Hovercraft recovery guide control method, device and equipment and storage medium

Abstract

The invention provides a hovercraft recovery guide control method, device and equipment and a storage medium, and the method comprises the steps: obtaining a current first position of a hovercraft and a second position of a dock, building a degree-of-freedom model of the hovercraft based on the first position, a hull coordinate system and a north-east coordinate system, establishing an anti-interference controller model based on the first position and the second position; setting an expected value of the anti-interference controller model based on a degree-of-freedom model, calculating an expected recovery path based on the expected value, and correcting the expected recovery path through a reinforcement learning network to obtain course control parameters of the hovercraft; on the basis of the current motion state of the hovercraft, calculating a sailing path of the hovercraft by using a first guidance algorithm under a Freight coordinate system, and controlling the hovercraft to reach a second position according to the sailing path on the basis of the course control parameters; and acquiring a third position in the dock, and controlling the hovercraft to travel from the second position to the third position by utilizing the first control system based on the second position and the third position.

Description

Technical Field

[0001] The present disclosure relates to the field of hovercraft control, and in particular to a method, device, equipment and storage medium for hovercraft recovery and guidance control. Background Art

[0002] With the continuous development of science and technology, the competition for marine resources has become increasingly fierce, and high-performance ships have received widespread attention. The full-cushion air cushion craft described in the present invention, as a kind of high-performance ship, in terms of its power, it floats on the water surface through an air cushion to get rid of the water surface resistance, and generates longitudinal thrust for sailing through an air propeller; in terms of attitude control, it realizes the bow turning and lateral control of the hull through unique actuators such as air rudders, bow nozzles, side wind gates, etc.

[0003] The control technology of hovercraft recovery is complex. In order to avoid the hovercraft from colliding with the two sides of the dock landing ship during recovery, we need to control the bow, speed and lateral displacement of the hovercraft. At high speed, only the bow and speed are controlled to avoid excessive heeling, while at low speed, the lateral displacement is controlled. Since the hovercraft only drops to the low speed section when approaching the dock landing ship, the scheme of "controlling the bow and speed first, and then controlling the bow, speed and lateral displacement after approaching the mother ship" is adopted to control the hovercraft to approach the cabin of the dock landing ship. However, the wind direction, wind speed, waves and the sailing speed of the hovercraft itself in the environment will also have a great impact on its driving stability and turning speed. Summary of the invention

[0004] The present disclosure provides a method, device, equipment and storage medium for controlling recovery and guidance of a hovercraft, so as to at least solve the above technical problems existing in the prior art.

[0005] According to a first aspect of the present disclosure, a method for controlling recovery and guidance of a hovercraft is provided, the method comprising: Acquire a current first position of the hovercraft and a second position of the dock, establish a degree of freedom model of the hovercraft based on the first position, a hull coordinate system and a north-east coordinate system, and establish an anti-disturbance controller model based on the first position and the second position; The expected value of the anti-disturbance controller model is set based on the degree of freedom model, the expected recovery path is calculated based on the expected value, and the expected recovery path is corrected through a reinforcement learning network to obtain a heading control parameter of the hovercraft; Based on the current motion state of the hovercraft, calculating the navigation path of the hovercraft using a first guidance algorithm in a Fresnel coordinate system, and controlling the hovercraft to reach the second position along the navigation path based on the heading control parameter; A third position in the dock is acquired, and based on the second position and the third position, the hovercraft is controlled by using a first control system to travel from the second position to the third position.

[0006] In one embodiment, the method further comprises: The positioning system obtains the observation value of the hovercraft within the sampling time, and the observation value includes position information and speed information; Establishing an observation model based on the observation values ​​and the observation noise existing in the observation values, and establishing a state model of the hovercraft based on the position information and the speed information; The observation noise in the observation model is eliminated based on the state model to obtain the target heading, target speed and lateral displacement of the hovercraft.

[0007] In one possible implementation manner, the calculating the expected recovery path based on the expected value and correcting the expected recovery path through a reinforcement learning network to obtain the heading control parameters of the hovercraft include: Calculating disturbance data and state data of the hovercraft based on the expected value control, and calculating a first target control amount of the anti-disturbance controller model based on the disturbance data and the state data; Acquiring a heading angle error of the hovercraft, and calculating corresponding differential data and integral data based on the heading angle error; Inputting the heading angle error, the differential data, the integral data and the first target control amount into the reinforcement learning network, and calculating a control increment of the first target control amount; A heading control parameter of the hovercraft is set based on the first target control amount and the control increment.

[0008] In one possible implementation, the calculating the navigation path of the hovercraft using the first guidance algorithm in the Fresnel coordinate system includes: Setting an expected navigation path of the hovercraft, and calculating an expected heading angle of the hovercraft based on the expected navigation path and a current position of the hovercraft; A first vector of a current attitude error of the hovercraft is set based on the north-east coordinate system, and a second vector of a current attitude error of the hovercraft is calculated by the Freynes coordinate system; Calculating a vector of the attitude error derivative of the hovercraft in the Fresnel coordinate system based on a conversion relationship between the first vector and the second vector; The guidance parameters of the first guidance algorithm are set based on the vector of the attitude error derivative, and the navigation path is set based on the guidance parameters.

[0009] In one embodiment, the method further comprises: Setting a path switching area circle with the second position as the origin, and using the radius of the path switching area circle as the path switching threshold; Acquiring the position of the hovercraft, and when the position of the hovercraft is less than the path switching threshold, calculating the path switching radius and the path switching speed of the hovercraft based on the current posture information of the hovercraft; The hovercraft is controlled to sail to the second position based on the path switching radius and the path switching speed.

[0010] According to a second aspect of the present disclosure, there is provided a hovercraft recovery guidance control device, the device comprising: a model building unit, configured to obtain a current first position of the hovercraft and a second position of the dock, establish a degree of freedom model of the hovercraft based on the first position, a hull coordinate system and a north-east coordinate system, and establish an anti-disturbance controller model based on the first position and the second position; a parameter correction unit, configured to set an expected value of the anti-disturbance controller model based on the degree of freedom model, calculate an expected recovery path based on the expected value, and correct the expected recovery path through a reinforcement learning network to obtain a heading control parameter of the hovercraft; a guidance control unit, configured to calculate a navigation path of the hovercraft using a first guidance algorithm in a Fresnel coordinate system based on a current motion state of the hovercraft, and control the hovercraft to reach the second position along the navigation path based on the heading control parameter; The recovery control unit is used to obtain a third position in the dock, and based on the second position and the third position, use the first control system to control the hovercraft to travel from the second position to the third position.

[0011] In one embodiment, the device further comprises: A noise elimination unit is used for the positioning system to obtain the observation value of the hovercraft within the sampling time, wherein the observation value includes position information and speed information; establish an observation model based on the observation value and the observation noise existing in the observation value, and establish a state model of the hovercraft based on the position information and the speed information; eliminate the observation noise in the observation model based on the state model to obtain the target heading, target speed and lateral displacement of the hovercraft; The path switching unit is used to set a path switching area circle with the second position as the origin, and use the radius of the path switching area circle as a path switching threshold; obtain the position of the hovercraft, and when the position of the hovercraft is less than the path switching threshold, calculate the path switching radius and the path switching speed of the hovercraft based on the current posture information of the hovercraft; and control the hovercraft to sail to the second position based on the path switching radius and the path switching speed.

[0012] In one possible implementation manner, the parameter correction unit is further used to calculate the disturbance data and state data of the hovercraft based on the expected value control, and calculate the first target control amount of the anti-disturbance controller model based on the disturbance data and the state data; obtain the heading angle error of the hovercraft, and calculate the corresponding differential data and integral data based on the heading angle error; input the heading angle error, the differential data, the integral data and the first target control amount into the reinforcement learning network, and calculate the control increment of the first target control amount; set the heading control parameter of the hovercraft based on the first target control amount and the control increment; The guidance control unit is also used to set an expected navigation path of the hovercraft, calculate an expected heading angle of the hovercraft based on the expected navigation path and the current position of the hovercraft; set a first vector of a current attitude error of the hovercraft based on the north-east coordinate system, and calculate a second vector of a current attitude error of the hovercraft in the Freynes coordinate system; calculate a vector of the attitude error derivative of the hovercraft in the Freynes coordinate system based on a conversion relationship between the first vector and the second vector; set guidance parameters of the first guidance algorithm based on the vector of the attitude error derivative, and set the navigation path based on the guidance parameters.

[0013] According to a third aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present disclosure.

[0014] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.

[0015] The hovercraft recovery guidance control method, device, equipment and storage medium disclosed in the present invention obtain the positions of the hovercraft and the dock, establish a degree of freedom model and an anti-disturbance controller model, use a reinforcement learning algorithm to adjust the anti-disturbance controller, and control the hovercraft recovery in combination with a control algorithm to ensure that the hovercraft can navigate safely and stably in a complex environment.

[0016] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which: In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0018] Figure 1 The schematic diagram shows the implementation process of a hovercraft recovery guidance control method according to the embodiment of the present disclosure. Figure 1 ; Figure 2 The schematic diagram shows the implementation process of a hovercraft recovery guidance control method according to the embodiment of the present disclosure. Figure 2 ; Figure 3 A schematic diagram of a Fresenius coordinate system guidance (SFLOS) in an embodiment of the present disclosure is shown; Figure 4 A schematic diagram of PID control of hovercraft recovery in an embodiment of the present disclosure is shown; Figure 5 A schematic diagram of a hovercraft recovery guidance control device according to an embodiment of the present disclosure is shown; Figure 6 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0019] In order to make the purpose, features, and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0020] Figure 1 The schematic diagram shows the implementation process of a hovercraft recovery guidance control method according to the embodiment of the present disclosure. Figure 1 ,like Figure 1 As shown, a hovercraft recovery guidance control method according to an embodiment of the present disclosure includes the following steps: Step 101, obtaining a current first position of the hovercraft and a second position of the dock, establishing a degree of freedom model of the hovercraft based on the first position, a hull coordinate system and a north-east coordinate system, and establishing an anti-disturbance controller model based on the first position and the second position.

[0021] In the disclosed embodiment, the current initial state information of the hovercraft is obtained through GPS, including the first position of the hovercraft and the second position of the dock. The first position is taken as the origin, a six-degree-of-freedom model of the hovercraft is created based on the north-east coordinate system and the hull coordinate system, and the second position is taken as the target position to establish an anti-disturbance controller model.

[0022] Step 102, setting an expected value of the anti-disturbance controller model based on the degree of freedom model, calculating an expected recovery path based on the expected value, and correcting the expected recovery path through a reinforcement learning network to obtain a heading control parameter of the hovercraft.

[0023] In the disclosed embodiment, the disturbance rejection controller model is an auto-disturbance rejection controller, which is mainly composed of four parts: a tracking differentiator TD, an extended state observer ESO, a nonlinear state error feedback control law NLSEF, and a disturbance compensation device. Based on the degree of freedom model and the second position as the target position, the expected value of the auto-disturbance rejection controller is set by the tracking differentiator, the disturbance data and the state data are estimated by the extended state observer, the first target control quantity of the auto-disturbance rejection controller is calculated according to the disturbance data and the state data, the heading angle error of the hovercraft is obtained, and the corresponding differential data and integral data are calculated based on the heading angle error; the heading angle error, the differential data, the integral data and the first target control quantity are input into the reinforcement learning network, and the control increment of the first target control quantity is calculated; the heading control parameter of the hovercraft is set based on the first target control quantity and the control increment.

[0024] Step 103, based on the current motion state of the hovercraft, calculate the navigation path of the hovercraft using the first guidance algorithm in the Fresnel coordinate system, and control the hovercraft to reach the second position along the navigation path based on the heading control parameters.

[0025] In the disclosed embodiment, an expected navigation path of the hovercraft is set, and an expected heading angle of the hovercraft is calculated based on the expected navigation path and the current position of the hovercraft; a first vector of a current attitude error of the hovercraft is set based on the northeast coordinate system, and a second vector of the current attitude error of the hovercraft is set in the Serret-Frenet coordinate system (SF); a vector of the attitude error derivative of the hovercraft in the Serret-Frenet coordinate system is calculated based on a conversion relationship between the first vector and the second vector; a guidance parameter of the first guidance algorithm is set based on the vector of the attitude error derivative, and the navigation path is set based on the guidance parameter. Preferably, the first guidance algorithm is a LOS guidance algorithm with a foresight distance parameter.

[0026] In the disclosed embodiment, the positioning system obtains observation values ​​of the hovercraft within a sampling time, wherein the observation values ​​include position information and speed information; an observation model is established based on the observation values ​​and observation noise existing in the observation values, and a state model of the hovercraft is established based on the position information and the speed information; the observation noise in the observation model is eliminated based on the state model to obtain the target heading, target speed and lateral displacement of the hovercraft.

[0027] Step 104, obtaining a third position in the dock, and based on the second position and the third position, controlling the hovercraft to travel from the second position to the third position by using a first control system.

[0028] In the disclosed embodiment, the third position is the docking position of the hovercraft. When the hovercraft approaches the second position, it is necessary to switch the path from the guidance path to the control path. A path switching area circle is set with the second position as the origin, and the radius of the path switching area circle is used as the path switching threshold. The position of the hovercraft is obtained. When the position of the hovercraft is less than the path switching threshold, the path switching radius and the path switching speed of the hovercraft are calculated based on the current posture information of the hovercraft. Based on the path switching radius and the path switching speed, the hovercraft is controlled to sail to the second position.

[0029] In the embodiment of the present disclosure, the hovercraft is controlled by a first control system to travel from the second position to the third position, wherein the first control system is a Proportion Integral Differential (PID) control system.

[0030] Figure 2 The schematic diagram shows the implementation process of a hovercraft recovery guidance control method according to the embodiment of the present disclosure. Figure 2 ,like Figure 2As shown, a hovercraft recovery guidance control method according to an embodiment of the present disclosure includes the following steps: Step 201, using GPS to obtain initial state information of the hovercraft, and establishing a mathematical model of the six degrees of freedom of the hovercraft.

[0031] In the disclosed embodiment, the initial state information of the hovercraft includes: the position information, bow direction and speed information of the hovercraft. Based on the position of the hovercraft, the freedom model of the hull is established according to the hull coordinate system and the northeast ground coordinate system, and the conversion relationship between the hull coordinate system and the northeast ground coordinate system and the six-degree-of-freedom motion relationship are combined to deduce:

[0032] in, They represent the six degrees of freedom of the hovercraft respectively, and the vector form is:

[0033] Right now:

[0034] Where:

[0035]

[0036] , It can be called a rotation transformation matrix.

[0037] The mathematical model equations of the full-cushion hovercraft motion are:

[0038] After the forces and moments of each module are combined, they can be synthesized in the motion coordinate system to form the lateral, longitudinal, and vertical forces and the moments of heel, trim, and bow turning of the full-lift air cushion craft, and the resultant force equation can be obtained as follows:

[0039] Among them, the subscript a in the formula represents aerodynamic force, m represents air momentum force, h represents hydrodynamic force, p represents propeller force, R represents rudder force, s represents side wind door force, and n represents bow nozzle force.

[0040]

[0041] Table 1, Hovercraft Symbol Correspondence Table The differential equation of motion of a full-lift hovercraft is:

[0042] In the formula, I z The moment of inertia of the hovercraft about the z-axis, Ix The moment of inertia of the hovercraft about the x-axis, I y Moment of inertia of the axis, F x The force on the hovercraft in the x-axis direction, F y The force on the hovercraft in the y-axis direction, F z The force on the hovercraft in the z-axis direction, M x The moment of force on the hovercraft about the x-axis, M y The total moment of the hovercraft around the y-axis, M z The moment around the z-axis that the hovercraft is subjected to. The above formula constitutes the complete degree of freedom model of the hovercraft.

[0043] Step 202: using reinforcement learning to optimize the parameter setting of the nonlinear state error feedback control law in the nonlinear active disturbance rejection controller.

[0044] In the disclosed embodiment, the self-disturbance rejection controller with disturbance estimation and compensation capabilities mainly consists of four parts: tracking differentiator TD (Tracking Differentiator), extended state observer ESO (Extended State Observer), nonlinear state error feedback control law NLSEF (Nonlinear State Error Feedback Law), and disturbance compensation device. Among them, the expected value of the self-disturbance rejection controller is set based on the tracking differential controller, the extended state observer estimates the expected value, and obtains the disturbance quantity and state quantity. The nonlinear state error feedback control rate calculates the control quantity according to the disturbance quantity and state quantity, and controls the hovercraft to enter the dock according to the calculation result. Among them, the heading controller is:

[0045] in: For the desired direction, for The tracking signal, for The approximate signal Z n+1 For X n+1 The observed value of … are observer parameters, is a constant, h is the integration step length, is the fastest control comprehensive function, and r is the speed factor of the tracking differentiator.

[0046] The function is:

[0047] in , , is the filtering parameter. The track deviation command control quantity is:

[0048] Where AB is the guidance path designed by the waypoint guidance strategy; AP is the actual path of the hovercraft; C AB C is the expected heading of the current route; AP is the angle between the ship and the north direction.

[0049] In the disclosed embodiment, in order to prevent the uncertainty of the ambient wind from affecting the heading of the hovercraft during the high-speed approach phase, a reinforcement learning algorithm based on the actor-critic framework is used to optimize the NLSEF link of the heading anti-disturbance controller. The control system of the anti-disturbance controller is:

[0050] in, is the system uncertainty function, is the system state variable. The system uncertainty function corresponds to factors such as wind direction and waves during the operation of the hovercraft, and needs to be set according to the specific driving environment. w(t) is the external disturbance, b is a constant, and u(t) is the control input.

[0051] The nonlinear state error feedback control law is: Taking the first-order nonlinear control system as an example, its equation is:

[0052] Design the feedback control rate for the above formula, then: , k is the coefficient of the nonlinear feedback control rate, substituted into the original formula, then:

[0053] Design a nonlinear inverse control law u=g(x1), where g(·) is a nonlinear function:

[0054] The control quantity is taken as the error feedback u=g(e), e=v(t)-x1, v(t) is the control expectation, and the nonlinear state error feedback control system is obtained:

[0055] Similarly, g(·) takes f al (·) function, then the NLSEF of the control system design is:

[0056] in, To control the gain, , for The i-th order differential signal of .

[0057] In the embodiment of the present disclosure, the reinforcement learning algorithm based on the actor-critic framework is specifically as follows: the state space set received by the DDPG environment includes four elements, namely, heading angle error , differential of heading angle error , integral of heading angle error With NLSEF control output The output of the action neural network (Actor) in the DDPG environment is the increment of the parameters of the NLSEF link at the current moment. Its mathematical description is as follows:

[0058] in and Parameters for the NLSEF link , The initial reference value of and is the output of the action neural network. Selecting the increment of the parameter rather than the parameter itself as the output of the action neural network can improve the convergence speed of the algorithm and avoid the severe jitter of the control effect caused by excessive parameter changes. The output of the value neural network (Critic) of the DDPG environment, that is, the design of the reward function value is as follows:

[0059] in and are the expected heading value and current heading value of heading ADRC respectively, is the output of the NLSEF link, is the turning torque output by the bow ADRC. Based on the above method, the reinforcement learning parameter setting is realized.

[0060] Step 203, according to the initial motion state of the dock landing ship, a dynamic forward-looking distance parameter SFLOS guidance algorithm is designed, and the path of the hovercraft guidance process is determined accordingly.

[0061] In the embodiment of the present disclosure, the LOS guidance algorithm is combined with the Serret-Frenet coordinate system, and a forward-looking distance parameter is proposed. The guidance algorithm is the SFLOS guidance algorithm. It places the current position of the ship in front of the projection point on the target path. The position at the distance is taken as the expected point, and the expected heading angle is calculated according to the foresight distance parameter, so as to realize the tracking of straight path and curved path. Figure 3As shown in the SFLOS guidance diagram, the attitude error vector is defined in the SF coordinate system: , the attitude error vector in the north-east coordinate system . Then according to the differential homeomorphism transformation, we can get the following relationship:

[0062] According to the properties of differential homeomorphism, if the error vector Converges in the SF coordinate system, then the error vector Converges in the north-east coordinate system. Therefore, it is only necessary to design the control law to ensure that the error vector Convergence in the SF coordinate system is sufficient. Let the transformation matrix in the formula be , then taking the derivative of the formula we can get the following relationship: , we can know from the formula, The derivative of is: Substituting the kinematic relationship of the hovercraft into the formula, we can get:

[0063] The derivative of is:

[0064] It can be seen from the formula that the heading tracking error The derivative of is:

[0065] The vector of the attitude error derivative of the hovercraft in the SF coordinate system can be obtained:

[0066] The position error vector in the SF coordinate system is defined as , then the control objective description of path tracking is as follows: ; The complete design of SFLOS guidance is as follows:

[0067] Where: the point on the curve P As the target tracking point, is the north-east coordinate system, , The curve P is formed at the point The SF coordinate system at is the bow phase angle of the hovercraft, is the sideslip angle of the hovercraft, is the track angle of the hovercraft, is the rotation angle from the North East coordinate system to the SF coordinate system, , and are the heading tracking errors of the hovercraft in the SF coordinate system, where is the virtual control rate, is the foresight distance parameter in SFLOS guidance, For hovercraft Position tracking error in direction, For hovercraft Position tracking error in direction, , , are the longitudinal velocity, lateral velocity and combined velocity of the hovercraft respectively. Based on this, the navigation path of the hovercraft during guidance is determined.

[0068] Step 204: Use Kalman filtering to eliminate environmental interference.

[0069] In the disclosed embodiment, since civil GPS navigation satellites artificially add interference, it is necessary to filter the position and velocity signals of GPS. The interference signal artificially added to GPS can be regarded as the measurement noise of GPS, that is, the observation noise V(k). In order to simplify the model, it is assumed that the hovercraft moves in a straight line, with the starting point as the origin, and the sampling time is set to T0. s(k) represents the position of the ship at the sampling time kT0, and y(k) is the observation value of GPS at kT0. Then the observation model is; y(k)=s(k)+v(k), v(k) is the measurement noise of GPS positioning, which is assumed to be Gaussian white noise. The acceleration a(k) is composed of two parts: maneuvering acceleration u(k) (power system control) and random acceleration w(k) (that is, the influence of waves and wind), that is: a(k)=u(k)+w(k), assuming that w(k) is white noise that conforms to the Gaussian distribution. The system state x(k) defined at the sampling time is the position and velocity of the ship, that is

[0070] The state equation is:

[0071] Observation equation:

[0072] Extending the motion to four dimensions, that is:

[0073] Based on the above method, Kalman filtering is performed to adjust the parameters and obtain the reference information of the hovercraft.

[0074] Step 205, based on the controller effect, taking into account the control effect on heading and speed, determine the safe turning limit of the hovercraft itself and determine the path switching threshold at the waypoint.

[0075] In the disclosed embodiment, the path switching threshold at the waypoint is determined according to the controller effect and the safety limit of the hovercraft. The path switching rotation safety limit is set. Generally, when the hovercraft rotates, its rotation rate is too large, which will lead to too large heel angle. In order to ensure the safe navigation of the ship, a range is generally specified, which is called the hovercraft safety limit.

[0076] In the disclosed embodiment, a circle is set with the waypoint as the origin, and the radius is the switching threshold. When the distance between the ship and the point is less than the switching radius value, the switching begins. The switching conditions are:

[0077] Among them, (x, y) is the current position coordinate of the hovercraft; is the coordinate of the end point of the i-th path; The radius value set for the i-th path. The switching radius expression is:

[0078] in: To switch the radius value; is the minimum switching radius; is the maximum switching radius; is the angle between adjacent switching paths; is the scale factor, The method of determining is:

[0079] is the direction vector of the i-th path, is the endpoint of the i-th path. The higher the speed of the hovercraft, the lower the safety upper limit of the turning rate and the sideslip angle, that is, the lower the safety of the turning maneuvering process. In order to make the hovercraft turn at a faster speed. The specific function expression is:

[0080] in: To switch the radius value; To switch the minimum speed; To switch the maximum speed; is the scale factor.

[0081] Step 206, using a method combining an anti-disturbance control and a PID controller to control the heading, speed and lateral displacement of the hovercraft to achieve the recovery action of the hovercraft.

[0082] In the embodiment of the present disclosure, after the path switching in the above step 205, the hovercraft enters the recovery control stage from the guidance stage. The recovery control stage mainly realizes fine control of the hovercraft through the PID controller. Figure 4 It is the control link of the PID control system, where r(t) represents the expected value, u(t) represents the controller output, y(t) represents the output value of the controlled object, and the control deviation e(t) formula is: e(t)=r(t)-y(t). The differential equation of its control law is:

[0083] The transfer function is:

[0084] in, is the proportional gain, is the integral gain, is the differential gain, e ( t ) is the current error, that is, the difference between the set value and the actual value The integral of is the accumulated error from the initial moment to the current moment, is the rate of change of the error. Combined with the heading controller design in step 202, the track control algorithm of the controller is derived as follows:

[0085] in, and is the optimal parameter for reinforcement learning, is the expected track deviation, set to 0, It is a course correction instruction. According to the current straight line azimuth of the hovercraft Determine the real-time desired heading with the heading correction command: , thereby completing the motion control process of the hovercraft.

[0086] Figure 5 FIG. 1 shows a schematic diagram of a hovercraft recovery guidance control device according to an embodiment of the present disclosure. Figure 5 As shown, an air cushion vehicle recovery guidance control device according to an embodiment of the present disclosure includes: The model building unit 501 is used to obtain the current first position of the hovercraft and the second position of the dock, establish a degree of freedom model of the hovercraft based on the first position, the hull coordinate system and the north-east coordinate system, and establish an anti-disturbance controller model based on the first position and the second position.

[0087] The parameter correction unit 502 is used to set the expected value of the anti-disturbance controller model based on the degree of freedom model, calculate the expected recovery path based on the expected value, and correct the expected recovery path through a reinforcement learning network to obtain the heading control parameter of the hovercraft.

[0088] The parameter correction unit 502 is also used to calculate the disturbance data and state data of the hovercraft based on the expected value control, and calculate the first target control quantity of the anti-disturbance controller model based on the disturbance data and the state data; obtain the heading angle error of the hovercraft, and calculate the corresponding differential data and integral data based on the heading angle error; input the heading angle error, differential data, integral data and the first target control quantity into the reinforcement learning network, and calculate the control increment of the first target control quantity; set the heading control parameters of the hovercraft based on the first target control quantity and the control increment.

[0089] The guidance control unit 503 is used to calculate the navigation path of the hovercraft using the first guidance algorithm in the Fresnel coordinate system based on the current motion state of the hovercraft, and control the hovercraft to reach the second position along the navigation path based on the heading control parameters.

[0090] The guidance control unit 503 is also used to set an expected navigation path of the hovercraft, calculate an expected heading angle of the hovercraft based on the expected navigation path and the current position of the hovercraft; set a first vector of the current attitude error of the hovercraft based on the north-east coordinate system, and calculate a second vector of the current attitude error of the hovercraft in the Freynes coordinate system; calculate a vector of the attitude error derivative of the hovercraft in the Freynes coordinate system based on a conversion relationship between the first vector and the second vector; set the guidance parameters of the first guidance algorithm based on the vector of the attitude error derivative, and set the navigation path based on the guidance parameters.

[0091] The recovery control unit 504 is used to obtain a third position in the dock, and based on the second position and the third position, control the hovercraft to travel from the second position to the third position using the first control system.

[0092] The noise elimination unit 505 is used for the positioning system to obtain the observation value of the hovercraft within the sampling time, and the observation value includes the position information and the speed information; establish an observation model based on the observation value and the observation noise existing in the observation value, and establish a state model of the hovercraft based on the position information and the speed information; eliminate the observation noise in the observation model based on the state model to obtain the target heading, target speed and lateral displacement of the hovercraft.

[0093] The path switching unit 506 is used to set a path switching area circle with the second position as the origin, and use the radius of the path switching area circle as the path switching threshold; obtain the position of the hovercraft, and when the position of the hovercraft is less than the path switching threshold, calculate the path switching radius and path switching speed of the hovercraft based on the current posture information of the hovercraft; and control the hovercraft to sail to the second position based on the path switching radius and the path switching speed.

[0094] In an exemplary embodiment, the model building unit 501, the parameter correction unit 502, the guidance control unit 503, the recovery control unit 504, the noise elimination unit 505 and the path switching unit 506 can be implemented by one or more central processing units (CPU), graphics processing units (GPU), application specific integrated circuits (ASIC), DSP, programmable logic devices (PLD), complex programmable logic devices (CPLD), field programmable gate arrays (FPGA), general-purpose processors, controllers, microcontrollers (MCU), microprocessors, or other electronic components.

[0095] Regarding the device in the above embodiment, the specific manner in which each module and unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0096] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0097] Figure 6A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0098] like Figure 6 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0099] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0100] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as a hovercraft recovery guidance control method. For example, in some embodiments, a hovercraft recovery guidance control method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the hovercraft recovery guidance control method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute a hovercraft recovery guidance control method in any other appropriate manner (for example, by means of firmware).

[0101] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0102] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0103] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0104] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0105] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0106] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0107] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0108] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0109] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for controlling the recovery and guidance of a hovercraft, characterized in that: The method comprises: Acquire a current first position of the hovercraft and a second position of the dock, establish a degree of freedom model of the hovercraft based on the first position, a hull coordinate system and a north-east coordinate system, and establish an anti-disturbance controller model based on the first position and the second position; The expected value of the anti-disturbance controller model is set based on the degree of freedom model, the expected recovery path is calculated based on the expected value, and the expected recovery path is corrected through a reinforcement learning network to obtain a heading control parameter of the hovercraft; Based on the current motion state of the hovercraft, calculating the navigation path of the hovercraft using a first guidance algorithm in a Fresnel coordinate system, and controlling the hovercraft to reach the second position along the navigation path based on the heading control parameter; A third position in the dock is acquired, and based on the second position and the third position, the hovercraft is controlled by using a first control system to travel from the second position to the third position.

2. The method according to claim 1, characterized in that The method further comprises: The positioning system obtains the observation value of the hovercraft within the sampling time, and the observation value includes position information and speed information; Establishing an observation model based on the observation values ​​and the observation noise existing in the observation values, and establishing a state model of the hovercraft based on the position information and the speed information; The observation noise in the observation model is eliminated based on the state model to obtain the target heading, target speed and lateral displacement of the hovercraft.

3. The method according to claim 1, characterized in that The step of calculating the expected recovery path based on the expected value and correcting the expected recovery path through a reinforcement learning network to obtain the heading control parameters of the hovercraft includes: Calculating disturbance data and state data of the hovercraft based on the expected value control, and calculating a first target control amount of the anti-disturbance controller model based on the disturbance data and the state data; Acquiring a heading angle error of the hovercraft, and calculating corresponding differential data and integral data based on the heading angle error; Inputting the heading angle error, the differential data, the integral data and the first target control amount into the reinforcement learning network, and calculating a control increment of the first target control amount; A heading control parameter of the hovercraft is set based on the first target control amount and the control increment.

4. The method according to claim 1, characterized in that: The calculating the navigation path of the hovercraft by using the first guidance algorithm in the Freynes coordinate system includes: Setting an expected navigation path of the hovercraft, and calculating an expected heading angle of the hovercraft based on the expected navigation path and a current position of the hovercraft; A first vector of a current attitude error of the hovercraft is set based on the north-east coordinate system, and a second vector of a current attitude error of the hovercraft is calculated by the Freynes coordinate system; Calculating a vector of an attitude error derivative of the hovercraft in the Fresnel coordinate system based on a conversion relationship between the first vector and the second vector; The guidance parameters of the first guidance algorithm are set based on the vector of the attitude error derivative, and the navigation path is set based on the guidance parameters.

5. The method according to claim 1, characterized in that The method further comprises: Setting a path switching area circle with the second position as the origin, and using the radius of the path switching area circle as the path switching threshold; Acquiring the position of the hovercraft, and when the position of the hovercraft is less than the path switching threshold, calculating the path switching radius and the path switching speed of the hovercraft based on the current posture information of the hovercraft; The hovercraft is controlled to sail to the second position based on the path switching radius and the path switching speed.

6. A hovercraft recovery guidance control device, characterized in that: The device comprises: a model building unit, configured to obtain a current first position of the hovercraft and a second position of the dock, establish a degree of freedom model of the hovercraft based on the first position, a hull coordinate system and a north-east coordinate system, and establish an anti-disturbance controller model based on the first position and the second position; a parameter correction unit, configured to set an expected value of the anti-disturbance controller model based on the degree of freedom model, calculate an expected recovery path based on the expected value, and correct the expected recovery path through a reinforcement learning network to obtain a heading control parameter of the hovercraft; a guidance control unit, configured to calculate a navigation path of the hovercraft using a first guidance algorithm in a Fresnel coordinate system based on a current motion state of the hovercraft, and control the hovercraft to reach the second position along the navigation path based on the heading control parameter; The recovery control unit is used to obtain a third position in the dock, and based on the second position and the third position, use the first control system to control the hovercraft to travel from the second position to the third position.

7. The device according to claim 6, characterized in that The device also includes; A noise elimination unit is used for the positioning system to obtain the observation value of the hovercraft within the sampling time, wherein the observation value includes position information and speed information; establish an observation model based on the observation value and the observation noise existing in the observation value, and establish a state model of the hovercraft based on the position information and the speed information; eliminate the observation noise in the observation model based on the state model to obtain the target heading, target speed and lateral displacement of the hovercraft; The path switching unit is used to set a path switching area circle with the second position as the origin, and use the radius of the path switching area circle as a path switching threshold; obtain the position of the hovercraft, and when the position of the hovercraft is less than the path switching threshold, calculate the path switching radius and the path switching speed of the hovercraft based on the current posture information of the hovercraft; and control the hovercraft to sail to the second position based on the path switching radius and the path switching speed.

8. The device according to claim 6, characterized in that The parameter correction unit is further used to calculate disturbance data and state data of the hovercraft based on the expected value control, and calculate a first target control amount of the anti-disturbance controller model based on the disturbance data and the state data; Acquire the heading angle error of the hovercraft, and calculate corresponding differential data and integral data based on the heading angle error; input the heading angle error, the differential data, the integral data and the first target control amount into the reinforcement learning network, and calculate the control increment of the first target control amount; Setting a heading control parameter of the hovercraft based on the first target control amount and the control increment; The guidance control unit is further used to set an expected navigation path of the hovercraft, calculate an expected heading angle of the hovercraft based on the expected navigation path and the current position of the hovercraft; set a first vector of the current attitude error of the hovercraft based on the north-east coordinate system, calculate a second vector of the current attitude error of the hovercraft set in the Fresnel coordinate system; calculate a vector of the attitude error derivative of the hovercraft in the Fresnel coordinate system based on a conversion relationship between the first vector and the second vector; The guidance parameters of the first guidance algorithm are set based on the vector of the attitude error derivative, and the navigation path is set based on the guidance parameters.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method according to any one of claims 1-5.

Images