Amphibious unmanned platform and motion control method thereof
By designing a multi-averse unmanned platform in the water and land, combining thrusters and tracked power devices, and using the PID controller set by the RBF neural network, the problems of poor obstacle crossing performance and handling of existing multi-averse vehicles are solved, and the problem of poor barrier-over performance and handling in water is realized. Flexible maneuvering and efficient movement on land and underwater.
Patent Information
- Application Number
- CN202411218740.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-02
AI Technical Summary
Existing multi-average vehicle has problems such as poor barrier performance, easy slippage, poor scalability, poor environmental adaptability and handling.
A multi-aquatic unmanned platform was designed, using symmetrically set propeller and track power device, combined with the controlled system, navigation and positioning system and communication system, and using the PID controller set by the RBF neural network to realize the thruster and track Coordinated control, able to maneuver in water, on land and underwater.
Improve the obstacle crossing ability and environmental adaptability of the multi-averse unmanned platform, reduce the turning radius, enhance the pitch angle adjustment ability, realize rapid lurking and adaptation of various terrain environments, with wireless control, light weight, and long remote control distance , the advantages of long running time and high efficiency.
Smart Images

Figure CN119078420A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of amphibious unmanned platforms, and in particular to an amphibious unmanned platform and a motion control method thereof. Background Art
[0002] With the development of the world economy and the need for national defense construction, it is a general trend to vigorously develop the marine economy, exploit marine resources and strengthen marine armament construction. However, with the deepening of marine development and the further demand for armament construction, there is a need for an amphibious unmanned carrier platform that can work in an environment that humans cannot reach or is harmful, equipped with multiple functional equipment, and can both sail in the water and crawl under the water and travel on land to complete tasks such as marine environment observation, seabed topography mapping, underwater rescue, unmanned island landing operations, and military exploration.
[0003] At present, ordinary robots can only move in water or on land, are unable to switch to amphibious movements, and have poor comprehensive operational capabilities. Based on the current development status at home and abroad, amphibious vehicles that are mainly bionic and paddle-wheel-type have problems such as poor obstacle crossing performance, easy slipping, poor scalability, environmental adaptability, and poor controllability. Summary of the invention
[0004] The technical problems to be solved by the present invention are:
[0005] In order to solve the problems of existing amphibious vehicles such as poor obstacle crossing performance, easy slipping, poor scalability, poor environmental adaptability and poor maneuverability.
[0006] The present invention adopts the following technical solutions to solve the above technical problems:
[0007] The present invention provides an amphibious unmanned platform, comprising an upper platform, an underwater propulsion device and a land power device.
[0008] The upper platform includes a closed electronic cabin and an external frame outside the electronic cabin, the electronic cabin is arranged at the center of the external frame, a controlled system, a navigation and positioning system, a communication system and a power control system are arranged in the electronic cabin, a water propulsion system is arranged on the external frame, and a land power device is arranged below the upper platform;
[0009] The underwater propulsion system includes a left main propeller and a right main propeller symmetrically arranged on both sides of the central axis of the stern of the amphibious unmanned platform, and also includes a stern vertical propeller, a stern horizontal propeller, a bow vertical propeller and a bow horizontal propeller. The propellers of the left main propeller and the right main propeller are horizontally facing the rear of the amphibious unmanned platform; the stern vertical propeller is arranged at the bottom of the external frame and the propeller of the stern vertical propeller is facing the tracked chassis direction of the land power device; the stern horizontal propeller and the bow horizontal propeller are parallel to each other and are respectively located on both sides of the bow and stern of the amphibious unmanned platform; the propeller of the bow vertical propeller is facing a direction perpendicular to the port side; the propeller of the bow horizontal propeller is facing a direction perpendicular to the starboard side;
[0010] The land power system includes a crawler chassis and two crawler assemblies arranged under the crawler chassis, each crawler assembly includes a driving wheel, a guide wheel, a load wheel, a crawler track and a crawler motor, a plurality of load wheels are evenly arranged between the driving wheel and the guide wheel, and the driving wheel and the guide wheel are both located obliquely above the load wheels at both ends, the crawler track is wrapped around the outside of the driving wheel, the guide wheel and the plurality of load wheels, the output end of the crawler motor is connected to the driving wheel, and the driving wheel, the guide wheel and the load wheel are all rotatably connected to the crawler chassis.
[0011] Furthermore, the controlled system includes a motion computer, a mission computer and a guidance computer. The motion computer is used for multi-sensor data processing and calculation of the multi-habitat unmanned platform body posture control commands; the mission computer is used for executing mission planning, and performing network communication and fault monitoring; the guidance computer is used for giving guidance instructions, including desired heading, desired speed and desired depth.
[0012] Furthermore, the navigation and positioning system includes a GPS module and an inertial navigation sensor in the electronic cabin, and a Doppler sensor and a depth meter located outside the electronic cabin; it is used to locate and calculate the attitude of the multi-habitat unmanned platform; the communication system includes a WiFi communication module and a wireless communication module, which are used to connect the multi-habitat unmanned platform to the host computer through the communication system.
[0013] Furthermore, the power control system includes a main single-chip microcomputer control board and a relay matrix board, each pin of the main single-chip microcomputer control board is used to control a relay switch and thus control the power supply of each module; the electronic cabin is powered by a dual power supply, and the power supply is a battery.
[0014] Furthermore, a plurality of buoyancy blocks are provided above the crawler chassis.
[0015] Furthermore, the crawler motor is powered by a battery arranged on the crawler chassis, and the crawler chassis is provided with a watertight control cabin, in which a crawler single-chip microcomputer is arranged, and the crawler single-chip microcomputer is used to control the crawler motor and communicate with the controlled system through a wired network connection.
[0016] Furthermore, for the controlled system, a PID controller based on RBF neural network tuning is set, including:
[0017] Let X = [x1, x2, ..., x n ] T is the network input vector, and the radial basis vector of the hidden layer node is H = [h1,h2...,h m ] T ,h j is the Gaussian basis function:
[0018]
[0019] The center vector of the jth node in the hidden layer of the RBF neural network is C j =[c j1 ,c j2 ,...,c jm ] T , let the base width vector of the hidden layer node of the RBF neural network be B = [b1, b2, ...., b m ] T , where b j is the basis width parameter of hidden layer node j and is a number greater than 0; the weight vector of the network is w=[w1,w2,...,w n ] T , the identified network output is:
[0020] y mout =w1h1+w2h2+...+w m h m
[0021] Assume that the theoretical output of the identified system at time k is y out (k), the output of network identification is y mout (k), then the identification system performance index function is:
[0022]
[0023] The output weight, node center and node base width parameters are obtained by gradient descent method.
[0024] The output weight expression is as follows:
[0025] w j (k) = w j (k-1)+η(y out (k)-y mout (k))h j +α(w j (k-1)-w j (k-2))+β(wj (k-2)-w j (k-3)) where η is the learning rate; α and β are momentum factors, both in the range of (0, 1);
[0026] Node base width change Δb j for:
[0027]
[0028] Node base width parameter b j for:
[0029] b j (k) = b j (k-1)+ηΔb j +α(b j (k-1)-b j (k-2))+β(b j (k-2)-b j (k-3))
[0030] Node center change Δc ji for:
[0031]
[0032] Node center c j for:
[0033] c ji =c ji (k-1)+ηΔc ji +α(c ji (k-1)-c ji (k-2))+β(c ji (k-2)-c ji (k-3))
[0034] Where, cj=[c11,c12,c13…c1m];
[0035] The PID parameter adjustment algorithm is as follows:
[0036] The control error is:
[0037] error(k)=u(k)-yout(k)
[0038] Among them, u(k) is the input of the controlled system, yout(k) is the output of the controlled system;
[0039] The three PID inputs are:
[0040] xc(1)=error(k)-error(k-1)
[0041] xc(2)=error(k)
[0042] xc(3)=error(k)-2error(k-1)+error(k-2)
[0043] The neural network tuning index is:
[0044]
[0045] By gradient descent method, we get three parameters K p ,K I ,K D The adjustment amount in decibels is:
[0046]
[0047]
[0048]
[0049] in, K is the sensitivity of the object output to the change of control input; p is the proportional gain term, K i is the integral gain term, K d is the differential gain term;
[0050]
[0051] The present invention provides a motion control method for an amphibious unmanned platform, comprising the following steps:
[0052] S100, when the amphibious unmanned platform moves in the water, only the propulsion system is used for driving, and the motion is decomposed into horizontal plane motion and vertical plane motion by using the underactuated control method; the controlled system controls the thrust of the bow vertical thruster and the stern vertical thruster to make the amphibious unmanned platform maintain depth; the controlled system controls the thrust of the bow horizontal thruster and the stern horizontal thruster to control the bow turning and navigation of the amphibious unmanned platform, and the forward speed of the amphibious unmanned platform is changed by controlling the thrust output of the thruster;
[0053] S200, when the multi-purpose unmanned platform moves on land, it is driven only by the land power device, and the crawler microcontroller in the control cabin set on the crawler chassis controls the differential speed of the crawler to realize the turning of the multi-purpose unmanned platform on land, and the crawler speed is controlled by controlling the duty cycle of the crawler motor to realize the acceleration, deceleration, forward and backward maneuvering mode;
[0054] S300. When the amphibious unmanned platform moves on the bottom of the water, the propulsion system and the land power unit are used in combination to increase the pressure of the amphibious unmanned platform and the bottom of the water by controlling the bow vertical thruster and the stern vertical thruster to apply thrust downward, and the left main thruster and the right main thruster are controlled to assist the amphibious unmanned platform in walking on the bottom of the water. The differential speed of the tracks and the thrust of the bow horizontal thruster and the stern horizontal thruster are controlled by the track microcontroller to realize the turning of the amphibious unmanned carrier platform on the bottom of the water.
[0055] Furthermore, when the amphibious unmanned platform is in the elevator mode, the pitch angle of the vehicle is controlled by the horizontal rudder, and the propulsion of the two main thrusters is coordinated to realize the surfacing or diving of the amphibious unmanned platform, specifically including:
[0056] The depth error is used as the input of the single neuron adaptive PID controller to output the horizontal rudder control command; combined with the line of sight navigation method, the 10m ahead of the multi-habitat unmanned platform’s own X direction position is used as the desired X direction position. d Direction position, expected depth position is Z d , the displacement error equation is obtained as:
[0057] x e =xx d ,z e =zz d
[0058] The desired trim angle is:
[0059] θ d =tan -1 ((zz d ) / (xx d )).
[0060] Compared with the prior art, the present invention has the following beneficial effects:
[0061] The present invention discloses an amphibious unmanned platform and a motion control method thereof. The amphibious unmanned platform comprises an upper platform, an underwater propulsion device and an onshore power device, and combines the advantages of propeller underwater maneuverability and tracked land maneuverability. The cooperation of bow and stern horizontal thrusters can enable the amphibious unmanned carrier platform to turn its bow in situ, greatly reducing the turning radius. The cooperation of bow and stern vertical thrusters can adjust the pitch angle of the amphibious unmanned carrier platform, which is conducive to rapid lurking. The tracks can improve the underwater and onshore obstacle-crossing capability of the amphibious unmanned carrier platform and adapt to a variety of terrain environments. The amphibious unmanned platform also adopts wireless control and autonomously maneuvers according to a predetermined program, thereby reducing its limitations during movement. In addition, it has the advantages of light weight, long remote control distance, long operating time, high efficiency, compact structure and convenient operation. The present invention also adopts a PID controller based on radial basis function network tuning, and utilizes the arbitrary nonlinear expression capability of the radial basis function network to achieve PID control with an optimal combination by learning system performance. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] Figure 1 This is a front view of an amphibious unmanned platform in an embodiment of the present invention;
[0063] Figure 2 A top view of an amphibious unmanned platform in an embodiment of the present invention;
[0064] Figure 3 The structure of the stern direction of an amphibious unmanned platform in an embodiment of the present invention is schematically shown;
[0065] Figure 4 A structural diagram of a radial basis function neural network in an embodiment of the present invention;
[0066] Figure 5 It is a block diagram of a PID controller based on radial basis function neural network tuning in an embodiment of the present invention;
[0067] Figure 6 This is a simulation result diagram obtained by using a PID controller tuned based on a radial basis function neural network in an embodiment of the present invention;
[0068] Figure 7 This is the flight path diagram of a multi-habitat unmanned platform obtained by using the traditional PID control algorithm;
[0069] Figure 8 The track map of a multi-habitat unmanned platform obtained by using a depth control method combined with line-of-sight navigation.
[0070] Description of reference numerals:
[0071] 2. Track chassis; 3. Battery compartment; 4. Electronic compartment; 5. External frame; 6. Buoyancy block; 201. Driving wheel; 202. Load wheel; 203. Guide wheel; 204. Track; 501. Left main thruster; 502. Right main thruster; 503. Stern vertical thruster; 504. Stern horizontal thruster; 505. Bow vertical thruster; 506. Bow horizontal thruster; 508. Doppler sensor. DETAILED DESCRIPTION
[0072] In the description of the present invention, it should be noted that the terminology nouns in the various embodiments, such as "up", "down", "front", "back", "left", "right", etc., which indicate directions, are only for simplifying the description of the positional relationship based on the drawings in the specification, and do not mean that the referred elements and devices must be operated according to the specific directions and defined operations and methods and structures in the specification. Such directional nouns do not constitute a limitation on the present invention.
[0073] In the description of the present invention, it should be noted that the terms "first", "second", and "third" mentioned in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second", and "third" may explicitly or implicitly include one or more of the features.
[0074] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
[0075] Specific implementation plan 1: Combine Figures 1 to 3 As shown, the present invention provides an amphibious unmanned platform, including an upper platform, an underwater propulsion device and a land power device.
[0076] The upper platform includes a closed electronic cabin 4 and an external frame 5 outside the electronic cabin 4. The electronic cabin 4 is arranged at the center of the external frame 5. The electronic cabin 4 is provided with a controlled system, a navigation and positioning system, a communication system and a power control system. The external frame 5 is provided with a water propulsion system. A land power device is provided below the upper platform.
[0077] The underwater propulsion system includes a left main propeller 501 and a right main propeller 502 symmetrically arranged on both sides of the central axis of the stern of the amphibious unmanned platform, and also includes a stern vertical propeller 503, a stern horizontal propeller 504, a bow vertical propeller 505 and a bow horizontal propeller 506. The propellers of the left main propeller 501 and the right main propeller 502 are horizontally facing the rear of the amphibious unmanned platform; the stern vertical propeller 503 is arranged at the bottom of the external frame 5 and the propeller of the stern vertical propeller 503 is facing the tracked chassis 2 of the land power device; the stern horizontal propeller 504 and The bow horizontal thrusters 506 are parallel to each other and are respectively located on both sides of the bow and stern of the amphibious unmanned platform; the propeller of the bow vertical thruster 505 is oriented perpendicular to the direction of the port side; the propeller of the bow horizontal thruster 506 is oriented perpendicular to the direction of the starboard side; the coordinated use of the six thrusters can realize the maneuvers of floating, diving and turning the bow of the amphibious unmanned platform; the thrusters are powered by the electronic cabin 4 for power and control signal power; the thrusters are watertight brushless DC motors powered by 48V, which can switch forward and reverse at any time, adopt closed-loop control, feedback thrust data in real time, and have an overcurrent protection mechanism;
[0078] The land power system includes a crawler chassis 2 and two crawler assemblies arranged below the crawler chassis 2, each crawler assembly includes a driving wheel 201, a guide wheel 203, a load wheel 202, a crawler 204 and a crawler motor, a plurality of load wheels 202 are evenly arranged between the driving wheel 201 and the guide wheel 203, and the driving wheel 201 and the guide wheel 203 are both located obliquely above the load wheels 202 at both ends, the crawler 204 is wrapped around the driving wheel 201, the guide wheel 203 and the outer side of the plurality of load wheels 202, the output end of the crawler motor is connected to the driving wheel 201, and the driving wheel 201, the guide wheel 203 and the load wheel 202 are all rotatably connected to the crawler chassis 2; the amphibious unmanned platform realizes forward and backward movement and left and right turning on land through the forward and backward rotation and differential speed of the two crawler assemblies;
[0079] The controlled system includes a motion computer, a mission computer and a guidance computer. The motion computer is used for multi-sensor data processing and calculation of the position and attitude control commands of the multi-amphibious unmanned platform. The mission computer is used for executing mission planning, network communication and fault monitoring. The guidance computer is used for giving guidance instructions, including the desired heading, desired speed and desired depth. The motion control algorithm of the multi-amphibious unmanned platform is run by the controlled system, and the instructions generated after the calculation can be transmitted to the underwater propulsion system or the land power system, thereby controlling the multi-amphibious unmanned platform to move in water, on land or underwater.
[0080] The navigation and positioning system includes a GPS module in the electronic cabin 4, an inertial combined sensor module (including an inertial navigation sensor and a Doppler sensor 508 (DVL) located outside the cabin) and a depth meter; it is used to locate and calculate the attitude of the multi-habitat unmanned platform, and realize combined navigation through the fusion of multiple sensors;
[0081] The communication system includes a WiFi communication module and a wireless communication module, which are used to connect to the host computer through the communication system. The communication mode can be adjusted according to the environment. The hybrid communication mode can ensure reliable communication of the multi-habitat unmanned carrier platform in a large range;
[0082] The power control system includes a main single-chip control board and a relay matrix board. Each pin of the main single-chip control board controls a relay switch and then controls the power supply of each module. The relay board is equipped with a voltage divider module, which divides the 48V battery voltage into three lines: 48V main power electricity, 24V auxiliary power electricity and 5-12V control electricity, and controls them in stages through relays. The rated capacity of the battery is 300Wh, and the total capacity of the battery is 600Wh. The 48V main power electricity is responsible for supplying power to six thrusters and the 24V auxiliary power electricity is responsible for supplying power to high-power sensors and computers, and the 5-12V control electricity is responsible for supplying power to low-power sensors and single-chip microcomputers. The relay and the current are sampled and processed by the single-chip board and sent to the mission computer. The electronic cabin 4 is powered by dual power supplies to avoid the current reduction caused by the operation of multiple motors and affecting the overall performance of the multi-habitat unmanned platform. The power supply is a rechargeable high-energy battery, which is arranged in a battery cabin 3 arranged at the stern of the external frame 5. The power control system is responsible for power supply management of all power supply equipment and monitoring the battery voltage and capacity.
[0083] Preferably, a plurality of buoyancy blocks 6 are provided above the track chassis 2. The buoyancy blocks 6 are foam-type buoyancy materials. The amphibious unmanned platform can be balanced by the buoyancy blocks 6. The center of gravity and the center of buoyancy of the amphibious unmanned platform after balancing are located at the geometric center position. The overall balancing is slightly negative buoyancy, which is conducive to the amphibious unmanned platform to travel on the bottom.
[0084] Preferably, the track motor can be powered by a battery on the track chassis 2. The track chassis 2 is provided with a watertight control cabin. The control cabin has a track microcontroller that directly controls the track motor and communicates with the controlled system through a wired network connection; the chassis control cabin is provided with a water cooling circulation system to cool the control cabin; the track motor is also equipped with an encoder to determine the movement speed of the track 204 by measuring the motor speed within a certain period of time.
[0085] Preferably, the electronic cabin 4 is a cylindrical stainless steel shell structure, which can effectively conduct heat in an underwater environment, and a heat dissipation module is provided in the electronic cabin 4; end covers with watertight piercing parts are provided at both ends of the shell of the electronic cabin 4; there are rubber watertight interfaces on the end covers, and electrical and signal connections can be established with external thrusters, sensors, and chassis components through watertight cables; the electronic cabin 4 uses sealing rings and vacuum treatment to ensure the internal sealing.
[0086] Preferably, for the controlled system, a PID controller based on radial basis function network tuning is set, the radial basis function network is synonymous with RBF radial basis function network, RBF network and RBF neural network, and the PID adaptive control based on RBF radial basis function network is an effective control method, which combines the simplicity of the PID controller and the nonlinear approximation ability of the RBF network, and can better adapt to the control requirements of various complex systems;
[0087] Since traditional PID control requires constant adjustment of parameters, it is difficult to achieve better results if the parameters are unreasonable. It takes a long time to achieve the best results. Therefore, on the basis of single neuron adaptive PID control, a PID controller based on RBF neural network tuning is used; compared with the single neuron adaptive PID controller, its advantage is that it is nonlinear; the control effect of PID controller depends on the three control effects of proportion, integration and differentiation, forming a relationship of mutual cooperation and mutual restriction in the control quantity, but the effect is not necessarily linear, so using nonlinear RBF can achieve better results; the arbitrary nonlinear expression ability of RBF neural network can realize PID control with the best combination by learning the system performance;
[0088] The radial basis function neural network is a three-layer feedforward network with a single hidden layer. The input to output is nonlinear, while the mapping from the hidden layer space to the output is linear, which speeds up the learning speed and avoids the local minimum problem. Its structure is as follows: Figure 4 As shown, in the RBF network structure, X = [x1, x2, ..., x n ] T is the network input vector, and the radial basis vector of the hidden layer node of the RBF neural network is H = [h1,h2...,h m ] T , where h j is the Gaussian basis function:
[0089]
[0090] The center vector of the jth node in the hidden layer of the RBF neural network is C j =[c j1 ,c j2 ,...,c jm ]T , let the base width vector of the hidden layer node of the RBF neural network be B = [b1, b2, ...., b m ] T , where b j is the basis width parameter of hidden layer node j and is a number greater than 0; the weight vector of the network is w=[w1,w2,...,w n ] T , the identified network output is:
[0091] y mout =w1h1+w2h2+...+w m h m
[0092] Combination Figure 5 The block diagram of the PID controller based on RBF network tuning is shown in the figure. The parameter adjustment algorithm in the network is NNI parameter adjustment. Assume that the theoretical output of the identified system at time k is y out (k), the output of network identification is y mout (k), then the identification system performance index function is:
[0093]
[0094] The iterative algorithm for obtaining the output weight, node center and node base width parameters by the gradient descent method is as follows:
[0095] The output weight expression is as follows:
[0096] w j (k) = w j (k-1)+η(y out (k)-y mout (k))h j +α(w j (k-1)-w j (k-2))+β(w j (k-2)-w j (k-3))
[0097] Among them, η is the learning rate; α and β are momentum factors, and their value ranges are both (0, 1);
[0098] Node base width change Δb j for:
[0099]
[0100] Node base width parameter b j for:
[0101] b j (k) = b j (k-1)+ηΔbj +α(b j (k-1)-b j (k-2))+β(b j (k-2)-b j (k-3))
[0102] Node center change Δc ji for:
[0103]
[0104] Node center c j for:
[0105] c ji =c ji (k-1)+ηΔc ji +α(c ji (k-1)-c ji (k-2))+β(c ji (k-2)-c ji (k-3))
[0106] Where cj=[c11,c12,c13…c1m] is the center vector value of the jth hidden layer neuron;
[0107] The PID parameter adjustment algorithm is as follows:
[0108] The control error is:
[0109] error(k)=u(k)-yout(k)
[0110] Among them, u(k) is the input of the controlled system, yout(k) is the output of the controlled system;
[0111] The 3 PID inputs are:
[0112] xc(1)=error(k)-error(k-1)
[0113] xc(2)=error(k)
[0114] xc(3)=error(k)-2error(k-1)+error(k-2)
[0115] The neural network tuning index is:
[0116]
[0117] By gradient descent method, we get three parameters K p ,K I ,K D The adjustment amount is:
[0118]
[0119]
[0120]
[0121] in, K is the Jacobian information of the controlled object, that is, the sensitivity of the object's output to the change of the control input, which can be identified by the RBF neural network; p is the proportional gain term, K i is the integral gain term, K d is the differential gain term;
[0122]
[0123] Taking the expected depth and the actual depth of the multi-habitat unmanned platform as the error, the RBF network structure is 3-6-1, and the three parameters of network identification are the control input increment, the depth at the current moment, and the depth information at the previous moment. The initial proportion, integral, and differential parameters are set to: 0.01, 0.02, and 0.03. When the simulation ends, it becomes 436.5727, 60.9628, and 1117. It can be seen that the three parameters will be continuously adjusted during the simulation process; the simulation results are shown in Figure 6 As shown;
[0124] Specific implementation plan 2: Combined Figures 1 to 3 As shown, the present invention provides a motion control method for an amphibious unmanned platform, comprising the following steps:
[0125] S100, when the amphibious unmanned platform moves in the water, only the propulsion system is used for driving, and the motion is decomposed into horizontal plane motion and vertical plane motion by underactuated control; the controlled system controls the thrust of the bow vertical thruster 505 and the stern vertical thruster 503 to make the amphibious unmanned platform maintain depth; the controlled system controls the thrust of the bow horizontal thruster 506 and the stern horizontal thruster 504 to control the bow turning and navigation of the amphibious unmanned platform, and the forward speed of the amphibious unmanned platform is changed by controlling the thrust output of the thruster;
[0126] When the amphibious unmanned platform is in the elevator mode, if it wants to float or dive, it can only control the pitch angle of the vehicle through the horizontal rudder, and cooperate with the two main thrusters to achieve floating or diving, that is, to achieve depth control; specifically,
[0127] Combination Figure 7The figure shows the use of the traditional PID control algorithm, with the depth error as the input of the PID controller and the output of the horizontal rudder control command. It can be seen that when the depth error is used as the controller input, oscillation will always occur when adjusting the parameters. For this reason, the line of sight navigation method is combined, and the 10m ahead of the X direction position of the multi-habitat unmanned platform itself is taken as the desired X direction. d Direction position, the desired depth position is Z d , from which the displacement error equation can be obtained:
[0128] x e =xx d ,z e =zz d
[0129] According to the line of sight navigation method, the desired pitch angle can be obtained, and its expression is as follows:
[0130] θ d =tan -1 ((zz d ) / (xx d ))
[0131] Combination Figure 8 As shown in the figure, the expected depths are 100m and 60m respectively. It can be seen from the navigation trajectory of the multi-functional unmanned platform that the depth control method combined with the line of sight navigation method can achieve better results, and can realize the convergence of the multi-functional unmanned platform to the specified position, thereby realizing the depth control problem. However, the selection of the specified position will have a greater impact on the final control effect. If the X-direction position is too far, the speed of convergence to the expected depth will be slowed down, and if it is too small, it will not converge to the expected depth.
[0132] S200, when the multi-purpose unmanned platform moves on land, it is driven only by the land power device, and the crawler microcontroller in the control cabin provided on the crawler chassis 2 controls the crawler differential to realize the turning of the multi-purpose unmanned platform on land, and the speed of the crawler 204 is controlled by controlling the duty cycle of the crawler motor to realize the acceleration, deceleration, forward and backward maneuvers;
[0133] S300. When the amphibious unmanned platform moves on the bottom of the water, the propulsion system and the land power device are used in combination to drive the amphibious unmanned platform so that it can fit the bottom of the water and perform underwater crawling maneuvers. The pressure of the amphibious unmanned platform and the bottom of the water is increased by controlling the bow vertical thruster 505 and the stern vertical thruster 503 to apply thrust downward, and the left main thruster 501 and the right main thruster 502 are controlled to assist the amphibious unmanned platform in walking on the bottom of the water. The differential speed of the track 204 and the thrust of the bow horizontal thruster 506 and the stern horizontal thruster 504 are controlled by the track microcontroller to realize the turning of the amphibious unmanned carrier platform on the bottom of the water.
[0134] The other combinations and connection relationships of this embodiment are the same as those of the first embodiment.
[0135] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.
Claims
1. An amphibious unmanned platform, characterized by: It includes upper platform, underwater propulsion device and land power device. The upper platform comprises a closed electronic cabin (4) and an external frame (5) outside the electronic cabin (4); the electronic cabin (4) is arranged at the center of the external frame (5); a controlled system, a navigation and positioning system, a communication system and a power control system are arranged in the electronic cabin (4); an underwater propulsion system is arranged on the external frame (5); and a land power device is arranged below the upper platform; The underwater propulsion system comprises a left main propeller (501) and a right main propeller (502) symmetrically arranged on both sides of the central axis of the stern of the amphibious unmanned platform, and also comprises a stern vertical propeller (503), a stern horizontal propeller (504), a bow vertical propeller (505) and a bow horizontal propeller (506), wherein the propellers of the left main propeller (501) and the right main propeller (502) are horizontally oriented to the rear of the amphibious unmanned platform; the stern vertical propeller (503) and the bow horizontal propeller (506) are symmetrically arranged on both sides of the central axis of the stern of the amphibious unmanned platform, and ... propellers of the stern vertical propeller (503) and the bow horizontal propeller (506) are symmetrically arranged to the rear of the amphibious unmanned platform; the propellers of the stern vertical propeller (503) and the bow horizontal propeller (506) are symmetrically oriented to the rear of the amphibious unmanned platform; the propellers of the stern vertical propeller (503) and the bow horizontal propeller (506) are symmetrically oriented to the rear of the amphibious unmanned platform; the propellers of the stern vertical propeller (503) and the bow horizontal propeller (5 03) is arranged at the bottom of the external frame (5) and the propeller of the stern vertical propeller (503) faces the direction of the crawler chassis (2) of the land power device; the stern horizontal propeller (504) and the bow horizontal propeller (506) are parallel to each other and are respectively located on the bow and stern sides of the amphibious unmanned platform; the propeller of the bow vertical propeller (505) faces a direction perpendicular to the port side; the propeller of the bow horizontal propeller (506) faces a direction perpendicular to the starboard side; The land power system comprises a crawler chassis (2) and two crawler assemblies arranged below the crawler chassis (2), each crawler assembly comprising a driving wheel (201), a guide wheel (203), a load wheel (202), a crawler track (204) and a crawler motor, a plurality of load wheels (202) are evenly arranged between the driving wheel (201) and the guide wheel (203), and the driving wheel (201) and the guide wheel (203) are both located obliquely above the load wheels (202) at both ends, the crawler track (204) is wrapped around the outside of the driving wheel (201), the guide wheel (203) and the plurality of load wheels (202), the output end of the crawler motor is connected to the driving wheel (201), and the driving wheel (201), the guide wheel (203) and the load wheel (202) are all rotationally connected to the crawler chassis (2).
2. The amphibious unmanned platform according to claim 1, characterized in that: The motion computer is used for multi-sensor data processing and calculation of the posture control commands of the multi-habitat unmanned platform; the mission computer is used for executing mission planning, network communication and fault monitoring; the guidance computer is used for giving guidance instructions, including the desired heading, desired speed and desired depth.
3. The amphibious unmanned platform according to claim 2, characterized in that: The navigation and positioning system comprises a GPS module and an inertial navigation sensor in an electronic cabin (4) and a Doppler sensor (508) and a depth meter located outside the electronic cabin; and is used for positioning and posture calculation of the multi-habitat unmanned platform; and the communication system comprises a WiFi communication module and a wireless communication module, and is used for connecting the multi-habitat unmanned platform to a host computer through the communication system.
4. The amphibious unmanned platform according to claim 3, characterized in that: The power control system comprises a main single-chip control board and a relay matrix board, each pin of the main single-chip control board is used to control a relay switch and thus control the power supply of each module; the electronic cabin (4) is powered by a dual power supply, and the power supply is a battery.
5. The amphibious unmanned platform according to claim 4, characterized in that: A plurality of buoyancy blocks (6) are arranged above the crawler chassis (2).
6. The amphibious unmanned platform according to claim 5, characterized in that: The crawler motor is powered by a storage battery arranged on the crawler chassis (2); the crawler chassis (2) is provided with a watertight control cabin, in which a crawler single-chip microcomputer is arranged; the crawler single-chip microcomputer is used to control the crawler motor and communicate with the controlled system via a wired network connection.
7. The amphibious unmanned platform according to claim 6, characterized in that: For the controlled system, a PID controller based on RBF neural network tuning is set, including: Let X = [x1, x2, ..., x n ] T is the network input vector, and the radial basis vector of the hidden layer node is H = [h1,h2...,h m ] T ,h j is the Gaussian basis function: The center vector of the jth node in the hidden layer of the RBF neural network is C j =[c j1 ,c j2 ,...,c jm ] T , let the base width vector of the hidden layer node of the RBF neural network be B = [b1, b2, ...., b m ] T , where b j is the basis width parameter of hidden layer node j and is a number greater than 0; the weight vector of the network is w=[w1,w2,...,w n ] T , the identified network output is: y mout =w1h1+w2h2+...+w m h m Assume that the theoretical output of the identified system at time k is y out (k), the output of network identification is y mout (k), then the identification system performance index function is: The output weight, node center and node base width parameters are obtained by gradient descent method. The output weight expression is as follows: w j (k)=w j (k−1)+η(y out (k)-y mout ( k )) h j +α(w j (k-1)-w j (k-2))+β(w j (k-2)-w j (k-3)) Among them, η is the learning rate; α and β are momentum factors, and their value ranges are both (0, 1); Node base width change Δb j for: Node base width parameter b j for: b j (k)=b j (k-1)+ηΔb j +α(b j (k-1)-b j (k-2))+β(b j (k-2)-b j (k-3)) Node center change Δc ji for: Node center c j for: c ji =c ji (k-1)+ηΔc ji +α(c ji (k-1)-c ji (k-2))+β(c ji (k-2)-c ji (k-3)) Where, cj=[c11,c12,c13,…,c1m]; The PID parameter adjustment algorithm is as follows: The control error is: error(k)=u(k)-yout(k) Among them, u(k) is the input of the controlled system, yout(k) is the output of the controlled system; The three PID inputs are: xc(1)=error(k)-error(k-1) xc(2)=error(k) xc(3)=error(k)-2error(k-1)+error(k-2) The neural network tuning index is: By gradient descent method, we get three parameters K p ,K I ,K D The adjustment amount in decibels is: in, K is the sensitivity of the object output to the change of control input; p is the proportional gain term, K i is the integral gain term, K d is the differential gain term; 8. A motion control method for an amphibious unmanned platform according to any one of claims 1 to 7, characterized in that: The following steps are involved: S100, when the amphibious unmanned platform moves in the water, only the propulsion system is used for driving, and the motion is decomposed into horizontal plane motion and vertical plane motion by using an underactuated control method; the controlled system controls the thrust of the bow vertical thruster (505) and the stern vertical thruster (503) to make the amphibious unmanned platform maintain depth; the controlled system controls the thrust of the bow horizontal thruster (506) and the stern horizontal thruster (504) to control the bow turning and navigation of the amphibious unmanned platform, and the forward speed of the amphibious unmanned platform is changed by controlling the thrust output of the thruster; S200, when the multi-functional unmanned platform moves on land, it is driven only by the land power device, and the crawler microcontroller in the control cabin provided on the crawler chassis (2) controls the differential speed of the crawler (204) to realize the turning of the multi-functional unmanned platform on land, and the speed of the crawler (204) is controlled by controlling the duty cycle of the crawler motor to realize the maneuvering mode of acceleration, deceleration, forward movement and backward movement; S300, when the amphibious unmanned platform moves on the bottom of the water, the propulsion system and the land power device are used in combination to increase the pressure of the amphibious unmanned platform and the bottom of the water by controlling the bow vertical thruster (505) and the stern vertical thruster (503) to apply thrust downward, and the left main thruster (501) and the right main thruster (502) are controlled to assist the amphibious unmanned platform to move on the bottom of the water. The differential speed of the crawler (204) and the thrust of the bow horizontal thruster (506) and the stern horizontal thruster (504) are controlled by the crawler microcontroller to realize the steering of the amphibious unmanned carrier platform on the bottom of the water.
9. The motion control method of an amphibious unmanned platform according to claim 8, characterized in that: When the amphibious unmanned platform is in the elevator mode, the horizontal rudder controls the pitch angle of the vehicle, and the two main thrusters are used to propel the amphibious unmanned platform up or down, including: The depth error is used as the input of the single neuron adaptive PID controller to output the horizontal rudder control command; combined with the line of sight navigation method, the 10m ahead of the multi-habitat unmanned platform’s own X direction position is used as the desired X direction position. d Direction position, expected depth position is Z d , the displacement error equation is obtained as: x e =x-x d ,z e =z-z d The desired trim angle is: θ d <tan -1 ((zz d ) / (xx d ))。
Citation Information
Patent Citations
Multifunctional operation type underwater robot
CN106143841A
Mode self-adaptive switching method of amphibious unmanned vehicle
CN114274719A
Underwater and wall-climbing dual-mode cleaning platform
CN114313138A
Amphibious manned submersible
CN201922869U
Composite drive type underwater robot
CN216507765U
