Unmanned ship obstacle avoidance control and wireless transmission method and system based on data fusion

Abstract

The application discloses an unmanned ship obstacle avoidance control and wireless transmission method and system based on data fusion, and belongs to the field of unmanned ship navigation and obstacle avoidance. The method comprises the following steps: S1, constructing an unmanned ship initialization dynamic model; S2, constructing a path navigation characteristic vector; S3, detecting sensors are arranged around the unmanned ship in a 360-degree full-coverage mode, and in the arrangement process, a dimension reduction mode is adopted, and the detecting sensors are arranged in a non-uniform distribution; and S4, formulating a collision avoidance decision, obtaining various information of obstacles through fusion, combining the conditions of the unmanned ship, and formulating a collision avoidance decision meeting the unmanned ship target and dynamic limitation. The technical scheme provided by the application effectively solves the problem that the unmanned ship cannot be accurately and efficiently navigated and obstacles avoided in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned ship navigation obstacle avoidance, and particularly relates to an unmanned ship obstacle avoidance control and wireless transmission method and system based on data fusion. BACKGROUND

[0002] In the process of autonomous water unmanned ship sailing, various factors need to be considered to ensure safe and efficient driving. In the marine environment, the unmanned ship faces various obstacles and needs to comply with international maritime collision avoidance rules. The traditional collision avoidance method may have certain limitations in complex dynamic environments, and may not be able to well consider the properties of obstacles and the actions required by international maritime collision avoidance rules, making it difficult to achieve the collision avoidance trajectory of the unmanned ship itself and adapt to its dynamic restrictions. SUMMARY

[0003] In view of the defects of the related art, the present application provides an unmanned ship obstacle avoidance control and wireless transmission method and system based on data fusion, aiming to solve the problem of inefficient and inaccurate collision avoidance of unmanned ships in the prior art.

[0004] The technical solution is as follows:

[0005] An unmanned ship obstacle avoidance control and wireless transmission method based on data fusion, comprising the following steps:

[0006] Step S1: Constructing an unmanned ship initialization dynamics model, constructing an unmanned ship initialization dynamics model by defining a coordinate frame, state space limit conditions, and ship driving environment limitations;

[0007] Step S2: Constructing a path navigation feature vector, defining a parameterized path representation, and setting path reference points based on the current unmanned ship position, Euclidean distance, forward path reference points, and path deviation, heading error, and path angle on the path to be navigated to represent the path navigation feature vector;

[0008] Step S3: Setting up a data acquisition and processing module, and equipping detection sensors around the unmanned ship in a 360-degree full coverage manner, and adopting dimension reduction during the equipping process, and setting the detection sensors in a non-uniform distribution;

[0009] Step S4: Making a collision avoidance decision, combining the situation of the unmanned ship, and making a collision avoidance decision that meets the unmanned ship's own target and dynamic restrictions by fusing various information of the obtained obstacles;

[0010] Step S5: Through the wireless data transmission module including the DTU unit and the Beidou client, the obstacle avoidance information and control instructions required in the process of unmanned ship driving are wirelessly communicated with other unmanned ships and the collaborative control center.

[0011] An unmanned ship obstacle avoidance control and wireless transmission system based on data fusion, the system comprises:

[0012] An unmanned ship obstacle avoidance control device and a cooperative control center;

[0013] The cooperative control center is arranged on a shore base, is used for being wirelessly connected with the unmanned ship, sending control instructions and wirelessly keeping the unmanned ship in an online state in real time, comprises a wireless communication module, the wireless communication module has a DTU unit and a Beidou client, and wireless radio or satellite signal communication is carried out with the unmanned ship obstacle avoidance control device through a 5G network or a Beidou satellite; when the 5G network is interrupted or fails within a certain time during the communication process, the Beidou satellite communication is switched to;

[0014] The unmanned ship obstacle avoidance control device comprises:

[0015] A dynamics model construction module is used for constructing an initial dynamics model of the unmanned ship, and the initial dynamics model of the unmanned ship is constructed by defining a coordinate frame, a state space limit condition and a ship running environment limit;

[0016] A path navigation feature vector construction module defines the representation of a parameterized path, and the path navigation feature vector is characterized by setting a path reference point based on the current unmanned ship position, a Euclidean distance, a forward path reference point and a path deviation, a heading error and a path angle which are constantly updated on the path to be navigated;

[0017] A data acquisition and processing module is equipped with detection sensors around the unmanned ship in a 360-degree full-coverage mode, and in the equipping process, the detection sensors are arranged in a non-uniform distribution by using a dimension reduction method;

[0018] A collision avoidance decision making module formulates a collision avoidance decision meeting the unmanned ship's own target and dynamically limited by fusing various information of the obtained obstacles and combining the unmanned ship's own conditions;

[0019] A wireless data transmission module comprises a DTU unit and a Beidou client, and is used for wirelessly communicating with other unmanned ships and the cooperative control center.

[0020] The present application has the following beneficial effects:

[0021] The unmanned ship obstacle avoidance control and wireless transmission method and system based on data fusion provided by the present application solve the problems of high-dimensional complex network data in the control process of the unmanned ship, slow control lag and slow reaction by a unique unmanned ship sensor arrangement method; the construction of the path navigation feature vector optimizes the through channel optimization problem caused by the minimum obstacle distance and the maximum obstacle distance; and accurate and efficient obstacle avoidance is realized by the collision avoidance control decision. Attached Figure Description

[0022] Figure 1 This is a flowchart of an obstacle avoidance control method for unmanned vessels based on data fusion, provided by an embodiment of the present invention.

[0023] Figure 2 This is a flowchart of the unmanned vessel dynamics model determination provided in an embodiment of the present invention;

[0024] Figure 3 This is a flowchart of the path navigation feature vector construction process provided in an embodiment of the present invention;

[0025] Figure 4 This is a flowchart illustrating the data acquisition module provided in this embodiment of the invention.

[0026] Figure 5 This is a flowchart of the collision avoidance decision-making process provided in an embodiment of the present invention;

[0027] Figure 6 This is a structural diagram of an unmanned surface vessel obstacle avoidance control and wireless transmission system based on data fusion, provided in an embodiment of the present invention.

[0028] Figure 7 This is a structural diagram of an unmanned surface vessel obstacle avoidance control device based on data fusion, provided in an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0030] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0031] SeeFigure 1 The application provides an unmanned ship obstacle avoidance control and wireless transmission method based on data fusion, comprising the following steps:

[0032] Step S1: constructing an unmanned ship initialization dynamics model, constructing the initialization dynamics model of the unmanned ship by defining a coordinate frame, state space limit conditions and ship driving environment limits;

[0033] Step S2: constructing a path navigation feature vector, defining a parameterized path representation, and representing the path navigation feature vector by setting path reference points based on the current unmanned ship position, Euclidean distance, forward path reference points and path deviation, heading error and path angle on the path to be navigated, which are constantly updated;

[0034] Step S3: setting up a data acquisition and processing module, and equipping the unmanned ship with detection sensors in a 360-degree full coverage manner, and adopting a dimension reduction method during the equipping process, and setting the detection sensors in a non-uniform distribution;

[0035] Step S4: making a collision avoidance decision, combining the conditions of the unmanned ship itself with various information obtained by fusing the obstacles to make a collision avoidance decision that meets the target of the unmanned ship and dynamically limits;

[0036] Step S5: transmitting the obstacle avoidance information and control instructions required during the driving of the unmanned ship to other unmanned ships and a collaborative control center through a wireless data transmission module including a DTU unit and a Beidou client.

[0037] Referring to Figure 2 Step S1: constructing an unmanned ship initialization dynamics model, constructing the initialization dynamics model of the unmanned ship by defining a coordinate frame, state space limit conditions and ship driving environment limits, specifically:

[0038] Step S11: defining that the unmanned ship is always located on the surface of the earth without up-and-down floating, pitching and rolling motion, so the coordinate frame of the environment in which the unmanned ship is located is which forms a tangent plane with the surface of the earth, wherein the axis points to the north, the axis points to the east, and the axis points to the center of the earth;

[0039] Step S12: defining the state vector of the unmanned ship , wherein and are the positions in the north and east directions of the coordinate frame of the environment, is the heading angle, that is, the angle between the longitudinal axis of the unmanned ship and the north axis; and the translation and angular velocity vectors consists of the forward velocity u, the lateral velocity h and the yaw rate r;

[0040] Step S13: The unmanned ship is equipped with a rudder and a propeller at the tail, and can freely move along any trajectory in the state space, and the control vector of the unmanned ship is wherein represents the torque input in the forward direction, represents the torque input in the yaw direction, and the initial dynamic model of the unmanned ship is represented as:

[0041] (1)

[0042] wherein , , are state space vectors of , i.e. ; is the mass matrix of the unmanned ship, which covers the rigid body effect and the added mass effect; is the centripetal force parameter matrix; is the damping matrix; B is the actuator configuration matrix, which belongs to the state space vector of ; represents the radian of rotation of along the axis.

[0043] Referring to Figure 3 , step S2: constructing a path navigation feature vector, defining the representation of the parameterized path, and representing the path navigation feature vector by setting a path reference point based on the current unmanned ship position constantly updated on the path to be navigated, a Euclidean distance, a forward path reference point, and a path deviation, a heading error and a path angle, which are specific to:

[0044] Step S21: defining the representation of the parameterized path as , wherein is a path variable, represents a path reference point, which is set to be a point on the right side of the unmanned ship and to generate a Euclidean distance with the unmanned ship, represents the coordinates of the path reference point, and correspondingly, a forward path reference point needs to be set, which is a point forward distance from the path reference point;

[0045] Step S22: when finding the path reference point , the corresponding value of the path variable at each time step needs to be calculated:

[0046] (3)

[0047] Define the path deviation between the desired path and the current trajectory as At the same time, define the heading error required for the unmanned ship to sail directly from the current position to the look-ahead path reference point , there is:

[0048] (4)

[0049] Further define the path angle , with the first-order path reciprocal as the reference, to ensure the smoothness of the trajectory of the unmanned ship when relying on the look-ahead path reference point, there is:

[0050] (5)

[0051] Step S23: construct the path navigation feature vector by combining the path variables calculated in the above steps , the corresponding value of each time step , the path deviation , the heading error , the path angle .

[0052] Referring to Figure 4 , step S3: set up a data acquisition and processing module to equip detection sensors around the unmanned ship in a 360-degree full coverage manner, and adopt dimension reduction in the equipping process to set the detection sensors in a non-uniform distribution, specifically:

[0053] Step S31: equip a ranging sensor as a detection sensor, the number of ranging sensors is N, and the maximum detection range is , equipped around the unmanned ship in a 360-degree full coverage manner;

[0054] In an embodiment provided by the present application, the ranging sensor can be a laser radar, a sonar, a depth camera, etc.

[0055] Although the area behind the unmanned ship is not very important for path planning and obstacle avoidance, and there is no need to consider the rear obstacles in pure static terrain navigation, in the present application, in order to consider various scenarios, such as the possibility of a moving obstacle approaching from the rear, the distance between the unmanned ship and the rear obstacle when the unmanned ship is about to overtake the obstacle and change the lane, etc., it is necessary to equip the ranging sensor around the unmanned ship in a 360-degree full coverage manner;

[0056] ​In the process of navigation obstacle avoidance experiment, it is found that the control information input into the unmanned ship is large in the process of fusing the path information feature vector with the output data of the ranging sensor, resulting in high-dimensional complex network data, causing control delay, slow response, and even if the number of ranging sensors is reduced, the same problem exists. If the number of ranging sensors is too small, the accuracy of obstacle detection is reduced; therefore, the data of the ranging sensor needs to be processed in the following manner;

[0057] Step S32: The 360-degree full-coverage ranging sensor is divided into D groups, and each group generates a scalar detection value, which is included in the final observation vector;

[0058] Since it is desired to minimize the data dimension input into the unmanned ship, uniformly dividing the ranging sensors into groups of the same size cannot meet the optimal way. Obstacles in front of the unmanned ship are more critical in the actual navigation obstacle avoidance process than obstacles behind the ship, and require higher perception accuracy, so non-uniform division processing needs to be performed in the following steps;

[0059] Step S33: Define the ranging sensors and groups from the rear of the unmanned ship in a counterclockwise and clockwise manner, and use the following formula for sorting:

[0060] (2)

[0061] wherein, is a nonlinear mapping part, is a constant offset part; map the given sensor index to the group index , wherein is a logical function ; is a scaling parameter for controlling the density of the distribution of the group, and the group near the front of the unmanned ship is the narrowest; at the same time, define the distance measurement vector measured by the ranging sensors in the first group as ;

[0062] For the selection of the measurement standard value of a group, the minimum obstacle distance is usually selected to represent, which is a conservative and safe value, but this selection may be too restrictive in some scenarios, resulting in the passage between obstacles being ignored, or the maximum obstacle distance is selected to represent the presence of small obstacles, which may cause danger in some scenarios; The present application considers the position of the ranging sensor reading and the width of the unmanned ship, calculates the maximum distance that each group of sensors can reach, and iterates the ranging sensor data in ascending order corresponding to the ranging sensor, checks whether the ship can pass at each distance level obtained, thereby optimizing the problems brought by the minimum obstacle distance and the maximum obstacle distance, the specific process is as follows:

[0063] Step S34: define the width of the unmanned ship as W, the included angle between adjacent ranging sensors of the 360-degree full-coverage ranging sensor as , and the measurement value of a ranging sensor in a group as , the ascending order of the measurement value x is arranged to form an index set I, then the arc length between adjacent ranging sensors is calculated for each index, the initial opening width that can pass between obstacles is set based on half of the arc length, and a loop from 0 to n is performed to traverse all ranging sensor readings, when a certain opening j is found to have a width greater than the current opening width, the opening width is updated to the value of the current opening width plus the radian corresponding to the opening width of the opening j, if the updated opening width is greater than the width W of the unmanned ship, a flag true is attached to the opening, and the loop is exited, if the updated opening width is not greater than the width W of the unmanned ship, the opening width is updated to the value of the current opening width plus half of the radian corresponding to the opening width of the opening j, and the above process is repeated to loop through; Select all openings with the flag true as potential passage options, if there is no opening with the flag true, it indicates that it cannot pass;

[0064] Referring to Figure 5 , step S4: making a collision avoidance decision, by fusing various information of the obtained obstacles, combining the situation of the unmanned ship itself, making a collision avoidance decision that meets the target of the unmanned ship itself and dynamically limits, specifically:

[0065] Step S41: simplify the dynamics model of the unmanned ship in step S1, define the dynamics model as , the vector represents the input caused by environmental disturbance; the vector is the control input , is a constant parameter, the estimated state and disturbance are used to track the reference speed , then the dynamics model can be represented as ; by integrating over a short time horizon using a number of discrete sampling times determined by the discretization interval achieved based on the dynamic model ; the predicted positions are used to calculate the predicted distances between the unmanned ship and each obstacle , respectively represent the position of the unmanned ship and the position of the obstacle;

[0066] Step S42: control the deviation from the preferred speed, define the candidate speed set as , where is a set of speed grid points selected according to a fixed offset from the preferred speed of the unmanned ship; the speed set is the reference speed set that satisfies the optimization condition;

[0067] Step S43: reduce the control instructions with large speed changes, define the objective function to discard those instructions that result in large speed changes, the objective function is:

[0068] (6)

[0069] where , , , and are the corresponding empirical coefficients, is the preferred speed of the unmanned ship, is the preferred heading of the unmanned ship, is the last speed of the unmanned ship, is the last heading of the unmanned ship, is a time-dependent variable that evaluates the time-varying responsibility of the unmanned ship in the collision process.

[0070] Referring to Figure 6 , the present application provides an unmanned ship obstacle avoidance control and wireless transmission system based on data fusion, for realizing the unmanned ship obstacle avoidance control and wireless transmission method based on data fusion, the system comprises:

[0071] an unmanned ship obstacle avoidance control device 100 and a cooperative control center 200;

[0072] ​​The cooperative control center 200 is arranged on the shore base, is used for wireless communication connection with the unmanned ship, sends control instruction and wireless real-time keeps the unmanned ship online state; including wireless communication module 201, the wireless communication module 201 has DTU unit and beidou client, through 5G network or beidou satellite and unmanned ship barrier control device 100 carry out radio or satellite signal communication, when 5G network is interrupted or appears fault in a certain time during communication process, switch to beidou satellite communication.

[0073] Referring to Figure 7 The unmanned ship barrier control device 100 includes:

[0074] The dynamic model construction module 101 is used for constructing the initialization dynamic model of the unmanned ship, and constructs the initialization dynamic model of the unmanned ship by defining the coordinate frame, the state space limit condition and the ship running environment limit;

[0075] The path navigation feature vector construction module 102 defines the representation of the parameterized path, and represents the path navigation feature vector by setting the path reference point based on the current unmanned ship position, the Euclidean distance, the forward path reference point and the path deviation, the heading error and the path angle constantly updated on the path needing navigation;

[0076] The data acquisition and processing module 103 is equipped with detection sensors around the unmanned ship in a 360-degree full-coverage manner, and the detection sensors are arranged in a non-uniform distribution in a dimension reduction manner during the equipping process;

[0077] The collision avoidance decision making module 104 formulates the collision avoidance decision meeting the unmanned ship's own target and dynamically limited by fusing various information of the obtained obstacles and combining the condition of the unmanned ship itself;

[0078] The wireless data transmission module 105 includes the DTU unit and the beidou client, and is used for wireless communication with other unmanned ships and the cooperative control center.

[0079] Those skilled in the art can easily understand that the above description is only the preferred embodiment of the present application, and is not used to limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for obstacle avoidance control and wireless transmission of unmanned surface vessels based on data fusion, characterized in that, Includes the following steps: Step S1: Construct the initial dynamic model of the unmanned vessel by defining the coordinate frame, state space constraints, and vessel operating environment. Step S2: Construct path navigation feature vectors and define the representation of parameterized paths. The path navigation feature vectors are characterized by setting path reference points, Euclidean distances, forward path reference points, path deviations, heading errors, and path angles that are continuously updated based on the current unmanned vessel position on the path to be navigated. Step S3: Set up the data acquisition and processing module, and equip the unmanned vessel with detection sensors in a 360-degree full coverage manner. In the process of equipping, the dimensional reduction method is adopted to set the detection sensors to be non-uniformly distributed. Step S4: Formulate collision avoidance decisions. By fusing various information about the obstacles and combining it with the situation of the unmanned vessel itself, formulate collision avoidance decisions that meet the goals of the unmanned vessel and are dynamically limited. Step S5: Through the wireless data transmission module including the DTU unit and the Beidou client, the obstacle avoidance information and control commands required by the unmanned vessel during its operation are wirelessly transmitted to other unmanned vessels and the collaborative control center.

2. The data fusion-based obstacle avoidance control and wireless transmission method for unmanned surface vessels as described in claim 1, characterized in that, Step S1 specifically includes: Step S11: Define the unmanned surface vessel as always remaining on the Earth's surface without any vertical, pitching, or rolling motion. Then, the coordinate frame of the unmanned surface vessel's environment is: It forms a tangential plane with the Earth's surface, in which The axis points north. The axis points eastward. The axis points towards the center of the Earth; Step S12: Define the state vector of the unmanned vessel. ,in and These refer to their positions in the north and east directions within the coordinate framework of their environment. It is the heading angle, that is, the angle between the longitudinal axis of the unmanned vessel and the north axis; the translation and angular velocity vectors. It consists of foreground velocity u, lateral velocity h, and yaw rate r; Step S13: The unmanned surface vessel (USV) is equipped with a rudder and propeller at its stern, allowing it to move freely along any trajectory in the state space. The control vector for controlling the USV is... ,in The torque input indicates the direction of travel. The initial dynamic model of the unmanned vessel, representing the torque input in the yaw direction, is as follows: （1） in , , All are The state space vector, i.e. ; It is the mass matrix of the unmanned vessel, which covers rigid body effects and added mass effects; It is the centripetal force parameter matrix; B is the damping matrix; B is the actuator configuration matrix, belonging to... The state space vector; Indicates along Axis rotation The curvature.

3. The data fusion-based obstacle avoidance control and wireless transmission method for unmanned surface vessels as described in claim 1, characterized in that, Step S2 specifically includes: Step S21: Define the representation of the parameterized path as follows ,in It is a path variable. This represents the path reference point, defined as the point to the right of the unmanned vessel, at which it generates an Euclidean distance from the unmanned vessel. The coordinates of the path reference point are represented by these coordinates, and correspondingly, a lookahead path reference point also needs to be set. It serves as a path reference point. Continue along the path The point of distance; Step S22: Finding path reference points At this time, path variables need to be calculated. The corresponding value at each time step : （3） Define the path deviation between the desired path and the current trajectory as Meanwhile, the heading error required for the unmanned vessel to navigate directly from its current position toward the look-ahead path reference point is defined. ,have: （4） Further define the path angle Using the reciprocal of the first-order path as a reference, to ensure the smoothness of the unmanned vessel trajectory when relying on the look-through path reference point, we have: （5） Step S23: By using the path variables calculated in the above steps The corresponding value at each time step Path deviation Heading error Path angle Together they form a path navigation feature vector .

4. The unmanned surface vessel obstacle avoidance control and wireless transmission method based on data fusion as described in claim 1, characterized in that, Step S3 specifically includes: Step S31: Equip distance sensors as detection sensors, with N distance sensors and a maximum detection range of [missing information]. They are deployed around the unmanned boat in a 360-degree full coverage manner; Step S32: Divide the 360-degree full-coverage ranging sensor into D groups, and each group generates a scalar detection value, which is included in the final observation vector; Step S33: Define the following formula for sorting the ranging sensors and their groups, starting from the rear of the unmanned vessel and proceeding counterclockwise and clockwise: （2） in, For the nonlinear mapping part, For the constant offset portion; use the given sensor index Mapping to Grouped Index ,in It is a logical function ; is a scaling parameter used to control the density of the group distribution; the groups near the bow of the unmanned vessel are the narrowest; and the first... The distance measurement vector measured by the group's range sensors is ; Step S34: Define the width of the unmanned vessel as W, and the included angle between adjacent ranging sensors of the 360-degree full-coverage ranging sensor as . The measured value of a certain group of distance measuring sensors The measured values ​​x are sorted in ascending order to form an index set I. Then, for each index, the arc length between adjacent ranging sensors is calculated. Based on half of the arc length, an initial opening width that allows passage between obstacles is set. A loop from 0 to n is performed, traversing the readings of all ranging sensors. When it is found that the width of an opening j is greater than the current opening width, the opening width is updated by adding the radian value corresponding to the opening width of opening j to the current opening width. If the updated opening width is greater than the width W of the unmanned vessel, the opening is marked as true and the loop is exited. If the updated opening width is not greater than the width W of the unmanned vessel, the opening width is updated by adding half of the radian value corresponding to the opening width of opening j to the current opening width, and the above process is repeated for loop traversal. All openings marked as true are selected as potential passage options. If no opening is marked as true, it means that passage is not possible.

5. The unmanned surface vessel obstacle avoidance control and wireless transmission method based on data fusion as described in claim 1, characterized in that, Step S4 specifically includes: Step S41: Simplify the unmanned vessel dynamics model in step S1, and define the dynamics model as follows: ,vector Represents the input caused by environmental disturbances; vector It is a control input , For constant parameters, use the estimated state. and interference To track reference speed Then the dynamic model can be expressed as ; through a short time range Integrating within the discretized interval The determined By using discrete sampling times, we can obtain the predicted position achievable based on the dynamic model. The predicted location is used to calculate the unmanned vessel's position relative to each obstacle. Predicted distance between , These indicate the positions of the unmanned vessel and the obstacles, respectively. Step S42: Control the reduction of deviation from the preferred speed, and define the candidate speed set as follows. , ,in It is a set of velocity grid points, based on the optimal speed of the unmanned vessel. Fixed offset selection; velocity set It is to satisfy A set of reference velocities for optimization conditions; Step S43: Reduce the number of control instructions that cause significant speed changes. Define an objective function to discard those instructions that lead to large speed changes. The objective function is: （6） in, , , , and It is the corresponding empirical coefficient. This is the preferred speed for unmanned vessels. This is the preferred course for unmanned vessels. That's the speed of one time on an unmanned boat. That was the last course of the unmanned vessel. It is a time-dependent variable used to assess the time-varying responsibility of unmanned vessels during collisions.

6. A data fusion-based obstacle avoidance control and wireless transmission system for unmanned surface vessels, used to implement the data fusion-based obstacle avoidance control and wireless transmission method for unmanned surface vessels as described in any one of claims 1-5, characterized in that, The system includes: Unmanned surface vessel obstacle avoidance control device 100 and collaborative control center 200; The collaborative control center 200 is set up on shore and is used to establish wireless communication with the unmanned vessel, send control commands, and keep the unmanned vessel online in real time. It includes a wireless communication module 201, which has a DTU unit and a Beidou client. It communicates with the unmanned vessel obstacle avoidance control device 100 via radio or satellite signals through a 5G network or Beidou satellite. When the 5G network is interrupted or malfunctions during the communication process, it switches to Beidou satellite communication.

7. The unmanned surface vessel obstacle avoidance control and wireless transmission system based on data fusion as described in claim 6, characterized in that: The unmanned vessel obstacle avoidance control device 100 includes: The dynamic model construction module 101 is used to construct the initial dynamic model of the unmanned vessel. The initial dynamic model of the unmanned vessel is constructed by defining the coordinate frame, state space constraints, and vessel driving environment constraints. The path navigation feature vector construction module 102 defines the representation of the parameterized path. It characterizes the path navigation feature vector by setting path reference points, Euclidean distances, forward path reference points, path deviations, heading errors, and path angles that are continuously updated based on the current unmanned vessel position on the path to be navigated. The data acquisition and processing module 103 is equipped with detection sensors around the unmanned vessel in a 360-degree full coverage manner. During the equipment process, a dimensional reduction method is adopted to set the detection sensors to be non-uniformly distributed. The collision avoidance decision-making module 104, by integrating various information about the acquired obstacles and combining them with the situation of the unmanned vessel itself, formulates collision avoidance decisions that meet the goals of the unmanned vessel and are dynamically limited. The wireless data transmission module 105 includes a DTU unit and a Beidou client, used for wireless communication with other unmanned vessels and collaborative control centers.

Images