A cross-medium vehicle system and a control method thereof

Abstract

The cross-medium vehicle system and the control method thereof provided by the present disclosure receive a task instruction sent by a ground station; real-time perception data of the vehicle in different medium environments is obtained, and the perception data is pre-processed into perception fusion data; real-time other perception fusion data sent by other vehicles in the cluster is received, and a cluster cooperative trajectory is generated according to the perception fusion data and the other perception fusion data sent by the other vehicles in the cluster; a target task of the vehicle is determined according to the cluster cooperative trajectory, a current running state of the vehicle and the task instruction; optimal water-entry and water-exit path parameters of the vehicle are determined according to the target task, and driving signals are generated based on the perception fusion data or the optimal water-entry and water-exit path parameters, so as to continuously control the vehicle to reach a target state, thereby solving technical problems such as low deformation efficiency of a wing of a traditional vehicle, poor water-entry and water-exit control accuracy, and lack of cluster cooperative capability.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer processing, and in particular, to a cross-medium vehicle system and a control method thereof. BACKGROUND

[0002] As an emerging technology, the cross-medium vehicle has the characteristics of strong adaptability and cross-domain operation, and has wide application prospects in the fields of ocean exploration, environmental monitoring, search and rescue operations, etc.

[0003] In the prior art, in order to realize continuous operation in underwater, water surface and air multi-medium environments, a single type of vehicle is usually used for mode switching to perform segmented operation in different medium environments. However, the existing cross-medium vehicle not only has poor control accuracy for entering and exiting water, which affects the continuity and safety of cross-medium operation, but also cannot realize large-scale and efficient tasks, and the operation coverage is limited. SUMMARY

[0004] The present disclosure provides a cross-medium vehicle system and a control method thereof to at least solve the above technical problems in the prior art.

[0005] According to a first aspect of the present disclosure, a cross-medium vehicle system is provided, the system comprising:

[0006] An autonomous decision and task planning system is configured to receive a task instruction sent by a ground station and send the task instruction to a cluster coordination system, wherein the task instruction is used to indicate a collective task that the cluster needs to complete;

[0007] A multi-source information perception and state identification system is configured to acquire perception data of the vehicle in different medium environments in real time, pre-process the perception data into perception fusion data, and send the perception fusion data to a multi-modal coordinated control and execution system and the cluster coordination system;

[0008] The cluster coordination system is configured to receive the perception fusion data sent by the local multi-source information perception and state identification system, other perception fusion data sent by other vehicles in the cluster, and the task instruction, generate a cluster coordination trajectory according to the perception fusion data and the other perception fusion data sent by other vehicles in the cluster, and determine a target task of the vehicle according to the cluster coordination trajectory, a current running state of the vehicle, and the task instruction, and send the target task to the autonomous decision and task planning system, wherein the current running state includes current running parameters of the vehicle when driving in different media or crossing media, and the target task belongs to at least one subtask in the collective task;

[0009] The autonomous decision-making and task planning system is also configured to receive a target task sent by the swarm coordination system, determine optimal in-out water path parameters of the vehicle according to the target task, and feed back the optimal in-out water path parameters to the multi-modal coordinated control and execution system.

[0010] The multi-modal coordinated control and execution system is configured to receive the perception fusion data sent by the multi-source information perception and state identification system and the optimal in-out water path parameters sent by the autonomous decision-making and task planning system, and generate a driving signal according to the perception fusion data or the optimal in-out water path parameters to constantly control the vehicle to reach a target state.

[0011] In an optional embodiment, the perception data includes at least one of original depth data, original attitude data, original positioning data, and contact state data, and the multi-source information perception and state identification system includes:

[0012] A depth perception sensor module is configured to measure original depth data of the vehicle in underwater diving in real time, and send the original depth data to a data preprocessing module.

[0013] An attitude and motion state detection module is configured to acquire original attitude data of the vehicle, and send the original attitude data to the data preprocessing module.

[0014] A high-precision positioning navigation module is configured to acquire original positioning data of the vehicle, and send the original positioning data to the data preprocessing module.

[0015] A medium environment detection module is configured to detect contact state data of each part of the vehicle and a water body in real time, and send the contact state data to the data preprocessing module.

[0016] The data preprocessing module is configured to receive and process the original depth data, the original attitude data, the original positioning data, and the contact state data, generate the perception fusion data, and send the perception fusion data to the multi-modal coordinated control and execution system and the swarm coordination system.

[0017] In an optional embodiment, the swarm coordination system includes:

[0018] A swarm communication coordination module is configured to receive the perception fusion data sent by the data preprocessing module of each vehicle in the swarm, generate swarm shared data, and send the swarm shared data to a swarm coordination navigation control module.

[0019] a cluster cooperative navigation control module configured to receive the cluster shared data sent by the cluster communication coordination module and other perception fusion data sent by other vehicles in the cluster, and to generate a cluster cooperative trajectory based on the cluster shared data and the other perception fusion data and send the cluster cooperative trajectory to a cooperative task allocation module,

[0020] a cooperative task allocation module configured to receive the cluster cooperative trajectory sent by the cluster cooperative navigation control module, and to generate a target task based on the cluster cooperative trajectory, a current operating state of the vehicle, and a task instruction, and send the target task to a cooperative task execution strategy module by using a distributed algorithm;

[0021] a cooperative task execution strategy module configured to receive the target task sent by the cooperative task allocation module, process the target task based on a cooperative task allocation algorithm, and generate a cooperative operation control instruction and send the cooperative operation control instruction to a multi-modal cooperative control and execution system.

[0022] In an optional embodiment, the multi-modal cooperative control and execution system comprises:

[0023] a control unit configured to receive the perception fusion data sent by the data preprocessing module and the cooperative operation control instruction sent by the cooperative task execution strategy module, determine a first type of driving signal, a second type of driving signal, and a third type of driving signal based on the perception fusion data, the cooperative operation control instruction, and a current operating state of the vehicle, send the first type of driving signal to a bionic variable-configuration wing control module, send the second type of driving signal to a multi-modal propulsion control module, and send the third type of driving signal to an attitude and heading control module, wherein the first type of driving signal is used to switch a wing configuration of the vehicle, the second type of driving signal is used to drive different propulsion units of the vehicle, and the third type of driving signal is used to drive a rudder surface control of the vehicle.

[0024] the bionic variable-configuration wing control module is configured to receive and respond to the first type of driving signal sent by the control unit to switch a wing configuration required by the vehicle for driving in different media or in a cross-media situation, and generate a first feedback signal;

[0025] the multi-modal propulsion control module is configured to receive and respond to the second type of driving signal sent by the control unit to drive a propulsion unit required by the vehicle for driving in different media or in a cross-media situation, and generate a second feedback signal;

[0026] the attitude and heading control module is configured to receive and respond to the third type of driving signal sent by the control unit to maintain attitude stability of the vehicle for driving in different media or in a cross-media situation, and generate a third feedback signal;

[0027] The first feedback signal, the second feedback signal and the third feedback signal collected in real time are current operation parameters of the aerial vehicle.

[0028] In an optional embodiment, the control unit comprises:

[0029] The first control unit is configured to receive the perception fusion data sent by the data preprocessing module and the cooperative task execution strategy module, and generate a coordination control instruction according to the perception fusion data, the cooperative task execution strategy and the current operation state of the aerial vehicle, and send the coordination control instruction to the second control unit and the autonomous decision and task planning system.

[0030] The second control unit is configured to receive the coordination control instruction of the first control unit, and convert the coordination control instruction into a first type of driving signal, a second type of driving signal and a third type of driving signal, and send the first type of driving signal to the bionic variable-configuration wing control module, the second type of driving signal to the multi-modal propulsion control module, and the third type of driving signal to the attitude and heading control module.

[0031] In an optional embodiment, the autonomous decision and task planning system comprises:

[0032] The mode switching decision module is configured to, in the case of cross-medium mode switching of the aerial vehicle, receive the coordination control instruction of the first control unit, generate a mode switching control instruction based on an adaptive rule algorithm and the coordination control instruction, and send the mode switching control instruction to the water-entry / exit path planning module.

[0033] The water-entry / exit path planning module is configured to receive the mode switching control instruction sent by the mode switching decision module, calculate optimal water-entry / exit path parameters according to the mode switching control instruction, and send the optimal water-entry / exit path parameters to the second control unit to constantly control the aerial vehicle to reach a target state.

[0034] The communication and instruction management module is configured to receive a task instruction sent by the ground station, send the task instruction to the cooperative task allocation module, and further configured to feed back task execution state information to the ground station.

[0035] In an optional embodiment, the second control unit is specifically further configured to:

[0036] In the case of cross-medium mode switching, the second control unit is configured to receive the optimal water-entry / exit path parameters sent by the water-entry / exit path planning module, generate a new driving signal according to the optimal water-entry / exit path parameters, and constantly update the first type of driving signal, the second type of driving signal and the third type of driving signal to control the aerial vehicle to reach a target state.

[0037] In an optional embodiment, the biomimetic variable configuration wing control module is specifically used for:

[0038] Receive the first type of drive signal sent by the control unit;

[0039] When the current operating mode of the vehicle meets the preset conditions, the wing configuration of the vehicle is adjusted to the target wing configuration by the first type of drive signal;

[0040] The target wing configuration is selected from one of the following based on preset conditions satisfied by the current operating mode of the aircraft:

[0041] When the current operating mode is underwater mode, adjust to a shark pectoral fin wing configuration;

[0042] When the current operating mode is the water inlet / outlet mode, adjust to the flying fish pectoral fin wing configuration;

[0043] When the current operating mode is ground effect flight mode, adjust to ground effect flight wing configuration;

[0044] When the current operating mode is the aerial flight mode, adjust to the albatross wing configuration.

[0045] In one optional embodiment, the adaptive rule algorithm is an algorithm that generates coordinated control commands based on the output of the sub-controller within the vehicle and the weights of fuzzy rules.

[0046] According to a second aspect of this disclosure, a control method for a cross-medium vehicle system is provided, characterized in that the method comprises:

[0047] Receive task instructions sent by the ground station, wherein the task instructions are used to indicate the collective tasks that the cluster needs to complete;

[0048] Real-time acquisition of sensing data of the vehicle in different media environments, and preprocessing of the sensing data into sensing fusion data;

[0049] The system receives other perception fusion data sent by other vehicles in the cluster in real time, and generates a cluster cooperative trajectory based on the perception fusion data and other perception fusion data sent by other vehicles in the cluster.

[0050] Based on the cluster collaborative trajectory, the current operating status of the vehicle, and the mission instructions, the target mission of the vehicle is determined, wherein the current operating status includes the current operating parameters of the vehicle when traveling on different media or crossing media, and the target mission belongs to at least one sub-task in the collective mission;

[0051] The optimal water entry and exit path parameters of the vehicle are determined according to the target mission, and then a drive signal is generated based on the perception fusion data or the optimal water entry and exit path parameters to continuously control the vehicle to reach the target state.

[0052] According to a third aspect of this disclosure, a control device for a cross-medium vehicle system is provided, characterized in that the device comprises:

[0053] The task receiving module is used to receive task instructions sent by the ground station, wherein the task instructions are used to indicate the collective tasks that the cluster needs to complete.

[0054] The first data acquisition module is used to acquire the sensing data of the vehicle in different media environments in real time, and preprocess the sensing data into sensing fusion data.

[0055] The second data acquisition module is used to receive other perception fusion data sent by other vehicles in the cluster in real time, and generate a cluster cooperative trajectory based on the perception fusion data and other perception fusion data sent by other vehicles in the cluster.

[0056] The task determination module is used to determine the target task of the vehicle based on the cluster collaborative trajectory, the current operating status of the vehicle, and the task instructions. The current operating status includes the current operating parameters of the vehicle when traveling on different media or crossing media, and the target task belongs to at least one sub-task in the collective task.

[0057] The state update module is used to determine the optimal water entry and exit path parameters of the vehicle according to the target task, and then generate a drive signal based on the perception fusion data or the optimal water entry and exit path parameters to continuously control the vehicle to reach the target state.

[0058] According to a fourth aspect of this disclosure, an electronic device is provided, comprising:

[0059] At least one processor; and

[0060] A memory communicatively connected to the at least one processor; wherein,

[0061] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described in this disclosure.

[0062] According to a fifth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the methods described in this disclosure.

[0063] This disclosed cross-medium vehicle system and its control method receive mission commands from a ground station; acquire real-time sensing data of the vehicle in different media environments, and preprocess the sensing data into sensing fusion data; receive other sensing fusion data sent by other vehicles in the cluster in real-time, and generate a cluster cooperative trajectory based on the sensing fusion data and other sensing fusion data sent by other vehicles in the cluster; determine the target mission of the vehicle based on the cluster cooperative trajectory, the current operating state of the vehicle, and the mission commands; determine the optimal water entry / exit path parameters of the vehicle based on the target mission, and then generate drive signals based on the sensing fusion data or the optimal water entry / exit path parameters to continuously control the vehicle to reach the target state. This solves the technical problems of low wing deformation efficiency, poor water entry / exit control accuracy, and lack of cluster cooperative capability in traditional vehicles.

[0064] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0065] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0066] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0067] Figure 1 A schematic diagram of the structure of a cross-medium vehicle system provided in an embodiment of this disclosure is shown;

[0068] Figure 2 This diagram illustrates the structure of a multi-source information sensing and state recognition system in a cross-medium vehicle system according to an embodiment of this disclosure.

[0069] Figure 3 This illustration shows a schematic diagram of the structure of a multimodal cooperative control and execution system in a cross-medium vehicle system provided by an embodiment of the present disclosure;

[0070] Figure 4 This illustration shows a schematic diagram of the structure of a cluster cooperative system in a cross-medium vehicle system provided by an embodiment of the present disclosure;

[0071] Figure 5 This illustration shows a schematic diagram of the structure of an autonomous decision-making and mission planning system in a cross-medium vehicle system provided by an embodiment of the present disclosure;

[0072] Figure 6A complete structural schematic diagram of an exemplary cross-medium vehicle system provided by an embodiment of this disclosure is shown;

[0073] Figure 7 A third-view diagram of an exemplary cross-medium vehicle provided in an embodiment of this disclosure is shown;

[0074] Figure 8 An explosion diagram of a cross-medium vehicle provided in an embodiment of this disclosure is shown;

[0075] Figure 9 A flowchart of a control method for a cross-medium vehicle system provided in an embodiment of this disclosure is shown;

[0076] Figure 10 A schematic diagram of the structure of a control device for a cross-medium vehicle system provided in an embodiment of this disclosure is shown. Detailed Implementation

[0077] To make the objectives, features, and advantages of this disclosure more apparent and understandable, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0078] Figure 1 A schematic diagram of a cross-medium vehicle system is provided. The system 10 includes: an autonomous decision-making and mission planning system 110, a multi-source information sensing and state recognition system 120, a multimodal cooperative control and execution system 130, and a swarm cooperative system 140.

[0079] The autonomous decision-making and task planning system 110 is used to receive task instructions sent by the ground station and send them to the cluster collaboration system 140, wherein the task instructions are used to indicate the collective tasks that the cluster needs to complete.

[0080] The cross-medium vehicle system provided in this embodiment is applied to ocean mooring monitoring tasks. It needs to rise from a preset underwater depth to the surface and then switch to ground effect flight mode or aerial flight mode to perform tasks and transmit data in the required mode according to the task instructions sent by the ground station.

[0081] Specifically, the autonomous decision-making and mission planning system 110 includes a module capable of communicating with a ground station to achieve two-way communication. For example, it can receive mission instructions sent by the ground station. These instructions can be collective tasks that the cluster needs to complete. These collective tasks can be tasks completed by all vehicles in the cluster, tasks completed by one or more vehicles in the cluster, or tasks completed by a specific vehicle in the cluster. This embodiment does not limit these specific tasks. After receiving the mission instructions, the autonomous decision-making and mission planning system 110 sends them to the cluster coordination system 140, which determines the tasks to be performed by the system in this collective mission.

[0082] The multi-source information perception and state recognition system 120 is used to acquire the perception data of the vehicle in different media environments in real time, preprocess the perception data into perception fusion data, and then send the perception fusion data to the multimodal cooperative control and execution system 130 and the cluster cooperative system 140.

[0083] The perception data includes at least one of the following: raw depth data, raw pose data, raw positioning data, and contact state data.

[0084] The multi-source information perception and state recognition system 120 in this embodiment can be used to acquire depth data, attitude data, positioning data and medium contact state data of the vehicle in different medium environments such as underwater, water surface and air. By monitoring the above data in real time, it can provide data support for subsequent bionic wing deformation, rapid water entry and exit and swarm collaboration.

[0085] Specifically, in this embodiment, the collected sensing data is aggregated and preprocessed, including standardization and unification, to obtain sensing fusion data. Then, the sensing fusion data is sent to other systems within the spacecraft for data support.

[0086] The cluster collaboration system 140 is used to receive perception fusion data sent by the local multi-source information perception and status recognition system 120, other perception fusion data sent by other vehicles in the cluster, and task instructions. Based on the perception fusion data and other perception fusion data sent by other vehicles in the cluster, it generates a cluster collaboration trajectory. Based on the cluster collaboration trajectory, the current operating status of the vehicle, and the task instructions, it determines the target task of the vehicle and sends it to the autonomous decision-making and task planning system 110.

[0087] The current operating status includes the current operating parameters of the vehicle when traveling on different media or crossing media, and the target mission belongs to at least one sub-mission in the collective mission.

[0088] Specifically, the target task can be a task allocation table and a priority list. The task allocation table records at least one task that the aircraft needs to complete, and the priority list records the priority of different tasks. Current operating parameters can include the aircraft's attitude feedback parameters, propulsion feedback parameters, wing feedback parameters, velocity parameters, and position parameters during operation. The swarm coordination trajectory is the aircraft's formation position within the swarm and the route it needs to take to coordinate with the swarm formation.

[0089] Specifically, in this embodiment, the cluster collaboration system 140 in the aircraft can clearly understand the operating status of all aircraft in the cluster by receiving the perception fusion data of the aircraft itself and the perception fusion data sent by other aircraft in the cluster. Then, by parsing the task instructions sent by the ground station and combining the current operating parameters of the aircraft (feedback signals from some modules), it can distribute and calculate the target task of the aircraft itself, and then send the target task to the multimodal collaborative control and execution system 130 for further planning and execution.

[0090] This embodiment uses the cluster collaboration system 140 to achieve multi-vehicle formation control, collaborative task allocation, and cluster communication coordination, forming the advantages of cluster operation. It can effectively solve the problem that the single-vehicle operation efficiency is limited and the operation coverage is limited, which makes it impossible to achieve large-scale and high-efficiency cluster collaborative tasks.

[0091] The autonomous decision-making and mission planning system 110 is also used to receive the target mission sent by the cluster collaboration system 140, determine the optimal water entry and exit path parameters of the vehicle according to the target mission, and then feed back the optimal water entry and exit path parameters to the multimodal collaborative control and execution system 130.

[0092] The optimal water entry / exit path parameters include parameters such as the angle, speed, and time of the vehicle's entry / exit. Since the vehicle may need to repeatedly enter and exit the water and experience different modal changes during mission execution, the vehicle needs to feed back the optimal water entry / exit path parameters to the multimodal cooperative control and execution system 130 to determine the next modal operation time and the desired operating state.

[0093] The autonomous decision-making and mission planning system 110 in this embodiment determines the optimal water entry and exit path parameters for the vehicle during the execution of the target mission by using perception fusion data and the target mission. Based on the optimal water entry and exit path parameters, it realizes intelligent cross-medium mode switching decision-making, repeated rapid water entry and exit path planning, and swarm collaborative navigation control. This novel underwater-airborne cross-medium special vehicle effectively realizes the technological innovations of biomimetic wing deformation, rapid water entry and exit, and swarm collaboration, improving the stability, speed, and collaboration during mode switching, and significantly improving the operational efficiency of a single platform and the swarm collaboration capability.

[0094] The multimodal collaborative control and execution system 130 is used to receive the perception fusion data sent by the multi-source information perception and state recognition system 120 and the optimal water entry and exit path parameters sent by the autonomous decision-making and mission planning system 110, and generate driving signals based on the perception fusion data or the optimal water entry and exit path parameters to continuously control the vehicle to reach the target state.

[0095] The target state refers to the operational state that the vehicle needs to achieve when traveling or crossing different media. For example, it can be one of the following configurations: shark pectoral fin wing configuration, flying fish pectoral fin wing configuration, ground effect flight wing configuration, or albatross wing configuration. The target state can also be the position and speed required when traveling or crossing different media according to the target mission requirements.

[0096] For example, if a vehicle goes through four stages during a mission, the first stage is underwater submersion, and the target state could be a state of submersion with a first specific speed, a first specific trajectory, and a shark pectoral fin wing configuration; the second stage is flying out of the water, and the target state could be a state of flight with a second specific speed, a second specific trajectory, and a flying fish pectoral fin wing configuration; the third stage is surface flight, and the target state could be a state of flight with a third specific speed, a third specific trajectory, and a ground effect wing configuration; the fourth stage is aerial flight, and the target state could be a state of flight with a fourth specific speed, a fourth specific trajectory, and an albatross wing configuration.

[0097] Specifically, the multimodal cooperative control and execution system 130 in this embodiment can generate drive signals based on sensing fusion data to control the vehicle to reach the target state when in different media. It can also generate drive signals through optimal water entry and exit path parameters when crossing media to continuously control the vehicle to reach the target state. This enables precise cooperative control of the vehicle's wing control, multimodal propulsion, attitude and heading control functions, achieving the organic integration of various innovative functions.

[0098] Figure 2 A schematic diagram of the structure of a multi-source information sensing and state recognition system in a cross-medium vehicle system is shown, according to an embodiment of this disclosure. Figure 2 As shown, the multi-source information perception and state recognition system 120 includes: a depth perception sensor module 1210, an attitude and motion state detection module 1220, a high-precision positioning and navigation module 1230, a medium environment detection module 1240, and a data preprocessing module 1250. Among them,

[0099] The depth sensing sensor module 1210 is used to measure the raw depth data of the vehicle while it is submerged in water in real time, and send the raw depth data to the data preprocessing module 1250. The raw depth data may include the vehicle's underwater depth information and its vertical speed during ascent and descent.

[0100] Specifically, the depth sensing sensor module 1210 in this embodiment employs a high-precision pressure sensor array, capable of accurately measuring the underwater depth information and vertical velocity of the vehicle during ascent and descent in real time. This raw depth data is then sent to the data preprocessing module for filtering and calibration, providing accurate depth reference data for subsequent mode switching decisions, path planning, and cluster collaboration. Alternatively, this embodiment can pre-set a preset depth. When the vehicle reaches the preset depth, the remaining depth from the water surface is monitored in real time, and the raw depth data is sent to the data preprocessing module 1250 to further achieve energy-saving effects.

[0101] The attitude and motion state detection module 1220 is used to acquire the original attitude data of the vehicle and send the original attitude data to the data preprocessing module; wherein, the original attitude data includes the vehicle's three-axis acceleration, three-axis angular velocity and three-axis magnetic field strength.

[0102] Specifically, the attitude and motion state detection module 1220 in this embodiment uses a nine-axis inertial measurement module (integrating a three-axis accelerometer, angular velocity meter, and magnetometer) to detect the attitude changes and motion state of the aircraft during wing deformation. It outputs raw attitude data such as three-axis acceleration, three-axis angular velocity, and three-axis magnetic field strength, which are sent to the data preprocessing module 1250 for sensor fusion processing to provide accurate real-time attitude feedback data for subsequent decision control, path planning, and cluster collaboration.

[0103] The high-precision positioning and navigation module 1230 is used to acquire the original positioning data of the vehicle and send the original positioning data to the data preprocessing module 1250; wherein, the original positioning data is the precise geographical location and movement trajectory of the vehicle.

[0104] Specifically, the high-precision positioning and navigation module 1230 in this embodiment uses a differential satellite navigation system to obtain the vehicle's precise geographical location and motion trajectory, and sends the raw positioning data to the data preprocessing module 1250 for processing, providing accurate position reference data for subsequent formation control, task allocation and cooperative navigation.

[0105] The medium environment detection module 1240 is used to detect the contact status data of various parts of the vehicle with the water in real time and send the contact status data to the data preprocessing module 1250; wherein, the contact status data is the contact status of various parts of the vehicle with the water, including the fully submerged state, the partially contacted state, and the completely detached state.

[0106] Specifically, the medium environment detection module 1240 in this embodiment adopts a multi-point distributed conductivity sensor array to determine the medium environment of the vehicle by the change in conductivity. That is, it detects the contact state between various parts of the vehicle and the water in real time and sends the contact state data to the data preprocessing module 1250 for signal processing to provide accurate environmental state data for subsequent mode switching decisions.

[0107] The data preprocessing module 1250 is used to receive and process the original depth data, the original attitude data, the original positioning data, and the contact state data to generate the perception fusion data; and to send the perception fusion data to the multimodal collaborative control and execution system, the cluster collaborative system, and the autonomous decision-making and task planning system.

[0108] Specifically, the data preprocessing module 1250 uses an embedded processor to fuse the sensor data sent by the above modules, perform filtering, calibration, time synchronization and data format unification processing, generate perception fusion data, and send the perception fusion data to other modules to provide data support.

[0109] Figure 3 A schematic diagram of a multimodal cooperative control and execution system in a cross-medium vehicle system is shown, according to an embodiment of this disclosure. Figure 3 As shown, the multimodal cooperative control and execution system 130 includes: a control unit 1310, a biomimetic variable configuration wing control module 1320, a multimodal propulsion control module 1330, and an attitude and heading control module 1340. And, Figure 4 A schematic diagram of a cluster cooperative system in a cross-medium vehicle system is shown, according to an embodiment of this disclosure. Figure 4 As shown, the cluster collaboration system 140 includes: a cluster communication coordination module 1410, a cluster collaborative navigation control module 1420, a collaborative task allocation module 1430, and a collaborative task execution strategy module 1440. Among them,

[0110] Control unit 1310 is used to receive perception fusion data sent by data preprocessing module 1250 and cooperative operation control command sent by cooperative task execution strategy module 1440. Based on the perception fusion data, the cooperative operation control command and the current operating state of the vehicle, it determines a first type of drive signal, a second type of drive signal and a third type of drive signal. It sends the first type of drive signal to the biomimetic variable configuration wing control module, the second type of drive signal to the multimodal propulsion control module, and the third type of drive signal to the attitude and heading control module. The first type of drive signal is used to switch the wing configuration of the vehicle, the second type of drive signal is used to drive different propulsion units of the vehicle, and the third type of drive signal is used to drive the control surface control of the vehicle.

[0111] The control unit 1310 may include a first control unit and a second control unit. The first control unit, also known as the top-level decision control unit, employs an embedded flight control computer and is capable of executing intelligent decision-making algorithms, cross-media mode switching logic, swarm cooperative control, and anomaly handling decisions. The second control unit, also known as the bottom-level execution control unit, employs a real-time microcontroller and, without involving cross-media mode switching, receives instructions from the first control unit and converts them into drive signals executable by the aircraft to achieve millisecond-level control response and precise execution.

[0112] The biomimetic variable configuration wing control module 1320 is used to receive and respond to a first type of drive signal sent by the control unit 1310 to switch to the wing configuration required by the vehicle in different media and / or cross-media situations, and to generate a first feedback signal.

[0113] The first feedback signal can be used to characterize the wing feedback parameters of the current wing state of the aircraft.

[0114] Specifically, the biomimetic variable configuration wing control module 1320 receives the first type of drive signal from the control unit 1310 and generates a first feedback signal to feed back the current wing feedback parameters of the aircraft. For example, it receives the first type of drive signal sent by the second control unit to simulate the contraction mechanism of fish pectoral fins and the unfolding mechanism of birds' wings, and realizes intelligent switching of wing configuration according to different media environments.

[0115] In one possible implementation, the biomimetic variable configuration wing control module 1320 is specifically configured to: receive a first type of drive signal sent by the control unit; and when the current operating mode of the vehicle meets preset conditions, adjust the wing configuration of the vehicle to a target wing configuration through the first type of drive signal; wherein, the target wing configuration is selected from the following based on the preset conditions met by the current operating mode of the vehicle:

[0116] When the current operating mode is underwater, adjust to a shark pectoral fin wing configuration; when the current operating mode is water entry / exit mode, adjust to a flying fish pectoral fin wing configuration; when the current operating mode is ground effect flight mode, adjust to a ground effect flight wing configuration; when the current operating mode is aerial flight mode, adjust to an albatross wing configuration.

[0117] The biomimetic variable-configuration wing control module 1320 employs servo actuators and integrated deformation / navigation coordinated control technology. It simulates the bending and contraction mechanism of fish pectoral fins and the unfolding mechanism of bird wings to dynamically adjust the wing configuration according to different navigation modes (underwater submersion, water entry and exit, ground effect flight, and aerial flight). This module receives drive signals from the underlying execution control unit and achieves intelligent biomimetic wing deformation control through an adaptive fuzzy switching control algorithm. The core innovation of the biomimetic variable-configuration wing control module lies in the engineering implementation of a multi-layered biomimetic mechanism.

[0118] The shark pectoral fin wing configuration is a biomimetic underwater design inspired by shark pectoral fins. Based on depth data from a depth-sensing sensor module, when the environment is determined to be underwater, the design simulates the retraction and body-hugging mechanism of a shark's pectoral fin during underwater swimming. A deep learning-based fluid dynamics optimization algorithm establishes a mapping relationship between the wing angle and hydrodynamic drag. The wing, optimized through intelligent algorithms, closely adheres to the fuselage, forming a streamlined shape to reduce turbulence and lower hydrodynamic drag.

[0119] Among them, the flying fish pectoral fin wing configuration is a biomimetic flying fish pectoral fin water-emerging configuration. Based on the signal that the fuselage begins to leave the water when the medium environment detection module detects that the fuselage is beginning to leave the water, the data-driven dynamic deployment control algorithm is adopted, which draws on the rapid deployment mechanism of the pectoral fin when the flying fish leaps out of the water. The wing achieves intelligent conversion from the retracted state to the deployed state through a multi-joint hinge design, ensuring that it obtains the best lift characteristics at the moment of water emergence.

[0120] Among them, the ground effect flight wing configuration, also known as the ground effect flight-specific configuration, is based on the high-precision positioning and navigation module confirming that the vehicle is near the water surface. It adopts a ground effect biomimetic optimization intelligent control algorithm and adjusts the wing to a dihedral configuration. Combined with the downward airflow generated by the front symmetrical dual propulsion unit in the multi-modal propulsion control module, a ground effect lift zone is formed between the lower surface of the wing and the water surface.

[0121] Among them, the albatross wing configuration, also known as the albatross wing biomimetic flight configuration, is based on the high-precision positioning and navigation module confirming that the aircraft leaves the ground effect zone. It refers to the airfoil adjustment mechanism of the albatross when gliding on the sea surface and adopts a data-driven optimization algorithm based on reinforcement learning. The wing has the ability to actively change camber and can adjust the airfoil geometry parameters in real time according to the flight environment to optimize the lift-to-drag ratio performance.

[0122] Specifically, in this embodiment, the biomimetic wing deformation process is uniformly coordinated by a top-level decision control unit, and a precise mode switching control is achieved using an adaptive fuzzy switching control algorithm. This algorithm constructs a fuzzy inference system based on multi-sensor fusion data. According to multi-dimensional input parameters such as depth information, attitude state, and medium environment, it automatically selects the optimal control strategy through a fuzzy rule base to achieve smooth switching between different modes.

[0123] The multimodal propulsion control module 1330 is used to receive and respond to a second type of drive signal sent by the control unit to drive the propulsion unit required by the vehicle in different media and / or cross-media situations, and to generate a second feedback signal.

[0124] The second feedback signal can be used to characterize the propulsion feedback parameters of the current propulsion state of the vehicle.

[0125] Specifically, the multimodal propulsion control module 1330 is used to receive the control unit 1310, for example, to receive the second type of drive signal sent by the second control unit, to drive the front symmetrical dual propulsion unit and the rear single propulsion module to adapt to the propulsion requirements of different media and rapid maneuvering, and to use the propulsion feedback parameters when the vehicle reaches the propulsion state after driving as the second feedback signal for feedback.

[0126] The attitude and heading control module 1340 is used to receive and respond to the third type of drive signal sent by the control unit to maintain the attitude stability of the vehicle when traveling in different media and / or crossing media, and to generate a third feedback signal.

[0127] The third feedback signal can be used to characterize the attitude feedback parameters of the vehicle's current attitude state.

[0128] Specifically, the attitude and heading control module 1340 receives third-type drive signals from the control unit 1310, such as those sent by the second control unit, and performs control surface control to ensure the attitude stability of the vehicle during different media travel and / or cross-media mode switching, as well as during swarm maneuvers. Furthermore, it feeds back the attitude feedback parameters achieved by the vehicle after the drive as a third feedback signal.

[0129] In addition, the cluster communication coordination module 1410 in the cluster collaboration system 140 is used to receive the perception fusion data sent by the data preprocessing module of each vehicle in the cluster, generate cluster shared data, and send the cluster shared data to the cluster collaborative navigation control module 1420.

[0130] The cluster shared data consists of cluster status information data packets and a command synchronization queue. The cluster status information includes the overall formation layout of the cluster and the position and operational status of each vehicle within the cluster. The command synchronization queue ensures the synchronization of commands among the vehicles within the cluster.

[0131] Specifically, in this embodiment, the cluster communication coordination module 1410 is used to realize communication between the various vehicles within the cluster, and to send the cluster-shared data collected from each vehicle to the cluster collaborative navigation control module 1420 to ensure real-time sharing of status information of each vehicle and accurate synchronization of collaborative commands.

[0132] The cluster collaborative navigation control module 1420 is used to receive cluster shared data sent by the cluster communication coordination module, and to receive other perception fusion data sent by other vehicles in the cluster. Based on the cluster shared data and other perception fusion data, it generates a cluster collaborative trajectory and sends it to the collaborative task allocation module 1430.

[0133] Among them, the swarm coordination trajectory can be the trajectory parameters that the aircraft refer to in order to complete the swarm formation requirements.

[0134] Specifically, the cluster collaborative navigation control module 1420 is used to generate a cluster collaborative trajectory based on the formation requirements of the cluster collaborative system 140 and the high-precision positioning and navigation data of each vehicle in the cluster, and distribute it to the collaborative task allocation module 1430 in the cluster collaborative system 140 of each vehicle, so as to ensure the collaborative navigation and formation control of each vehicle in the cluster.

[0135] The collaborative task allocation module 1430 is used to receive the cluster collaborative trajectory sent by the local cluster collaborative navigation control module 1420, and generate a target task based on the cluster collaborative trajectory, the current operating status of the vehicle and the task instructions through a distributed algorithm and send it to the collaborative task execution strategy module.

[0136] This embodiment can learn the upcoming flight trajectories of other vehicles in the cluster by receiving the cluster's collaborative trajectory. Combined with the current operating status and task instructions of the local vehicle, intelligent task allocation and load balancing can be performed through distributed algorithms to generate target tasks. This embodiment can allocate tasks to vehicles with different modal advantages based on their biomimetic wing deformability and cross-medium flight performance: for example, underwater reconnaissance tasks are assigned to vehicles with shark pectoral fin configuration advantages, ground effect flight tasks are assigned to vehicles with ground effect flight configuration advantages, and high-altitude cruise tasks are assigned to vehicles with albatross wing configuration advantages.

[0137] The collaborative task execution strategy module 1440 is used to receive the target task sent by the collaborative task allocation module 1430, process the target task based on the collaborative task allocation algorithm, generate a collaborative operation control command, and send it to the control unit 1310 in the multimodal collaborative control and execution system 130.

[0138] Among them, the collaborative operation control command is the cluster team control command obtained by parsing the target task, which is used to control the aircraft to form up and change formation as required.

[0139] Specifically, in this embodiment, the collaborative task execution strategy module 1440 is used to receive the task allocation table and priority list from the collaborative task allocation module 1430, generate collaborative operation control instructions according to the collaborative task allocation algorithm, and realize the dynamic formation and formation change of multiple vehicles.

[0140] Furthermore, in this embodiment, the collaborative task execution strategy module 1440 employs a biomimetic swarm intelligence algorithm to coordinate the mode switching and timing control of each spacecraft:

[0141] Based on the swimming behavior of fish, underwater formation control coordinates multiple vehicles to maintain the biomimetic underwater configuration of shark pectoral fins when multiple vehicles are submerged, so as to achieve close formation and flexible obstacle avoidance.

[0142] Aerial formation control based on bird flock flight mode: when the group of aircraft enters the aerial flight mode, it coordinates each aircraft to switch to the albatross wing biomimetic flight configuration to maintain formation stability and optimal energy consumption.

[0143] Based on the dolphin group leaping behavior, the water entry and exit formation coordination is carried out to coordinate the repeated rapid water entry and exit sequence of each vehicle, ensure that collisions are avoided when the group enters and exits the water synchronously, and optimize the overall cross-media conversion efficiency.

[0144] This embodiment enables multi-directional, multi-level collaborative operations and efficient task execution by sending collaborative operation control commands to the top-level decision control unit in the multimodal collaborative control and execution system 130 of each aircraft.

[0145] In one embodiment, the control unit 1310 includes:

[0146] The first control unit is used to receive the perception fusion data sent by the data preprocessing module 1250 and the collaborative operation control command sent by the collaborative task execution strategy module 1440, and generate a coordinated control command based on the perception fusion data, the collaborative operation control command and the current operating status of the vehicle, and send it to the second control unit and the autonomous decision-making and mission planning system 110.

[0147] The second control unit is used to receive the coordinated control command from the first control unit, and respond by converting it into a first type of drive signal, a second type of drive signal, and a third type of drive signal. The first type of drive signal is sent to the biomimetic variable configuration wing control module 1320, the second type of drive signal is sent to the multimodal propulsion control module 1330, and the third type of drive signal is sent to the attitude and heading control module 1340.

[0148] Among them, the coordinated control command can be the control command for controlling the vehicle's trajectory and mode switching.

[0149] Specifically, in this embodiment, the first control unit is the top-level decision control unit, and the second control unit is the bottom-level execution control unit. The top-level decision control unit and the bottom-level execution control unit adopt a hierarchical collaborative control architecture. The top-level decision control unit runs adaptive control firmware and is responsible for executing high-level control algorithms such as adaptive fuzzy switching control, trajectory tracking, and mode switching decision-making. The bottom-level execution control unit focuses on receiving control commands from the top-level decision control unit and the optimal inlet / outlet path parameters from the inlet / outlet path planning module, converting them into pulse width modulation signals for output. This enables precise driving of the actuators of the biomimetic variable configuration wing control module, the multimodal propulsion control module, and the attitude and heading control module. Real-time communication between the high- and low-level control modules is achieved through a standard communication bus, improving the modular design, reliability, and functional scalability of the control system.

[0150] For example, the second control unit receives the coordinated control command from the first control unit and responds by converting it into a first type of drive signal, a second type of drive signal, and a third type of drive signal. The first type of drive signal is sent to the biomimetic variable configuration wing control module 1320, the second type of drive signal is sent to the multimodal propulsion control module 1330, and the third type of drive signal is sent to the attitude and heading control module 1340. In this way, the aircraft is adjusted to reach the target state.

[0151] Figure 5 This illustration shows a schematic diagram of the structure of an autonomous decision-making and mission planning system in a cross-medium vehicle system provided by an embodiment of this disclosure. Figure 5 As shown, the autonomous decision-making and task planning system 110 includes: a mode switching decision module 1110, an inlet / outlet water path planning module 1120, and a communication and command management module 1130. Among them,

[0152] The mode switching decision module 1110 is used to receive the coordinated control command from the first control unit when the vehicle is switching modes across media, and generate a mode switching control command based on the adaptive rule algorithm and the coordinated control command, and send it to the water inlet / outlet path planning module 1120.

[0153] Among them, the mode switching control command can be a command that controls the vehicle to switch modes in cross-media situations.

[0154] Specifically, the mode switching decision module 1110 is used to receive the coordinated control command of the first control unit, process the uncertainty of multi-sensor data of the multi-source information perception and state recognition system in combination with the adaptive fuzzy control rule base, realize intelligent mode switching decision based on the bionic wing deformation state and medium environment characteristics, and generate mode switching control command using finite state machine and fuzzy logic control algorithm and send it to the inlet and outlet water path planning module 1120.

[0155] The water inlet / outlet path planning module 1120 receives the mode switching control command sent by the mode switching decision module 1110, calculates the optimal water inlet / outlet path parameters according to the mode switching control command, and sends the optimal water inlet / outlet path parameters to the second control unit to continuously control the vehicle to reach the target state.

[0156] Among them, the optimal water entry and exit path parameters can be the water entry and exit angle, speed sequence, and timing control parameters of the vehicle when entering and exiting the water.

[0157] Specifically, the water entry / exit path planning module 1120 is used to receive the mode switching control command from the mode switching decision module 1110, and process the depth reference data, real-time attitude feedback data and environmental status data of the multi-source information perception and state recognition system based on the neural network algorithm, calculate the optimal water entry / exit path parameters, and send the optimal water entry / exit path parameters to the second control unit in the multi-modal cooperative control and execution system 130 to realize the trajectory planning and attitude optimization of the vehicle's repeated rapid water entry / exit.

[0158] The communication and command management module 1130 is used to receive task commands sent by the ground station, send the task commands to the collaborative task allocation module, and also to feed back task execution status information to the ground station.

[0159] Specifically, the communication and command management module 1130 is used for two-way data interaction with the ground station, receiving task commands and distributing them to the collaborative task allocation module 1430 in the cluster collaborative system 140. It supports online updates and remote monitoring of control parameters, and at the same time feeds back the system operating status and task execution results to the ground station to realize remote command and control.

[0160] In one possible implementation, the second control unit is further configured to:

[0161] In the case of cross-media mode switching, the system receives the optimal water inlet / outlet path parameters sent by the water inlet / outlet path planning module 1120, and updates the first type of drive signal, the second type of drive signal, and the third type of drive signal according to the optimal water inlet / outlet path parameters and the cluster cooperative trajectory, thereby controlling the vehicle to reach the target state.

[0162] Because swarm vehicles not only need to work collaboratively in groups and perform corresponding position changes for different modes and tasks during mission execution, but also need to complete their own mission objectives according to the target mission requirements, the vehicles often need to repeatedly and rapidly enter and exit the water during mission execution. In this embodiment, by sending the optimal water entry and exit path parameters to the second control unit, the corresponding drive signals can be parsed and generated, and the first type of drive signal, the second type of drive signal, and the third type of drive signal can be updated in a timely manner, thereby fulfilling the requirements of repeated water entry and exit and formation.

[0163] Figure 6 A complete structural schematic diagram of an exemplary cross-medium vehicle system provided by an embodiment of this disclosure is shown. Figure 6 As shown, this embodiment, with a first control unit and a second control unit as its core, exemplifies a clearer and more complete vehicle system structure. The interactions between different modules have been detailed above and will not be repeated here. It is important to note that, because the vehicle needs to complete the target task assigned by the cluster based on its position and characteristics within the cluster, and because it frequently enters and exits the water, the control mechanism for the vehicle body differs under different circumstances. For example, in different media, the first control unit in this embodiment can generate coordinated control commands based on the perception fusion data sent by the data preprocessing module, the coordinated operation control commands sent by the coordinated task execution strategy module, and the vehicle's current operating state, and send these commands to the second control unit to achieve the target state. Simultaneously, the first control unit also sends the coordinated control commands to the mode switching decision module, facilitating the generation of mode switching control commands based on the adaptive rule algorithm in the mode switching decision module when crossing media. These commands are then sent to the water entry / exit path planning module, which calculates the optimal water entry / exit path parameters and sends them to the second control unit to continuously control the vehicle to achieve the target state.

[0164] This embodiment achieves comprehensive perception of the vehicle in different media environments through a multi-source information perception and state recognition system, providing precise data support for biomimetic wing deformation, rapid water entry and exit, and swarm collaboration. A multi-modal collaborative control and execution system enables precise coordination of biomimetic variable-configuration wings, rapid water entry and exit trajectory control, and multi-modal propulsion, with each module working together to form a unified control system. A swarm collaboration system enables formation control, task allocation, and collaborative operation of multiple vehicles, fully leveraging swarm advantages. An autonomous decision-making and mission planning system enables intelligent mode switching decisions, path planning, and collaborative control, achieving overall optimization. Applying this system effectively realizes intelligent control of biomimetic wing deformation, precise control of repeated rapid water entry and exit, and collaborative operation of multiple vehicle swarms. A single platform can achieve cross-media mode conversion and collaborative control in underwater submersion, surface effect flight, and aerial flight, significantly improving the stability, continuity, speed, and autonomy of cross-media operations. This solves the technical challenges of traditional vehicles being unable to operate across boundaries, having low wing deformation efficiency, poor water entry and exit control accuracy, and lacking swarm collaboration capabilities.

[0165] In one embodiment, the adaptive rule algorithm is an algorithm that generates coordinated control commands based on the output of the sub-controllers within the aircraft and the weights of fuzzy rules.

[0166] The sub-controllers can be specialized controllers designed for different flight modes of the aircraft. For example, they may include: an underwater submersible mode controller for controlling the biomimetic underwater configuration of the shark's pectoral fins; an out-of-water mode controller for controlling the biomimetic out-of-water configuration of the flying fish's pectoral fins; a ground effect flight mode controller for controlling the ground effect flight configuration; and an aerial flight mode controller for controlling the biomimetic flight configuration of the albatross's wings.

[0167] Specifically, the calculation process of the adaptive rule algorithm can be found as follows:

[0168] The attitude quaternion solution formula (1) is expressed as:

[0169] (1)

[0170] in, For attitude quaternions Describe the current attitude of the vehicle. It is the angular velocity vector. Represents quaternion multiplication; The time derivative of the attitude quaternion; This is the current time of the vehicle.

[0171] This embodiment can determine the real-time attitude information of the vehicle based on the perception fusion data collected by the vehicle. Constructing state vectors This can include, for example, depth values, attitude angles, medium contact states, and velocities. The state vector... Input the fuzzy weight calculation formula (2).

[0172] The fuzzy weight calculation formula (2) is expressed as:

[0173] (2)

[0174] in, For the first The activation weight of a fuzzy rule; For the first The membership function value of a fuzzy rule; For the first The membership function value of a fuzzy rule; The total number of fuzzy rules; This is the current system state vector; the denominator ensures that the sum of all weights is 1, achieving normalization.

[0175] Specifically, this embodiment can be based on the current state of the aircraft. The activation weights of each mode are calculated to determine how to fuse different sub-controllers, thus deriving fuzzy weights. Then fuzzy weights Input the adaptive fuzzy switching control algorithm formula (3). For example, when the vehicle switches from underwater to air, the weight of the underwater sub-controller gradually decreases, while the weight of the surface mode sub-controller increases, achieving smooth mode switching.

[0176] The adaptive fuzzy switching control algorithm formula (3) is expressed as:

[0177] (3)

[0178] in, For the first The activation weight of a fuzzy rule. For the first The output of each sub-controller, where n is the total number of fuzzy rules, corresponding to four navigation modes, n=4; This is the total control output.

[0179] Specifically, total control output The final control command sent to the second control unit. The outputs of dedicated controllers are designed to correspond to the four modes of underwater navigation, surface flight, ground effect flight, and aerial flight. Indicates the first The activation level of each mode. This embodiment uses the total control output. It can integrate the outputs of all sub-controllers to generate the final control command. Since the aircraft may have execution deviations during the mission, this embodiment also sets an adaptive parameter update rate formula (4).

[0180] The adaptive parameter update rate formula (4) is:

[0181] (4)

[0182] in, For the first The adaptive parameter vector of each sub-controller; For adaptive gain, e(t) is the tracking error; It is a positive definite weight matrix. For the first A vector of basis functions for each mode;

[0183] Specifically, The speed is adjusted to control the parameters; e(t) can be the difference between the desired trajectory and the actual trajectory. The update weights for different parameters can be adjusted. It can describe the characteristic function of the vehicle in a certain mode of navigation. In this embodiment, the execution effect of the vehicle can be known by collecting data, thereby updating the sub-controller parameters of the vehicle in a certain mode.

[0184] The adaptive rule algorithm in this embodiment can dynamically adjust control parameters according to environmental conditions and task requirements, ensuring intelligent switching and precise control between different modes such as underwater submersion, rapid water surfacing, ground effect flight, and aerial cruise. Precise driving is achieved through the second control unit, that is, the underlying execution control unit, and the entire deformation process can be completed quickly to ensure the continuity of cross-media conversion.

[0185] Figure 7 A third-view diagram of an exemplary cross-medium vehicle provided in this disclosure embodiment. Figure 8 An explosion diagram of an exemplary cross-medium vehicle provided for embodiments of this disclosure.

[0186] like Figure 8As shown, the cross-medium vehicle includes, but is not limited to: a wing 810, a front thruster 821, a rear thruster 822, a fuselage 830, and a tail 840. The wing 810 integrates the biomimetic variable configuration wing control module 1320 described in the above embodiment, enabling the module to adjust the wing configuration. The front thruster 821 and rear thruster 822 integrate a multi-modal propulsion control module 1330, enabling the module to achieve propulsion. The tail 840 integrates the attitude and heading control module 1340 described in the above embodiment, enabling the module to maintain attitude stability, thereby completing the tasks issued by the ground station.

[0187] Figure 9 This flowchart illustrates a control method for a cross-medium vehicle system provided in this disclosure. This method can be executed by a control device for the cross-medium vehicle system provided in this disclosure, and the device can be implemented in software and / or hardware. Specifically, the method includes:

[0188] S910 receives mission instructions sent by the ground station.

[0189] The task instruction is used to indicate the collective task that the cluster needs to complete.

[0190] Specifically, the mission instructions are the mission instructions and operational requirements for switching modes from underwater to air, which are received by the communication and command management module in each aircraft of the aircraft cluster from the ground station, and the mission instructions are sent to the collaborative mission allocation module.

[0191] S920. Real-time acquisition of the vehicle's perception data in different media environments, and preprocessing the perception data into perception fusion data.

[0192] The perception data includes at least one of the following: raw depth data, raw pose data, raw positioning data, and contact state data.

[0193] Specifically, the aircraft receives the raw data from each sensor, performs filtering, calibration, time synchronization, and data format unification processing, and uses the processed environmental perception information as perception fusion data.

[0194] S930: Receive other perception fusion data sent by other vehicles in the cluster in real time, and generate a cluster cooperative trajectory based on the perception fusion data and other perception fusion data sent by other vehicles in the cluster.

[0195] Specifically, in this embodiment, the vehicle generates cluster-shared data based on its own perception fusion data, and generates a cluster-coordinated trajectory by combining the perception fusion data sent by other vehicles in the cluster, thereby obtaining the vehicle's own driving trajectory within the cluster.

[0196] S940. Determine the target mission of the vehicle based on the cluster cooperative trajectory, the current operating status of the vehicle, and the mission instructions.

[0197] The current operating status includes the current operating parameters of the vehicle when traveling on different media or crossing media, and the target mission belongs to at least one sub-mission in the collective mission.

[0198] Specifically, in this embodiment, the vehicle generates a target task belonging to the vehicle itself through a distributed algorithm based on the cluster collaborative trajectory, the vehicle's current operating status, and the task instructions, and finally processes the target task based on the collaborative task allocation algorithm.

[0199] S950. Determine the optimal water entry / exit path parameters of the vehicle according to the target mission, and then generate a drive signal based on the perception fusion data or the optimal water entry / exit path parameters to continuously control the vehicle to reach the target state.

[0200] Specifically, in this embodiment, when no cross-medium interaction is involved, coordinated control commands executable by the vehicle itself can be generated based on the sensing fusion data, and the coordinated control commands can be converted into first-type drive signals, second-type drive signals, and third-type drive signals to control the vehicle to reach the target state. When cross-medium interaction is involved, coordinated control commands executable by the vehicle itself can be generated based on the optimal water inlet and outlet path parameters, and the coordinated control commands can be converted into first-type drive signals, second-type drive signals, and third-type drive signals to control the vehicle to reach the target state.

[0201] The first type of drive signal is used to switch the wing configuration of the aircraft, the second type of drive signal is used to drive different propulsion units of the aircraft, and the third type of drive signal is used to drive the control surfaces of the aircraft.

[0202] In this embodiment, when the vehicle undergoes cross-media mode switching, it receives coordinated control commands from the first control unit. Based on an adaptive rule algorithm and the coordinated control commands, it generates mode switching control commands. Optimal water ingress / exit path parameters are calculated according to these commands. Then, based on sensing fusion data or the optimal water ingress / exit path parameters, the vehicle's operating state is continuously adjusted to reach the target state, thereby completing the target mission. Specifically, the first, second, and third types of drive signals are updated using the optimal water ingress / exit path parameters to continuously update the vehicle's operating state. Furthermore, this embodiment also feeds back mission execution status information to the ground station.

[0203] In addition, this embodiment receives the sensing fusion data of the vehicle itself in real time after receiving the first type of drive signal; based on the sensing fusion data, it monitors the current state of the vehicle in real time; when the current state meets the preset conditions, it adjusts the wing configuration of the vehicle to the target wing configuration through the first type of drive signal; wherein, the target wing configuration is selected from the following according to the preset conditions met by the current state: when the current state is underwater mode, it is adjusted to a shark pectoral fin wing configuration; when the current state is water entry / exit mode, it is adjusted to a flying fish pectoral fin wing configuration; when the current state is ground effect flight mode, it is adjusted to a ground effect flight wing configuration; when the current state is aerial flight mode, it is adjusted to an albatross wing configuration.

[0204] For ease of understanding, this embodiment provides a more detailed example of a control flow method:

[0205] Specifically, the communication and command management module receives mission instructions and operational requirements from the ground station regarding the mode switching from underwater to airborne, and then sends these mission requirements to the collaborative task allocation module. The collaborative task allocation module receives the cluster collaborative trajectory from the cluster communication coordination module, the mission requirements from the communication and command management module, and the vehicle's current operating parameters. It then performs intelligent task allocation and load balancing, generating target tasks, i.e., a task allocation table and a priority list. The collaborative task execution strategy module receives the task allocation table and priority list, generates collaborative operation control instructions based on the collaborative task allocation algorithm, and sends them to the top-level decision control unit.

[0206] During the underwater ascent phase, which does not involve cross-medium mode switching, the top-level decision control unit receives fused sensor data from the multi-source information perception and state recognition system, collaborative operation control commands from the swarm coordination system, and the current operating parameters of the vehicle. Based on the intelligent decision-making algorithm, it generates coordinated control commands and sends them directly to the bottom-level execution control unit. The bottom-level execution control unit converts the coordinated control commands into pulse-width modulated drive signals, which are then sent to: the rear single propulsion module in the multi-modal propulsion control module to provide stable vertical ascent thrust; the attitude and heading control module to execute control surface control, ensuring attitude stability during ascent; and the biomimetic variable configuration wing control module to maintain the shark-like underwater pectoral fin biomimetic configuration. Simultaneously, the swarm communication coordination module continuously updates the position information of each vehicle, and the collaborative task execution strategy module ensures formation coordination during the ascent process.

[0207] When the depth sensing sensor module detects that the aircraft has ascended to a preset cross-medium switching depth threshold, or when the medium environment detection module detects that the fuselage has begun to leave the water (partial contact state), the data preprocessing module sends depth reference data and other environmental state data to the top-level decision control unit. The top-level decision control unit determines that a cross-medium mode switch is required and generates a coordinated control command, which is then sent to the mode switch decision module.

[0208] The modal switching decision module, combined with an adaptive fuzzy control rule base, handles the uncertainties of multi-sensor data to achieve intelligent modal switching decisions based on the biomimetic wing deformation state and medium environment characteristics. It generates modal switching control commands and sends them to the repeated rapid water inlet / outlet path planning module. This module uses a neural network algorithm to process multi-source sensor fusion data, calculates the optimal water outlet path parameters (including outlet angle, velocity sequence, and timing control parameters), and sends these parameters to the underlying execution control unit. The underlying execution control unit converts the optimal water outlet / outlet path parameters into precise drive signals, simultaneously driving the biomimetic variable configuration wing control module, the modal propulsion control module, and the modal propulsion control module.

[0209] Specifically, the biomimetic variable configuration wing control module rapidly transforms from a shark-inspired underwater configuration to a flying fish-inspired emerging configuration, mimicking the rapid deployment mechanism of a flying fish's pectoral fin to ensure optimal lift characteristics at the moment of emergence. The forward and backward propulsion units of the modal propulsion control module work together to provide precise cross-medium thrust conversion and overcome surface resistance. The attitude and heading control module executes precise control surfaces to maintain stable attitude along the planned path during the emergence process.

[0210] Once the environmental monitoring module confirms that the vehicle has completely separated from the water (fully separated state) and entered the air, it sends the environmental status data to the data preprocessing module. Simultaneously, the high-precision positioning and navigation module begins GPS positioning and sends the positioning data to the data preprocessing module. The data preprocessing module then sends the environmental status information and positioning information to the top-level decision control unit. The top-level decision control unit executes an intelligent decision-making algorithm to generate coordinated control commands, which are then sent to the bottom-level execution control unit.

[0211] The underlying execution control unit then drives the biomimetic variable configuration wing control module to adjust the wing to a ground effect flight configuration, employing a ground effect-based biomimetic optimized intelligent control algorithm. Simultaneously, it drives the forward symmetrical dual propulsion units in the multimodal propulsion control module to generate downdrafts, creating a ground effect lift zone between the lower wing surface and the water surface. Furthermore, the swarm cooperative navigation control module updates the swarm cooperative trajectory, and the cooperative mission execution strategy module coordinates the various vehicles to establish formation at a preset ground effect flight altitude.

[0212] After each vehicle has flown a predetermined distance in ground effect flight mode, the top-level decision control unit completes attitude stability checks and self-checks of each subsystem's status, generating coordinated control commands and sending them to the bottom-level execution control unit. The bottom-level execution control unit then drives the biomimetic variable-configuration wing control module to adjust the wing to an albatross-wing biomimetic flight configuration, simulating the efficient gliding mechanism of an albatross wing, and improving aerodynamic performance through a data-driven optimization algorithm based on reinforcement learning. Simultaneously, it drives the rear single-propulsion module in the multi-modal propulsion control module to increase thrust.

[0213] The cluster collaborative navigation control module generates a cluster collaborative trajectory for air patrol, and the collaborative mission execution strategy module coordinates each vehicle to climb to the preset cruise altitude and enter the air patrol formation mode.

[0214] During aerial patrol, the communication and command management module establishes a high-quality wireless communication link with the ground station to transmit ocean mooring monitoring data. After completing the data transmission task, it can coordinate to return to underwater or continue to perform other aerial tasks based on new instructions issued by the ground station through the communication and command management module.

[0215] This embodiment effectively realizes intelligent deformation of biomimetic wings, precise control of repeated rapid water entry and exit, and collaborative operation of multiple aircraft swarms, significantly improving the stability and autonomy of cross-medium operations, and solving the technical problems of low deformation efficiency, poor water entry and exit control accuracy, and lack of swarm collaboration capability of traditional aircraft wings.

[0216] Furthermore, this embodiment can flexibly adjust the settings of bionic wing deformation parameters, rapid water entry / exit control parameters, and swarm coordination strategies according to actual sea conditions and mission requirements to ensure optimal overall performance and safety. When sea conditions are poor, the triggering conditions for bionic wing deformation and the trajectory parameters for rapid water entry / exit can be adjusted; when rapid swarm maneuvering is required, the bionic wing deformation speed and swarm coordination timing can be optimized.

[0217] Figure 10 This is a schematic diagram of the structure of a control device for a cross-medium vehicle system provided in an embodiment of this disclosure. The device specifically includes:

[0218] The task receiving module 1010 is used to receive task instructions sent by the ground station, wherein the task instructions are used to indicate the collective tasks that the cluster needs to complete.

[0219] The first data acquisition module 1020 is used to acquire the sensing data of the vehicle in different media environments in real time, and preprocess the sensing data into sensing fusion data.

[0220] The second data acquisition module 1030 is used to receive perception fusion data sent by other vehicles in the cluster in real time, and generate a cluster cooperative trajectory based on the perception fusion data and the perception fusion data sent by other vehicles in the cluster.

[0221] The task determination module 1040 is used to determine the target task of the vehicle based on the cluster cooperative trajectory, the current operating status of the vehicle and the task instructions, wherein the current operating status includes the current operating parameters of the vehicle when traveling on different media or crossing media, and the target task belongs to at least one sub-task in the collective task.

[0222] The state update module 1050 is used to determine the optimal water entry and exit path parameters of the vehicle according to the target task, and then generate a drive signal based on the perception fusion data or the optimal water entry and exit path parameters to continuously control the vehicle to reach the target state.

[0223] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0224] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.

[0225] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure 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 disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A cross-medium vehicle system, characterized in that, The system includes: An autonomous decision-making and task planning system is used to receive task instructions sent by the ground station and send them to the cluster collaboration system. The task instructions are used to indicate the collective tasks that the cluster needs to complete. A multi-source information perception and state recognition system is used to acquire perception data of the vehicle in different media environments in real time, preprocess the perception data into perception fusion data, and then send the perception fusion data to a multimodal collaborative control and execution system and a cluster collaborative system. The cluster collaboration system is used to receive perception fusion data sent by the local multi-source information perception and state recognition system, other perception fusion data sent by other vehicles in the cluster, and task instructions. Based on the perception fusion data and other perception fusion data sent by other vehicles in the cluster, a cluster collaboration trajectory is generated. Based on the cluster collaboration trajectory, the current operating status of the vehicle, and the task instructions, the target task of the vehicle is determined and sent to the autonomous decision-making and task planning system. The current operating status includes the current operating parameters of the vehicle when traveling on different media or crossing media. The target task belongs to at least one sub-task in the collective task. The autonomous decision-making and mission planning system is also used to receive the target mission sent by the cluster collaboration system, determine the optimal water entry and exit path parameters of the vehicle based on the target mission, and then feed back the optimal water entry and exit path parameters to the multimodal collaborative control and execution system. The multimodal collaborative control and execution system is used to receive the perception fusion data sent by the multi-source information perception and state recognition system and the optimal water entry and exit path parameters sent by the autonomous decision-making and mission planning system, and generate driving signals based on the perception fusion data or the optimal water entry and exit path parameters to continuously control the vehicle to reach the target state. The multimodal collaborative control and execution system includes: The biomimetic variable configuration wing control module is used to receive and respond to the first type of drive signal sent by the control unit in the multimodal cooperative control and execution system, so as to switch to the wing configuration required by the vehicle when traveling in different media or crossing media, and generate a first feedback signal; The biomimetic variable configuration wing control module is specifically used for: Receive the first type of drive signal sent by the control unit; When the current operating mode of the vehicle meets the preset conditions, the wing configuration of the vehicle is adjusted to the target wing configuration by the first type of drive signal; The target wing configuration is selected from one of the following based on preset conditions satisfied by the current operating mode of the aircraft: When the current operating mode is underwater mode, adjust to a shark pectoral fin wing configuration; When the current operating mode is the water inlet / outlet mode, adjust to the flying fish pectoral fin wing configuration; When the current operating mode is ground effect flight mode, adjust to ground effect flight wing configuration; When the current operating mode is the aerial flight mode, adjust to the albatross wing configuration.

2. The system according to claim 1, wherein, The sensing data includes at least one of raw depth data, raw pose data, raw positioning data, and contact state data. The multi-source information sensing and state recognition system includes: The depth sensing sensor module is used to measure the raw depth data of the vehicle while it is submerged in water in real time, and send the raw depth data to the data preprocessing module. The attitude and motion state detection module is used to acquire the raw attitude data of the vehicle and send the raw attitude data to the data preprocessing module. A high-precision positioning and navigation module is used to acquire the raw positioning data of the vehicle and send the raw positioning data to the data preprocessing module; The medium environment detection module is used to detect the contact status data between various parts of the vehicle and the water in real time, and send the contact status data to the data preprocessing module. The data preprocessing module is used to receive and process the raw depth data, the raw attitude data, the raw positioning data, and the contact state data to generate the perception fusion data; and to send the perception fusion data to the multimodal collaborative control and execution system and the cluster collaborative system.

3. The system according to claim 2, characterized in that, The cluster collaboration system includes: The cluster communication coordination module is used to receive perception fusion data sent by the data preprocessing modules of each vehicle in the cluster, generate cluster shared data, and send the cluster shared data to the cluster cooperative navigation control module. The cluster collaborative navigation control module is used to receive cluster shared data sent by the cluster communication coordination module, and to receive other perception fusion data sent by other vehicles in the cluster. Based on the cluster shared data and other perception fusion data, it generates a cluster collaborative trajectory and sends it to the collaborative task allocation module. The collaborative task allocation module is used to receive the cluster collaborative trajectory sent by the cluster collaborative navigation control module, and based on the cluster collaborative trajectory, the current operating status of the vehicle and the task instructions, generate a target task through a distributed algorithm and send it to the collaborative task execution strategy module. The collaborative task execution strategy module is used to receive the target task sent by the collaborative task allocation module, process the target task based on the collaborative task allocation algorithm, generate collaborative operation control instructions and send them to the multimodal collaborative control and execution system.

4. The system according to claim 3, characterized in that, The multimodal collaborative control and execution system also includes: The control unit is configured to receive perception fusion data sent by the data preprocessing module and collaborative operation control commands sent by the collaborative task execution strategy module. Based on the perception fusion data, the collaborative operation control commands, and the current operating state of the vehicle, it determines a first type of drive signal, a second type of drive signal, and a third type of drive signal. The first type of drive signal is sent to the biomimetic variable configuration wing control module, the second type of drive signal is sent to the multimodal propulsion control module, and the third type of drive signal is sent to the attitude and heading control module. The first type of drive signal is used to switch the wing configuration of the vehicle, the second type of drive signal is used to drive different propulsion units of the vehicle, and the third type of drive signal is used to drive the control surfaces of the vehicle. The multimodal propulsion control module is used to receive and respond to the second type of drive signal sent by the control unit to drive the propulsion unit required by the vehicle in different media or cross-media situations, and to generate a second feedback signal; The attitude and heading control module is used to receive and respond to the third type of drive signal sent by the control unit to maintain the attitude stability of the vehicle when traveling in different media or crossing media, and to generate a third feedback signal. The first feedback signal, the second feedback signal, and the third feedback signal collected in real time are used as the current operating parameters of the vehicle.

5. The system according to claim 4, characterized in that, The control unit includes: The first control unit is used to receive the perception fusion data sent by the data preprocessing module and the collaborative operation control command sent by the collaborative task execution strategy module, and generate a coordinated control command based on the perception fusion data, the collaborative operation control command and the current operating status of the vehicle, and send it to the second control unit and the autonomous decision-making and mission planning system. The second control unit is used to receive the coordinated control command from the first control unit, and respond by converting it into a first type of drive signal, a second type of drive signal, and a third type of drive signal. The first type of drive signal is sent to the biomimetic variable configuration wing control module, the second type of drive signal is sent to the multimodal propulsion control module, and the third type of drive signal is sent to the attitude and heading control module.

6. The system according to claim 5, characterized in that, The autonomous decision-making and task planning system includes: The mode switching decision module is used to receive the coordinated control command from the first control unit when the vehicle is switching modes across media, and generate a mode switching control command based on the adaptive rule algorithm and the coordinated control command, and send it to the water entry and exit path planning module. The water entry / exit path planning module is used to receive the mode switching control command sent by the mode switching decision module, calculate the optimal water entry / exit path parameters according to the mode switching control command, and send the optimal water entry / exit path parameters to the second control unit to continuously control the vehicle to reach the target state. The communication and command management module is used to receive task commands sent by the ground station, send the task commands to the collaborative task allocation module, and also to feed back task execution status information to the ground station.

7. The system according to claim 6, wherein, The second control unit is further configured to: In the case of cross-media mode switching, the system receives the optimal water inlet / outlet path parameters sent by the water inlet / outlet path planning module, and updates the first type of drive signal, the second type of drive signal, and the third type of drive signal according to the optimal water inlet / outlet path parameters and the cluster cooperative trajectory, thereby controlling the vehicle to reach the target state.

8. The system according to claim 6, characterized in that, The adaptive rule algorithm is an algorithm that generates coordinated control commands based on the output of the sub-controller inside the aircraft and the weights of fuzzy rules.

9. A control method for a cross-medium vehicle system according to any one of claims 1-8, characterized in that, The method includes: Receive task instructions sent by the ground station, wherein the task instructions are used to indicate the collective tasks that the cluster needs to complete; Real-time acquisition of sensing data of the vehicle in different media environments, and preprocessing of the sensing data into sensing fusion data; The system receives other perception fusion data sent by other vehicles in the cluster in real time, and generates a cluster cooperative trajectory based on the perception fusion data and other perception fusion data sent by other vehicles in the cluster. Based on the cluster cooperative trajectory, the current operating status of the vehicle, and the mission instructions, the target mission of the vehicle is determined, wherein the current operating status includes the current operating parameters of the vehicle when traveling on different media or crossing media, and the target mission belongs to at least one sub-task in the collective mission; The optimal water entry and exit path parameters of the vehicle are determined according to the target mission, and then a drive signal is generated based on the perception fusion data or the optimal water entry and exit path parameters to continuously control the vehicle to reach the target state.

Images