Method and system for salvaging floating objects on water, storage medium and program product
By acquiring information on floating objects and robot status in the aquatic environment, and using multi-source sensing devices and optimization algorithms to generate path planning, the problem of low cleaning efficiency of cleaning robots has been solved, and efficient global cleaning has been achieved.
Patent Information
- Application Number
- CN202511347092.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-19
- Publication Date
- 2026-01-09
AI Technical Summary
Existing cleaning robots lack a global perspective, resulting in blind and inefficient cleaning operations, as well as repeated cleaning and missed cleaning.
By acquiring the status information of all floating objects and cleaning robots in the aquatic environment, multi-source sensing devices are used for data fusion processing, and combined with optimization algorithms to generate robot path planning results, thereby controlling the cleaning robots to efficiently clean up floating objects.
It achieves efficient global-level floating debris removal, avoiding blind and missed cleaning, and improving cleaning coverage and efficiency.
Smart Images
Figure CN121300344A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of floating debris removal technology, and in particular to a method, system, storage medium, and program product for salvaging floating debris on water. Background Technology
[0002] When large and medium-sized hydropower stations face the problem of clearing floating debris in the reservoir area, they usually use intelligent cleaning robots for automatic retrieval. In related technologies, intelligent cleaning robots typically adopt a random patrol mode for retrieval; that is, the cleaning robot moves randomly in the water area or performs a full-coverage retrieval without targeting the entire water area, passively detecting and clearing floating debris by relying on local sensors.
[0003] However, the above methods lack a global perspective and make it difficult to perceive the overall distribution of floating objects in the reservoir area, resulting in blind and inefficient cleanup operations, with repeated cleanup and missed cleanup. Summary of the Invention
[0004] The main purpose of this application is to provide a method, system, storage medium, and program product for retrieving floating objects from water, aiming to solve the technical problem of low cleaning efficiency of cleaning robots in related technologies.
[0005] To achieve the above objectives, this application proposes a method for retrieving floating objects from water, which can be used in the control platform of a floating object retrieval system. This control platform is connected to at least one cleaning robot. The floating object retrieval method includes:
[0006] Acquire the status information of all floating objects in the aquatic environment and the current status information of all cleaning robots; among which, the status information of floating objects includes the location information of floating objects, and the current status information includes the current location information and the current battery level information;
[0007] Based on the status information of all floating objects and the current status information, a robot path planning result is generated; the robot path planning result includes the floating object location information corresponding to one or more floating objects to be cleaned assigned to each cleaning robot;
[0008] Based on the robot path planning results, control all cleaning robots to perform salvage operations.
[0009] In one embodiment, before the step of generating robot path planning results based on all floating object state information and all current state information, the method further includes:
[0010] Acquire environmental meteorological information within the aquatic environment; environmental meteorological information includes wind speed, rate of water level rise, and rate of water level fall.
[0011] Based on the robot path planning results, the steps for controlling all cleaning robots to perform salvage operations include:
[0012] If the wind speed is greater than the preset wind speed, control all cleaning robots to activate their windproof anchors and lower their working height;
[0013] If the rate of water level rise exceeds the preset rate of rise, control all cleaning robots to activate the pressure boosting and waterproofing function. After detecting that the rate of water level drop reaches the preset safety threshold, control all cleaning robots to perform salvage operations according to the robot path planning results.
[0014] In one embodiment, the environmental meteorological information further includes rainfall; after the step of acquiring environmental meteorological information within the aquatic environment, the method further includes:
[0015] If the rainfall exceeds the preset rainfall amount, control all cleaning robots to return to the safe base.
[0016] In one embodiment, the floating object state information also includes the floating object volume; the cleaning robot includes multiple robots; the step of generating robot path planning results based on all floating object state information and all current state information includes:
[0017] A first set of floating objects is determined based on all floating objects whose volume is greater than a preset volume threshold.
[0018] A second set of floating objects is determined based on all floating objects whose volume is less than or equal to a preset volume threshold.
[0019] Based on the location information of all floating objects in the first set of floating objects and all current status information, the first path planning result is determined with the optimization objective of the optimal total navigation path; the first path planning result is used to control all cleaning robots to move together toward a single floating object.
[0020] Based on the location information and current status information of all floating objects in the second set of floating objects, the second path planning result is determined with the optimization objectives of minimizing the total salvage task completion time and optimizing the total navigation path. The second path planning result is used to assign one or more cleaning robots to each floating object in the second set of floating objects, and to control the assigned cleaning robots to drive to the corresponding floating object.
[0021] In one embodiment, the step of obtaining the floating object state information corresponding to each floating object in the aquatic environment includes:
[0022] Sensing data of the aquatic environment is collected through multi-source sensing devices, including visible light cameras, thermal imaging cameras, and side-scan sonar.
[0023] By fusing and enhancing the perceived data, floating objects in the aquatic environment can be identified and located, and their status information can be obtained.
[0024] Furthermore, to achieve the above objectives, this application also proposes a floating object retrieval system, which includes:
[0025] The control platform includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the above-described method for retrieving floating objects from the water.
[0026] At least one cleaning robot, connected to a control platform, is used to perform floating debris retrieval operations.
[0027] In one embodiment, the floating object retrieval system further includes:
[0028] Multi-source sensing devices, connected to the control platform, are used to identify and locate floating objects in the aquatic environment; the multi-source sensing devices include visible light cameras, thermal imaging cameras, and side-scan sonar.
[0029] In one embodiment, the cleaning robot includes a Beidou positioning chip; and / or a 50MPa cavitation jet module and a stratified filter chamber.
[0030] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, storing a computer program on the storage medium. When the computer program is executed by a processor, it implements the steps of the above-described method for salvaging floating objects on water.
[0031] In addition, to achieve the above objectives, this application also proposes a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the above-described method for salvaging floating objects on water.
[0032] One or more technical solutions proposed in this application have at least the following technical effects:
[0033] The floating object retrieval method proposed in this application can obtain the floating object status information corresponding to all floating objects in the aquatic environment and the current status information of all cleaning robots. Based on the floating object status information containing the floating object location information and the current status information of the cleaning robots (current location information and current power information, etc.), a robot path planning result can be generated. Based on the robot path planning result, all cleaning robots can be controlled to perform retrieval operations.
[0034] The status information of all floating objects in the aquatic environment in this application can help to fully understand the distribution of floating objects. Based on the status information of all floating objects, robot path planning can be carried out. One or more floating objects to be cleaned can be assigned to each cleaning robot at a global level, ensuring that each robot can efficiently and specifically clean up floating objects in the entire area. This avoids the blind cleaning and missed cleaning caused by the lack of global information in the random patrol mode, and can improve the coverage and efficiency of floating object retrieval. Attached Figure Description
[0035] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0036] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0037] Figure 1 This is a flowchart illustrating an embodiment of the method for salvaging floating objects on water provided in this application.
[0038] Figure 2 This is a flowchart illustrating an example method for retrieving floating objects from water.
[0039] Figure 3 This is a schematic diagram of the "edge-cloud" collaborative architecture involved in an example method for salvaging floating objects on water.
[0040] Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the floating object retrieval method in this application embodiment.
[0041] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0042] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0043] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0044] The main solution of this application embodiment is: to obtain the floating object status information corresponding to all floating objects in the aquatic environment and the current status information of all cleaning robots; wherein, the floating object status information includes floating object location information, and the current status information includes current location information and current power information; based on all floating object status information and all current status information, to generate robot path planning results; the robot path planning results include the floating object location information corresponding to one or more floating objects to be cleaned assigned to each cleaning robot; based on the robot path planning results, to control all cleaning robots to perform salvage operations.
[0045] When large and medium-sized hydropower stations face the problem of cleaning floating debris in the reservoir area, they can adopt either a "debris removal vessel + manual cleaning" or a "fixed camera + gate and debris removal machine linkage system". Among them, the "debris removal vessel + manual cleaning" method is highly dependent on manual labor and requires professional personnel with certain technical skills to carry out the cleaning work, resulting in a low level of intelligence. While the "fixed camera + gate and debris removal machine linkage system" is more intelligent, it mainly relies on water flow to drive the movement of floating debris, making it difficult to apply to still water reservoirs and other reservoir sites.
[0046] Therefore, related technologies have proposed using intelligent cleaning robots for automatic retrieval. In this method, the cleaning robot typically adopts a random patrol mode for retrieval, that is, the cleaning robot moves erratically in the water, passively detecting and clearing floating debris based on local sensors.
[0047] However, random patrols lack a global perspective and struggle to perceive the overall distribution of floating debris within the reservoir area, resulting in blind and inefficient cleanup operations. Additionally, the cleanup coverage is low, leading to repeated cleanup and missed cleanup.
[0048] The solution provided in this application is that the status information of all floating objects in the aquatic environment can help to fully understand the distribution of floating objects. Based on the status information of all floating objects, robot path planning can be performed, and one or more floating objects to be cleaned can be assigned to each cleaning robot at a global level. This ensures that each robot can efficiently and specifically clean up floating objects in the entire area, avoiding the blind cleaning and missed cleaning caused by the lack of global information in the random patrol mode, and improving the coverage and efficiency of floating object retrieval.
[0049] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer or personal computer, or an electronic device capable of performing the above functions. The following description uses the control platform of a floating debris retrieval system as an example to illustrate this embodiment and the subsequent embodiments.
[0050] Based on this, the embodiments of this application provide a method for salvaging floating objects on water, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the method for salvaging floating objects on water according to this application.
[0051] In this embodiment, the above-mentioned method for salvaging floating objects on water includes steps S100 to S400:
[0052] Step S100: Obtain the floating object status information corresponding to all floating objects in the aquatic environment and the current status information of all the cleaning robots; wherein, the floating object status information includes the floating object location information, and the current status information includes the current location information and the current power information.
[0053] Step S200: Based on the status information of all floating objects and the current status information, generate robot path planning results; the robot path planning results include the floating object location information corresponding to one or more floating objects to be cleaned, assigned to each cleaning robot.
[0054] Step S300: Based on the robot path planning results, control all cleaning robots to perform salvage operations.
[0055] Specifically, the control platform of this application can be connected to at least one cleaning robot in the water area. The cleaning robot can be remotely controlled through the control platform to complete the retrieval of floating objects in the water area.
[0056] In practical applications, floating objects on the water surface can be monitored in real time using sensors, cameras, remote sensing technology, and other means in the aquatic environment to obtain information on their status. This information may include, but is not limited to, location information (such as latitude and longitude, XY coordinates in a coordinate system established based on the surface area of the reservoir), object type, and volume.
[0057] In one feasible implementation, step S100, which involves obtaining the floating object state information corresponding to each floating object in the aquatic environment, may specifically include steps S110 to S120, used to determine more accurate floating object state information through multi-source data fusion:
[0058] Step S110: Collect sensing data of the aquatic environment through multi-source sensing devices; the multi-source sensing devices include visible light cameras, thermal imaging cameras, and side-scan sonar.
[0059] Step S120: Perform fusion processing and image enhancement processing on the perceived data to identify and locate floating objects in the aquatic environment and obtain floating object status information.
[0060] Specifically, the multi-sensing devices can include visible light cameras, thermal imaging cameras, and side-scan sonar, that is, "visible light + thermal imaging + side-scan sonar" are used for joint identification.
[0061] Visible light cameras can be used to collect image data of floating objects on the water surface. They are suitable for sunny, well-lit environments and can provide high-resolution images, with good ability to capture information such as the color, shape, and size of floating objects. Thermal imaging cameras generate images by detecting the infrared radiation emitted by objects. In aquatic environments, especially at night or in low-light conditions, thermal imaging cameras can effectively identify floating objects. When some floating objects cannot be clearly captured by visible light cameras, thermal imaging cameras can also identify objects with higher or lower temperatures on the water surface through infrared radiation, thus distinguishing different types of floating objects. Side-scan sonar detects floating objects or obstacles under the water surface by emitting sound waves and receiving the echoes, providing relatively accurate distance information and object outlines.
[0062] Data from different sensors (visible light cameras, thermal imaging cameras, and side-scan sonar) is fused. For example, data fusion algorithms such as Kalman filtering and particle filtering can be used to integrate data from multiple sensors into a more accurate and comprehensive aquatic environment perception information. For instance, fusing visible light and thermal imaging images can effectively compensate for the blind spots of single sensing devices and improve the recognition rate of floating objects. Joint identification using "visible light + thermal imaging + side-scan sonar" can effectively solve the problem of missed detection of floating objects at night or in turbid water. Image enhancement processing can also be applied to images captured by visible light and thermal imaging cameras to improve image contrast, clarity, and detail, enabling better identification of floating objects in complex aquatic environments (such as areas with large water surface fluctuations, low light levels, and foggy weather); for example, image enhancement processing using MSG-net can increase detection accuracy in complex aquatic environments.
[0063] Deep learning algorithms (such as Convolutional Neural Networks, CNNs) are used to classify processed images, identifying floating objects (such as garbage and plants) in water bodies and distinguishing between different types of floating objects, thus achieving automatic detection and classification of floating objects. Furthermore, by combining the perceived data with geographic information of the aquatic environment (such as GPS coordinates and BeiDou satellite positioning coordinates), the precise location of floating objects can be determined. Integrating depth data from side-scan sonar and other perceived data can further improve the accuracy of floating object location information. Through the fusion processing of perceived data, more comprehensive and accurate floating object status information can be obtained, providing data support for subsequent path planning of the cleaning robot.
[0064] In practical applications, visible light cameras can be selected from 2K-4K resolution industrial cameras. These cameras have wide-angle lenses and can capture high-definition color images of the water surface, using image comparison technology to identify floating objects in the reservoir area. Thermal imaging cameras can be selected from uncooled infrared thermal imagers with a resolution of 640×512 and a working wavelength set to 8-14µm. They can sense differences in water surface temperature and identify floating objects (such as garbage, which are usually at different temperatures than the water). Side-scan sonar can be selected from high-frequency (200kHz-500kHz) multibeam sonar, typically installed about 0.5 meters underwater, scanning underwater and near-surface suspended objects with a fan-shaped beam. Visible light cameras, thermal imaging cameras, and side-scan sonar can acquire data in real time; alternatively, they can acquire data at preset frequencies. Synchronization triggers can be used to trigger data acquisition by all three, ensuring that they acquire data at the same time or within a very short time difference, providing time consistency for subsequent data fusion.
[0065] It should be noted that the image fusion and recognition operations performed by the visible light camera, thermal imaging camera, and side-scan sonar after acquiring the corresponding data can be executed on a cloud-based control platform. Alternatively, to improve computational efficiency and optimize cloud computing resources, data processing can be performed locally on the visible light camera, thermal imaging camera, and side-scan sonar, and the processing results (i.e., floating object status information) can be directly sent to the cloud-based control platform. Local edge computing can reduce latency and improve processing efficiency compared to cloud computing, which helps to achieve real-time path planning and control of the cleaning robot. The aforementioned perception fusion technology can reduce the false detection rate of target detection in foggy environments and nighttime recognition to below 5%, which is significantly lower than the infrared single-mode technology (false detection rate > 30%).
[0066] The aforementioned cleaning robots are all equipped with GPS positioning, sensors, and wireless communication systems, enabling them to provide real-time feedback on their current status to the control platform. This status information includes, but is not limited to, current location, current battery level, and operational status (such as whether a malfunction has occurred or if an obstacle has been encountered). Real-time access to the robots' status information ensures that the control platform can allocate tasks appropriately based on their actual condition, preventing retrieval failures due to insufficient battery power or unsuitable positioning. In one feasible implementation, a BeiDou positioning chip can be configured in each cleaning robot, allowing the control platform to obtain accurate real-time location information for all robots via BeiDou positioning technology, facilitating path planning.
[0067] The control platform integrates the acquired floating object status information with the current status information of the cleaning robots. Using optimization algorithms (such as A* algorithm and Dijkstra's algorithm) with the shortest total navigation path and the shortest total salvage task completion time as optimization objectives, and combining the floating object location information, the current location information of the cleaning robots, and current battery information, it determines the optimal travel route for each cleaning robot, obtaining robot path planning results. It then assigns one or more floating object cleaning tasks to each cleaning robot, ensuring balanced and efficient task allocation. Based on real-time updates of floating object location information and robot current status information, the path planning results are dynamically adjusted, ensuring the real-time nature and adaptability of the path planning.
[0068] In one feasible implementation, when planning the robot path and task, the size of the floating objects to be cleaned can be taken into account, so the above step S200 can specifically include steps S210 to S240:
[0069] Step S210: Determine the first set of floating objects based on all floating objects whose volume is greater than a preset volume threshold.
[0070] Step S220: Determine the second set of floating objects based on all floating objects whose volume is less than or equal to a preset volume threshold.
[0071] Step S230: Based on the position information of all floating objects in the first set of floating objects and all current status information, the first path planning result is determined with the optimization objective of the overall navigation path being optimal; the first path planning result is used to control all cleaning robots to jointly drive towards a single floating object.
[0072] Step S240: Based on the location information of all floating objects in the second set of floating objects and all current status information, the second path planning result is determined with the optimization objectives of minimizing the total salvage task completion time and optimizing the total navigation path. The second path planning result is used to assign one or more cleaning robots to each floating object in the second set of floating objects, and to control the assigned cleaning robots to drive to the corresponding floating objects.
[0073] Specifically, a preset volume threshold can be determined through experiments or experience based on the individual working capabilities of the cleaning robot (such as gripping force and storage capacity). All floating objects with a volume greater than the preset volume threshold are selected and included in the first set of floating objects; similarly, all floating objects with a volume less than or equal to the preset volume threshold are selected and included in the second set of floating objects. This allows for targeted path planning and task allocation for floating objects of different sizes.
[0074] For each large floating object in the first set of floating objects, it can be treated as an independent task. Utilizing the positional information of all floating objects in the first set, combined with the current positional information of the cleaning robots, an optimization algorithm is applied to determine the shortest or optimal path, aiming to optimize the overall navigation path (i.e., ensuring all cleaning robots reach the target point via the shortest total path and in the fastest time). This algorithm plans a cluster navigation path for the multiple cleaning robots, taking into account formation to avoid collisions. The first path planning result will control all cleaning robots to move together towards a large floating object, ensuring rapid and efficient cleanup. This solves the technical challenge of a single cleaning robot being unable to handle large and heavy floating objects. For floating objects that may endanger reservoir safety (such as large tree trunks), it enables rapid mobilization of collective resources for quick disposal, improving the system's safety and reliability.
[0075] For small-volume floating objects in the second set of floating objects, the required number of robots for each small-volume floating object can be dynamically calculated based on its specific volume and the current status information of the cleaning robots (battery level, distance, etc.). For example, 3 robots are needed for a tree trunk, 2 for a pile of styrofoam, and 1 for a plastic bag. A corresponding number of robots can then be assigned from the robot cluster to form a "temporary collaborative cleaning group." This allows one or more cleaning robots to be allocated to each floating object in the second set, and the assigned robots can be controlled to navigate to their respective objects. Alternatively, all small floating objects in the second set can be treated as individual "points" to be visited. With the dual optimization objectives of minimizing the total salvage task completion time and optimizing the total navigation path, reinforcement learning or intelligent optimization algorithms (such as genetic algorithms or ant colony algorithms) can be used to determine which floating object(s) each cleaning robot is responsible for cleaning, the order in which each robot visits its assigned floating objects, and the optimal navigation path connecting these floating objects. The handling of small floating objects can greatly reduce the robot's "empty driving" mileage and repeated paths, achieving optimal global efficiency. Compared with random patrols or fixed area division, the cleaning efficiency can be improved by several times.
[0076] Based on the aforementioned robot path planning results, all cleaning robots are controlled to travel along the predetermined path to perform retrieval operations. The robot paths can be dynamically adjusted according to actual conditions (such as changes in floating objects, the appearance of obstacles, etc.) to complete the floating object retrieval work.
[0077] It is worth mentioning that, to address the risks associated with the operation of the cleaning robot in inclement weather, the control platform can comprehensively consider the impact of meteorological factors when planning the path and task. In one feasible implementation, environmental meteorological information of the aquatic environment can be acquired before step S200; this information includes, but is not limited to, wind speed, water level rise rate, and water level fall rate. Therefore, step S300 can specifically include steps S310 to S320:
[0078] Step S310: When the wind speed is greater than the preset wind speed, control all cleaning robots to activate their windproof anchors and lower their working height.
[0079] Step S320: When the water level rise rate is greater than the preset rise rate, control all cleaning robots to activate the pressure boosting and waterproofing function, and after detecting that the water level drop rate reaches the preset safety threshold, control all cleaning robots to perform salvage operations according to the robot path planning results.
[0080] The control platform can interface with the hydropower station's disaster early warning system to directly obtain environmental meteorological information within the aquatic environment. When the wind speed exceeds the preset wind speed, it indicates that the cleaning robot may face significant wind impact, especially when operating on the water surface, where wind can easily reduce the robot's stability. Therefore, all cleaning robots can be controlled to activate their wind anchors and lower their operating height. Wind anchors are stabilizing devices that increase the robot's anchoring force, preventing it from drifting or experiencing uneven stress in strong winds, which could lead to low operating efficiency or accidents. The gripping force of wind anchors is typically ≥5 tons. Simultaneously, lowering the operating height reduces the direct impact of wind speed, preventing the robot from being blown off its intended path or overturning.
[0081] When the rate of water level rise exceeds the preset rate, it indicates a potential flood risk that could threaten the robot's operational safety and the stability of the work area. In this situation, all cleaning robots can be controlled to activate their pressurized waterproofing function (activating the waterproof sealing chamber) to prevent water from entering the robots and ensure they are not damaged or submerged in rising water conditions. Operations are then delayed, and water level changes are continuously monitored. When the rate of water level drop reaches the preset safety threshold, it indicates that the water level can return to normal, and the salvage operation can be restarted. Therefore, after the water level drop rate reaches the preset safety threshold, the salvage operation can be restarted based on the robot's path planning results, improving the robot's adaptability and operational efficiency, reducing operational interruptions or risks caused by external environmental factors, and ensuring the smooth progress of the cleaning operation.
[0082] In addition, the above-mentioned environmental meteorological information also includes rainfall; when the rainfall exceeds the preset rainfall, for example, when the rainfall is >50mm / h, it corresponds to a red rainstorm warning. In order to avoid safety problems that may be caused by the sudden change in water flow due to heavy rain (such as the robot being submerged or malfunctioning), all cleaning robots can be controlled to raise their cleaning arms to stop the current operation and return to a safe base.
[0083] Understandably, the status information of all floating objects in the aquatic environment in this application embodiment can help to fully understand the distribution of floating objects. Therefore, robot path planning based on all floating object status information can allocate one or more floating objects to be cleaned to each cleaning robot from a global perspective, ensuring that each robot can efficiently and specifically clean up floating objects in the entire area. This avoids the blind cleaning and missed cleaning phenomena caused by the lack of global information in the random patrol mode, and can improve the coverage and efficiency of floating object retrieval.
[0084] For example, to help understand the implementation process of the floating object retrieval method in Embodiment 1, please refer to... Figure 2 and Figure 3 .
[0085] like Figure 3 As shown, Figure 3 This is a schematic diagram of the "edge-cloud" collaborative architecture involved in the floating object retrieval method in this example. Figure 3 The sensor terminals (visible light camera, thermal imaging camera, and sonar) and the BeiDou positioning terminal on the cleaning robot are deployed locally at the edge layer. Data collected by the sensor terminals can be input into a lightweight recognition model to obtain local floating object status information (including floating object location information). The BeiDou positioning terminal can use BeiDou positioning technology to perform centimeter-level location annotation on the cleaning robot's current position. The edge layer, through a 5G industrial router, can feed back the floating object coordinates and the cleaning robot's current position information to the cloud-based control platform. Based on the acquired floating object and cleaning robot location information, the control platform can perform dynamic path planning, then generate robot control commands from the path planning results and send them to the cleaning robot at the edge layer. The control platform also interfaces with a disaster early warning system to obtain environmental meteorological information about the aquatic environment for appropriate decision-making.
[0086] like Figure 2 As shown, Figure 2This is a flowchart illustrating the process architecture of a method for retrieving floating debris from water. Images of the water area are acquired using visible light cameras and thermal imaging cameras. The raw camera data is input into a pre-defined target detection model (such as a lightweight recognition model) to identify and locate floating debris within the water environment. Then, the corresponding 3D geocoding (i.e., current location information) is determined using the BeiDou positioning data of the debris-removing robot. Based on meteorological warning data obtained from a disaster warning system, an operational safety assessment is performed. Combining the aforementioned factors, dynamic path planning is conducted, ultimately generating the operational content, and controlling the debris-removing robot to carry out the operation according to the planned path. In this example, the operational safety assessment based on meteorological warning data mainly includes the following: when rainfall > 50 mm / h, a red rainstorm warning is triggered, at which point the debris-removing robot is controlled to immediately terminate the operation and return to base; when the water level rise rate > 0.5 m / h, a flood warning is triggered, controlling the debris-removing robot to delay the operation and activate the equipment's pressure-boosting and waterproofing functions; when the wind speed > 10.8 m / s (approximately level 6 gale), a gale warning is triggered, allowing the debris-removing robot to lower its operating height and activate its windproof anchor. In practical applications, the response latency for a red rainstorm warning can be ≤10s, for a flood warning ≤30s, and for a gale warning, the anchoring response latency can be ≤15s. Some of the aforementioned solutions can be deployed and implemented using the code snippets in the following example:
[0087] "class CleaningSystem:
[0088] def__init__(self):
[0089] self.camera_net = CameraNetwork(num_nodes = 12) # Camera network
[0090] self.beidou = BD2Receiver(accuracy = 0.05) # Beidou positioning
[0091] self.robots = [AmphibiousRobot(id = i) for i in range(4)] # Amphibious Robot
[0092] def execute_cleaning(self):
[0093] while True:
[0094] debris_map = self.detect_debris() # Floating object recognition model
[0095] if weather_system.check_safety(): # Weather safety check
[0096] task_list=planner.generate_task(debris_map)
[0097] For the robot in self.robots:
[0098] robot.assign_task(task_list.pop(0))
[0099] def emergency_stop(self):
[0100] if weather_system.hazard_level>X: # The hazard level exceeds the threshold X
[0101] For the robot in self.robots:
[0102] robot.return_to_base().
[0103] The above examples demonstrate how integrated identification, precise BeiDou positioning, meteorological early warning analysis, and collaborative operation of intelligent cleaning robots can achieve comprehensive management of floating debris in waterways. It should be noted that the above examples are for understanding this application only and do not constitute a limitation on the floating debris retrieval method described in this application. Any simple modifications based on this technical concept are within the scope of protection of this application.
[0104] This application provides a floating object retrieval system, which includes a control platform and at least one cleaning robot.
[0105] The control platform includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform the floating object retrieval method in Embodiment 1 described above.
[0106] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a control platform suitable for implementing embodiments of this application. The control platform in these embodiments may include, but is not limited to, mobile terminals such as laptops, digital broadcast receivers, and PADs (Portable Application Description: Tablet computers), as well as fixed terminals such as desktop computers. Figure 4 The control platform shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0107] like Figure 4 As shown, the control platform may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the control platform. The processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the control platform to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a control platform with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.
[0108] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0109] All debris removal robots are connected to a control platform and can be used to perform floating debris retrieval operations. The robot may include a Beidou positioning chip for centimeter-level precision positioning; the Beidou positioning chip can be the Hexin Xingtong UM960, supporting BDS-3 full-frequency positioning. The robot may also include a 50MPa cavitation jet module and a layered filtration chamber; the cleaning chamber volume of the robot can be 2m³. 3The cleaning robot with the above structure has a single-unit processing speed of ≥100kg / h, which is significantly improved compared to the cleaning speed of general mechanical grippers (30kg / h). Multiple robots working together can effectively increase the cleaning coverage area, with a collaborative processing coverage area greater than or equal to 5000m². 3 The coverage area is higher than that of a single-player random patrol (≤1000m). 3 ).
[0110] The aforementioned floating object retrieval system may also include multi-source sensing devices. These devices can be connected to a control platform to identify and locate floating objects in the aquatic environment and send information about the floating objects' status to the control platform. The multi-source sensing devices include visible light cameras, thermal imaging cameras, and side-scan sonar. In practical applications, the visible light camera and thermal imaging camera can be integrated into a single unit, using an industrial television camera model Hikvision DS-2DF8836IX-A, which features 40x optical zoom and thermal imaging capabilities, enabling accurate identification and capture of floating objects.
[0111] The floating debris retrieval system provided in this application, employing the floating debris retrieval method described in the above embodiments, can solve the technical problems of low cleaning coverage and low cleaning efficiency of cleaning robots in related technologies. Compared with related technologies, the beneficial effects of the floating debris retrieval system provided in this application are the same as those of the floating debris retrieval method provided in the above embodiments, and other technical features of this floating debris retrieval system are the same as those disclosed in the previous embodiment method, and will not be repeated here.
[0112] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0113] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0114] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the waterborne object retrieval method described in the above embodiments.
[0115] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0116] The aforementioned computer-readable storage medium may be included in the control platform; or it may exist independently and not be assembled into the control platform.
[0117] The aforementioned computer-readable storage medium carries one or more programs. When the control platform executes the aforementioned one or more programs, the control platform causes the control platform to: acquire the floating object status information corresponding to all floating objects in the aquatic environment and the current status information of all cleaning robots; wherein, the floating object status information includes floating object location information, and the current status information includes current location information and current battery level information; generate robot path planning results based on all floating object status information and all current status information; the robot path planning results include the floating object location information corresponding to one or more floating objects to be cleaned assigned to each cleaning robot; and control all cleaning robots to perform salvage operations based on the robot path planning results.
[0118] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0120] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0121] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described method for retrieving floating objects from water. This solves the technical problems of low cleaning coverage and low cleaning efficiency of cleaning robots in related technologies. Compared with related technologies, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the floating object retrieval method provided in the above embodiments, and will not be elaborated upon here.
[0122] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for salvaging floating objects on water.
[0123] The computer program product provided in this application can solve the technical problems of low cleaning coverage and low cleaning efficiency of cleaning robots in related technologies. Compared with related technologies, the beneficial effects of the computer program product provided in this application are the same as those of the floating debris retrieval method provided in the above embodiments, and will not be repeated here.
[0124] The above description is only a part of the embodiments of this application and does not limit the scope of protection. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included within the scope of protection.
Claims
1. A method for salvaging floating objects on water, characterized in that, A control platform for a floating debris retrieval system, the control platform being connected to at least one debris removal robot; the floating debris retrieval method includes: Acquire the floating object status information corresponding to all floating objects in the aquatic environment and the current status information of all the cleaning robots; wherein, the floating object status information includes floating object location information, and the current status information includes current location information and current battery level information; Based on all the floating object status information and all the current status information, a robot path planning result is generated; the robot path planning result includes the floating object location information corresponding to one or more floating objects to be cleaned, assigned to each of the cleaning robots; Based on the robot path planning results, all the cleaning robots are controlled to perform salvage operations.
2. The method for salvaging floating objects on water as described in claim 1, characterized in that, Before the step of generating robot path planning results based on all the floating object state information and all the current state information, the method further includes: Acquire environmental meteorological information within the aquatic environment; the environmental meteorological information includes wind speed, water level rise rate, and water level fall rate. The step of controlling all the cleaning robots to perform the salvage operation based on the robot path planning results includes: When the wind speed is greater than the preset wind speed, control all the cleaning robots to activate their windproof anchors and lower their working height; If the rate of water level rise exceeds the preset rate of rise, control all the cleaning robots to activate the pressure boosting and waterproofing function. After detecting that the rate of water level drop reaches the preset safety threshold, control all the cleaning robots to perform the salvage operation according to the robot path planning result.
3. The method for salvaging floating objects on water as described in claim 2, characterized in that, The environmental meteorological information also includes rainfall; after the step of acquiring environmental meteorological information within the aquatic environment, the method further includes: If the rainfall exceeds the preset rainfall amount, control all the cleaning robots to return to the safe base.
4. The method for salvaging floating objects on water as described in claim 1, characterized in that, The floating object status information also includes the floating object volume; the cleaning robot includes multiple robots; the step of generating robot path planning results based on all the floating object status information and all the current status information includes: A first set of floating objects is determined based on all floating objects whose volume is greater than a preset volume threshold. A second set of floating objects is determined based on all floating objects whose volume is less than or equal to a preset volume threshold. Based on the location information of all floating objects in the first set of floating objects and all the current status information, the first path planning result is determined with the optimization objective of the optimal total navigation path; the first path planning result is used to control all cleaning robots to move together toward a single floating object. Based on the location information of all floating objects in the second set of floating objects and all the current status information, the second path planning result is determined with the optimization objectives of minimizing the total salvage task completion time and optimizing the total navigation path. The second path planning result is used to assign one or more cleaning robots to each floating object in the second set of floating objects, and to control the assigned cleaning robots to drive to the corresponding floating object.
5. The method for salvaging floating objects on water as described in claim 1, characterized in that, The steps for obtaining the floating object status information corresponding to each floating object in the aquatic environment include: Sensing data of the aquatic environment are collected through multi-source sensing devices, including visible light cameras, thermal imaging cameras, and side-scan sonar. The sensed data is fused and image-enhanced to identify and locate floating objects in the aquatic environment, thereby obtaining the state information of the floating objects.
6. A system for salvaging floating objects on water, characterized in that, The floating object retrieval system includes: A control platform, the control platform including a memory, a processor and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the method for retrieving floating objects on water as described in any one of claims 1 to 5; At least one cleaning robot is connected to the control platform to perform floating debris retrieval operations.
7. The floating object retrieval system as described in claim 6, characterized in that, The floating object retrieval system also includes: A multi-source sensing device, connected to the control platform, is used to identify and locate floating objects in the aquatic environment; the multi-source sensing device includes a visible light camera, a thermal imaging camera, and a side-scan sonar.
8. The floating object retrieval system as described in claim 6, characterized in that, The cleaning robot includes a Beidou positioning chip; and / or a 50MPa cavitation jet module and a layered filter chamber.
9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the method for salvaging floating objects on water as described in any one of claims 1 to 5.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the method for salvaging floating objects on water as described in any one of claims 1 to 5.