CN114274719B - Mode self-adaptive switching method of amphibious unmanned vehicle - Google Patents

Abstract

The invention relates to a mode self-adaptive switching method of an amphibious unmanned vehicle, belonging to the technical fields of vehicle engineering and ship industry. The invention provides a novel mode self-adaptive switching method for solving the problem that the existing amphibious unmanned vehicle has limited autonomous functions and needs personnel to operate and switch the amphibious unmanned vehicle modes in real time at the amphibious interface. The method is based on structural feature models of the amphibious unmanned vehicle in three different working environments of land, water surface and underwater, and an omnibearing mode self-adaptive switching method is built, so that autonomous capacity of the amphibious mode is improved, and burden of operators is greatly reduced. The invention can be applied to the technical field of ship industry and the technical field of amphibious unmanned vehicles.

Description

A mode adaptive switching method for amphibious unmanned vehicles

Technical field

The invention relates to a mode adaptive switching method for an amphibious unmanned vehicle, and belongs to the technical fields of vehicle engineering and shipbuilding industry.

Background technique

The amphibious vehicle is a special vehicle that has both water and land driving functions and can complete underwater detection, offshore landing and other functions. It plays an irreplaceable role in the unique geographical environment. At present, amphibious vehicles are developing in the direction of lightweight and unmanned vehicles. However, due to the different working requirements of amphibious vehicles in water and on land, their own structures need to change accordingly as the environment changes. Therefore, existing amphibious unmanned vehicles often cannot achieve true autonomy and generally require human-in-the-loop remote control. In view of the current situation that existing amphibious unmanned vehicles cannot realize autonomous switching between amphibious and land modes, it is necessary to invent an adaptive switching method for amphibious unmanned vehicles that can automatically change its own mode according to the surrounding environment, thereby further improving the amphibious unmanned vehicles. autonomy and adaptability to the environment.

Contents of the invention

In order to solve the problem that existing amphibious unmanned vehicles have limited autonomous functions and require real-time human control and switching of amphibious unmanned vehicle modes at the amphibious interface, the present invention proposes a new mode adaptive switching method. This method is based on the structural characteristics model of amphibious unmanned vehicles in three different working environments of land, water and underwater, and builds a comprehensive mode adaptive switching method, thereby improving the autonomy of amphibious modes and greatly reducing the control personnel burden. The invention can be applied to the technical field of shipbuilding industry and the technical field of amphibious unmanned vehicles.

A mode adaptive switching method for amphibious unmanned vehicles, including the following steps:

Step 1. Determine the working status of the key deformation mechanisms of the body of the amphibious unmanned vehicle in different environments on land, water and underwater. The key deformation mechanisms of the body include: crawler tracks, water jet propulsion devices and buoys;

When the amphibious unmanned vehicle is working on land, the crawler tracks are in an extended state, the water-jet propulsion device is retracted into the body, and the buoy is in a retracted state and is tightly sucked to the top of the body. When the amphibious unmanned vehicle is working on the water, the tracks are retracted, the water jet propulsion device is deployed, and the buoy is in the retracted state. When the amphibious unmanned vehicle is working underwater, the tracks are retracted, the water-jet propulsion device is deployed, and the buoy is released.

Step 2: Use various devices to collect data. The data includes: surrounding environment information, navigation and positioning information, water depth, and humidity. The collected data is transmitted to the computer control system in the vehicle. At the same time, the buoy is used to communicate with the outside world, the data format is checked and stored in the database.

Step 3: Use the information recognition algorithm to detect noise on the data saved in Step 2 and eliminate irrelevant data. After sorting, classifying and identifying different types of data, the corresponding environmental information is obtained, thereby judging the environmental status of the amphibious unmanned vehicle, and at the same time outputting the environmental status results to the electronic control system in the vehicle.

Step 4: According to the environmental state results input to the electronic control system in Step 3, drive the deformation mechanism in Step 1 to complete the amphibious unmanned vehicle mode switching. After the switch is completed, the amphibious unmanned vehicle uses the buoy to communicate with the outside world and output surrounding environment information.

The device for implementing the method includes: a buoy 1 that can automatically retract and release a line, a steering thruster 2, a water jet thruster 3, a crawler track 4, a sonar 9, a pressure sensor 10, an attitude sensor 11 and a humidity sensor 12;

The buoy 1 includes a 5G communication module 5, a Beidou navigation module 6, a TOF camera 7 and a laser radar 8; the main function of the buoy is to obtain environmental signals on land and water, and at the same time communicate with external remote control systems and operators;

The pressure sensor 10, attitude sensor 11 and humidity sensor 12 are used to obtain surrounding environment information and monitor the status of the amphibious unmanned vehicle;

Beneficial effects:

1. The mode adaptive switching method of the amphibious and unmanned amphibious vehicle of the present invention overcomes the shortcomings of the traditional unmanned amphibious and unmanned vehicle that require remote control by the operator at the amphibious and land interface. It can independently control the mode through a series of sensing devices and intelligent algorithms. Switching between water and land modes reduces the workload of the operator.

2. According to the adaptive switching method of the amphibious unmanned vehicle mode of the present invention, when the amphibious unmanned vehicle is patrolling on land, the internal lidar sends instructions to the control system in the amphibious unmanned vehicle by sensing the surrounding environment, and can plan its next route. And stored in the database, further improving the autonomy of amphibious unmanned vehicles.

3. The amphibious unmanned vehicle mode adaptive switching method of the present invention, when it works underwater, forward-looking sonar and side-scanning sonar actively detect the surrounding environment, and can model and monitor the underwater environment, etc., expanding the scope of Application scenarios of amphibious unmanned vehicles.

4. The adaptive switching method of the amphibious unmanned vehicle mode of the present invention can facilitate personnel to confirm the location and environmental information of the unmanned vehicle based on the synchronized database when special circumstances occur, further improving the safety factor of the amphibious unmanned vehicle. .

5. The mode adaptive switching method of the amphibious unmanned vehicle of the present invention can be built on different types of amphibious platforms, and can adapt to the actual terrain and work needs to the maximum extent.

Description of the drawings

Figure 1 is a schematic diagram of a deformation mechanism of an amphibious unmanned vehicle used in an embodiment of the present invention;

Figure 2 is a schematic diagram of the internal structure of the buoy mounted on the amphibious unmanned vehicle in the embodiment of the present invention;

Figure 3 is a schematic structural diagram of the amphibious unmanned vehicle body mounted on the amphibious unmanned vehicle in an embodiment of the present invention;

Figure 4 is an environmental information detection flow chart of the mode adaptive switching method in an embodiment of the present invention;

Figure 5 is a flow chart of state switching in the mode adaptive switching method in the embodiment of the present invention.

Explanation of reference signs: 1-1 - the released state of the automatically retractable and retractable buoy, 1-2 - the adsorption state of the automatically retractable and retractable buoy, 2 - steering propeller, 3 - water jet propeller, 4 ——Crawler, 5—5G communication module, 6—Beidou navigation module, 7—TOF camera, 8—Lidar, 9—Sonar module, 10—Pressure sensor, 11—Attitude sensor, 12— -Humidity Sensor.

Detailed ways

In order to better illustrate the purpose and advantages of the present invention, the content of the invention will be further described below in conjunction with the accompanying drawings and examples. Obviously, the described embodiments are only some of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other methods obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present invention.

The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

A mode adaptive switching method for amphibious unmanned vehicles, including the following steps:

Step 1. Determine the working status of the key deformation mechanisms of the body of the amphibious unmanned vehicle in different environments on land, water and underwater. The key deformation mechanisms of the body include: crawler tracks, water jet propulsion devices and buoys;

When the amphibious unmanned vehicle is working on land, the crawler tracks are in an extended state, the water-jet propulsion device is retracted into the body, and the buoy is in a retracted state and is tightly sucked to the top of the body. When the amphibious unmanned vehicle is working on the water, the tracks are retracted, the water jet propulsion device is deployed, and the buoy is in the retracted state. When the amphibious unmanned vehicle is working underwater, the tracks are retracted, the water-jet propulsion device is deployed, and the buoy is released.

Step 2: Use various devices to collect data. The data includes: surrounding environment information, navigation and positioning information, water depth, and humidity. The collected data is transmitted to the computer control system in the vehicle. At the same time, the buoy is used to communicate with the outside world, the data format is checked and stored in the database.

Step 3: Use the information recognition algorithm to detect noise on the data saved in Step 2 and eliminate irrelevant data. After sorting, classifying and identifying different types of data, the corresponding environmental information is obtained, thereby judging the environmental status of the amphibious unmanned vehicle, and at the same time outputting the environmental status results to the electronic control system in the vehicle.

Step 4: According to the environmental state results input to the electronic control system in Step 3, drive the deformation mechanism in Step 1 to complete the amphibious unmanned vehicle mode switching. After the switch is completed, the amphibious unmanned vehicle uses the buoy to communicate with the outside world and output surrounding environment information.

The device that implements the above method includes a buoy 1 that can automatically retract and release a line, a steering thruster 2, a water jet thruster 3, a crawler track 4, a sonar 9, a pressure sensor 10, an attitude sensor 11 and a humidity sensor 12;

The buoy 1 includes a 5G communication module 5, a Beidou navigation module 6, a TOF camera 7 and a laser radar 8.

The buoy 1 is located on the top of the vehicle body, and its main function is to obtain environmental signals from land and water, and at the same time communicate with external remote control systems and operators;

The steering propeller 2 is located at the front end of the vehicle body, and its main function is to control the amphibious unmanned vehicle to steer underwater;

The water jet propeller 3 is located at the rear end of the vehicle body and is the power source for the amphibious unmanned vehicle in the water;

The crawler tracks 4 are located at the bottom of the vehicle body and are the walking mechanism of the amphibious unmanned vehicle on land;

The 5G real-time communication module 5 is arranged in an amphibious unmanned vehicle buoy to transmit underwater signals, environmental wind speed and direction, camera images, and navigation and positioning positions to the outside world in real time;

The Beidou navigation module 6 is arranged in an amphibious unmanned vehicle buoy, supports Beidou navigation, Beidou short message communication, and can automatically return location information;

The TOF camera 7 is arranged in an amphibious unmanned vehicle buoy. It uses imaging equipment to obtain two images of the measured object from different positions based on the principle of parallax, and obtains the three-dimensional geometry of the object by calculating the position deviation between corresponding points in the image. information;

The lidar 8 is arranged in an amphibious unmanned vehicle buoy and is a radar system that emits a laser beam to detect characteristic quantities such as the position and speed of a target. When the amphibious unmanned vehicle is on land or water, it emits detection signals to environmental targets, and relevant information about the environment can be obtained based on the signals reflected back by the environmental targets;

The sonar module 9 is arranged directly in front of the amphibious unmanned vehicle body. When the amphibious unmanned vehicle works in the water, the sonar module is used to detect the underwater environment;

The pressure sensor 10 is arranged in front of the amphibious unmanned vehicle body and is used to monitor pressure values and calculate depth information;

The attitude sensor 11 is arranged in front of the amphibious unmanned vehicle body and can output zero-drift three-dimensional attitude data expressed in quaternions, Euler angles, etc. in real time;

The humidity sensor 12 is arranged in front of the amphibious unmanned vehicle body. The value measured by the humidity sensor can reflect the environmental status of the amphibious unmanned vehicle.

A mode adaptive switching method for amphibious unmanned vehicles, specifically including the following steps:

Step 1. Determine the working status of the key deformation mechanisms of the body of the amphibious unmanned vehicle in different environments on land, water and underwater. The key deformation mechanisms of the body include: crawler tracks, water jet propulsion devices and buoys;

When the amphibious unmanned vehicle is working on land, the crawler tracks are in an extended state, the water-jet propulsion device is retracted into the body, and the buoy is in a retracted state and is tightly sucked to the top of the body. When the amphibious unmanned vehicle is working on the water, the tracks are retracted, the water jet propulsion device is deployed, and the buoy is in the retracted state. When the amphibious unmanned vehicle is working underwater, the tracks are retracted, the water-jet propulsion device is deployed, and the buoy is released.

Step 2: Use various devices to collect data. The data includes: navigation and positioning information, surrounding environment information, water depth, water pressure, humidity, etc. The collected data is passed to the in-vehicle computer control system, where the data format is checked and stored in the database. At the same time, buoys are used to communicate with the outside world and synchronize database information.

The Beidou navigation and positioning module is the basis for the autonomous work of amphibious unmanned vehicles and provides important guarantees for the real-time positioning and route control of amphibious unmanned vehicles. The Beidou navigation and positioning module receives Beidou satellite signals every 1 second, updates the map position and outputs GetLocation(X,Y,Z) to the computer system. In an open wild environment, the measurement accuracy of Beidou navigation can usually reach 2-3 meters, which can provide environmental information reference for amphibious unmanned vehicle mode switching.

When the amphibious vehicle works on land, it uses TOF cameras and lidar to realize the environmental information perception of the amphibious unmanned vehicle. Lidar is used to obtain a large range of rough environmental landform information. It uses the pulse ranging method and multiplies the time difference Δt between transmitting and receiving laser light with the speed of light c to obtain the distance L _i of the amphibious unmanned vehicle to a certain target i.

During the movement of the amphibious vehicle, the relative position of the lidar and the target object will change. The angle θ _i with the target object i can be obtained by comparing adjacent moments.

The main function of the TOF camera is to obtain detailed information about the surrounding environment of the amphibious unmanned vehicle. Through the phase difference Δψ of the emitted and returned light, the wavelength λ, the speed of light c and the number of returned wavelengths, the distance s _j of a certain target j can be obtained.

The terrestrial environment is mapped, and L _i , s _j , and θ _i are summarized to obtain the terrestrial environment information matrix [LS θ].

Since lidar and TOF cameras cannot work underwater, amphibious unmanned vehicles need to make use of the propagation and reflection characteristics of sound waves in water and use the electroacoustic conversion and information processing technology of sonar modules to conduct underwater amphibious unmanned vehicle navigation and water navigation. Measure distances from obstacles below to achieve accurate detection of underwater targets. Using the sound wave speed w and the received sound wave delay τ, the distance d _k between the target k and the amphibious unmanned vehicle can be calculated.

In underwater environment azimuth detection, the MUSIC algorithm is used, and the target azimuth matrix A can be obtained by using the sonar array signal processing result X(t), echo arrival signal S(t) and noise N(t).

X(t)=AS(t)+N(t)

A＝[α ₁ , α ₂ , α ₃ ... α _n ]

The underwater environment is mapped, and d _k and A are summarized to obtain the underwater environment information matrix [DA].

When water is adsorbed on the moisture-sensing film of the humidity sensor, the resistivity and resistance value of the element change. This characteristic is used to determine the status of the amphibious unmanned vehicle. When the humidity sensor determines that the amphibious unmanned vehicle is in a draft state, the state variable SV is assigned a value of 1; otherwise, SV=0.

According to the ratio of the pressure P measured by the pressure sensor to the density of water and the acceleration of gravity, the water depth h is calculated.

Based on the above information, the amphibious unmanned vehicle's position information GetLocation(X, Y, Z), the land environment information matrix [L S θ] measured by the lidar and TOF camera at each moment, and the underwater environment information matrix measured by the sonar module are [D A], state variable SV and depth information h are stored in the database.

Step 3: Use the information recognition algorithm to detect targets and environmental noise from the data saved in the database in Step 2. After preprocessing and feature extraction, the surrounding environment information of the amphibious vehicle is obtained. As shown in Figure 4, after a series of logical judgments, the environmental information EI judgment results are output to the amphibious unmanned vehicle electronic control system.

Kalman filtering is used to fuse lidar and TOF camera data. Taking the position L measured by lidar and the position S measured by TOF camera as an example, record the state vector at time k-1:

X _k-1 = (l, s) ^T

Introduce the prediction matrix F _k so that the state vector at time k is:

X _k ＝F _k X _k-1 +B _k u _k

Among them, B _k is the control matrix applied externally to the amphibious vehicle at time k, such as braking, acceleration, etc.; u _k is the control vector.

The uncertainty at time k, the covariance matrix P _k is:

Among them, Q _k is a Gaussian distribution of uncertainty, such as track slippage, surface obstacle bulges and other unpredictable factors.

The linear change matrix H _k is introduced to unify the scale units of the lidar and TOF camera observation results; the sensor noise R _k is introduced to describe the uncertainty of the sensor; the observation result distribution z _k is introduced, and the Kalman gain matrix K is introduced. After linear transformation, the correction values X′ _k , P′ _k and K′ are obtained.

_X′k ＝ _xk +K′( _{zk - HkXk} )

P′ _k =(1-K′H _k )P _k

According to the above process, the L and S values are continuously revised and iterated, and data fusion is performed, and finally the identification and mapping of the surrounding environment information of the amphibious unmanned vehicle are obtained.

Perform a loopback test on the fused three-dimensional map database with the GetLocation(X,Y,Z) obtained by Beidou Navigation to check whether there are any errors (for example, an amphibious vehicle positioned in the sea displays land as land in its own mapping database).

When there is no obvious discrepancy between the map database and the navigation and positioning system, the computer system determines whether the amphibious vehicle is in a land environment based on the map information. If the amphibious vehicle is in a land environment, the environmental information EI in the computer system is assigned the value "land". No, call the SV and h information in the database to determine whether the amphibious vehicle is on the water. If yes, the EI value is "water surface"; if not, the EI value is "underwater".

Step 4: According to the environmental information result EI in step 3, use the deformation control mechanism in step 1 to drive the amphibious vehicle to complete the state switch. The attitude sensor is used to detect the real-time attitude of the amphibious vehicle and is also used to assist the mode switching of the amphibious vehicle. After the amphibious vehicle mode switching is completed, the buoy is used to communicate with the outside world and output its own status, as shown in Figure 5.

When EI is "land", the computer system issues instructions to the driving mechanism of the amphibious unmanned vehicle. First, an electromagnet is used to adsorb the buoy above the vehicle body. Based on the terrain signals sent in real time by the lidar and TOF camera in the amphibious unmanned vehicle, Plan the next patrol route of the amphibious unmanned vehicle and save it in the database.

When the EI changes from "land" to "water", the computer electronic control system will reduce the speed of the amphibious unmanned vehicle, deploy the body's water jet thrusters and steering thrusters, and after entering the water-land interface, slowly retract the crawler mechanism and call the interior of the body The humidity sensor monitors whether there is water seepage inside the amphibious unmanned vehicle. After working for a period of time and no alarm signal is found, the amphibious unmanned vehicle can switch between water and land modes.

When the EI changes from "water surface" to "underwater", the amphibious unmanned amphibious vehicle will cut off the electromagnet power to release the buoy. At the same time, it will adjust the center of gravity of the amphibious unmanned vehicle, retract the wings to reduce the drainage volume, and the sonar module will start working. The sinking controls the buoy motor to release the cable based on the depth information h. The buoy continuously monitors the water surface environment information and sends in-vehicle sensor signals to the remote control terminal to complete the diving state switch. When working underwater, the remote control terminal communicates with the buoy floating on the water to grasp the underwater situation and body status in real time, such as the humidity in the car, water depth pressure, body pressure, etc., and use this as the basis for commanding the amphibious unmanned vehicle. .

When EI changes from "underwater" to "surface", monitoring information from various sensor equipment is sent to the computer system, and the contraction speed of the buoy motor cable is adjusted in real time according to the h value. After arriving at the water surface, the amphibious unmanned vehicle connects the electromagnet circuit of the buoy and sucks the buoy tightly. At the same time, it checks the working status of each component in the vehicle, completes the water surface state switching, and feeds back signals to the remote control terminal.

When the amphibious unmanned vehicle lands, the EI changes from "water surface" to "land". The driving mechanism tightens the buoy, extends the track and retracts the propeller, completing the entire amphibious unmanned vehicle mode switching cycle in the amphibious area.

In order to solve the problem that existing amphibious unmanned vehicles have limited autonomous functions and require real-time human control and switching of amphibious unmanned vehicle modes at the amphibious interface, the present invention proposes a new mode adaptive switching method. This method is based on the structural characteristics model of amphibious unmanned vehicles in three different working environments of land, water and underwater, and builds a comprehensive mode adaptive switching method, thereby improving the autonomy of amphibious modes and greatly reducing the control personnel burden. The invention can be applied to the technical field of shipbuilding industry and the technical field of amphibious unmanned vehicles.

The above-mentioned specific description further explains the purpose, technical solutions and beneficial effects of the invention in detail. It should be understood that the above-mentioned are only specific embodiments of the invention and are not intended to limit the protection of the invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims (1)

1. A method for adaptive mode switching of amphibious unmanned vehicles, which is characterized by including the following steps: Step 1: Determine the working status of the key deformation mechanisms of the body of the amphibious unmanned amphibious vehicle in different modes; the key deformation mechanisms of the body include: crawler tracks, water-jet propulsion devices and buoys; When the amphibious unmanned vehicle is working on land, the crawler tracks are in the extended state, the water-jet propulsion device is retracted into the body, and the buoy is in the retracted state and is tightly sucked to the top of the vehicle body; when the amphibious unmanned vehicle is working on the water, The crawler tracks are in the retracted state, the water-jet propulsion device is deployed, and the buoy is in the retracting state; when the amphibious unmanned vehicle is working underwater, the crawler tracks are in the retracted state, the water-jet propulsion device is deployed, and the buoy is in the pay-off state; Step 2: Use various devices to collect data; the data includes: navigation and positioning information, surrounding environment information, water depth, water pressure, and humidity; the collected data is transferred to the in-vehicle computer control system, the data format is checked and saved in the database at the same time, use buoys to communicate with the outside world and synchronize database information; Use the Beidou navigation and positioning module to output the real-time location GetLocation (X, Y, Z) to the computer system; Use lidar to obtain a large range of rough environmental landform information, and obtain the distance L _i and angle θ _i of an amphibious unmanned vehicle to a certain target i; where Δt is the time difference; c is the speed of light; Use the TOF camera to obtain detailed information about the surrounding environment of the amphibious unmanned vehicle and obtain the distance s _j of a certain target j; Among them, Δψ is the phase difference of light waves; λ is the wavelength of light; n is the number of returned wavelengths; Map the terrestrial environment, and summarize L _i , s _j , θ _i to obtain the terrestrial environment information matrix [LS θ]; Use the sonar module to accurately detect the underwater environment and obtain the distance d _k to the target k and the target azimuth angle matrix A; X(t)=AS(t)+N(t) A＝[α ₁ , α ₂ , α ₃ ... α _n ] Among them, w is the sound wave speed; τ is the received sound wave delay; X(t) is the sonar array signal processing result; S(t) is the echo arrival signal; N(t) is the noise; Carry out mapping of the underwater environment, and summarize d _k and A to obtain the underwater environment information matrix [DA]; The humidity sensor is used to determine the environmental state of the amphibious unmanned vehicle; when the humidity sensor determines that the amphibious unmanned vehicle is in a draft state, the state variable SV is assigned a value of 1; otherwise, SV=0; Calculate the water depth h based on the pressure sensor; Among them, P is the pressure; ρ is the density of water; g is the acceleration of gravity; Get the location information of the amphibious unmanned vehicle at each moment GetLocation(X, Y, Z), the land environment information matrix [L S θ] measured by the lidar and TOF camera, and the underwater environment information matrix [D A] measured by the sonar module ], state variable SV and depth information h are stored in the database; Step 3: Use the information recognition algorithm to detect noise and eliminate irrelevant data on the data saved in step 2; after sorting, classifying and identifying different types of data, obtain the corresponding environmental information, and thereby determine the location of the amphibious unmanned vehicle. environmental status, and at the same time output the environmental status results to the electronic control system in the vehicle; Kalman filtering is used to perform data fusion on the position L measured by the lidar and the position S measured by the TOF camera; Remember the state vector at time k-1: X _k-1 = (l, s) ^T Introduce the prediction matrix F _k so that the state vector at time k is: X _k ＝F _k X _k-1 +B _k u _k Where B _k is the control matrix externally applied to the amphibious vehicle at time k; u _k is the control vector; The uncertainty at time k, the covariance matrix P _k is: Among them, Q _k is a Gaussian distribution of uncertainty, which is used to simulate unpredictable factors such as track slippage and surface obstacle bulges; The linear change matrix H _k is introduced to unify the scale units of the lidar and TOF camera observation results; the sensor noise R _k is introduced to describe the uncertainty of the sensor; the observation result distribution z _k is introduced, and the Kalman gain matrix K is introduced; through linear After transformation, the correction values X′ _k , P′ _k and K′ are obtained; _X′k ＝ _Xk +K′( _{zk - HkXk} ) P′ _k =(1-K′H _k )P _k According to the above process, the L and S values are continuously revised and iterated, and data fusion is performed, and finally the identification and mapping of the surrounding environment information of the amphibious unmanned vehicle are obtained; Perform a loopback test on the fused three-dimensional map database with the GetLocation(X, Y, Z) obtained by Beidou Navigation to check whether there are any errors; when there is no obvious discrepancy between the map database and the navigation positioning system, the computer system will make a judgment based on the map database information. Whether the amphibious vehicle is in a land environment; if the amphibious vehicle is in a land environment, the environmental information EI in the computer system is assigned the value "land"; if not, call the SV and h information in the database to determine whether the amphibious vehicle is on the water; if so, EI The value is assigned to "water surface"; no, the EI value is assigned to "underwater"; Step 4: According to the environmental information result EI in step 3, use the deformation control mechanism in step 1 to drive the amphibious vehicle to complete the state switch; use the attitude sensor to detect the real-time attitude of the amphibious vehicle, and also to assist the amphibious vehicle mode switching; the amphibious vehicle After the mode switching is completed, the buoy is used to communicate with the outside world and output its own status; When EI is "land", the computer system issues instructions to the driving mechanism of the amphibious unmanned vehicle. First, an electromagnet is used to adsorb the buoy above the vehicle body. Based on the terrain signals sent in real time by the lidar and TOF camera in the amphibious unmanned vehicle, Plan the next patrol route of the amphibious unmanned vehicle and save it in the database; When the EI changes from "land" to "water", the computer electronic control system will reduce the speed of the amphibious unmanned vehicle, deploy the body's water jet thrusters and steering thrusters, and after entering the water-land interface, slowly retract the crawler mechanism and call the interior of the body The humidity sensor monitors whether there is water seepage inside the amphibious unmanned vehicle. After working for a period of time and no alarm signal is found, the water and land modes can be switched; When the EI changes from "water surface" to "underwater", the amphibious unmanned amphibious vehicle will cut off the electromagnet power to release the buoy. At the same time, it will adjust the center of gravity of the amphibious unmanned vehicle, retract the wings to reduce the drainage volume, and the sonar module will start working. The sinking controls the buoy motor to release the cable based on the depth information h. The buoy continuously monitors the water surface environment information and sends in-vehicle sensor signals to the remote control terminal to complete the diving state switching; when working underwater, the remote control terminal communicates with the floating on the water surface. buoy communication to grasp the underwater situation and body status in real time and use it as a basis for commanding amphibious unmanned vehicles; The vehicle body status includes the attitude of the amphibious vehicle, the humidity inside the vehicle, and the vehicle body pressure; When EI changes from "underwater" to "surface", various sensor equipment monitoring information is sent to the computer system, and the contraction speed of the buoy motor cable is adjusted in real time according to the h value; after reaching the water surface, the amphibious unmanned vehicle connects the buoy electromagnet loop Suction the buoy tightly, check the working status of each component in the car at the same time, complete the water surface status switching and feed back signals to the remote control terminal; When the amphibious unmanned vehicle lands, the EI changes from "water surface" to "land". The driving mechanism tightens the buoy, extends the crawler track and retracts the propeller, completing the mode switching cycle of the amphibious unmanned vehicle in the entire amphibious and land area; The device for realizing the mode adaptive switching method of the amphibious unmanned vehicle includes: a buoy (1) on the top of the vehicle body that can automatically retract and release the line, a steering propeller (2), a water jet propeller (3), and a crawler track ( 4), sonar (9), pressure sensor (10), attitude sensor (11) and humidity sensor (12); The pressure sensor (10), attitude sensor (11) and humidity sensor (12) are used to obtain surrounding environment information and monitor the status of the amphibious unmanned vehicle; The sonar (9) is used to obtain underwater environment information; The buoy (1) includes a 5G communication module (5), a Beidou navigation module (6), a TOF camera (7) and a lidar (8); its main function is to obtain environmental signals on land and water, and at the same time communicate with the external remote control system Communicate with controllers; The environmental information obtained above is summarized and input into the computer system to control the operation of the steering propeller (2), the water jet propeller (3), and the crawler track (4).