Ship control method, device, equipment, medium and product

Abstract

The invention discloses a ship control method, device and equipment, a medium and a product. The method is applied to a ship and comprises the following steps: acquiring ship observation information corresponding to a to-be-processed ship; inputting the ship observation information into a ship control strategy network to obtain a control decision of the ship to be processed; determining a ship prediction position of the to-be-processed ship according to the control decision and the ship navigational speed under the condition that the obstacle object associated with the to-be-processed ship exists; and under the condition of determining that the ship prediction position is located in the target obstacle avoidance area, repeatedly executing the steps of determining the control decision and determining the ship prediction position until the ship prediction position is not located in the target obstacle avoidance area, obtaining a target control decision of the to-be-processed ship, and controlling the to-be-processed ship based on the target control decision. According to the technical scheme, the effects that the ship control decision is determined by combining the strategy network and the preset collision avoidance rule, and the control strategy is dynamically adjusted in the ship navigation process to effectively avoid the obstacle object are achieved.

Description

Technical Field

[0001] The present invention relates to the field of ship control technology, and in particular to a ship control method, device, equipment, medium and product. Background Art

[0002] In the field of modern shipping, intelligent control of ships has become one of the key technologies to improve shipping efficiency and safety.

[0003] Traditional ship control methods mainly rely on rule-based decision-making systems, such as collision avoidance rules. Although these systems can ensure safety to a certain extent, they often lack flexibility and cannot cope with complex marine environments and dynamically changing traffic conditions. Summary of the invention

[0004] The present invention provides a ship control method, device, equipment, medium and product to achieve the effect of determining ship control decisions by combining a strategy network and preset collision avoidance rules, and achieve the effect of dynamically adjusting the control strategy during the ship's navigation to effectively avoid obstacles.

[0005] According to one aspect of the present invention, a ship control method is provided, which is applied to a ship and comprises:

[0006] Obtaining the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed;

[0007] Inputting the ship observation information into a pre-trained ship control strategy network to obtain a control decision corresponding to the ship to be processed at the current moment; wherein the ship control strategy network is obtained by training the simulation interaction data between the ship simulation model and the neural network model including the strategy network based on a reinforcement learning algorithm;

[0008] In the case where there is an obstacle object associated with the ship to be processed at the current moment, determining the predicted ship position of the ship to be processed at a future moment according to the control decision and the ship speed; wherein the obstacle object is an object that the ship to be processed needs to avoid within a preset obstacle detection area corresponding to the ship to be processed;

[0009] In the case where it is determined that the predicted position of the ship is located in a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, the steps of determining the control decision and determining the predicted position of the ship are repeatedly executed until it is determined that the determined predicted position of the ship is not located in the target obstacle avoidance area, and a target control decision corresponding to the ship to be processed at the current moment is obtained, so as to control the ship to be processed based on the target control decision;

[0010] The target obstacle avoidance area is determined based on the ship observation information corresponding to the ship to be processed at the current moment.

[0011] According to another aspect of the present invention, there is provided a ship control device, which is configured in a ship and comprises:

[0012] An observation information acquisition module is used to acquire the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed;

[0013] A control decision determination module, used for inputting the ship observation information into a pre-trained ship control strategy network to obtain a control decision corresponding to the ship to be processed at the current moment; wherein the ship control strategy network is obtained by training the simulation interaction data between the ship simulation model and the neural network model including the strategy network based on a reinforcement learning algorithm;

[0014] A ship predicted position determination module is used to determine the ship predicted position of the ship to be processed at a future time according to the control decision and the ship speed when there is an obstacle object associated with the ship to be processed at the current time; wherein the obstacle object is an object that the ship to be processed needs to avoid within a preset obstacle detection area corresponding to the ship to be processed;

[0015] A ship control module is used to repeatedly execute the steps of determining the control decision and determining the predicted position of the ship when it is determined that the predicted position of the ship is within a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, until it is determined that the determined predicted position of the ship is not within the target obstacle avoidance area, and obtain the target control decision corresponding to the ship to be processed at the current moment, so as to control the ship to be processed based on the target control decision; wherein the target obstacle avoidance area is determined based on the ship observation information corresponding to the ship to be processed at the current moment.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the ship control method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the ship control method described in any embodiment of the present invention when executed.

[0021] According to another aspect of the present invention, a computer program product is provided. The computer program product comprises a computer program. When the computer program is executed by a processor, the ship control method according to any embodiment of the present invention is implemented.

[0022] The technical solution of the embodiment of the present invention is to obtain the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed; further, the ship observation information is input into the pre-trained ship control strategy network to obtain the control decision corresponding to the ship to be processed at the current moment; in the case that there is an obstacle object corresponding to the ship to be processed at the current moment, the ship predicted position of the ship to be processed at the future moment is determined according to the control decision and the ship speed; further, in the case that it is determined that the predicted ship position is located in a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, the steps of determining the control decision and determining the predicted ship position are repeated until the determined predicted ship position is determined. The target control decision corresponding to the ship to be processed at the current moment is obtained when the ship is not located in the target obstacle avoidance area, so as to control the ship to be processed based on the target control decision, thereby solving the problem that the ship control method in the related technology lacks flexibility and cannot cope with the complex marine environment and dynamically changing traffic conditions, and realizes the effect of determining the ship control decision by combining the strategy network and the preset collision avoidance rules, and realizes the effect of dynamically adjusting the control strategy during the navigation process of the ship to effectively avoid obstacles, thereby improving the intelligence of the ship control, enhancing the safety and adaptability of the ship, and effectively improving the collision avoidance effect of the ship, which can achieve the effect of improving the collision avoidance efficiency of the ship on the basis of reducing the collision avoidance cost of the ship, and the application of the strategy network for ship control can make the ship adapt to different navigation scenarios and navigation mission requirements, thereby improving the universality of the ship control method.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of a ship control method provided according to Embodiment 1 of the present invention;

[0026] Figure 2 is a flow chart of a ship control method provided according to Embodiment 2 of the present invention;

[0027] Figure 3 is a schematic diagram of an initial obstacle avoidance area provided according to the second embodiment of the present invention;

[0028] Figure 4 is a structural schematic diagram of a ship control device provided according to Embodiment 3 of the present invention;

[0029] Figure 5 It is a schematic diagram of the structure of an electronic device for implementing the ship control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 This is a flow chart of a ship control method provided by the first embodiment of the present invention. This embodiment is applicable to the case of controlling the navigation of a ship during navigation. The method can be executed by a ship control device. The ship control device can be implemented in the form of hardware and / or software. The ship control device can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0034] S110. Obtain ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed.

[0035] Among them, the ship to be processed may be a ship currently sailing. The ship to be processed may be any type of ship, and may optionally be an unmanned ship, an autonomous ship including an autonomous driving function, and an ordinary ship without an autonomous driving function. The current moment may be any moment during the navigation process of the ship to be processed. The ship observation information may be used to characterize the state of the ship and its surrounding environment. The ship observation information may include multiple pieces of information associated with the ship to be processed, and optionally, the ship observation information may include at least the ship position and navigation status information of the ship to be processed. The ship position may be used to indicate the location of the ship to be processed at the current moment. The ship position may be any form of position information, and may optionally be latitude and longitude coordinates and / or spatial coordinates. The navigation status information may be understood as information characterizing the specific navigation conditions of the ship during navigation. The navigation status information may include a variety of information characterizing the navigation conditions of the ship, and may optionally include at least the ship speed and the ship heading angle. The ship speed is the navigation speed of the ship during navigation. The heading angle of a ship usually refers to the angle between the line connecting the center of gravity of the ship and the bow (or the longitudinal midsection of the ship) and an axis (such as the earth's meridian or X-axis) in a fixed coordinate system (such as a geographic coordinate system or a navigation coordinate system) during the voyage. The heading angle of a ship is used to describe the direction of a ship's navigation on the horizontal plane. The heading angle of a ship is measured in a clockwise direction with the geographic north direction (or a specified starting direction) as the starting point. Its definition domain is usually 0° to 360°, where 0° represents the due north direction, 90° represents the due east direction, 180° represents the due south direction, and 270° represents the due west direction.

[0036] It should be noted that, in addition to the ship position and navigation status information, the ship observation information may also include the object position corresponding to the obstacle object associated with the ship to be processed at the current moment. It can be understood that during the voyage at sea, the ship may encounter an obstacle object that is close to the ship. At this time, in order to enable the ship to be processed to effectively avoid the obstacle object, the object position corresponding to the obstacle object at the current moment can be used as the ship observation information, so that the ship to be processed can make a decision based on the ship observation information. Based on this, the ship observation information corresponding to the ship to be processed at the current moment may include at least two situations: there is no obstacle object associated with the ship to be processed; there is an obstacle object associated with the ship to be processed.

[0037] Furthermore, there are multiple ways to obtain the ship observation information, including, optionally, obtaining the information through a sensor disposed on the ship to be processed, or obtaining the information through a control terminal associated with the ship to be processed, etc.

[0038] Optionally, ship observation information corresponding to the ship to be processed at the current moment is obtained, including: when there is no obstacle object associated with the ship to be processed at the current moment, the ship position and navigation status information corresponding to the ship to be processed at the current moment is obtained, and the ship position and navigation status information are used as the ship observation information corresponding to the ship to be processed at the current moment.

[0039] Among them, the obstacle object may be an object that the ship to be processed needs to avoid within the preset obstacle detection area corresponding to the ship to be processed. Optionally, the obstacle object includes a static obstacle object (for example, a static obstacle at sea, such as an island or reef, etc.) and / or a dynamic obstacle object (for example, other ships, etc.). The preset obstacle detection area may be an area constructed with the ship to be processed as the center and a preset detection distance as the radius, and the area is the area that can be covered by the obstacle detection device corresponding to the ship to be processed. In general, an obstacle detection device corresponding to the ship to be processed may be set, and a preset detection distance corresponding to the obstacle detection device may be determined. Furthermore, during the navigation process of the ship to be processed, a detection area may be constructed with the ship to be processed as the center and a preset detection distance as the radius to detect obstacle objects within the detection area, and the detection area may be used as a preset obstacle detection area.

[0040] As an optional implementation of this embodiment, during the navigation process of the ship to be processed, if no obstacle object is detected within the preset obstacle detection area corresponding to the ship to be processed at the current moment, the ship position and navigation status information corresponding to the ship to be processed at the current moment can be obtained through the sensors pre-set on the ship to be processed. Furthermore, the obtained ship position and navigation status information can be used as the ship observation information corresponding to the ship to be processed at the current moment.

[0041] Optionally, the ship observation information corresponding to the ship to be processed at the current moment is obtained, including: when there is an obstacle object associated with the ship to be processed at the current moment, the ship position and navigation status information corresponding to the ship to be processed at the current moment and the object position corresponding to the obstacle object at the current moment are obtained, and the ship position, navigation status information and object position are used as the ship observation information corresponding to the ship to be processed at the current moment.

[0042] The object position can be used to indicate the location of the obstacle object at the current moment. The object position can be any form of position information, and optionally, can be latitude and longitude coordinates and / or spatial coordinates.

[0043] It should be noted that the number of obstacle objects associated with the ship to be processed may be one or more. When the number of obstacle objects is one, the object position corresponding to the obstacle object can be obtained, and the ship position, navigation status information and the object position are used as the ship observation information of the ship to be processed; when the number of obstacle objects is multiple, the object position corresponding to each obstacle object can be obtained, and the ship position, navigation status information and multiple object positions are used as the ship observation information of the ship to be processed.

[0044] As another optional implementation of this embodiment, during the navigation process of the ship to be processed, if an obstacle object is detected within the preset obstacle detection area corresponding to the ship to be processed at the current moment, the ship position and navigation state information corresponding to the ship to be processed at the current moment and the object position corresponding to the obstacle object at the current moment can be obtained through the sensors pre-set on the ship to be processed. Furthermore, the obtained ship position, navigation state information and object position can be used as the ship observation information corresponding to the ship to be processed at the current moment.

[0045] The sensors may include a global positioning system (GPS), an automatic identification system (AIS), and a radar detection system.

[0046] S120, inputting the ship observation information into the pre-trained ship control strategy network to obtain the corresponding control decision of the ship to be processed at the current moment.

[0047] Among them, the ship control strategy network is obtained by training the simulation interaction data between the ship simulation model and the neural network model including the strategy network based on the reinforcement learning algorithm.

[0048] Among them, the ship control strategy network can be a neural network model that takes the ship observation information corresponding to the ship at the current moment as an input object to determine the control decision corresponding to the ship at the current moment based on the input object. The ship control strategy network can be a strategy network obtained by training the second neural network model based on the reinforcement learning algorithm. It can be understood that the strategy network can be a deep neural network model that deploys a strategy function, and its corresponding input object can be the state information of the environment in which the agent is located, and its corresponding output object can be a decision action determined according to the input state. In this embodiment, the input object corresponding to the ship control strategy network can be the ship observation information corresponding to the ship to be processed at the current moment, and its corresponding output object is the control decision determined according to the input ship observation information. The ship control strategy network can be a deep neural network model of any model structure. The model structure of the ship control strategy network is not limited here, and can be customized according to actual needs. Exemplarily, the ship control strategy network includes at least a residual network (Residual Network, Res-Net), a Transformer model and a recurrent neural network (Recurrent Neural Network, RNN). The control decision can be understood as a decision action made for the ship observation information corresponding to the current moment in order to achieve a preset goal. The control decision can be used to indicate the actions that need to be taken by the ship to be processed at the current time in order to achieve the preset target. The preset target can be to avoid obstacles encountered in the process of reaching the target destination. Optionally, the control decision includes at least one of the degree of left turn, the degree of right turn, the number of acceleration knots and the number of deceleration knots. Exemplarily, the control decision corresponding to the ship to be processed at the current time can be to accelerate by 5 knots. Or, the control decision corresponding to the ship to be processed at the current time can be to turn left by 15 degrees.

[0049] It should be noted that, during the navigation process of the ship to be processed, the information included in the ship observation information corresponding to the ship to be processed at each moment is determined based on whether there is an obstacle object associated with the ship to be processed at that moment, that is, the information included in the ship observation information corresponding to the ship to be processed at each moment is dynamically changing, that is, except for the ship position and navigation status information corresponding to the ship to be processed at each moment, which are fixed information in the ship observation information, the object position in the ship observation information changes dynamically according to the number of obstacle objects.

[0050] In this embodiment, the ship control strategy network is obtained by training the simulated interaction data between the ship simulation model and the neural network model including the strategy network based on the reinforcement learning algorithm. Before applying the ship control strategy network provided by this embodiment, the pre-constructed neural network model can be trained in a supervised or unsupervised manner. Before training the model, multiple training samples can be constructed to train the model based on the multiple training samples. Optionally, the training process of the ship control strategy network can be: extract multiple training samples from a pre-constructed experience playback pool, wherein the training samples include the first simulation state information at a historical moment, the first ship control decision and its corresponding probability information, advantage parameters and expected value parameters; the first ship control decision is used to control the simulated ship model to avoid collision with obstacles in the process of reaching the target destination; the training samples are constructed based on the simulation interaction data between the ship simulation model and the first neural network model; for multiple training samples, the first simulation state information at a historical moment in the training samples is respectively input into the value network and the strategy network in the second neural network model to obtain the actual value parameters corresponding to the value network and the second ship control strategy corresponding to the strategy network; according to the actual value parameters and the expected value parameters, determine the first loss value, and modify the model parameters in the value network based on the first loss value; and, according to the second ship control strategy, the first ship control decision and its corresponding probability information and advantage parameters, determine the second loss value, and modify the model parameters in the strategy network based on the second loss value, until the training ends when the preset convergence condition corresponding to the strategy network is reached, and the ship control strategy network is obtained. Wherein, the first neural network model can be a neural network model applied to the simulation interaction process, which is used to generate simulation interaction data. The second neural network model can be a neural network model in a model training process or a reinforcement learning process. The second neural network model has the same model structure as the first neural network model, but the basis for correcting the model parameters is inconsistent. In other words, the first neural network model is a neural network model used to simulate the simulation environment model and to interact with the ship simulation model, and is a neural network model in the interaction process; the basis for correcting the model parameters of the first neural network model is the second neural network model, that is, the model parameters in the first neural network model are synchronized according to the model parameters in the second neural network model at every preset period, thereby realizing distributed training. The second neural network model is applied to the reinforcement learning stage, that is, the second neural network model is trained based on the reinforcement learning algorithm to obtain a trained ship control strategy network; the basis for correcting the model parameters of the second neural network model is the loss value. The second neural network model includes a value network and a strategy network.

[0051] It should also be noted that the ship control strategy network can be deployed in the ship to be processed, or can be deployed in a control terminal associated with the ship to be processed. Preferably, the ship control strategy network can be deployed in the ship to be processed.

[0052] As an optional implementation mode of this embodiment, when the ship observation information corresponding to the ship to be processed at the current moment is obtained, the acquired ship observation information can be input into the ship control strategy network deployed in the ship to be processed, and the control decision corresponding to the ship to be processed at the current moment can be obtained.

[0053] S130: When there is an obstacle object associated with the ship to be processed at the current moment, determine the predicted ship position of the ship to be processed at a future moment according to the control decision and the ship speed.

[0054] The future time may be a time after a preset time from the current time. The preset time may be any time, such as 5 minutes, 10 minutes or 30 minutes. The predicted position of the ship may be the predicted position of the ship to be processed at the future time.

[0055] In this embodiment, when there is an obstacle object associated with the ship to be processed at the current moment, in order to ensure that the final control decision can enable the ship to be processed to avoid the obstacle object, the effectiveness of the control decision can be tested when the control decision is obtained, and the effectiveness of the control decision can be tested by predicting the position of the ship at a future moment according to the control decision. The advantage of this setting is that the control decision is effectively combined with the ship collision avoidance rules, so that the ship can identify and effectively avoid the obstacle object in real time, optimize the navigation path, and reduce the risk of ship collision.

[0056] In this embodiment, there are multiple ways to determine the predicted position of the ship, including, optionally, determining the predicted position of the ship based on the control decision and the ship speed based on a pre-trained position prediction model; or, determining the predicted position of the ship based on the control decision and the ship speed based on the position prediction algorithm, etc.

[0057] Optionally, the predicted ship position of the ship to be processed at a future time is determined based on the control decision and the ship speed, including: processing the control decision and the ship speed according to a pre-trained position prediction model to predict the predicted ship position of the ship to be processed at a future time.

[0058] The position prediction model may be a neural network model that takes the control decision and the ship speed as input objects to predict the ship's position at a future time based on the input objects. The position prediction model may be a neural network model of any model structure that can predict the ship's position at a future time. The model structure of the position prediction model is not limited here, and can be customized according to actual needs.

[0059] In this embodiment, the position prediction model can be obtained by training a deep learning model based on sample decisions, sample ship speeds, and expected ship positions at future times. Before applying the position prediction model provided by this embodiment, the pre-constructed deep learning model can be trained in a supervised or unsupervised manner. Before training the model, multiple training samples can be constructed to train the model based on the multiple training samples.

[0060] As an optional implementation of this embodiment, after the position prediction model is trained, the position prediction model can be deployed in the ship to be processed. Further, when it is determined that there is an obstacle object associated with the ship to be processed at the current moment and a control decision is obtained, the obtained control decision and the ship speed can be input into the position prediction model. Further, the ship position prediction can be performed on the control decision and the ship speed based on the position prediction model to obtain the predicted ship position of the ship to be processed at a future moment.

[0061] S140. When it is determined that the predicted position of the ship is within a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, the steps of determining the control decision and determining the predicted position of the ship are repeated until it is determined that the determined predicted position of the ship is not within the target obstacle avoidance area, and the target control decision corresponding to the ship to be processed at the current moment is obtained, so as to control the ship to be processed based on the target control decision.

[0062] Among them, the target obstacle avoidance area can be understood as the area where the ship to be processed needs to avoid the obstacle object, that is, the ship to be processed may collide with the obstacle object in this target collision avoidance area. The target obstacle avoidance area is determined based on the ship observation information corresponding to the ship to be processed. That is to say, when there is an obstacle object associated with the ship to be processed at the current moment, the ship observation information includes the ship position, navigation status information and the object position of the obstacle object, and then, the target obstacle avoidance area can be determined based on the ship position, navigation status information and the object position of the obstacle object. The target obstacle avoidance area can be corresponding to the obstacle object, the number of target obstacle avoidance areas can be consistent with the number of existing obstacle objects, and different obstacle objects can correspond to different target obstacle avoidance areas. The target control decision can be a control decision based on which the predicted position of the ship is determined when the predicted position of the ship is not located in the target obstacle avoidance area.

[0063] As an optional implementation of this embodiment, when it is determined that there is an obstacle object associated with the ship to be processed at the current moment, the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment can be determined based on the ship position, navigation status information and object position of the obstacle object corresponding to the ship to be processed at the current moment. Further, when the predicted ship position of the ship to be processed at a future moment is obtained, the predicted ship position can be compared with the target obstacle avoidance area. Further, when it is determined that the predicted ship position is within the target obstacle avoidance area, the steps of determining the control decision and determining the predicted ship position can be repeated until the determined predicted ship position is not within the target obstacle avoidance area. Further, when it is determined that the predicted ship position is not within the target obstacle avoidance area, the control decision based on which the predicted ship position is determined can be used as the target control decision corresponding to the ship to be processed at the current moment. Thereby, the ship to be processed can be controlled based on the target control decision.

[0064] In this embodiment, when there is no obstacle object associated with the ship to be processed at the current moment, it is not necessary to determine the predicted position of the ship at the future moment, and the control decision output by the ship control network can be directly used as the target control decision corresponding to the ship to be processed at the current moment. Then, the ship to be processed can be controlled based on the target control decision.

[0065] It should be noted that there are at least two ways to control the ship to be processed based on the target control decision, optionally including directly controlling the ship to be processed based on the target control decision; and / or using the target control decision as a reference control decision so that the user controls the ship to be processed based on the reference control decision.

[0066] Optionally, controlling the ship to be processed based on the target control decision includes: generating a ship control instruction based on the target control decision, and controlling the ship to be processed based on the ship control instruction.

[0067] The ship control instructions may generally refer to a series of instructions for manipulating and controlling the movement of the ship. Optionally, the ship control instructions include propulsion control instructions and / or rudder angle control instructions.

[0068] As an optional implementation of this embodiment, when the target control decision corresponding to the ship to be processed at the current moment is obtained, the target control decision can be parsed to convert the target control decision into a ship control instruction. Further, when the ship control instruction is obtained, the ship control instruction can be sent to the execution structure such as the propulsion system and the rudder system of the ship to be processed to control the ship to be processed.

[0069] Optionally, controlling the ship to be processed based on the target control decision includes: displaying the target control decision on the target interface so that the user can input a ship control instruction according to the target control decision, and controlling the ship to be processed based on the ship control instruction.

[0070] The target interface may be understood as an interface included in the local terminal of the ship, or an interface included in the control terminal of the ship, or a display interface of a user terminal associated with the ship, etc. The user may be the object of controlling the ship.

[0071] As another optional implementation of this embodiment, when the target control decision corresponding to the ship to be processed at the current moment is obtained, the target control decision can be displayed on the target interface. Furthermore, the user can use the displayed target control decision as a reference for instructions to determine the ship control instruction according to the target control decision, and input the determined ship control instruction into the ship to be processed. Furthermore, when the ship to be processed receives the ship control instruction, the ship control instruction can be sent to the execution structure such as the propulsion system and rudder system of the ship to be processed to control the ship to be processed.

[0072] The technical solution of the embodiment of the present invention is to obtain the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed; further, the ship observation information is input into the pre-trained ship control strategy network to obtain the control decision corresponding to the ship to be processed at the current moment; in the case that there is an obstacle object corresponding to the ship to be processed at the current moment, the ship predicted position of the ship to be processed at the future moment is determined according to the control decision and the ship speed; further, in the case that it is determined that the predicted ship position is located in a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, the steps of determining the control decision and determining the predicted ship position are repeated until the determined predicted ship position is determined. The target control decision corresponding to the ship to be processed at the current moment is obtained when the ship is not located in the target obstacle avoidance area, so as to control the ship to be processed based on the target control decision, thereby solving the problem that the ship control method in the related technology lacks flexibility and cannot cope with the complex marine environment and dynamically changing traffic conditions, and realizes the effect of determining the ship control decision by combining the strategy network and the preset collision avoidance rules, and realizes the effect of dynamically adjusting the control strategy during the navigation process of the ship to effectively avoid obstacles, thereby improving the intelligence of the ship control, enhancing the safety and adaptability of the ship, and effectively improving the collision avoidance effect of the ship, which can achieve the effect of improving the collision avoidance efficiency of the ship on the basis of reducing the collision avoidance cost of the ship, and the application of the strategy network for ship control can make the ship adapt to different navigation scenarios and navigation mission requirements, thereby improving the universality of the ship control method.

[0073] Embodiment 2

[0074] Figure 2 This is a flow chart of a ship control method provided by Embodiment 2 of the present invention. Based on the above embodiment, before determining whether the predicted position of the ship is within the target obstacle avoidance area, the target obstacle avoidance area can be determined based on the ship observation information corresponding to the ship to be processed at the current moment. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or similar to the above embodiment are not repeated here.

[0075] like Figure 2 As shown, the method includes:

[0076] S210. Obtain the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed; the ship observation information also includes the object position corresponding to the obstacle object corresponding to the ship to be processed at the current moment; the navigation status information includes the heading angle.

[0077] S220, inputting the ship observation information into the pre-trained ship control strategy network to obtain the corresponding control decision of the ship to be processed at the current moment.

[0078] S230: When there is an obstacle object corresponding to the ship to be processed at the current moment, determine the predicted ship position of the ship to be processed at a future moment according to the control decision and the ship speed.

[0079] S240: Determine the azimuth of the ship to be processed relative to the obstacle object according to the ship position, the heading angle and the object position.

[0080] The azimuth can be understood as a measure of the relative relationship between the ship and the obstacle. Specifically, the azimuth represents the angle between the line from the ship's location to the obstacle and a fixed direction (such as the north direction). For example, if the obstacle is located northeast of the ship to be processed, the azimuth of the ship to be processed relative to the obstacle can be the angle between the northeast direction and the north direction.

[0081] As an optional implementation of this embodiment, for at least one obstacle object associated with the ship to be processed at the current moment, when the ship position and heading angle corresponding to the ship to be processed at the current moment and the object position corresponding to the obstacle object at the current moment are obtained, the ship position, heading angle and object position can be processed according to a preset direction angle determination algorithm to obtain the azimuth of the ship to be processed relative to the obstacle object. Furthermore, the azimuth of the ship to be processed relative to each obstacle object can be obtained.

[0082] S250: Determine an initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object according to the ship position and the object position.

[0083] The initial obstacle avoidance area may be a default obstacle avoidance area determined when an obstacle object is determined to exist. The initial obstacle avoidance area is only associated with the ship position and the object position; the area angle associated in the initial obstacle avoidance area is uniformly set and has no association with the ship to be processed and the obstacle object, that is, for each obstacle object, the area size of the initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object is the same.

[0084] Optionally, an initial obstacle avoidance area for the ship to be processed relative to the obstacle object is determined based on the ship position and the object position, including: determining the center radius of the area based on the ship position and the object position; taking the ship position as the center point, rotating the center radius of the area along a first direction around the center point by a first preset angle to obtain a first area boundary, and rotating the center radius of the area along a second direction around the center point by a second preset angle to obtain a second area boundary; determining the endpoint distance between a first boundary endpoint excluding the center point in the first area boundary and a second boundary endpoint excluding the center point in the second area boundary; and constructing an initial obstacle avoidance area for the ship to be processed relative to the obstacle object based on the first area boundary, the second area boundary and the endpoint distance.

[0085] Among them, the area center radius can be the area radius of the initial obstacle avoidance area finally determined. The center point can be a rotation center point, that is, the rotation is performed with the point as the center. The first direction can be any rotation direction, and optionally, it is counterclockwise or clockwise. The first preset angle can be any angle, and optionally, it is 15°. The first area boundary can be the center radius obtained by rotating the area center radius around the center point along the first direction by a first preset angle. The second direction can be the direction opposite to the first direction. Optionally, when the first direction is counterclockwise, the second direction can be clockwise; when the first direction is clockwise, the second direction can be counterclockwise. The second preset angle can be any angle, and optionally, it is 15°. The second area boundary can be the center radius obtained by rotating the area center radius around the center point along the second direction by a second preset angle. The connecting line segment can be a straight line segment, an arc line segment, or other forms of connecting line segments.

[0086] As an optional implementation of this embodiment, the ship position and the object position can be used as endpoints, and the straight-line distance between the two endpoints can be used as the center radius of the area. Further, the ship position can be used as the center point, and the center radius of the area can be rotated around the center point along the first direction by a first preset angle, and the first area boundary can be obtained, and the first area boundary can be a line segment with the center point as one of the endpoints. And, the center radius of the area can be rotated around the center point along the second direction by a second preset angle, and the second area boundary can be obtained, and the second area boundary can be a line segment with the center point as one of the endpoints. Further, another endpoint other than the center point in the first area boundary can be determined, and the endpoint is used as the first boundary endpoint. And, another endpoint other than the center point in the second area boundary can be determined, and the endpoint is used as the second boundary endpoint. Afterwards, the connecting line segment between the first boundary endpoint and the second boundary endpoint can be determined, and the area constructed by the first area boundary, the second area boundary and the connecting line segment is used as the initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object.

[0087] For example, Figure 3 FIG. 1 is a schematic diagram of an initial obstacle avoidance area provided according to an embodiment of the present invention. Figure 3 As shown, point O is the center point, that is, the position of the ship; point A is the object position of obstacle object A; line segment 301 is the area center radius; line segment 302 is the first area boundary; line segment 303 is the second area boundary; line segment 303 is the connecting line segment; and furthermore, the area constructed by the first area boundary, the second area boundary and the connecting line segment is the initial obstacle avoidance area 30.

[0088] S260: Determine a target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment according to the initial obstacle avoidance area and the azimuth.

[0089] In this embodiment, after the initial obstacle avoidance area and azimuth are obtained, the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment can be determined according to the initial obstacle avoidance area and azimuth.

[0090] Optionally, a target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment is determined based on the initial obstacle avoidance area and the azimuth angle, including: taking the ship position as the center point, rotating the first area boundary along a first direction around the center point by an angle corresponding to the azimuth angle to obtain a first target area boundary, and rotating the second area boundary along a second direction around the center point by an angle corresponding to the azimuth angle to obtain a second target area boundary; updating the initial obstacle avoidance area based on the first target area boundary and the second target area boundary, and using the updated initial obstacle avoidance area as the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment.

[0091] As an optional implementation of this embodiment, the ship position can be used as the center point, and the first area boundary in the initial obstacle avoidance area can be rotated around the center point along the first direction by an angle corresponding to the azimuth, and the rotated first area boundary can be used as the first target area boundary. Also, the second area boundary in the initial obstacle avoidance area can be rotated around the center point along the second direction by an angle corresponding to the azimuth, and the rotated second area boundary can be used as the second target area boundary. Further, the initial obstacle avoidance area is updated according to the first target area boundary and the second target area boundary, so that the connecting line segment in the initial obstacle avoidance area is extended to connect the first target area boundary and the second target area boundary to obtain an updated initial obstacle avoidance area. Further, the updated initial obstacle avoidance area is used as the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment.

[0092] S270. When it is determined that the predicted position of the ship is within the predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, the steps of determining the control decision and determining the predicted position of the ship are repeated until it is determined that the determined predicted position of the ship is not within the target obstacle avoidance area, and the target control decision corresponding to the ship to be processed at the current moment is obtained, so as to control the ship to be processed based on the target control decision.

[0093] The technical solution of the embodiment of the present invention determines the azimuth of the ship to be processed relative to the obstacle object according to the ship position, heading angle and object position; and determines the initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object according to the ship position and the object position; further, determines the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment according to the initial obstacle avoidance area and the azimuth, thereby realizing the effect of determining the target obstacle avoidance area based on the acquired ship observation information, and then, performing ship obstacle avoidance detection based on the target obstacle avoidance area, realizing the effect of performing secondary detection on the control decision output by the strategy network based on the target obstacle avoidance area, ensuring that the ship can effectively avoid obstacles and improving the safety of ship navigation.

[0094] Embodiment 3

[0095] Figure 4 Schematic diagram of the structure of a ship control device provided by the third embodiment of the present invention. Figure 4 As shown, the device is configured in a ship, and includes: an observation information acquisition module 310, a control decision determination module 320, a ship predicted position determination module 330 and a ship control module 340.

[0096] Among them, the observation information acquisition module 310 is used to obtain the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed; the control decision determination module 320 is used to input the ship observation information into the pre-trained ship control strategy network to obtain the control decision corresponding to the ship to be processed at the current moment; wherein the ship control strategy network is obtained by training the simulation interaction data between the ship simulation model and the neural network model including the strategy network based on the reinforcement learning algorithm; the ship predicted position determination module 330 is used to, in the case where there is an obstacle object associated with the ship to be processed at the current moment, according to the control decision and the ship navigation The method comprises the steps of: quickly determining the predicted ship position of the ship to be processed at a future moment; wherein the obstacle object is an object that the ship to be processed needs to avoid within a preset obstacle detection area corresponding to the ship to be processed; and a ship control module 340, which is used to repeatedly execute the steps of determining the control decision and determining the predicted ship position when it is determined that the predicted ship position is within a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, until it is determined that the determined predicted ship position is not within the target obstacle avoidance area, and obtaining the target control decision corresponding to the ship to be processed at the current moment, so as to control the ship to be processed based on the target control decision; wherein the target obstacle avoidance area is determined based on the ship observation information corresponding to the ship to be processed at the current moment.

[0097] The technical solution of the embodiment of the present invention is to obtain the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed; further, the ship observation information is input into the pre-trained ship control strategy network to obtain the control decision corresponding to the ship to be processed at the current moment; in the case that there is an obstacle object corresponding to the ship to be processed at the current moment, the ship predicted position of the ship to be processed at the future moment is determined according to the control decision and the ship speed; further, in the case that it is determined that the predicted ship position is located in a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, the steps of determining the control decision and determining the predicted ship position are repeated until the determined predicted ship position is determined. The target control decision corresponding to the ship to be processed at the current moment is obtained when the ship is not located in the target obstacle avoidance area, so as to control the ship to be processed based on the target control decision, thereby solving the problem that the ship control method in the related technology lacks flexibility and cannot cope with the complex marine environment and dynamically changing traffic conditions, and realizes the effect of determining the ship control decision by combining the strategy network and the preset collision avoidance rules, and realizes the effect of dynamically adjusting the control strategy during the navigation process of the ship to effectively avoid obstacles, thereby improving the intelligence of the ship control, enhancing the safety and adaptability of the ship, and effectively improving the collision avoidance effect of the ship, which can achieve the effect of improving the collision avoidance efficiency of the ship on the basis of reducing the collision avoidance cost of the ship, and the application of the strategy network for ship control can make the ship adapt to different navigation scenarios and navigation mission requirements, thereby improving the universality of the ship control method.

[0098] Optionally, the ship observation information also includes the object position corresponding to the obstacle object corresponding to the ship to be processed at the current moment; the observation information acquisition module 310 includes: a first observation information acquisition unit or a second observation information acquisition unit. The first observation information acquisition unit is used to obtain the ship position and navigation status information corresponding to the ship to be processed at the current moment and the object position corresponding to the obstacle object at the current moment when there is an obstacle object associated with the ship to be processed at the current moment, and use the ship position, the navigation status information and the object position as the ship observation information corresponding to the ship to be processed at the current moment; or, the second observation information acquisition unit is used to obtain the ship position and navigation status information corresponding to the ship to be processed at the current moment when there is no obstacle object associated with the ship to be processed at the current moment, and use the ship position and the navigation status information as the ship observation information corresponding to the ship to be processed at the current moment.

[0099] Optionally, the ship observation information also includes the object position corresponding to the obstacle object associated with the ship to be processed at the current moment; the navigation status information includes the heading angle; the device also includes: an azimuth angle determination module, an initial obstacle avoidance area determination module and a target obstacle avoidance area determination module. Among them, the azimuth angle determination module is used to determine the azimuth angle of the ship to be processed relative to the obstacle object according to the ship position, the heading angle and the object position; and the initial obstacle avoidance area determination module is used to determine the initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object according to the ship position and the object position; the target obstacle avoidance area determination module is used to determine the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment according to the initial obstacle avoidance area and the azimuth angle.

[0100] Optionally, the initial obstacle avoidance area determination module includes: an area center radius determination unit, an area boundary determination unit, an endpoint distance determination unit and an initial obstacle avoidance area determination unit. Among them, the area center radius determination unit is used to determine the area center radius according to the ship position and the object position; the area boundary determination unit is used to take the ship position as the center point, rotate the area center radius along a first direction around the center point by a first preset angle to obtain a first area boundary, and rotate the area center radius along a second direction opposite to the first direction around the center point by a second preset angle to obtain a second area boundary; the connecting line segment determination unit is used to determine the connecting line segment between the first boundary endpoint excluding the center point in the first area boundary and the second boundary endpoint excluding the center point in the second area boundary; the initial obstacle avoidance area determination unit is used to construct the initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object according to the first area boundary, the second area boundary and the connecting line segment.

[0101] Optionally, the target obstacle avoidance area determination module includes: an area boundary determination unit and a target obstacle avoidance area determination unit. The area boundary determination unit is used to take the ship position as the center point, rotate the first area boundary along the first direction around the center point by the angle corresponding to the azimuth angle to obtain the first target area boundary, and rotate the second area boundary along the second direction around the center point by the angle corresponding to the azimuth angle to obtain the second target area boundary; the target obstacle avoidance area determination unit is used to update the initial obstacle avoidance area according to the first target area boundary and the second target area boundary, and use the updated initial obstacle avoidance area as the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment.

[0102] Optionally, the ship predicted position determination module 330 is specifically used to process the control decision and the ship speed according to a pre-trained position prediction model to predict the predicted ship position of the ship to be processed at a future moment.

[0103] Optionally, the ship control module 340 includes: an instruction generation unit and / or an instruction input unit. The instruction generation unit is used to generate a ship control instruction based on the target control decision, and control the ship to be processed based on the ship control instruction; and / or the instruction input unit is used to display the target control decision on the target interface so that the user can input the ship control instruction according to the target control decision, and control the ship to be processed based on the ship control instruction.

[0104] The ship control device provided in the embodiment of the present invention can execute the ship control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0105] Embodiment 4

[0106] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention 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 (such as helmets, glasses, watches, etc.) 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 invention described and / or required herein.

[0107] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0108] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0109] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a ship control method.

[0110] In some embodiments, the ship control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the ship control method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the ship control method in any other appropriate manner (e.g., by means of firmware).

[0111] 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.

[0112] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program 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.

[0113] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0114] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend 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 backend components, middleware components, or frontend 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), a target blockchain network, and the Internet.

[0116] A computing 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 client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0117] 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 described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0118] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A ship control method, characterized in that: Applied in ships, including: Obtaining the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed; Inputting the ship observation information into a pre-trained ship control strategy network to obtain a control decision corresponding to the ship to be processed at the current moment; wherein the ship control strategy network is obtained by training the simulation interaction data between the ship simulation model and the neural network model including the strategy network based on a reinforcement learning algorithm; In the case where there is an obstacle object associated with the ship to be processed at the current moment, determining the predicted ship position of the ship to be processed at a future moment according to the control decision and the ship speed; wherein the obstacle object is an object that the ship to be processed needs to avoid within a preset obstacle detection area corresponding to the ship to be processed; In the case where it is determined that the predicted position of the ship is located in a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, the steps of determining the control decision and determining the predicted position of the ship are repeatedly executed until it is determined that the determined predicted position of the ship is not located in the target obstacle avoidance area, and a target control decision corresponding to the ship to be processed at the current moment is obtained, so as to control the ship to be processed based on the target control decision; The target obstacle avoidance area is determined based on the ship observation information corresponding to the ship to be processed at the current moment.

2. The ship control method according to claim 1, characterized in that: The ship observation information also includes an object position corresponding to the obstacle object associated with the ship to be processed at the current moment; the obtaining of the ship observation information corresponding to the ship to be processed at the current moment includes: In the case where there is an obstacle object associated with the ship to be processed at the current moment, obtaining the ship position and navigation status information corresponding to the ship to be processed at the current moment and the object position corresponding to the obstacle object at the current moment, and using the ship position, the navigation status information and the object position as the ship observation information corresponding to the ship to be processed at the current moment; or, When there is no obstacle object associated with the ship to be processed at the current moment, the ship position and navigation status information corresponding to the ship to be processed at the current moment are obtained, and the ship position and the navigation status information are used as the ship observation information corresponding to the ship to be processed at the current moment.

3. The ship control method according to claim 1, characterized in that: The ship observation information also includes the object position corresponding to the obstacle object associated with the ship to be processed at the current moment; the navigation state information includes the heading angle; the method also includes: Determining the azimuth of the ship to be processed relative to the obstacle object according to the ship position, the heading angle and the object position; and Determine an initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object according to the ship position and the object position; A target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment is determined according to the initial obstacle avoidance area and the azimuth.

4. The ship control method according to claim 3, characterized in that: The step of determining an initial obstacle avoidance area of ​​the ship to be processed relative to the obstacle object according to the ship position and the object position includes: Determine the area center radius according to the ship position and the object position; Taking the position of the ship as the center point, rotating the center radius of the area along a first direction around the center point by a first preset angle to obtain a first area boundary, and rotating the center radius of the area along a second direction opposite to the first direction around the center point by a second preset angle to obtain a second area boundary; Determine a connecting line segment between a first boundary endpoint excluding the center point in the boundary of the first region and a second boundary endpoint excluding the center point in the boundary of the second region; An initial obstacle avoidance area for the ship to be processed relative to the obstacle object is constructed according to the first area boundary, the second area boundary and the connecting line segment.

5. The ship control method according to claim 4, characterized in that: The step of determining a target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment according to the initial obstacle avoidance area and the azimuth includes: Taking the ship position as the center point, rotating the first area boundary along the first direction around the center point by an angle corresponding to the azimuth angle to obtain a first target area boundary, and rotating the second area boundary along the second direction around the center point by an angle corresponding to the azimuth angle to obtain a second target area boundary; The initial obstacle avoidance area is updated according to the first target area boundary and the second target area boundary, and the updated initial obstacle avoidance area is used as the target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment.

6. The ship control method according to claim 1, characterized in that: The step of determining the predicted ship position of the ship to be processed at a future time according to the control decision and the ship speed includes: The control decision and the ship speed are processed according to a pre-trained position prediction model to predict the ship's predicted position at a future moment.

7. The ship control method according to claim 1, characterized in that: The controlling the ship to be processed based on the target control decision comprises: generating a ship control instruction based on the target control decision, and controlling the ship to be processed based on the ship control instruction; and / or, The target control decision is displayed on a target interface, so that a user can input a ship control instruction according to the target control decision, and control the ship to be processed based on the ship control instruction.

8. A ship control device, characterized in that: Configured in ships, including: An observation information acquisition module is used to acquire the ship observation information corresponding to the ship to be processed at the current moment; wherein the ship observation information at least includes the ship position and navigation status information of the ship to be processed; the navigation status information at least includes the ship speed; A control decision determination module, used for inputting the ship observation information into a pre-trained ship control strategy network to obtain a control decision corresponding to the ship to be processed at the current moment; wherein the ship control strategy network is obtained by training the simulation interaction data between the ship simulation model and the neural network model including the strategy network based on a reinforcement learning algorithm; A ship predicted position determination module is used to determine the ship predicted position of the ship to be processed at a future time according to the control decision and the ship speed when there is an obstacle object associated with the ship to be processed at the current time; wherein the obstacle object is an object that the ship to be processed needs to avoid within a preset obstacle detection area corresponding to the ship to be processed; A ship control module is used to repeatedly execute the steps of determining the control decision and determining the predicted position of the ship when it is determined that the predicted position of the ship is within a predetermined target obstacle avoidance area of ​​the ship to be processed relative to the obstacle object at the current moment, until it is determined that the determined predicted position of the ship is not within the target obstacle avoidance area, and obtain the target control decision corresponding to the ship to be processed at the current moment, so as to control the ship to be processed based on the target control decision; wherein the target obstacle avoidance area is determined based on the ship observation information corresponding to the ship to be processed at the current moment.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the ship control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the ship control method according to any one of claims 1 to 7 when executed.

Images