Water surface cleaning unmanned ship assisted to perceive by unmanned aerial vehicle and operation method of water surface cleaning unmanned ship

Abstract

The invention provides a water surface cleaning unmanned ship assisted by an unmanned aerial vehicle to perceive and an operation method thereof, the unmanned ship adopts a double-ship-body structure, and a sensor module, a controller module, a data transmission module, a power supply module and an execution module are arranged on a ship body. And the unmanned ship receives a two-dimensional grid map obtained by executing the SLAM mapping task by the unmanned aerial vehicle and junk information identified by the unmanned aerial vehicle through the data transmission module. And the controller module plans a floating garbage cleaning task according to the received information. Further, the unmanned ship uses a sensor module to perform secondary identification on the garbage preliminarily identified by the unmanned aerial vehicle, and dynamically corrects the predetermined route in combination with the real-time environment information. The application condition of the unmanned water surface garbage cleaning ship is improved, and the problem that an existing garbage cleaning ship is not high in detection and cleaning precision is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of water environment management, and in particular to an unmanned water surface cleaning boat assisted by drone sensing and an operation method thereof. Background Art

[0002] With the acceleration of urbanization, many cities are facing the problem of difficulty in quickly cleaning up floating objects on the water surface. These garbage will not only cause excessive growth of aquatic plants and destroy the water ecological balance, but also seriously affect the beauty and environmental quality of scenic spots. At present, although large garbage cleaning ships on the market can handle surface garbage to a certain extent, they usually have some limitations. These ships often require manual cooperation to achieve semi-automatic operation, and due to their large size and high cost, they are not suitable for cleaning small waters such as artificial lakes.

[0003] At present, garbage cleaning in small waters mainly relies on manual work, which is not only inefficient but also has certain safety risks. Manual cleaning methods are difficult to adapt to the high efficiency and safety requirements of modern cities for water surface cleaning, so a new solution is urgently needed. Summary of the invention

[0004] In view of the above problems, the present invention proposes a drone-assisted sensing water surface cleaning unmanned boat and its operation method. This unmanned boat can meet the basic automation tasks such as garbage detection, garbage positioning and garbage salvage, and replace the manual salvage of surface garbage. In addition, the unmanned boat can realize unmanned operation and automatically collect floating objects on the water surface, which helps to reduce labor costs and improve the safety of cleaning work. It can also be widely used in various small waters, including artificial lakes, park lakes, etc., to effectively maintain the cleanliness and ecological health of water bodies.

[0005] In order to realize the above-mentioned technical features, the purpose of the present invention is realized as follows: a drone-assisted sensing water surface cleaning unmanned boat comprises a hull, on which is arranged a structural component for floating support of the entire hull; the hull is equipped with an execution module for providing hull movement and garbage cleaning; the hull is equipped with a sensor module for garbage identification and hull control; the sensor module is connected to a controller module, and the controller module realizes intelligent identification of floating objects on the water surface and planning of cleaning routes by receiving and processing environmental information collected by the sensor module in real time; it also includes a data transmission module, which is responsible for data transmission between the drone and the unmanned boat, and between the unmanned boat and the remote monitoring platform; it also includes a power supply module for providing electrical energy.

[0006] Preferably, the structural components include buoys, which are respectively installed at the front and rear ends of the hull and provide sufficient buoyancy for the hull; a garbage bin is installed in a detachable structure in the middle recess of the hull; a conveyor belt mechanism for conveying garbage is installed obliquely in front of the hull, and a water pump and a spray head for cleaning garbage are installed at the tail of the conveyor belt mechanism; a trapezoidal frame is fixedly installed at the rear end of the hull; and a guide plate for collecting garbage is installed at the front end of the hull and is arranged in an eight-shaped shape.

[0007] Preferably, the end of the deflector is equipped with a coaxially mounted cutting device and an anti-collision wheel, and is used to cut up large floating objects on the water surface to protect the hull from damage; Algae removal devices are symmetrically distributed on the guide plates on both sides of the center line of the hull, and the algae removal devices are used to remove algae on the water surface.

[0008] Preferably, lighting lamps are installed on both sides of the top of the hull, which are arranged above the first camera recognition sensor and the second camera recognition sensor and are used to provide auxiliary lighting at night or in low-light environments to ensure that the camera can effectively identify and locate surface garbage.

[0009] Preferably, the execution module comprises a left propeller motor and a right propeller motor installed on the left and right sides of the stern of the hull, and the left propeller motor and the right propeller motor work together to provide propulsion and heading control of the ship; The first conveyor belt motor and the second conveyor belt motor are installed at both ends of the conveyor belt mechanism and are used to drive the conveyor belt mechanism to operate and transport the garbage to the garbage bin.

[0010] Preferably, the first cutting device motor and the second cutting device motor are installed at the front end of the guide plate, coaxially with the anti-collision wheel and the cutting device, and are used to drive the cutting device to chop floating objects that are difficult to collect directly.

[0011] Preferably, the sensor module includes a first camera recognition sensor and a second camera recognition sensor installed on the left and right sides of the front end of the hull, the first camera recognition sensor and the second camera recognition sensor work together to perform secondary recognition of the surface garbage pre-recognized by the drone, and dynamically correct the scheduled route in combination with real-time environmental information, so that the unmanned boat can accurately go to the target point; The lidar sensor is installed in the center of the hull's trapezoidal frame to perform high-precision distance measurements and three-dimensional environment modeling; The first ultrasonic sensor and the second ultrasonic sensor are arranged on both sides of the hull, and the detected close-range obstacle information is fused with the point cloud data generated by the lidar sensor to supplement the detection blind spot of the lidar and ensure more accurate obstacle positioning and shape information.

[0012] Preferably, the RTK positioning sensor and the IMU sensor are installed on the hull ladder frame and are used for positioning and attitude monitoring of the hull; The tilt sensor is installed at the bottom of the left side of the trash bin to monitor and transmit the tilt angle data of the hull to the controller module in real time; The weight sensor is installed at the bottom of the right side of the trash bin to monitor the weight of the trash. The data is transmitted to the controller module and an overload alarm is issued when the preset threshold is reached; Volume sensor: installed on the top of the trash bin to monitor the height of the garbage pile and provide an indication when it is close to full load; The power module is installed behind the hull ladder frame of the ship. It consists of a high-performance rechargeable battery pack, which is compatible with shore-based solar charging stations and supports solar charging. The power status can be displayed locally and transmitted to the remote monitoring platform via Wi-Fi; The shore-based solar charging station comprises: Solar photovoltaic panels: responsible for collecting solar energy and converting it into electrical energy; Energy storage system: stores the converted electrical energy to ensure the continuity and stability of the unmanned boat charging; Charging port: Automatic charging port designed specifically for unmanned boats, enabling fast charging of unmanned boats; Control unit: An intelligent control unit responsible for optimizing charging plans and improving energy efficiency; Protection device: ensure the safety of the charging process and prevent risks such as overcharging and short circuit; The remote monitoring platform includes: Central processing unit: responsible for processing various data and instructions from the unmanned ship; User interface: Provides an intuitive operating interface that enables operators to easily monitor and control the unmanned vessel; Data storage system: stores environmental data, operation status and other information collected by the unmanned ship; Communication system: ensure data transmission and communication coordination between the unmanned ship and the monitoring platform; Analysis tools: Analyze the collected data to optimize operation strategies and improve operation efficiency; Alarm system: monitors the operating status of the unmanned boat and issues an alarm immediately if any abnormality is detected.

[0013] On the other hand, the present invention provides an operation method of a water surface cleaning unmanned boat with drone-assisted perception, the operation method is based on the water surface cleaning unmanned boat, and the operation method comprises the following steps: Step 1: The drone and unmanned boat travel to the target waters and detect the surrounding water environment; Step 2: Enter the corresponding IP in the remote monitoring platform to establish communication with the drone and unmanned ship; Step 3: The drone takes off to a suitable height, and uses the Cartographer algorithm to map the target waters according to the planned route, while using the yoloV8 detection model to identify floating garbage on the water surface; Step 4: The drone returns, and at the same time transmits the collected garbage coordinate information in the drone coordinate system and the two-dimensional grid map to the remote monitoring platform and the unmanned ship through the data transmission module; Step 5: The remote monitoring platform converts the garbage coordinates collected by the drone into the unmanned ship coordinate system; Step 6: The remote monitoring platform traverses the detected garbage coordinates. At the same time, the unmanned ship reads the current position and attitude information through the RTK positioning sensor and IMU sensor and transmits it to the remote monitoring platform. The remote monitoring platform first uses the improved particle swarm algorithm to obtain the optimal order for the unmanned ship to go to all garbage coordinates, and then uses the hybrid A* algorithm to plan the local path between the current garbage coordinate and the next garbage coordinate; Step 7: The unmanned boat uses the MPC-CBF algorithm to track the path obtained by the hybrid A* algorithm and dynamically avoid local obstacles. At the same time, the laser radar starts to build a map, the binocular camera obtains the video stream of the current scene, and uses the yoloV8 detection model to perform secondary recognition of floating garbage in each frame of the video stream; Step 8: The binocular camera identifies the garbage and outputs the distance and location coordinates of the garbage through binocular ranging. The motor receives the driving signal to perform differential steering and adjust the position of the unmanned boat to the location of the garbage. Step 9: The guide plate gathers the floating garbage, and the conveyor belt mechanism transports the garbage to the storage bin; Step 10: Repeat steps 7 to 9 until the garbage cleaning task in the target waters is completed and the unmanned boat returns.

[0014] Preferably, a multi-strategy path optimization and obstacle avoidance algorithm is also included, including the following steps: (1) Initialize the population, set the number of target points and the number of iterations, and use the local search strategy to enhance the local search performance of the particle swarm optimization algorithm; (2) Use crossover and mutation mechanisms to replace the speed update step in PSO to effectively explore the solution space and obtain individual optimal solutions and global optimal solutions; (3) After reaching the preset number of iterations, an optimized path node access sequence is obtained; (4) Using the optimized path node access sequence as the starting point of the hybrid A* algorithm; (5) Put the nodes into Openlist in pairs. If Openlist is empty, the path search is completed; otherwise, extract the node with the minimum cost as the current node; (6) Determine whether the current node is the end point. If so, the node is the path point searched by the hybrid A* algorithm; otherwise, the Dubins path is used to connect the current node and the target node, and obstacle detection is performed; (7) If there is an obstacle, expand the current node and update the Openlist to continue searching; (8) Finally, a series of path points generated by the hybrid A* algorithm are obtained and used as reference points for the model predictive control algorithm to achieve path following; (9) In this process, the obstacle function is controlled as an inequality constraint to ensure that the unmanned ship can effectively perform dynamic obstacle avoidance during the mission.

[0015] The present invention has the following beneficial effects: 1. Improve search efficiency and operational flexibility: The operation method of the present invention combines the mobility and wide field of view of the drone to quickly and efficiently identify and locate surface garbage, effectively broaden the operational field of view of the unmanned boat, and significantly improve the efficiency of garbage search and cleaning. At the same time, the real-time monitoring and remote operation functions of the remote monitoring platform further improve the flexibility and safety of the operation.

[0016] 2. Enhanced cleaning effect and environmental adaptability: The design of the surface cleaning unmanned boat reduces the restrictions on garbage types and working scenes, greatly improving the effect of garbage cleaning. The intelligent unmanned cleaning method makes up for the shortcomings of manual salvage and traditional mechanical salvage, and realizes the effective treatment of various surface garbage. In addition, the unmanned boat has a compact structure design and a large garbage storage space, which can adapt to the cleaning needs of different water environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0018] Figure 1 It is a schematic diagram of the overall structure of the water surface cleaning unmanned boat of the present invention.

[0019] Figure 2 It is a schematic diagram of the side structure of the water surface cleaning unmanned boat of the present invention.

[0020] Figure 3 It is a schematic diagram of the back structure of the water surface cleaning unmanned boat of the present invention.

[0021] Figure 4 It is a schematic diagram of the installation of the sensor module of the surface cleaning unmanned boat of the present invention.

[0022] Figure 5 The figure is a schematic diagram of the installation of the power module of the surface cleaning unmanned boat of the present invention.

[0023] Figure 6The figure is a schematic diagram of the installation of the controller module of the water surface cleaning unmanned boat of the present invention.

[0024] Figure 7 The figure is a schematic diagram of the installation of the data transmission module of the water surface cleaning unmanned boat of the present invention.

[0025] Figure 8 This is a schematic diagram of the first installation structure of the execution module of the water surface cleaning unmanned boat of the present invention.

[0026] Fig. 9 This is a schematic diagram of a second installation structure of the execution module of the surface cleaning unmanned boat of the present invention.

[0027] Fig.10 This is a schematic diagram of the first installation structure of the structural components of the water surface cleaning unmanned boat of the present invention.

[0028] Fig.11 This is a schematic diagram of the first installation structure of the structural components of the water surface cleaning unmanned boat of the present invention.

[0029] Fig.12 This is a schematic diagram of the first installation structure of the structural components of the water surface cleaning unmanned boat of the present invention.

[0030] Fig.13 It is a schematic diagram of the shore-based solar charging station and remote monitoring platform of the present invention.

[0031] Fig.14 The integrated flow chart of the unmanned ship path planning algorithm of the present invention.

[0032] In the figure: sensor module 10, power module 20, controller module 30, data transmission module 40, execution module 50, structural component 60; A first camera recognition sensor 101, a second camera recognition sensor 102, a laser radar sensor 103, a first ultrasonic distance sensor 104, a second ultrasonic distance sensor 105, an RTK positioning sensor 106, an IMU sensor 107, an inclination sensor 108, a weight sensor 109, and a volume sensor 110; A propeller left motor 501, a propeller right motor 502, a first conveyor belt motor 503, a second conveyor belt motor 504, a first cutting device motor 505, and a second cutting device motor 506; Floating drum 601 , trash bin 602 , conveyor belt mechanism 603 , water pump 604 , sprinkler head 605 , ladder-shaped frame 606 , guide plate 607 , cutting device 608 , anti-collision wheel 609 , lighting lamp 610 , algae removal device 611 . DETAILED DESCRIPTION

[0033] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0034] Embodiment 1: The present embodiment provides a surface cleaning unmanned boat with drone-assisted perception, including a hull, on which a structural component 60 for floating support of the entire hull is arranged; an execution module 50 for providing hull movement and garbage cleaning is installed on the hull; a sensor module 10 for garbage identification and hull control is installed on the hull; the sensor module 10 is connected to a controller module 30, and the controller module 30 realizes intelligent identification of floating objects on the water surface and planning of cleaning routes by receiving and processing environmental information collected by the sensor module 10 in real time; it also includes a data transmission module 40, which is responsible for data transmission between the drone and the unmanned boat, and between the unmanned boat and the remote monitoring platform; and it also includes a power supply module 20 for providing electric energy. The unmanned boat receives the two-dimensional grid map obtained by the drone performing the SLAM mapping task and the garbage information identified by the drone through the data transmission module. The controller module plans the cleaning task of floating garbage based on the received information. Furthermore, the unmanned boat uses the sensor module to perform secondary identification of the garbage initially identified by the drone, and dynamically corrects the scheduled route in combination with real-time environmental information. It has improved the applicability of unmanned surface garbage cleaning ships and effectively solved the problem of low detection and cleaning accuracy of current garbage cleaning ships.

[0035] Furthermore, the unmanned boat system consists of three main parts: a surface garbage cleaning unmanned boat, a shore-based solar charging station and a remote monitoring platform.

[0036] like Figures 1 to 3 As shown, the present invention relates to a water surface cleaning unmanned boat assisted by drone sensing, the main components of which include: Sensor module 10: integrates multiple sensors to monitor the environmental information and working status of the unmanned ship in real time, and is connected to the controller module 30 to ensure real-time data transmission and processing.

[0037] Power module 20: provides power for the unmanned boat, and supplies power to the controller module 30, the data transmission module 40 and the execution module 50 through electrical connection to ensure the normal operation of the unmanned boat.

[0038] Controller module 30: receives data input from sensor module 10, processes information and issues control instructions to instruct execution module 50 to perform corresponding operations.

[0039] Data transmission module 40: responsible for data transmission between the unmanned ship, the unmanned aerial vehicle and the remote monitoring platform.

[0040] The execution module 50 drives the mechanical parts of the unmanned boat, such as the propeller and the garbage collection device, according to the instructions of the controller module 30 to complete the cleaning of the garbage on the water surface.

[0041] Structural component 60: constitutes the physical foundation of the unmanned ship, including the hull, garbage bin, conveyor belt, etc., supporting the structural integrity and functionality of the unmanned ship.

[0042] like Figure 4 Furthermore, the sensor module 10 includes a first camera recognition sensor 101, which is particularly installed on the right side of the front end of the hull, with an angle of 52.5° with the side of the ship, and is responsible for capturing image information on the right side of the hull's traveling direction.

[0043] The second camera recognition sensor 102 is particularly installed on the left side of the front end of the hull, with an angle of 52.5° with the side of the ship, and is responsible for capturing image information on the left side of the hull's traveling direction.

[0044] The first camera recognition sensor 101 and the second camera recognition sensor 102 form a 15° overlapping viewing angle in front of the hull, ensuring that there is no blind spot and covers a 120° image information range.

[0045] The first camera recognition sensor 101 and the second camera recognition sensor 102 work together to perform secondary recognition of the surface garbage pre-recognized by the drone, ensuring that the unmanned boat can quickly adjust its course and go directly to the target for effective cleaning.

[0046] Lidar sensor 103: positioned at the center of the hull ladder frame 606, performs high-precision distance measurement and three-dimensional environment modeling.

[0047] The first ultrasonic sensor 104 and the second ultrasonic sensor 105 are arranged on the side of the ship.

[0048] The close-range obstacle information detected by the first ultrasonic sensor 104 and the second ultrasonic sensor 105 is fused with the point cloud data generated by the lidar sensor 103 to supplement the detection blind area of ​​the lidar and ensure more accurate obstacle positioning and shape information.

[0049] The RTK positioning sensor 106 and the IMU sensor 107 are installed on the hull ladder frame 606 and are used for positioning and attitude monitoring of the hull.

[0050] Inclination sensor 108 : installed at the bottom of the left side of the garbage bin 602 , monitors in real time and transmits the hull inclination angle data to the controller module 30 .

[0051] Weight sensor 109: Installed at the right bottom of the trash bin 602, monitors the trash weight, transmits data to the controller module 30, and issues an overload alarm when a preset threshold is reached.

[0052] Volume sensor 110: Installed on the top of the trash bin 602, monitors the trash accumulation height and provides an indication when it is close to being full.

[0053] like Figure 5 ,Furthermore, the power module 20: is composed of a high-performance rechargeable battery pack, which is compatible with the shore-based solar charging station and supports solar charging. The power status can be displayed locally and transmitted to the remote monitoring platform via Wi-Fi.

[0054] In addition, the installation position of the power module 20 is located behind the hull ladder frame 606 of the hull. Such a layout helps to adjust the center of gravity of the unmanned boat, and by raising the bow and lowering the stern, the maneuverability and controllability of the boat are optimized, making the unmanned boat more stable and flexible when operating on the water.

[0055] like Figure 6 Furthermore, the controller module 30 as a core processing unit integrates powerful computing power and deep learning accelerator, which can quickly process the environmental information collected by the sensor module 10, realize the intelligent identification of floating objects on the water surface and the planning of cleaning routes.

[0056] The module supports multiple interfaces for connecting to high-definition cameras and peripherals, and has an audio codec and GPIO expansion port to ensure high-quality data and audio transmission, enabling the controller module 30 to perform complex visual tasks at a high frame rate.

[0057] In addition, the high energy efficiency ratio of the controller module 30 enables it to control power consumption at an extremely low level while maintaining high performance, which is very suitable for battery-powered unmanned ship applications.

[0058] like Figure 7 ,Furthermore, the data transmission module 40 is responsible for data transmission between the UAV and the unmanned ship and between the unmanned ship and the remote monitoring platform like Figure 8-9 Further, the execution module 50 includes a left propeller motor 501, a right propeller motor 502, a first conveyor belt motor 503, a second conveyor belt motor 505, a first cutting device motor 505 and a second cutting device motor 506. These motors receive instructions from the controller module 30 and perform corresponding actions to complete garbage cleaning tasks and other operations.

[0059] The left propeller motor 501 and the right propeller motor 502 are respectively installed on the left and right sides of the tail of the unmanned boat, and work together to provide propulsion and heading control for the boat. The first conveyor belt motor 503 and the second conveyor belt motor 505 are installed at both ends of the conveyor belt mechanism 603 to drive the conveyor belt to operate and transport the garbage to the garbage bin 602.

[0060] The first cutting device motor 505 and the second cutting device motor 506 are installed at the front end of the guide plate 607, coaxially installed with the anti-collision wheel 609 and the cutting device 608, and are used to drive the cutting device 608 to chop floating objects such as water plants and branches that are difficult to collect directly, so as to avoid affecting the normal operation of the unmanned boat.

[0061] like Figure 10-12 , further, the structural component 60 specifically includes: Buoys 601: are installed at the front and rear ends of the hull, respectively, and are located at 1 / 5 of the total length of the hull to ensure that the hull has sufficient buoyancy and stability.

[0062] Trash bin 602: Located in the concave part in the middle of the hull, it adopts a detachable design to facilitate quick loading and unloading of trash.

[0063] Conveyor belt mechanism 603: Located in front of the unmanned boat, it is configured in an inclined shape and is provided with leakage holes and rectangular holes at the bottom of the baffle to prevent the accumulation of garbage and water.

[0064] Water pump 604 and spray head 605: The spray head is installed above the tail of the conveyor belt mechanism and is supplied with water by the water pump to clean the garbage on the conveyor belt and keep the conveyor belt clean.

[0065] Ladder frame 606: installed at the rear end of the hull to provide necessary structural support for the unmanned ship.

[0066] Guide plate 607: Located at the front end of the hull, it is equipped with a coaxially mounted cutting device 608 and an anti-collision wheel 609, which are used to cut up large floating objects on the water surface and protect the hull from damage.

[0067] Lighting lamp 610: It is arranged above the camera recognition sensors 101 and 102 to provide auxiliary lighting at night or in low-light environments, ensuring that the camera can effectively identify and locate surface garbage.

[0068] Algae removal device 611: symmetrically distributed on the guide plates 607 on both sides of the center line of the hull, dedicated to removing algae on the water surface.

[0069] like Fig.13 , the shore-based solar charging station consists of the following parts: Solar photovoltaic panels: responsible for collecting solar energy and converting it into electrical energy.

[0070] Energy storage system: stores the converted electrical energy to ensure the continuity and stability of the unmanned boat's charging.

[0071] Charging port: Automatic charging port designed specifically for unmanned boats to enable fast charging of unmanned boats.

[0072] Control unit: An intelligent control unit responsible for optimizing charging plans and improving energy efficiency.

[0073] Protection device: ensures the safety of the charging process and prevents risks such as overcharging and short circuit.

[0074] The remote monitoring platform consists of the following parts: Central processing unit: responsible for processing various data and instructions from the unmanned ship.

[0075] User Interface: Provides an intuitive operating interface that enables operators to easily monitor and control the unmanned vessel.

[0076] Data storage system: stores environmental data, operation status and other information collected by the unmanned ship.

[0077] Communication system: ensure data transmission and communication coordination between the unmanned ship and the monitoring platform.

[0078] Analysis tools: Analyze the collected data to optimize operation strategies and improve operation efficiency.

[0079] Alarm system: monitors the operating status of the unmanned boat and issues an alarm immediately if any abnormality is detected.

[0080] Embodiment 2: The unmanned ship receives the two-dimensional grid map obtained by the drone performing the SLAM mapping task through the data transmission module, and adopts a multi-strategy path optimization and obstacle avoidance algorithm to plan the path of multiple target points, wherein the multi-strategy path optimization and obstacle avoidance algorithm integrates the following algorithms: Improved particle swarm algorithm: used for global path planning of unmanned ships to multiple target points, replacing traditional speed updates with crossover and mutation operations to avoid falling into local optimal solutions and ensure global path optimization.

[0081] Improved hybrid A* algorithm: used for local path planning between target points, enhancing the smoothness of the path by introducing steering angle and turning cost.

[0082] Model Predictive Control (MPC) and Constraint-Based Fast Search (CBF): The path points planned by the improved hybrid A* algorithm are used as intermediate waypoints in the local planner to achieve effective avoidance of dynamic and static obstacles and accurate trajectory tracking.

[0083] Embodiment 3: like Fig.14As shown in the figure, the steps of multi-strategy path optimization and obstacle avoidance algorithm are as follows: (1) Initialize the population, set basic parameters such as the number of target points and the number of iterations, and use the local search strategy to enhance the local search performance of the particle swarm optimization algorithm.

[0084] (2) The crossover and mutation mechanisms are used to replace the velocity update step in traditional PSO to effectively explore the solution space and obtain individual optimal solutions and global optimal solutions.

[0085] (3) After reaching the preset number of iterations, an optimized path node access sequence is obtained.

[0086] (4) Use the optimized path node access sequence as the starting point of the hybrid A* algorithm.

[0087] (5) Put the nodes into Openlist in pairs. If Openlist is empty, the path search is completed; otherwise, extract the node with the lowest cost as the current node.

[0088] (6) Determine whether the current node is the end point. If so, the node is the path point searched by the hybrid A* algorithm; otherwise, the Dubins path is used to connect the current node and the target node, and obstacle detection is performed.

[0089] (7) If there is an obstacle, expand the current node and update the Openlist to continue searching.

[0090] (8) Finally, a series of path points generated by the hybrid A* algorithm are obtained and used as reference points for the model predictive control algorithm to achieve path following.

[0091] (9) In this process, the obstacle function is controlled as an inequality constraint to ensure that the unmanned ship can effectively perform dynamic obstacle avoidance during the mission.

[0092] Embodiment 4: A method for operating a water surface cleaning unmanned boat with drone-assisted sensing includes the following steps: Step 1: The drone and unmanned boat travel to the target waters and detect the surrounding water environment; Step 2: Enter the corresponding IP in the remote monitoring platform to establish communication with the drone and unmanned ship; Step 3: The drone takes off to a suitable height, and uses the Cartographer algorithm to map the target waters according to the planned route, while using the yoloV8 detection model to identify floating garbage on the water surface; Step 4: The drone returns, and at the same time transmits the collected garbage coordinate information in the drone coordinate system and the two-dimensional grid map to the remote monitoring platform and the unmanned ship through the data transmission module; Step 5: The remote monitoring platform converts the garbage coordinates collected by the drone into the unmanned ship coordinate system; Step 6: The remote monitoring platform traverses the detected garbage coordinates. At the same time, the unmanned ship reads the current position and attitude information through the RTK and attitude sensors and transmits it to the remote monitoring platform. The remote monitoring platform first uses the improved particle swarm algorithm to obtain the optimal order for the unmanned ship to go to all garbage coordinates, and then uses the improved hybrid A* algorithm to plan the local path between the current garbage coordinate and the next garbage coordinate; Step 7: The unmanned boat uses the MPC-CBF algorithm to track the path obtained by the hybrid A* algorithm and dynamically avoid local obstacles. At the same time, the laser radar starts to build a map, the binocular camera obtains the video stream of the current scene, and uses the yoloV8 detection model to perform secondary recognition of floating garbage in each frame of the video stream; Step 8: The binocular camera identifies the garbage and outputs the distance and location coordinates of the garbage through binocular ranging. The motor receives the driving signal to perform differential steering and adjust the position of the unmanned boat to the location of the garbage. Step 9: The guide plate gathers the floating garbage, and the conveyor belt transports the garbage to the storage bin; Step 10: Repeat steps 7 to 9 until the garbage cleaning task in the target waters is completed and the unmanned boat returns.

Claims

1. A drone-assisted sensing surface cleaning unmanned boat, characterized in that: The invention comprises a hull, on which is arranged a structural component (60) for floating and supporting the entire hull; the hull is equipped with an execution module (50) for providing hull movement and garbage cleaning; the hull is equipped with a sensor module (10) for garbage identification and hull control; the sensor module (10) is connected to a controller module (30), and the controller module (30) receives and processes environmental information collected by the sensor module (10) in real time, thereby realizing intelligent identification of floating objects on the water surface and planning of cleaning routes; the invention also comprises a data transmission module (40), and the data transmission module (40) is responsible for data transmission between a drone and an unmanned ship, and between an unmanned ship and a remote monitoring platform; and the invention also comprises a power supply module (20) for providing electric energy.

2. According to claim 1, a drone-assisted sensing water surface cleaning unmanned boat is characterized in that: The structural assembly (60) comprises buoys (601), which are respectively installed at the front and rear ends of the hull and provide sufficient buoyancy for the hull; a garbage bin (602) is installed in a detachable structure in the middle concave part of the hull; a conveyor belt mechanism (603) for conveying garbage is installed obliquely at the front of the hull, and a water pump (604) and a spray head (605) for cleaning garbage are installed at the tail of the conveyor belt mechanism (603); a ladder-shaped frame (606) is fixedly installed at the rear end of the hull; and a guide plate (607) for collecting garbage and arranged in an eight-shaped shape is installed at the front end of the hull.

3. According to claim 2, a drone-assisted sensing water surface cleaning unmanned boat is characterized in that: The end of the deflector (607) is equipped with a coaxially mounted cutting device (608) and an anti-collision wheel (609), and is used to cut up large floating objects on the water surface to protect the hull from damage; Algae removal devices (611) are symmetrically distributed on the guide plates (607) on both sides of the centerline of the hull, and the algae removal devices (611) are used to remove algae on the water surface.

4. According to claim 2, a drone-assisted sensing water surface cleaning unmanned boat is characterized in that: Lighting lamps (610) are installed on both sides of the top of the hull. The lighting lamps (610) are arranged above the first camera recognition sensor (101) and the second camera recognition sensor (102) and are used to provide auxiliary lighting at night or in an environment with insufficient light, thereby ensuring that the camera can effectively recognize and locate the garbage on the water surface.

5. According to claim 3, the drone-assisted sensing water surface cleaning unmanned boat is characterized in that: The execution module (50) comprises a left propeller motor (501) and a right propeller motor (502) installed on the left and right sides of the stern of the ship, and the left propeller motor (501) and the right propeller motor (502) work in coordination to provide propulsion and heading control for the ship; The first conveyor belt motor (503) and the second conveyor belt motor (505) are installed at both ends of the conveyor belt mechanism (603) and are used to drive the conveyor belt mechanism (603) to operate and transport the garbage to the garbage bin (602).

6. The surface cleaning unmanned boat with drone-assisted sensing according to claim 5, characterized in that: The first cutting device motor (505) and the second cutting device motor (506) are installed at the front end of the guide plate (607), and are coaxially installed with the anti-collision wheel (609) and the cutting device (608), and are used to drive the cutting device (608) to perform a shredding operation on floating objects that are difficult to collect directly.

7. The surface cleaning unmanned boat with drone-assisted sensing according to claim 5 is characterized in that: The sensor module (10) comprises a first camera recognition sensor (101) and a second camera recognition sensor (102) installed on the left and right sides of the front end of the hull, wherein the first camera recognition sensor (101) and the second camera recognition sensor (102) work in coordination to perform secondary recognition of surface garbage pre-recognized by the unmanned aerial vehicle, and dynamically correct the predetermined route in combination with real-time environmental information, so that the unmanned boat can accurately move to the target point; The laser radar sensor (103) is installed at the center of the hull ladder frame (606) for performing high-precision distance measurement and three-dimensional environment modeling; The first ultrasonic sensor (104) and the second ultrasonic sensor (105) are arranged on both sides of the hull, and the detected close-range obstacle information is fused with the point cloud data generated by the laser radar sensor (103) to supplement the detection blind area of ​​the laser radar, thereby ensuring that more accurate obstacle positioning and shape information is obtained.

8. The surface cleaning unmanned boat with drone-assisted sensing according to claim 7, characterized in that: The RTK positioning sensor (106) and the IMU sensor (107) are installed on the hull ladder frame (606) and are used for positioning and attitude monitoring of the hull; The tilt sensor (108) is installed at the bottom of the left side of the garbage bin (602) to monitor and transmit the tilt angle data of the hull to the controller module (30) in real time; A weight sensor (109) is installed at the bottom right of the trash bin (602) to monitor the weight of the trash, transmit the data to the controller module (30), and issue an overload alarm when a preset threshold is reached; Volume sensor (110): installed on the top of the garbage bin (602), monitoring the garbage accumulation height and providing an indication when it is close to being full; The power module (20) is installed at the rear of the hull ladder frame (606) of the hull, and is composed of a high-performance rechargeable battery pack, which is compatible with a shore-based solar charging station and supports solar charging. The power status can be displayed locally and transmitted to a remote monitoring platform via Wi-Fi; The shore-based solar charging station comprises: Solar photovoltaic panels: responsible for collecting solar energy and converting it into electrical energy; Energy storage system: stores the converted electrical energy to ensure the continuity and stability of the unmanned boat charging; Charging port: Automatic charging port designed specifically for unmanned boats, enabling fast charging of unmanned boats; Control unit: An intelligent control unit responsible for optimizing charging plans and improving energy efficiency; Protection device: ensure the safety of the charging process and prevent risks such as overcharging and short circuit; The remote monitoring platform includes: Central processing unit: responsible for processing various data and instructions from the unmanned ship; User interface: Provides an intuitive operating interface that enables operators to easily monitor and control the unmanned vessel; Data storage system: stores environmental data, operation status and other information collected by the unmanned ship; Communication system: ensure data transmission and communication coordination between the unmanned ship and the monitoring platform; Analysis tools: Analyze the collected data to optimize operation strategies and improve operation efficiency; Alarm system: monitors the operating status of the unmanned boat and issues an alarm immediately if any abnormality is detected.

9. A method for operating a water surface cleaning unmanned boat with drone-assisted sensing, characterized in that: The operation method is based on the unmanned water surface cleaning boat according to claim 8, and the operation method comprises the following steps: Step 1: The drone and unmanned boat travel to the target waters and detect the surrounding water environment; Step 2: Enter the corresponding IP in the remote monitoring platform to establish communication with the drone and unmanned ship; Step 3: The drone takes off to a suitable height, and uses the Cartographer algorithm to map the target waters according to the planned route, while using the yoloV8 detection model to identify floating garbage on the water surface; Step 4: The drone returns, and at the same time transmits the collected garbage coordinate information in the drone coordinate system and the two-dimensional grid map to the remote monitoring platform and the unmanned ship through the data transmission module (40); Step 5: The remote monitoring platform converts the garbage coordinates collected by the drone into the unmanned ship coordinate system; Step 6: The remote monitoring platform traverses the detected garbage coordinates, and the unmanned ship reads the current position and attitude information through the RTK positioning sensor (106) and the IMU sensor (107) and transmits it to the remote monitoring platform. The remote monitoring platform first uses the improved particle swarm algorithm to obtain the optimal order for the unmanned ship to go to all garbage coordinates, and then uses the hybrid A* algorithm to perform local path planning between the current garbage coordinate and the next garbage coordinate; Step 7: The unmanned boat uses the MPC-CBF algorithm to track the path obtained by the hybrid A* algorithm and dynamically avoid local obstacles. At the same time, the laser radar starts to build a map, the binocular camera obtains the video stream of the current scene, and uses the yoloV8 detection model to perform secondary recognition of floating garbage in each frame of the video stream; Step 8: The binocular camera identifies the garbage and outputs the distance and location coordinates of the garbage through binocular ranging. The motor receives the driving signal to perform differential steering and adjust the position of the unmanned boat to the location of the garbage. Step 9: The guide plate gathers the floating garbage, and the conveyor belt mechanism transports the garbage to the storage bin; Step 10: Repeat steps 7 to 9 until the garbage cleaning task in the target waters is completed and the unmanned boat returns.

10. The method for operating a water surface cleaning unmanned boat with drone-assisted sensing according to claim 9, characterized in that: It also includes a multi-strategy path optimization and obstacle avoidance algorithm, including the following steps: (1) Initialize the population, set the number of target points and the number of iterations, and use the local search strategy to enhance the local search performance of the particle swarm optimization algorithm; (2) Use crossover and mutation mechanisms to replace the speed update step in PSO to effectively explore the solution space and obtain individual optimal solutions and global optimal solutions; (3) After reaching the preset number of iterations, an optimized path node access sequence is obtained; (4) Using the optimized path node access sequence as the starting point of the hybrid A* algorithm; (5) Put the nodes into Openlist in pairs. If Openlist is empty, the path search is completed; otherwise, extract the node with the minimum cost as the current node; (6) Determine whether the current node is the end point. If so, the node is the path point searched by the hybrid A* algorithm; otherwise, the Dubins path is used to connect the current node and the target node, and obstacle detection is performed; (7) If there is an obstacle, expand the current node and update the Openlist to continue searching; (8) Finally, a series of path points generated by the hybrid A* algorithm are obtained and used as reference points for the model predictive control algorithm to achieve path following; (9) In this process, the obstacle function is controlled as an inequality constraint to ensure that the unmanned ship can effectively perform dynamic obstacle avoidance during the mission.

Images