Motion prediction method of unmanned ship

Abstract

The invention relates to a motion prediction method of an unmanned ship. The method mainly comprises the steps of S1, obtaining wave data information and the turning radius and the transverse drift distance of the unmanned ship to form a training data set, S2, constructing a first prediction model, S3, training the first prediction model through the training data set, S4, obtaining the wave data information, inputting the wave data information into the trained first prediction model, and obtaining the wave data information. And outputting the predicted turning radius and transverse drift distance of the unmanned ship through the first prediction model. According to the method, the influence of waves on the turning radius and the transverse floating distance of the unmanned ship is considered, the turning radius and the transverse floating distance of the unmanned ship under different waves can be predicted, reference can be provided for motion path planning of the unmanned ship, and the probability of collision and even damage of the unmanned ship is reduced.

Description

Technical Field

[0001] The present invention relates to the field of unmanned ship prediction, and in particular to a motion prediction method for an unmanned ship. Background Art

[0002] An unmanned ship is an unmanned vessel. It is a fully automatic surface robot that can navigate on the water according to preset tasks without remote control, with the help of precise satellite positioning and self-sensing. Unmanned ships are widely used in various fields. Unmanned ships include single-hull unmanned ships, catamaran unmanned ships, high-speed wave-piercing ships, etc. Unmanned ships will be affected by waves during their travel. Waves will change the predetermined motion trajectory of the unmanned ship, causing the unmanned ship to have abnormal motion behavior, and even causing the unmanned ship to be at risk of collision and damage. Therefore, it is particularly necessary to study the impact of waves on the motion trajectory of unmanned ships. Summary of the invention

[0003] Based on this, a motion prediction method for an unmanned ship is provided. This method takes into account the influence of waves on the turning radius and drifting distance of the unmanned ship, and can predict the turning radius and drifting distance of the unmanned ship under different waves, which can provide a reference for the motion path planning of the unmanned ship, so as to reduce the probability of collision or even damage of the unmanned ship.

[0004] The scheme of this application is:

[0005] A motion prediction method for an unmanned ship, comprising:

[0006] S1. Obtain wave data information, the turning radius and drift distance of the unmanned boat to form a training data set.

[0007] S2, constructing the first prediction model,

[0008] S3, training the first prediction model using the training data set,

[0009] S4, obtaining wave data information, inputting the wave data information into the trained first prediction model, and outputting the predicted turning radius and lateral drift distance of the unmanned boat through the first prediction model.

[0010] In one embodiment, the wave data information in step S4 is data actually measured.

[0011] In one of the embodiments, wave data information is acquired by a ship-borne wave sensor, and the wave data information includes wave height and period.

[0012] There are many implementations of the first prediction model, which can be implemented using existing neural networks. For example, in one embodiment, the first prediction model is a deep learning neural network. The deep learning neural network is trained with a training data set formed by wave data information, the turning radius of the unmanned boat, and the lateral drift distance. After the training is completed, the actually acquired wave data information is input into the trained deep learning neural network, and then the predicted turning radius and lateral drift distance of the unmanned boat are output.

[0013] On the basis of the above, in one of the embodiments, a second prediction model is also included. The second prediction model is a trained model for predicting wave data information. The wave data information of step S4 is obtained by prediction through the second prediction model.

[0014] In one embodiment, the second prediction model is a deep learning neural network.

[0015] A computer storage medium stores at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the motion prediction method of an unmanned ship based on a deep unmanned network.

[0016] A computer device includes: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus, and the memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the motion prediction method of an unmanned ship based on a deep unmanned network.

[0017] The beneficial effects of this application are:

[0018] This method takes into account the impact of waves on the turning radius and drift distance of the unmanned ship, and can predict the turning radius and drift distance of the unmanned ship under different waves, and can provide a reference for the motion path planning of the unmanned ship to reduce the probability of collision or even damage of the unmanned ship. Moreover, the turning radius and drift distance have a great impact on the path of the unmanned ship, so this application mainly studies these two factors. At the same time, this application also combines the prediction of wave data information with the prediction of the turning radius and drift distance of the unmanned ship, which is conducive to significantly reducing the probability of collision or even damage of the unmanned ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a motion prediction method for an unmanned ship according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] like Figure 1 As shown, the first embodiment of the present application provides a motion prediction method for an unmanned ship, and the motion prediction method for an unmanned ship comprises the following steps:

[0022] S1. Obtain wave data information, the turning radius and drift distance of the unmanned boat to form a training data set.

[0023] S2, constructing the first prediction model,

[0024] S3, training the first prediction model using the training data set,

[0025] S4, obtaining wave data information, inputting the obtained wave data information into the trained first prediction model, and outputting the predicted turning radius and lateral drift distance of the unmanned boat through the first prediction model.

[0026] Specifically, the wave data information, the turning radius and the lateral drift distance of the unmanned ship obtained above are historical data, and these data are preprocessed to form a training data set for training the first prediction model.

[0027] It should be noted that the first prediction model of the present application can apply an existing deep learning neural network. The turning radius and drift distance of the unmanned boat under different wave data information are learned through the deep learning neural network, and finally the predicted turning radius and drift distance of the unmanned boat are output through the first prediction model.

[0028] Specifically, the unmanned ship in the above method of the present application includes a single-body unmanned ship, a double-body unmanned ship, a high-speed wave-piercing ship, etc. The above types of unmanned ships are all relatively commonly used unmanned ships.

[0029] By predicting the turning radius and lateral drift distance of the unmanned boat, this application can provide a basis for the subsequent motion trajectory planning of the unmanned boat, which is conducive to helping the unmanned boat avoid water obstacles and reduce the probability of collision or even damage of the unmanned boat.

[0030] Based on the above, in one embodiment, the wave data information in step S4 is data obtained by actual measurement.

[0031] Specifically, during actual measurement, wave data information may be obtained through a ship-borne wave sensor or a wave measurement system. The wave data information includes elements such as wave height, period, and wave direction.

[0032] On the basis of the above, in one of the embodiments, a second prediction model is also included. The second prediction model is a trained model for predicting wave data information. The wave data information of step S4 is obtained by prediction through the second prediction model.

[0033] Specifically, in one embodiment, the second prediction model is a deep learning neural network, which can be implemented by applying existing deep learning neural networks and existing prediction methods.

[0034] Specifically, the second prediction model can be used to predict the wave data information for a period of time in the future, and then the turning radius and drift distance of the unmanned ship for a period of time in the future can be obtained based on the wave data information for a period of time in the future and the first prediction model. This can provide a reference for the path planning of the unmanned ship, which is conducive to the unmanned ship reaching the destination in a safe and fast manner.

[0035] Through a lot of research, the present application found that the wave data information has a great influence on the turning radius and drift distance of the unmanned boat, and the turning radius and drift distance of the unmanned boat have a great influence on the running track of the unmanned boat. Therefore, it is particularly necessary to predict the turning radius and drift distance of the unmanned boat by the method of the present application, which is helpful to provide a reference for the path planning of the unmanned boat. And through comparative experiments, it is found that the error between the predicted data obtained by the method of the present application and the actual measured data is less than 10%.

[0036] A second embodiment of the present application provides a computer storage medium, in which at least one executable instruction is stored, and the executable instruction enables a processor to execute operations corresponding to the motion prediction method of an unmanned ship based on a deep unmanned network.

[0037] The third embodiment of the present application provides a computer device, including: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus, and the memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the motion prediction method of an unmanned ship based on a deep unmanned network.

[0038] As an embodiment of the present invention, the communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0039] As an implementation mode of the present invention, the communication interface is used for communication between the above-mentioned terminal and other devices.

[0040] As an embodiment of the present invention, the memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0041] As an embodiment of the present invention, the above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0042] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A motion prediction method for an unmanned ship, characterized in that: include: S1. Obtain wave data information, the turning radius and drift distance of the unmanned boat to form a training data set. S2, constructing the first prediction model, S3, training the first prediction model using the training data set, S4, obtaining wave data information, inputting the wave data information into the trained first prediction model, and outputting the predicted turning radius and lateral drift distance of the unmanned boat through the first prediction model.

2. The motion prediction method of an unmanned ship according to claim 1, characterized in that: The wave data information in step S4 is data actually measured.

3. The motion prediction method of an unmanned ship according to claim 1 or 2, characterized in that: The wave data information is obtained through the ship-borne wave sensor, and the wave data information includes the wave height and period.

4. The motion prediction method of an unmanned ship according to claim 1, characterized in that: The first prediction model is a deep learning neural network.

5. The motion prediction method of an unmanned ship according to claim 1, characterized in that: It also includes a second prediction model, which is a trained model for predicting wave data information. The wave data information in step S4 is obtained by prediction using the second prediction model.

6. The motion prediction method of an unmanned ship according to claim 5, characterized in that: The second prediction model is a deep learning neural network.

7. A computer storage medium, characterized in that: The computer storage medium stores at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the motion prediction method of an unmanned ship based on a deep unmanned network as described in any one of claims 1 to 6.

8. A computer device, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus, and the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the motion prediction method of an unmanned ship based on a deep unmanned network as described in any one of claims 1 to 6.

Images