rescue area is as follows: based on the search and rescue starting point, eight two-dimensional grids are found around the search and rescue starting point, using the formula Min{s1 s2…s8}, where s1 to s8 represent the two-dimensional grids around the search and rescue starting point; when the priority of a two-dimensional grid around the search and rescue starting point is a first-level search and rescue area and the comprehensive environmental impact value of the two-dimensional grid is the smallest, the two-dimensional grid is selected as the next search and rescue point, and the searched two-dimensional grid is marked as searched; For the secondary search and rescue area and the tertiary search and rescue area, different strategies are adopted according to the search and rescue capabilities of the UAV and combined with the A* area coverage path planning algorithm.

6. The method for maritime search and rescue path planning according to claim 5, characterized in that: The step S3 comprises: If the unmanned boat carries only one drone and the drone's search and rescue capability meets the requirements, after the drone completes the search of the primary search and rescue area, it will search the secondary and tertiary search and rescue areas, with priority given to the secondary search and rescue area. If the unmanned boat carries two drones and the search and rescue capabilities of the two drones meet the requirements, one drone is assigned to search and rescue the first-level search and rescue area, and the other drone is assigned to search and rescue the second-level search and rescue area and the third-level search and rescue area, among which the second-level search and rescue area is searched first; If the unmanned boat carries three drones and the search and rescue capabilities of the three drones meet the requirements, one drone will be allocated to each of the first-level search and rescue area, the second-level search and rescue area, and the third-level search and rescue area for search and rescue.

7. The method for planning a maritime search and rescue path according to claim 1, wherein: In the step S4: The unmanned boat includes a drone take-off and landing module, a communication module, a charging and storage module, and a controlled module. The drone take-off and landing module is used to control the take-off and landing of the drone; the communication module is used to maintain communication between the unmanned boat and the drone and the search and rescue center; the charging and storage module is used to charge the drone; and the controlled module is used for remote control of the unmanned boat. The UAV includes a multimodal perception module, a communication module, a flight control module and a computing and processing module, wherein the multimodal perception module is used for the UAV to search and rescue under different environmental conditions; the communication module is used to maintain communication between the UAV and the unmanned boat; the flight control module is used to control the flight of the UAV; and the computing and processing module is used to determine whether the acquired perception information is a search and rescue target.

8. The method for maritime search and rescue path planning according to claim 1, characterized in that: In step S5, the step of setting the drone detection confidence level according to different weather conditions includes: If the weather condition is good and meets the pre-set conditions, then when the UAV detection confidence level is greater than a first confidence level threshold, it is considered a suspicious target; If the weather condition is normal weather that meets the pre-set conditions, then when the UAV detection confidence level is greater than a second confidence level threshold, it is considered a suspicious target; If the weather condition is severe weather that meets the pre-set conditions, then when the UAV detection confidence level is greater than a third confidence level threshold, it is considered a suspicious target; The first confidence threshold is greater than the second confidence threshold, and the second confidence threshold is greater than the third confidence threshold.

9. A device for maritime search and rescue path planning, characterized in that: The method comprises a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to implement the steps of the maritime search and rescue path planning method according to any one of claims 1 to 8.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the maritime search and rescue path planning method according to any one of claims 1 to 8 are implemented.

Images