Semi-submersible lifeboat and rescue control method thereof

Abstract

The invention discloses a semi-submersible lifeboat which comprises a boat body, and a power system, a semi-submersible system, a navigation control system, a sensing system, an interaction system and a control system are arranged on the boat body. The navigation control system is composed of a positioning module, a control module and a communication module. The sensing system comprises a camera and a sensing processor, the camera obtains image information of the surrounding environment and personnel, and the sensing processor obtains the position and state of a rescue target according to the image information and sends the position and state to the control module for processing through the communication module; the interaction system can collect voice signals of a rescue target and send out voice prompts to the rescue target at the same time. The control system is used for remotely controlling the lifeboat; the power system is arranged at the tail of the ship body and provides propulsive force for the ship body. The invention further provides a rescue control method, the difficulty that a rescue target is insufficient in strength and difficult to climb is avoided, and the rescue success rate is increased.

Description

Technical Field

[0001] This invention relates to the field of emergency rescue technology, and in particular to a semi-submersible lifeboat and its rescue control method. Background Technology

[0002] In the field of water emergency rescue, traditional lifeboats have long faced core problems such as complex operation, low response efficiency, and insufficient safety. Most existing lifeboats are buoyancy-based, relying on the rescue target to actively climb onto the hull. However, in actual rescues, the target often struggles to climb due to exhaustion, serious injury, or panic, resulting in a high failure rate. Furthermore, traditional lifeboats have a fixed course and cannot dynamically adjust to different rescue scenarios. For example, they are susceptible to instability due to waves in rough seas, or pose a collision risk due to improper speed control when approaching the rescue target. Summary of the Invention

[0003] The purpose of this invention is to overcome the above-mentioned defects in the prior art and provide a semi-submersible lifeboat and its rescue control method. This invention avoids the difficulties of rescue targets being too weak or unable to climb, and improves the success rate of rescue.

[0004] To achieve the above objectives, the present invention provides a semi-submersible lifeboat, including a hull, on which a power system, a semi-submersible system, a navigation control system, a sensing system, an interaction system, and a control system are provided;

[0005] The semi-submersible system is located in the mid-to-rear area of ​​the hull, enabling the hull to perform semi-submersible operations.

[0006] The navigation control system consists of a positioning module, a control module, and a communication module. The positioning module obtains the current position of the lifeboat, the communication module obtains the control commands, and the control module controls the navigation of the lifeboat according to the control commands.

[0007] The perception system includes a camera and a perception processor. The camera acquires image information of the surrounding environment and people. The perception processor obtains the location and status of the rescue target based on the image information and sends it to the control module for processing through the communication module.

[0008] The interactive system can collect the voice signals of the rescue target and issue voice prompts to the rescue target.

[0009] The control system is used for remote control of the lifeboat;

[0010] The power system is located at the stern of the hull and provides propulsion for the hull.

[0011] Furthermore, the power system includes a waterjet propulsion system and a battery for providing power. The waterjet propulsion system is installed at the stern of the hull, and a battery compartment is provided in the middle of the hull for installing the battery.

[0012] Furthermore, the semi-submersible system includes a water pump, a water tank, a level sensor, and a semi-submersible controller. The level sensor is located inside the water tank and is used to detect the water volume inside the water tank. The semi-submersible controller is connected to the water pump and controls the amount of water in the water tank, thereby enabling the hull to submerge and float.

[0013] Furthermore, the control system comprises a remote control handle, a Bluetooth module, and a mobile app, wherein the remote control handle and the mobile app are respectively connected to the communication module via the Bluetooth module.

[0014] Furthermore, pressure sensors are installed on the surface of the hull.

[0015] A rescue control method is also provided, including the following steps:

[0016] S1. Based on the location of the rescue target, the lifeboat is controlled via a remote control system to move to the vicinity of the rescue target;

[0017] S2. Based on the location of the rescue target, move the rescue boat toward the rescue target and enter semi-submersible mode. Maintain semi-submersible mode while planning a route to approach the rescue target without colliding with it.

[0018] S3. Obtain the status of the rescue target, identify different statuses of the rescue target, send corresponding voice instructions, interact with the rescue target, and instruct the rescue target to hold onto the lifeboat;

[0019] S4. Based on the change in surface pressure of the lifeboat, determine whether the rescue target is holding onto the lifeboat securely. If it is confirmed that the target is holding onto the lifeboat securely, the lifeboat will rise to the surface, and an instruction will be issued to the lifeboat to return to a safe area.

[0020] Furthermore, in step S2, the route planning includes planning the lifeboat's turning, navigation attitude, and navigation path; when the lifeboat approaches the target, the water tank level h is monitored by a level sensor, and when... At that time, it is considered to have entered semi-submersible mode, in which It is a set value.

[0021] Furthermore, the lifeboat's steering is achieved by controlling its steering angle and thruster speed. The specific steps are as follows: The location coordinates of the rescue target are obtained via a camera. The current coordinates of the lifeboat are Then, the required turning angle δ and thruster speed ω of the lifeboat can be calculated as follows:

[0022] ;

[0023] ;

[0024] in This is the gain coefficient.

[0025] Furthermore, during the semi-submerged state, the lifeboat adjusts its navigation attitude by regulating the water levels in the forward and aft water tanks. Let the water level difference between the forward and aft water tanks be... , where h q h represents the water level depth of the forward water tank. h The water level depth of the aft water tank is given, and the pitch angle of the hull is given. ,but The size is calculated by the following formula

[0026] ;

[0027] in , , These are control parameters.

[0028] Furthermore, once the lifeboat enters semi-submersible mode, it identifies the location of the rescue target via a camera and plans its navigation path using the following algorithm, ensuring that the lifeboat reaches the rescue target's location at a speed of 0. Specifically: First, a Kalman filter is used to predict the next moment's position of the rescue target. ,in At the current speed, In terms of direction of motion;

[0029] Secondly, using the dynamic window method, the cost function C is defined as follows: ;

[0030] in The minimum distance between the path and the obstacle. The proximity of the path to the target. The norm of curvature, , , These are the weighting coefficients;

[0031] Finally, at each interval Recalculate the optimal path It also adjusts the thruster speed and heading angle in real time.

[0032] This invention achieves target localization and path planning through image recognition and sensor fusion, dynamically adjusts buoyancy distribution during semi-submersible / floating transitions, and compensates for the impact of mass changes on stability through an adaptive dynamics model, enabling efficient and safe rescue in complex aquatic environments.

[0033] Throughout the entire process, the person being rescued only needs to hold onto the lifeboat, making it simple to operate and greatly reducing the learning cost for the person being rescued. At the same time, by using a semi-submerged and then surfacing rescue method, the difficulties of insufficient strength and inability to climb are avoided, thus improving the success rate of the rescue. Attached Figure Description

[0034] To more clearly illustrate the technology in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram of the structure of the semi-submersible lifeboat of the present invention;

[0036] Figure 2 This is a flowchart illustrating the rescue control method of the present invention.

[0037] The diagram includes:

[0038] 1. Hull; 21. Forward water tank; 22. Aft water tank; 3. Camera; 31. Lookout post; 4. Waterjet propulsion; 41. Battery; 5. Navigation control system. Detailed Implementation

[0039] The technology of this embodiment of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiment is one embodiment of the present invention, and not all embodiments thereof. Based on this embodiment of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0041] Furthermore, if the embodiments of the present invention involve descriptions such as "first" or "second", such descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated.

[0042] This invention provides a semi-submersible lifeboat, such as Figure 1As shown, the vessel includes a hull 1, on which a power system, a semi-submersible system, a navigation control system 5, a sensing system, an interaction system, and a control system are installed.

[0043] A pressure sensor is installed on the surface of the hull 1 to sense pressure changes on the surface of the hull 1. When the rescue target boards the lifeboat, the pressure sensor instantly captures the change in weight distribution and transmits the signal to the navigation control system 5 and the sensing system to realize automatic balance adjustment and judgment of whether the rescue target has grabbed the lifeboat.

[0044] The hull 1 is a long and slender monohull, preferably in the shape of a long cylindrical bar. The bottom of the hull is a planing boat structure, and the top is a semi-circular structure. The overall center of gravity is distributed at the bottom, which gives the entire lifeboat a certain self-righting function. In the event of capsizing, it can automatically recover to a stable posture by relying on the gravitational torque.

[0045] The semi-submersible system is located in the aft region of the hull 1, enabling the hull 1 to perform semi-submersible operations. Specifically, the semi-submersible system includes a water pump, a water tank, a level sensor, and a semi-submersible controller. The water pump is connected to the water tank and is used to inject or drain water into the water tank. The level sensor is located inside the water tank and is used to monitor the water level in real time, feeding the data back to the semi-submersible controller. The semi-submersible controller controls the working state of the water pump according to a preset program and the sensor feedback signal, thereby regulating the descent and ascent process of the hull 1 to ensure stable and safe semi-submersible operations. Preferably, this embodiment has two water tanks, namely a forward water tank 21 and a rear water tank 22, as shown below. Figure 1 As shown, the forward water tank 21 and the aft water tank 22 are respectively located on the front and rear sides of the hull 1, and both the forward water tank 21 and the aft water tank 22 are independently controlled, which can realize the adjustment of the pitch angle of the hull 1 to adapt to the navigation needs under different sea conditions. At the same time, liquid level sensors are installed on both the forward water tank 21 and the aft water tank 22 to monitor the changes in liquid level in each tank in real time, ensuring precise control of the water injection and drainage process.

[0046] The navigation control system 5 consists of a positioning module, a control module, and a communication module. The positioning module obtains the current position of the lifeboat, the communication module obtains the control commands, and the control module controls the navigation of the lifeboat according to the control commands.

[0047] Preferably, the positioning module uses a GPS module or a Beidou module to ensure high-precision positioning in complex marine environments. The aforementioned communication module uses 5G and satellite dual-mode communication to ensure stable signal coverage throughout the nearshore area and automatically switches to satellite communication mode in signal blind spots to ensure uninterrupted command transmission.

[0048] The perception system includes a camera 3 and a perception processor. The camera 3 acquires image information of the surrounding environment and people. The perception processor obtains the location and status of the rescue target based on the image information and sends it to the control module for processing through the communication module.

[0049] Preferably, a lookout post 31 is installed on the hull 1, and a camera 3 is installed on the top of the lookout post 31. The camera 3 collects image information of the water surface around the hull 1 and then sends it to the perception processor. The perception processor can use a large model to identify the location and state of the rescue target, including states such as panic, calmness, and struggling.

[0050] The interactive system can collect the voice signals of the rescue target and issue voice prompts to the rescue target. Typically, the interactive system includes a voice acquisition module, a voice playback module, and an interactive controller. The voice acquisition module is used to capture the rescue target's distress calls or commands, while the voice playback module delivers reassuring information or operational instructions to the rescue target according to the instructions of the interactive controller. Specifically, the state of the rescue target is obtained through the aforementioned perception processor, and the interactive controller can send different voice instructions according to the state of the rescue target. For example, if the rescue target is panicked, it will be reassured and its panicked state will be alleviated through voice; if it is calm, it will be instructed on how to board the lifeboat.

[0051] Of course, back-end staff can also remotely connect to the interactive controller via the communication module to intervene in rescue dialogues in real time, thereby improving rescue efficiency and humanization.

[0052] The interactive controller has built-in multilingual recognition and synthesis functions, which can automatically match the language of the rescue target for communication, ensuring efficient communication across language barriers; at the same time, the voice acquisition module has noise suppression and sound source localization capabilities, which can accurately capture the voice of the person in distress in complex sea conditions.

[0053] The control system is used for remote control of the lifeboat. Specifically, the control system includes a remote control handle, a Bluetooth module, and a mobile app. The remote control handle and the mobile app are connected to the communication module via the Bluetooth module to remotely control various modules of the lifeboat, enabling remote operation. The mobile app provides a visual interface that displays the lifeboat's position, heading, battery level, and the status of the rescue target in real time. Users can set automatic navigation paths or switch to manual mode for precise control via the app. The Bluetooth module supports low-latency data transmission, ensuring rapid command response. In large-scale search and rescue missions, the Bluetooth module can establish stable connections with multiple lifeboats to achieve coordinated operations and improve search and rescue coverage efficiency.

[0054] The propulsion system is located at the stern of the hull 1, providing propulsion for the hull 1. The propulsion system includes a waterjet propulsion unit 4 and a battery 41 for providing power. The waterjet propulsion unit 4 is mounted at the stern of the hull 1. A battery compartment 41 is located in the middle of the hull 1 for housing the battery 41. Preferably, the battery 41 is a cylindrical structure, and the structure of the battery compartment 41 is adapted to the shape of the battery 41. The battery compartment 41 is equipped with a door for locking and sealing the interior of the battery compartment 41.

[0055] like Figure 2 As shown, the present invention also provides a rescue control method, comprising the following steps:

[0056] S1. Based on the location of the rescue target, the lifeboat is controlled via a remote control system to move to the vicinity of the rescue target;

[0057] The specific steps are as follows: After receiving a rescue mission, the lifeboat can be launched into the water manually or automatically. Then, the lifeboat is manually controlled by the remote control system to move to the vicinity of the rescue area. After arriving at the rescue area, the sensing system analyzes the water surface image information obtained by camera 3 to determine whether it is a rescue target and feeds back to the mobile APP. If it is confirmed to be a rescue target, the lifeboat quickly locks the location of the rescue target after receiving the confirmation information and starts the automatic rescue mode. Otherwise, the lifeboat continues to be manually controlled by the remote control system to continue searching in the rescue area.

[0058] S2. Based on the location of the rescue target, move the lifeboat toward the rescue target and enter semi-submersible mode. Maintain semi-submersible mode while planning a route to approach the rescue target without colliding with it.

[0059] Once the sensing system locks onto the rescue target, the lifeboat will slowly move towards it, approaching via the positioning module. When it reaches a certain range, such as when the distance to the rescue target is less than 10 meters, the semi-submersible system will activate, monitoring the water level h in the tank via a level sensor. When the water level reaches a set value... When this happens, it is considered to have entered semi-submersible mode, where the set value is... It is preset.

[0060] In a semi-submerged state, the lifeboat performs automatic path planning to approach the rescue target without colliding with it. The aforementioned path planning includes the planning of the lifeboat's turning, navigation attitude, and navigation path.

[0061] Specifically, the lifeboat's steering is achieved by controlling its steering angle and thruster speed. The specific steps are as follows: The location coordinates of the rescue target are obtained through camera 3. The current coordinates of the lifeboat are Then, the required turning angle δ and thruster speed ω of the lifeboat can be calculated as follows:

[0062] ;

[0063] ;

[0064] in This is the gain coefficient.

[0065] After adjusting its direction, the lifeboat approaches the rescue target at a set speed. During its journey, the lifeboat's attitude needs to be monitored and adjusted in real time to ensure a smooth approach. This invention adjusts its attitude by regulating the water levels of the forward water tank 21 and the aft water tank 22. The water level difference between the forward and aft water tanks is defined as follows: , where h q h is the water level depth of the forward water tank 21. h The water level depth of aft water tank 22, and the pitch angle of hull 1 are... ,but The size is calculated by the following formula

[0066] ;

[0067] in , , For control parameters, Let be the desired pitch angle of hull 1. For time integration variables, The time differential variable is used; by adjusting the above parameters, the pitch angle of the lifeboat can be precisely controlled to ensure that it approaches the rescue target smoothly in a semi-submerged state.

[0068] Once the lifeboat enters semi-submersible mode, camera 3 identifies the location of the rescue target and uses the following algorithm to plan its navigation path, ensuring that the lifeboat reaches the target location at a speed of 0. Specifically: First, Kalman filtering is used to predict the target's position at the next moment. ,in At the current speed, p represents the direction of motion. t Given the current position; then based on the predicted position p t+1 Calculate the expected course of the lifeboat.

[0069] Secondly, using the dynamic window method, the cost function C is defined as follows: ;

[0070] in The minimum distance between the path and the obstacle. The proximity of the path to the target. The norm of curvature, , , These are the weighting coefficients;

[0071] Finally, at each interval Recalculate the optimal path It also adjusts the thruster speed and heading angle in real time to make the lifeboat smoothly approach the rescue target along the optimal trajectory.

[0072] S3. Obtain the status of the rescue target, identify different statuses of the rescue target, send corresponding voice instructions, and interact with the rescue target;

[0073] In the final stage of approaching the rescue target, when the distance is reduced to a safe contact range, generally when camera 3 can clearly capture images of the rescue target's movements and expressions, the perception processor identifies the captured images, analyzes the images to determine the rescue target's consciousness and limb activity, and extracts facial features and postures in real time. If the rescuer is identified as calm and cooperative, a voice broadcast guides them to hold onto the lifeboat handle or a designated area. If the rescuer is identified as panicked or struggling, voice or manual intervention is automatically initiated to calm them down and guide them to gradually approach and hold onto the lifeboat. If the rescue target is identified as unconscious or unresponsive (e.g., no limb movement for a long time, face down, or drifting with the current), the system immediately requests manual takeover or support. At the same time, the lifeboat automatically switches to "guardian and lift mode": using the positioning module and power system to maintain synchronous drift with the rescue target, and using the semi-submersible system to control the hull to submerge to the side and below the rescue target, then controlling the discharge to slowly rise, using the hull's buoyancy to attempt to lift the rescue target, thereby achieving the rescue.

[0074] S4. Based on the change in surface pressure of the lifeboat, determine whether the rescue target is holding onto the lifeboat securely. If it is confirmed that the target is holding onto the lifeboat securely, the lifeboat will rise to the surface, and an instruction will be issued to the lifeboat to return to a safe area.

[0075] When the lifeboat detects that the surface pressure distribution is stabilizing and continues to exceed a preset threshold, it determines that the rescue target has firmly grasped the lifeboat. At this time, the control system triggers the buoyancy mode, adjusts the discharge rate of the front and rear water tanks 22, and causes the hull 1 to rise to the water surface at a set angle and speed.

[0076] Preferably, during the ascent process, the current draft of the lifeboat is continuously calculated, and the weight of the person to be rescued can be calculated based on the water levels in the forward and aft water tanks 21 and 22. Specifically, the hydrostatic pressure value P is collected in real time by an external pressure sensor, and the hydrostatic formula is used... Calculate the current draft of the lifeboat. .

[0077] in, For the density of water, It is the acceleration due to gravity;

[0078] Next, based on the known geometric model of hull 1, the control system calculates the draft based on the real-time measured depth. Using linear interpolation, the current precise drainage volume is quickly retrieved and calculated from a pre-stored drainage volume table. Specifically, the control system has a pre-stored table of displacement volume (i.e., draft) of the ship's geometric model. With drainage volume The corresponding relationship curve is obtained by integrating the width function of the hull cross-section from the bottom to different drafts.

[0079] At the same time, the current liquid level of each water tank is collected by the level gauge inside the water tank. Calculate the total mass of the current ballast water. Finally, based on Archimedes' principle (buoyancy equals weight), the weight of the person to be rescued was calculated by reverse calculation using the following equilibrium equation:

[0080]

[0081] in, For the fixed empty weight of the lifeboat, The total number of water tanks, Indicates the first One water tank; For the first The cross-sectional area of ​​each water tank; For the first Real-time water level height in each water tank.

[0082] At this point, the dynamic model changes, therefore the lifeboat's motion control algorithm should be adaptive. The control parameters need to be load-related to continuously monitor pitch angle changes and adjust the ballast water volume in the forward and aft tanks 21 and 22 to ensure stable attitude. Specifically, firstly, the system's total mass parameter is updated to ensure the lifeboat's total inertial mass during return is... for:

[0083]

[0084] in, For the empty ship mass, This represents the current mass of the remaining water in the ballast tank. To calculate the mass of the people to be rescued; secondly, a mass correction factor is introduced. , defined as the ratio of the current total mass to the design unloaded mass:

[0085]

[0086] Then, a gain scheduling strategy is used to correct the PID parameters of the navigation controller in real time. The speed control proportional gain under no-load conditions is designed to be... Integral gain is The differential gain is The gain after correction during the return phase , They are respectively:

[0087]

[0088]

[0089]

[0090] Finally, based on the corrected gain, the control module calculates the thruster's output thrust using the following formula. To overcome the inertial hysteresis caused by increased load:

[0091]

[0092] in, The error between the set speed in the return path planning and the current actual speed.

[0093] This is the rate of change of error, thus ensuring that the lifeboat maintains the same response speed and navigation stability when manned as when unloaded.

[0094] Upon reaching the water's surface, the system obtains its current location via the positioning module, automatically plans its return route, and returns to a safe area to complete the rescue. Simultaneously, the communication module uploads the rescue status to the command center.

[0095] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A semi-submersible lifeboat, characterized in that, It includes a hull (1), on which a power system, a semi-submersible system, a navigation control system (5), a sensing system, an interaction system and a control system are provided; The semi-submersible system is located in the aft region of the hull (1), enabling the hull (1) to perform semi-submersible operations; The navigation control system (5) consists of a positioning module, a control module, and a communication module. The positioning module obtains the current position of the lifeboat, the communication module obtains the control commands, and the control module controls the navigation of the lifeboat according to the control commands. The perception system includes a camera (3) and a perception processor. The camera (3) acquires image information of the surrounding environment and people. The perception processor obtains the location and status of the rescue target based on the image information and sends it to the control module for processing through the communication module. The interactive system can collect the voice signals of the rescue target and issue voice prompts to the rescue target. The control system is used for remote control of the lifeboat; The power system is located at the stern of the hull (1) and provides propulsion for the hull (1).

2. A semi-submersible lifeboat according to claim 1, characterized in that, The power system includes a water jet propulsion unit (4) and a battery (41) for providing power. The water jet propulsion unit (4) is installed at the stern of the hull (1), and a battery (41) compartment is provided in the middle of the hull (1) for installing the battery (41).

3. A semi-submersible lifeboat according to claim 1, characterized in that, The semi-submersible system includes a water pump, a water tank, a level sensor, and a semi-submersible controller. The level sensor is located inside the water tank and is used to detect the water volume inside the water tank. The semi-submersible controller is connected to the water pump and controls the water volume in the water tank, thereby enabling the hull 1 to submerge and float.

4. A semi-submersible lifeboat according to claim 1, characterized in that, The control system comprises a remote control handle, a Bluetooth module, and a mobile app. The remote control handle and the mobile app are respectively connected to the communication module via the Bluetooth module.

5. A semi-submersible lifeboat according to claim 1, characterized in that, A pressure sensor is provided on the surface of the hull (1).

6. A rescue control method, characterized in that, Includes the following steps: S1. Based on the location of the rescue target, the lifeboat is controlled via a remote control system to move to the vicinity of the rescue target; S2. Based on the location of the rescue target, move the rescue boat toward the rescue target and enter semi-submersible mode. Maintain semi-submersible mode while planning a route to approach the rescue target without colliding with it. S3. Obtain the status of the rescue target, identify different statuses of the rescue target, send corresponding voice instructions, interact with the rescue target, and instruct the rescue target to hold onto the lifeboat; S4. Based on the change in surface pressure of the lifeboat, determine whether the rescue target is holding onto the lifeboat securely. If it is confirmed that the target is holding onto the lifeboat securely, the lifeboat will rise to the surface, and an instruction will be issued to the lifeboat to return to a safe area.

7. A rescue control method according to claim 6, characterized in that, In step S2, the route planning includes planning the lifeboat's turning, navigation attitude, and navigation path; when the lifeboat approaches the target, the water tank level h is monitored by a level sensor, and when... At that time, it is considered to have entered semi-submersible mode, in which It is a set value.

8. A rescue control method according to claim 7, characterized in that, The lifeboat's steering is achieved by controlling its steering angle and thruster speed. The specific steps are as follows: Obtain the location coordinates of the rescue target through the camera (3). The current coordinates of the lifeboat are Then, the required turning angle δ and thruster speed ω of the lifeboat can be calculated as follows: ； ； in This is the gain coefficient.

9. A rescue control method according to claim 7, characterized in that, During the semi-submerged state, the lifeboat adjusts its navigation attitude by regulating the water level depth of the forward water tank (21) and the aft water tank (22). Let the water level difference between the forward water tank (21) and the aft water tank (22) be... , where h q h is the water level depth of the forewater tank (21). h The water level depth of the aft water tank (22) is given by the pitch angle of the hull (1). ,but The size is calculated by the following formula ； in , , These are control parameters.

10. A rescue control method according to claim 7, characterized in that, Once the lifeboat enters semi-submersible mode, the location of the rescue target is identified by the camera (3), and the navigation path is planned using the following algorithm to ensure that the speed is 0 when the lifeboat reaches the location of the rescue target. Specifically, the following steps are taken: First, Kalman filtering is used to predict the location of the rescue target at the next moment. ,in At the current speed, In terms of direction of motion; Secondly, using the dynamic window method, the cost function C is defined as follows: ; in The minimum distance between the path and the obstacle. The proximity of the path to the target. The norm of curvature, , , These are the weighting coefficients; Finally, at each interval Recalculate the optimal path It also adjusts the thruster speed and heading angle in real time.

Images