CN105197004A - System and method for hovercraft docking control based on laser range finder - Google Patents

Abstract

The invention discloses a control system and a control method for an air cushion vehicle docking based on a laser range finder. Including compass, laser rangefinder, comparator, controller, air rudder and side damper; the compass collects the current heading angle of the hovercraft and sends it to the comparator; the laser rangefinder collects the current left and right distance of the hovercraft and sends it to the comparator; The controller compares the received heading angle with the commanded heading angle to obtain the heading deviation, compares the received left and right distances to obtain the position deviation, and transmits the heading deviation and position deviation to the controller; the controller includes a heading controller and a position traverse controller , the heading controller outputs the rudder angle command according to the received heading deviation and sends it to the air rudder to adjust the air rudder rudder angle, and the position sway controller outputs the side air door opening and closing command according to the received position deviation and sends it to the side air door to control the opening of the side air door close. The invention can improve the control level and sailing stability.

Description

A hovercraft docking control system and control method based on laser range finder

technical field

The invention belongs to the field of motion control of hovercraft, and in particular relates to a control system and method for docking an hovercraft based on a laser range finder.

Background technique

The maneuverability of the hovercraft is extremely poor. Due to the support of static pressure, it is suspended on the water surface (ground). The navigation state is greatly affected by the external environment, and it is prone to sideslip and high-speed rotation, and its stability is extremely poor. After decades of development, the hovercraft has changed from the earliest manual control to the current automatic control, which has improved the control level of the hovercraft, reduced the difficulty of manipulation, reduced the work intensity of the driver, and improved the safety of the hovercraft.

As the prominent position of hovercraft continues to strengthen, more and more attention is paid to the maintenance and repair of hovercraft, and docking of hovercraft is an essential step. Ensuring the fast and safe docking of the hovercraft can improve the economic benefits of the hovercraft.

Countries such as the United States, Russia, and the United Kingdom have successively developed integrated driving and control systems for hovercraft. Hovercraft such as LCAC in the United States are equipped with automatic driving control systems with coordinated control methods. Russia has rich theoretical and practical experience in hovercraft control systems. In the 1990s, it developed the "Yellow Peridot-32M" hovercraft coordinated motion control system. This type of hovercraft coordinated motion control system has been equipped on the "European Bison" On a large air cushion landing craft. But above-mentioned systems all do not mention the docking control of hovercraft, also do not see relevant open literature.

Contents of the invention

The object of the present invention is to provide a docking control system for hovercraft based on a laser rangefinder that can reduce time and fuel consumption. The object of the present invention also includes providing a method for controlling the docking of the hovercraft based on a laser range finder, which can improve the control level and navigation stability.

A hovercraft docking control system based on a laser range finder, including a compass, a laser range finder, a comparator, a controller, an air rudder and a side air door;

The compass collects the heading angle of the hovercraft at the current moment and sends it to the comparator;

The laser range finder collects the left and right distance of the hovercraft at the current moment and sends it to the comparator;

The comparator compares the received heading angle with the commanded heading angle to obtain the heading deviation, compares the received left and right distances to obtain the position deviation, and transmits the heading deviation and position deviation to the controller;

The controller includes a course controller and a position traverse controller. The course controller outputs the rudder angle command according to the received course deviation and sends it to the air rudder to adjust the air rudder angle. The position traverse controller outputs the side air door opening according to the received position deviation. The closing command is sent to the side air door to control the opening and closing of the side air door.

A kind of hovercraft docking control method based on laser range finder, comprises the following steps,

Step 1: The compass collects the heading angle of the hovercraft at the current moment, and the laser rangefinder collects the left and right distances of the hovercraft at the current moment;

Step 2: The comparator compares the current heading angle with the command heading angle to obtain the heading deviation, and compares the received left and right distances to obtain the position deviation;

Step 3: The course controller receives the course deviation, adopts the neural network synovial film control method, and outputs the rudder angle command; the position sway controller receives the position deviation, and adopts the logic judgment method to obtain the side air door opening and closing command;

Step 4: The air rudder changes the rudder angle according to the received rudder angle command, changes the torque on the hovercraft, and realizes course control, and the side damper performs opening and closing operations according to the received opening and closing commands, so as to realize the lateral movement of the hovercraft.

A method for controlling the docking of a hovercraft based on a laser range finder in the present invention may also include:

1. The control law in the neural network synovium control method is:

$\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; b</span>}}^{<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&lsqb;</span>\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; \&beta;</span>}\frac{\mathrm{<span\; class="notranslate">\; q</span>}}{\mathrm{<span\; class="notranslate">\; p</span>}}{{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; -</span>\frac{\mathrm{<span\; class="notranslate">\; p</span>}}{\mathrm{<span\; class="notranslate">\; q</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; |</span>{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; |</span>{<span\; class="notranslate">\; |</span>}^{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\stackrel{<span\; class="notranslate">\; ^</span>}{\mathrm{<span\; class="notranslate">\; l</span>}}\mathrm{<span\; class="notranslate">\; g</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\mathrm{<span\; class="notranslate">\; sgn</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>{\stackrel{<span\; class="notranslate">\; \&CenterDot;\&CenterDot;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}}_{\mathrm{<span\; class="notranslate">\; d</span>}}<span\; class="notranslate">\; \&rsqb;</span>$

Among them, e ₁ is the heading deviation, e ₂ is the change rate of the heading deviation, α, β, γ>0 are constants, p, q are positive odd numbers, and satisfy 1<p/q<2, is the output value of the neural network, lg is the switching gain of the control law, η>0 is the parameter, f(x) is the force of the actuator on the hovercraft.

2. The logical judgment method is: when the position deviation is positive, open the right side damper, and when the position deviation is negative, open the left side damper.

Beneficial effect:

Docking of a hovercraft is a difficult task. With the assistance of this control method, the task can be completed more quickly and accurately, reducing time and fuel consumption, reducing the driver's mental pressure, and enhancing the maneuverability of the hovercraft. Good control effect, make full use of the control device of the hovercraft, and improve the navigation safety of the hovercraft.

Description of drawings

The principle block diagram of the control method for docking of the hovercraft of Fig. 1;

Fig. 2 hovercraft docking control method program flow chart;

Fig. 3 block diagram of controller principle of air cushion vehicle docking control method;

Fig. 4 principle block diagram of heading controller of hovercraft docking control method;

Figure 5 is a block diagram of the principle block diagram of the traversing control of the hovercraft docking control method;

Fig. 6 simulation diagram of heading control of hovercraft docking control method;

Figure 7 is a schematic diagram of the left-right distance measured by the laser range finder of the hovercraft; Figure 7(a) is a schematic diagram of the left-right distance when the hovercraft is on the center line; Figure 7(b) is a schematic diagram of the left-right distance when the hovercraft is parallel to one side of the center line; Figure 7(c) Schematic diagram of the left and right distances when the hovercraft heading deviates from the center line.

Fig. 8 is a schematic diagram of the structure of the RBF neural network of the present invention.

Detailed ways

The present invention will be described in further detail below in conjunction with the accompanying drawings.

The invention proposes a method for controlling the docking of a hovercraft based on a laser rangefinder, with the purpose of realizing the docking control of the hovercraft, reducing the work intensity and mental burden of the driver, and improving the control level and navigation stability.

The principle of the hovercraft docking control method proposed by the present invention is as shown in Figure 1, and the process is as follows:

1. Data collection, calculate the heading angle and lateral position status at the current moment according to the compass and laser range finder;

2. The comparator, which compares the heading obtained by the data acquisition module with the command heading to obtain the heading deviation, and compares the d ₁ and d ₂ obtained by the laser range finder to obtain the position deviation;

3. The controller calculates the rudder angle command according to the course deviation, sends it to the air rudder system, obtains the side air door control information according to the position deviation, and sends it to the switch control device, as shown in Figure 3.

4. The change of the rudder angle of the air rudder makes the moment of the hovercraft change, so as to achieve the course control, and the side air door makes the hovercraft get a lateral force to complete the lateral movement of the hovercraft.

The invention discloses a docking control method of an hovercraft based on a laser rangefinder, which is a docking control method of the hovercraft composed of a laser rangefinder, compass data acquisition, a comparator and a controller. The laser rangefinder gives the position and distance information of the current hovercraft docking, and the compass gives the actual heading angle of the hovercraft. The comparator compares the current course with the command course to obtain the course deviation and the position deviation of the left and right distances, and judges the current position state of the hovercraft. The controller outputs control commands to the air rudder and side air door according to the position state, adjusts the current course and the left and right distance, so that the hovercraft completes the docking task along the center line. The present invention can realize the control of the course of the hovercraft by automatically adjusting the air rudder, and can realize the lateral movement control of the hovercraft by adjusting the side damper, which can not only improve the maneuverability of the hovercraft, but also improve the control level of the hovercraft and reduce the working intensity and spirit of the operator burden, reducing the difficulty of the hovercraft docking task and playing a better control effect.

The method for controlling the docking of the hovercraft mainly includes data acquisition, a comparator and a controller. Data acquisition realizes the collection of current position and heading information, the comparator performs heading comparison and left and right position comparison to obtain heading deviation and position deviation, and the controller solves the control command. The present invention is described a few times below.

1. Including data collection, the actual heading angle of the current hovercraft is measured by the compass sensor, and the position information of the left and right distance of the current hovercraft docking is measured by the laser range finder.

2. It includes a controller. The input of the controller is the deviation and position deviation between the current command heading output by the comparator and the current actual heading, and the output is the rudder angle and the open state of the side air door.

3. The course control method adopts the neural network sliding mode control, uses the neural network to observe the external disturbance in real time, and uses the sliding mode control to make the course deviation close to zero. The lateral movement control of the position adopts basic logic judgment, and controls the opening state of the side air door through the position deviation, so that the hovercraft can complete the docking task along the center line.

4. The output command of the course controller is the rudder angle of the air rudder, which is output to the air rudder system, and the course control of the hovercraft is realized by adjusting the rudder angle of the air rudder; The opening and closing of the damper realizes the lateral movement of the hovercraft, so that the hovercraft is at the centerline position.

The flow chart of the program implementation of the hovercraft docking control method is shown in Figure 2, and the steps are as follows:

1. Read the actual heading angle at the current moment, and the comparator uses the difference between the command heading angle at the current moment and the actual heading angle to obtain the heading deviation. In the actual implementation of the comparator, the heading deviation is limited to -180 degrees to 180 degrees If the deviation is positive, it means that the ship will turn right, otherwise the ship will turn left. When the course deviation is zero, go to step 2.

2. According to the d ₁ and d ₂ measured by the laser range finder, the position deviation is obtained by comparing, as shown in Figure 7, the hovercraft performs lateral movement through the control of the side air door;

Heading Controller Design

The principle block diagram of the heading controller is shown in Figure 4. The sliding mode variable structure has a unique effect on the control of nonlinear uncertain systems. , so as to ensure that the system is invariant when receiving parameter perturbations and external disturbances. For uncertain nonlinear systems, the non-singular terminal sliding mode controller is simple in design, good in robustness, fast in response and has terminal sliding mode finite time convergence Compared with the linear sliding mold, it has higher stability.

For the hovercraft system, in order to further improve the control performance of the sliding mode control system and further accelerate the convergence speed of the system reaching the equilibrium point, the nonlinear sliding mode surface is selected as:

$\mathrm{<span\; class="notranslate">\; the\; s</span>}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; |</span>{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; |</span>{<span\; class="notranslate">\; |</span>}^{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; \&beta;</span>}}{{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}^{\frac{\mathrm{<span\; class="notranslate">\; p</span>}}{\mathrm{<span\; class="notranslate">\; q</span>}}}$

In the formula, e ₁ is the heading deviation, e ₂ is the change rate of the heading deviation, α, β, γ>0 are constants, p, q are positive odd numbers, and satisfy 1<p/q<2.

The control law u is designed to make the system reach the sliding mode surface in a finite time, and make the tracking error on the sliding mode surface converge to zero in a finite time. The form of the control law is:

$\begin{array}{c}\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; q</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; w</span>}}\\ <span\; class="notranslate">\; =</span><span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; b</span>}}^{<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&lsqb;</span>\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; \&beta;</span>}\frac{\mathrm{<span\; class="notranslate">\; q</span>}}{\mathrm{<span\; class="notranslate">\; p</span>}}{{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; -</span>\frac{\mathrm{<span\; class="notranslate">\; p</span>}}{\mathrm{<span\; class="notranslate">\; q</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; |</span>{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; |</span>{<span\; class="notranslate">\; |</span>}^{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; +</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; lg</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\mathrm{<span\; class="notranslate">\; sgn</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>{\stackrel{<span\; class="notranslate">\; \&CenterDot;\&CenterDot;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}}_{\mathrm{<span\; class="notranslate">\; d</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&rsqb;</span>\end{array}$

where u _eq represents the equivalent control designed for the nominal system, which can be calculated according to Calculated, u _sw =-(lg+ηsgn(s))/b means switching control, the purpose is to offset the uncertainty existing in the system, lg>0 is the upper limit value of external disturbance, η>0 is the design parameter, f(x) is the force of some actuators on the hovercraft, etc.

In sliding mode control, lg is the switching gain of the control law, and the size of lg is related to the uncertainty disturbance. Based on the uncertainty of the disturbance, if lg is large enough to ensure the sliding mode arrival condition, it will bring a large Chattering reduces system stability and increases system response time. Therefore, in order to eliminate this influence, maintain the stability of the sliding mode control and reduce the chattering of the sliding mode control, the present invention uses the RBF neural network to adjust the switching gain lg. Design an RBF neural network with two inputs, two hidden layer nodes and one output, the structure diagram is shown in Figure 8.

Then the control law can be expressed as:

$\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; b</span>}}^{<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&lsqb;</span>\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; \&beta;</span>}\frac{\mathrm{<span\; class="notranslate">\; q</span>}}{\mathrm{<span\; class="notranslate">\; p</span>}}{{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; -</span>\frac{\mathrm{<span\; class="notranslate">\; p</span>}}{\mathrm{<span\; class="notranslate">\; q</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; |</span>{\mathrm{<span\; class="notranslate">\; e</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; |</span>{<span\; class="notranslate">\; |</span>}^{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\stackrel{<span\; class="notranslate">\; ^</span>}{\mathrm{<span\; class="notranslate">\; l</span>}}\mathrm{<span\; class="notranslate">\; g</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; \&eta;</span>}\mathrm{<span\; class="notranslate">\; sgn</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>{\stackrel{<span\; class="notranslate">\; \&CenterDot;\&CenterDot;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}}_{\mathrm{<span\; class="notranslate">\; d</span>}}<span\; class="notranslate">\; \&rsqb;</span>$

In the formula, Output values for the neural network. h ₁ and h ₂ are Gaussian functions, ω ₁ and ω ₂ are the weight vectors of the network

Lateral Movement Controller Design

The lateral controller is realized by controlling the side air door, and the control principle block diagram is shown in Figure 5. The position deviation is obtained by comparing the distance d ₁ and d ₂ collected by the laser range finder, and the opening and closing status and opening and closing size of the left and right side air doors are controlled by the positive and negative values of the position deviation. When the deviation is positive, the right Side damper, when the deviation is negative, open the left side damper.

According to the above method, the course control program of the hovercraft is compiled by using C++ programming language, and the semi-physical simulation experiment of the laboratory is carried out. The heading simulation diagram is shown in Figure 6.

Claims (4)

1. to lie up a control system based on the air cushion vehicle of laser rangefinder, it is characterized in that: comprise compass, laser rangefinder, comparator, controller, air rudder and crosswind door;

The course angle that compass gathers air cushion vehicle current time sends comparator to;

The left and right distance that laser rangefinder gathers air cushion vehicle current time sends comparator to;

The course angle and instruction course angle of reception compares and obtains course deviation by comparator, the left and right distance of reception is compared and obtains position deviation, send course deviation and position deviation to controller;

Controller comprises the traversing controller of direction controller and position, direction controller exports rudder angle instruction according to the course deviation received and sends air rudder to, regulate air rudder rudder angle, the traversing controller in position sends crosswind door to according to the position deviation outgoing side air door opening and closing instruction received, and controls the opening and closing of crosswind door.

2. a control method for the control system that lies up based on the air cushion vehicle based on laser rangefinder according to claim 1, is characterized in that: comprise the following steps,

Step one: compass gathers the course angle of air cushion vehicle current time, laser rangefinder gathers the left and right distance of air cushion vehicle current time;

Step 2: the course angle and instruction course angle of current time compares and obtains course deviation by comparator, and the left and right distance of reception compares and obtains position deviation;

Step 3: direction controller receives course deviation, adopts neural network synovial membrane control method, exports rudder angle instruction; Position traversing controller receiving position deviation, adopts logic judging method, obtains crosswind door opening and closing instruction;

Step 4: air rudder changes rudder angle according to the rudder angle instruction received, changes air cushion vehicle Moment, realizes Heading control, and crosswind door carries out opening and closing operations according to the opening and closing instruction received, and realizes the transverse shifting of air cushion vehicle.

3. a kind of air cushion vehicle based on laser rangefinder according to claim 2 lies up control method, it is characterized in that: in described neural network synovial membrane control method, control law is:

$u=-b^{-1}\&lsqb;f\left(x\right)+\mathrm{\&beta;}\frac{q}{p}{e_2}^{2-\frac{p}{q}}(1+\frac{\mathrm{\&gamma;}+1}{\mathrm{\&alpha;}}|\left|e_1\right|{|}^{\mathrm{\&gamma;}})+\hat{l}g+\mathrm{\&eta;}\mathrm{sgn}\left(s\right)-{\stackrel{\&CenterDot;\&CenterDot;}{x}}_d\&rsqb;$

Wherein, e ₁for course deviation, e ₂for the rate of change of course deviation, α, beta, gamma >0 are constant, and p, q are positive odd number, and meet 1<p/q<2, for neural network output valve, lg is the handoff gain of control law, and η >0 is the power of parameter, f (x) part actuating unit suffered by air cushion vehicle.

4. a kind of air cushion vehicle based on laser rangefinder according to claim 2 lies up control method, it is characterized in that: described logic judging method is: when position deviation is on the occasion of unlatching right side crosswind door, when position deviation is that negative value opens left side crosswind door.