Autonomous warehousing method for unmanned ship

Abstract

The embodiment of the invention discloses an autonomous warehousing method of an unmanned ship. The autonomous warehousing method comprises the following steps: marking a parking space: marking a GPS coordinate and a parking space direction angle of the parking space; ship dynamic performance calculation: driving the unmanned ship to travel according to specific actions, and obtaining dynamic constraint conditions of the unmanned ship; planning an in-storage path: planning a global in-storage path based on dynamic constraints; calculating a path curvature: calculating the path curvature in combination with the path points of the planned global warehousing path; target speed calculation: calculating the target speed of the unmanned ship at each path point according to the path curvature obtained by calculation; and control output calculation: according to the real-time speed and the target speed of the unmanned ship at each path point, performing real-time calculation to obtain a control output instruction. According to the autonomous warehousing method of the unmanned ship, the path of the unmanned ship is planned based on the dynamic constraint, so that the path planning is more accurate, the positioning accuracy is improved, and the target speed of the unmanned ship is calculated according to the path curvature obtained through calculation, so that the driving of the unmanned ship is accurately controlled.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to an autonomous warehousing method for an unmanned ship. Background Art

[0002] With the rapid development of big data and artificial intelligence, and the maturation of unmanned vehicle technology on land, autonomous driving technology on the water is also gaining increasing attention. Furthermore, by leveraging unmanned driving technologies such as environmental perception and navigation on land, we can obtain more accurate information about the vessel's position and heading angle, thus enabling more precise unmanned control on the water.

[0003] The development of autonomous surface driving technology has led to a growing demand for autonomous docking capabilities for ships. Docks are typically constructed with standard pontoons. Precise control of the ship's position is essential to prevent collisions during entry and exit. However, existing autonomous driving technology suffers from low positioning accuracy. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an autonomous warehousing method for an unmanned boat to accurately plan a path and improve positioning accuracy.

[0005] To solve the above technical problems, an embodiment of the present invention provides an autonomous warehousing method for an unmanned vessel, comprising the following steps:

[0006] Storage location mark: mark the GPS coordinates and direction angle of the storage location;

[0007] Ship dynamic performance calculation: Drive the unmanned ship to follow specific actions and obtain the dynamic constraints of the unmanned ship;

[0008] Warehouse entry path planning: planning the global warehouse entry path based on dynamic constraints;

[0009] Path curvature calculation: Calculate the path curvature based on the path points of the planned global inbound path;

[0010] Target speed calculation: Calculate the target speed of the unmanned ship at each path point based on the calculated path curvature;

[0011] Control output calculation: Based on the real-time speed and target speed of the unmanned ship at each path point, the control output instruction is calculated in real time.

[0012] A further technical solution is as follows: the steps for calculating the power performance of the vessel are specifically as follows:

[0013] Only longitudinal throttle is applied to drive the unmanned boat, and the speed corresponding to the maximum longitudinal throttle value is obtained as the maximum speed of the unmanned boat, and the maximum value of the acceleration values ​​corresponding to the maximum longitudinal throttle value is obtained as the maximum acceleration;

[0014] When driving the unmanned boat, only the lateral throttle is applied, and the angular velocity corresponding to the maximum lateral throttle value is obtained as the maximum angular velocity of the unmanned boat;

[0015] The unmanned boat is driven to apply longitudinal throttle and lateral throttle, and the turning radius corresponding to the maximum longitudinal throttle value and the maximum lateral throttle value is obtained as the maximum turning radius;

[0016] The maximum speed, maximum acceleration, maximum angular velocity and maximum turning radius of the unmanned ship are recorded as the dynamic constraints of the unmanned ship.

[0017] The further technical solution is: the steps of the warehousing path planning specifically include:

[0018] Global path pre-planning: Based on the obtained dynamic constraints of the unmanned ship and combined with the prior safety zone information, a global entry path to bypass the obstacle zone is planned;

[0019] Available route generation: Predict the local trajectory of the unmanned vessel and generate an available actual planned route.

[0020] Its further technical solution is: after the step of generating the available routes, the method further comprises:

[0021] Route smoothing: Smoothing the generated available actual planned route.

[0022] A further technical solution is that the steps of planning a global entry path that bypasses the obstacle zone by combining the prior safety zone information in the global path pre-planning step are specifically as follows:

[0023] The drivable area is calculated and obtained, and a path search algorithm is used to quickly plan a global drivable path that bypasses the obstacle area based on the obtained drivable area; wherein the path search algorithm includes the Dijkstra search algorithm, the heuristic A* algorithm and the rapidly expanding random tree (RRT) algorithm.

[0024] Its further technical solution is: the step of generating available routes specifically includes:

[0025] According to the initial position information, final position information, velocity information and acceleration information of the unmanned vessel, a local trajectory is generated by direct construction method;

[0026] Verify the generated local trajectory;

[0027] Generate an available actual planned route based on the verified and available local trajectory.

[0028] A further technical solution is as follows: the step of verifying the generated local trajectory specifically includes:

[0029] Path point splitting: Split the generated local trajectory into several line segments and several path points according to the preset spacing;

[0030] Curvature judgment: Set a sliding window of preset length, and slide each path point as the starting point to intercept a curve of preset length as a local curve, and judge whether the curvature of each local curve meets the standard.

[0031] A further technical solution is as follows: the step of calculating the path curvature specifically includes:

[0032] According to the obtained path points, multiple continuous path points are selected, and the line segments corresponding to the selected multiple continuous path points are accumulated to obtain the trajectory distance;

[0033] According to the selected multiple continuous path points, the tangent directions of the path points at the beginning and end of the corresponding trajectory are obtained, the angular difference between the tangent directions of the path points at the beginning and end of the corresponding trajectory is calculated, and the angular difference is converted into radians to obtain the tangent radian difference of the trajectory;

[0034] The trajectory radius is calculated based on the ratio of the trajectory distance to the trajectory tangential arc difference, and the path curvature is calculated based on the trajectory radius; wherein the path curvature and the trajectory radius are reciprocals of each other.

[0035] Its further technical solution is: the steps of the storage location marking are specifically as follows:

[0036] Control the unmanned boat to maintain a fixed position and angle at the berth for a preset period of time, calculate the average GPS coordinates and average angles of the unmanned boat during the preset period of time, obtain the position corresponding to the average GPS coordinates as the storage location, obtain the average angle as the storage location direction angle, and record and store the storage location and storage location direction angle.

[0037] Its further technical solution is: after the step of the storage location marking, the following steps are also included:

[0038] Distance and angle verification: Based on the GPS coordinates of the storage location, convert them from the geodetic coordinate system to the plane rectangular coordinate system; obtain the actual docking position of the unmanned boat, and calculate the Euclidean distance between the actual docking position of the unmanned boat and the storage location; obtain the heading angle of the unmanned boat, and calculate the angle difference between the heading angle of the unmanned boat and the direction angle of the storage location based on the direction angle of the storage location; determine whether the calculated Euclidean distance is less than the preset distance and whether the angle difference is less than 90°.

[0039] The beneficial technical effect of the present invention is that: the autonomous warehousing method of an unmanned boat of the present invention plans the path of the unmanned boat based on dynamic constraints, so that the path planning is more in line with practical applications, more accurate, improves the positioning accuracy, makes the control stable and reliable, and calculates the path curvature of the unmanned boat path, calculates the target speed of the unmanned boat according to the path curvature, and controls the output instructions according to the real-time speed and target speed of the unmanned boat at each path point in the planned path, so as to accurately control the movement of the unmanned boat. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A schematic diagram of a flow chart of an autonomous warehousing method for an unmanned vessel provided in an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of a specific process flow of an autonomous warehousing method for an unmanned vessel provided in an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of a specific process for generating available routes for an autonomous warehousing method of an unmanned vessel provided in an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of a sub-process for generating available routes for an autonomous warehousing method of an unmanned vessel provided in an embodiment of the present invention;

[0045] Figure 5 A schematic diagram of a specific process flow for calculating path curvature in an autonomous warehousing method for an unmanned vessel provided by an embodiment of the present invention;

[0046] Figure 6 A schematic diagram of a specific process for calculating target speed of an autonomous warehousing method for an unmanned vessel provided by an embodiment of the present invention;

[0047] Figure 7 A schematic flow chart of an autonomous warehousing method for an unmanned vessel provided in accordance with another embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0049] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0050] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0051] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0052] See also Figure 1 As shown, Figure 1 A flow chart of an autonomous warehousing method for an unmanned vessel provided in an embodiment of the present invention includes the following steps:

[0053] Step S11, storage location marking: marking the GPS coordinates and direction angle of the storage location.

[0054] Among them, step S11 can be specifically as follows: controlling the unmanned boat to maintain a fixed position and angle at the berth for a preset time period, calculating the average GPS coordinate and average angle of the unmanned boat within the preset time period, obtaining the position corresponding to the average GPS coordinate as the storage location, obtaining the average angle as the storage location direction angle, and recording and storing the storage location and storage location direction angle.

[0055] Step S12, calculating the dynamic performance of the vessel: driving the unmanned vessel to move according to a specific action to obtain the dynamic constraint conditions of the unmanned vessel.

[0056] The feasibility of the planned path can be determined based on the dynamic constraints of the unmanned vessel. If the planned path does not meet the dynamic constraints, the planned path is infeasible, so that the path planning is more accurate and more suitable for practical applications. The step S12 may specifically include:

[0057] Only longitudinal throttle is applied to drive the unmanned boat, and the speed corresponding to the maximum longitudinal throttle value is obtained as the maximum speed of the unmanned boat, and the maximum value of the acceleration values ​​corresponding to the maximum longitudinal throttle value is obtained as the maximum acceleration;

[0058] When driving the unmanned boat, only the lateral throttle is applied, and the angular velocity corresponding to the maximum lateral throttle value is obtained as the maximum angular velocity of the unmanned boat;

[0059] The unmanned boat is driven to apply longitudinal throttle and lateral throttle, and the turning radius corresponding to the maximum longitudinal throttle value and the maximum lateral throttle value is obtained as the maximum turning radius;

[0060] The maximum speed, maximum acceleration, maximum angular velocity and maximum turning radius of the unmanned ship are recorded as the dynamic constraints of the unmanned ship.

[0061] Step S13, warehousing path planning: planning a global warehousing path based on dynamic constraints.

[0062] Step S14, path curvature calculation: Calculate the path curvature based on the path points of the planned global warehousing path.

[0063] Step S15, target speed calculation: Calculate the target speed of the unmanned vessel based on the calculated path curvature.

[0064] Step S16, control output calculation: according to the real-time speed and target speed of the unmanned boat at each path point, the control output instruction is obtained by real-time calculation.

[0065] Among them, the autonomous warehousing method of the unmanned boat can ensure the accuracy of positioning by marking the storage location and the storage location direction angle, and plan the unmanned boat path based on dynamic constraints to make the path planning more in line with practical applications and more accurate, improve the positioning accuracy, make the control stable and reliable, and calculate the path curvature of the unmanned boat path, calculate the target speed of the unmanned boat according to the path curvature, and output command control according to the real-time speed and target speed of the unmanned boat at each path point in the planned path to accurately control the movement of the unmanned boat.

[0066] In some embodiments, as Figure 2 As shown, the step S13 may be specifically as follows:

[0067] Step S131, global path pre-planning: Based on the obtained dynamic constraints of the unmanned ship and combined with the prior safety zone information, a global entry path that bypasses the obstacle zone is planned. The prior safety zone information refers to the regional information of the prior safety zone, and multiple prior safety zones and multiple obstacle zones constitute the environmental map. Global path pre-planning is to load the stored known obstacle information to plan a path to bypass the obstacle. The environmental map can be sensed by the radar and camera of the unmanned ship according to the corresponding environmental information or by manual assistance to add "safe" signs or "dangerous" signs, so as to mark "safe" in the area where the obstacle is removed, and mark "dangerous" in the area covered by the corresponding static obstacle. The area marked with "safe" is the prior safety zone, and the area marked with "dangerous" is the obstacle zone.

[0068] The steps of planning a global entry path around the obstacle zone in step S131 by combining the prior safety zone information are as follows:

[0069] The drivable area is calculated and obtained. Based on the obtained drivable area, a path search algorithm is used to quickly plan a global drivable path that bypasses the obstacle zone. The path search algorithm includes the Dijkstra search algorithm, the heuristic A* algorithm, and the rapidly expanding random tree (RRT) algorithm. The drivable area is the set of areas formed by connecting all prior safety zones after bypassing each obstacle zone. The obstacle zone and the prior safety zone are used to calculate and obtain the drivable area that bypasses the obstacle zone, making the planned route safer and more reliable. The path search method can also be an experience-based planning algorithm. The appropriate path search method can be selected for path planning based on different usage scenarios.

[0070] Step S132: Generate available routes: predict the local trajectory of the unmanned vessel and generate available actual planned routes.

[0071] Among them, the global entry path is planned in combination with the prior safety zone information to make the planned route safer and more reliable, and the planned route is further improved by predicting the local trajectory.

[0072] Specifically, after step S132, the following steps are further included:

[0073] Step S133, route smoothing: smoothing the generated available actual planned route, wherein the global route can be smoothed by fitting a curve based on a B-spline interpolation method and a quadratic programming (QP) algorithm.

[0074] Combine Figure 3 Specifically, in some embodiments, step S132 may include the following steps:

[0075] Step S1321: Generate a local trajectory by direct construction method based on the initial position information, final position information, speed information and acceleration information of the unmanned boat.

[0076] Among them, the initial position information and the end position information of the unmanned ship refer to the corresponding latitude and longitude data collected by the GPS at the initial point and the end point and the corresponding azimuth information measured by the IMU sensor. The speed information and acceleration information of the unmanned ship are collected by the GPS and accelerometer of the unmanned ship respectively. The initial point can be the path point where the unmanned ship is currently located, which is the starting point of the path planning and the first path point in the planned route; the end point refers to the target point where the unmanned ship is traveling, which is the last path point in the planned route. A fifth-order polynomial can be set to fit a route from the initial point to the end point, and the initial position information and the end position information are known. The fifth-order polynomial can be expressed by the following calculation formula (1) to generate a local trajectory by a direct construction method through calculation formula (1):

[0077] q(t)=q0+a1*(t-t0)+a2*(t-t0) 2 +a3*(t-t0) 3 +a4*(t-t0) 4 +a5*(t-t0) 5 (1)

[0078] Where q0 represents the initial position information, t represents time, t0 represents the initial moment, q(t) represents the position information of the unmanned ship at moment t, and a1, a2, a3, a4, and a5 represent different parameter variables.

[0079] Among them, when t is the initial moment, that is, t=t0, then q(t)=q0; when t is the termination moment, the corresponding q(t) is the position information of the unmanned ship at the termination moment; the first-order derivative of q(t) with respect to t can obtain the velocity information, and the second-order derivative of q(t) with respect to t can obtain the acceleration information. The speed information and acceleration information of the unmanned ship are collected by GPS and accelerometer, so the speed information and acceleration information of the unmanned ship are both known, and the parameter variables can be solved.

[0080] Step S1322: Verify the generated local trajectory.

[0081] Step S1323: Generate an available actual planned route based on the verified and available local trajectories.

[0082] By generating local trajectories based on actual navigation data to adjust the pre-planned global path, the final generated global route is safe, reliable, more practical, and more accurate.

[0083] Combine Figure 4 Specifically, in some embodiments, step S1322 may include:

[0084] Step S3221, path point splitting: Split the generated local trajectory into several line segments and several path points according to a preset spacing. Among them, the path points are the corresponding points except the starting point when the local trajectory is split into several line segments according to the preset spacing. The path points include the end point. The serial numbers of each path point can be sequentially represented by 1, 2,..., N, where N represents the serial number corresponding to the end point. Each line segment is sequentially represented by l1, l2,..., l N represented.

[0085] Step S3222, curvature judgment: Set a sliding window with a preset length, and sequentially use each path point as the starting point to slide and intercept a curve with a preset length as the local curve, and judge whether the curvature of each local curve is qualified. Among them, set the preset length as l m , m refers to the number of path points, m is an integer, and 1 < m < N. Then the length of the local curve is the preset length, which is m times that of the line segment. When the curvature of the local curve is greater than the maximum curvature when the unmanned ship moves at the planned speed, the unmanned ship cannot turn along the route at the current real-time speed, then the curvature of the local curve does not meet the standard, and the verification result of the local trajectory is verification failure. The planned speed refers to the speed of the unmanned ship planned when planning the route, to judge whether the planned local curve is feasible. The judgment of the curvature of the local curve is specifically:

[0086] Take the connecting line of the first two path points of the local curve as the reference line, calculate the distance between the remaining path points of the local curve and the reference line, and obtain the average distance between the remaining path points of the local curve and the reference line; Compare and judge whether the maximum value and the average distance of the distance between the remaining path points of the local curve and the reference line are both less than the set distance threshold. If so, the curvature of the local curve meets the standard; if the maximum value of the distance between the remaining path points of the local curve and the reference line is not less than the set distance threshold and / or the average distance is not less than the set distance threshold, then the curvature of the local curve does not meet the standard.

[0087] After step S3222, it further includes: When all local curves meet the standard, the verification result of the local trajectory is verification qualified, and step S1323 is executed. When there are local curves that do not meet the standard, the verification result of the local trajectory is verification failure, adjust the navigation angle, and re-execute steps S221 - S222.

[0088] Among them, the distance threshold is obtained according to the length of the local curve, the maximum speed of the unmanned ship, and the speed of the unmanned ship. Then the distance threshold can be calculated using the following calculation formula (2):

[0089] d = v × (lm / v max ) (2)

[0090] Where, v refers to the real-time speed of the unmanned ship, l m is the length of the local curve, v max It refers to the maximum speed of the unmanned ship, and d refers to the distance threshold.

[0091] Combine Figure 5 In some embodiments, step S14 specifically includes:

[0092] Step S141: Select multiple continuous path points based on the obtained path points, accumulate the line segments corresponding to the selected multiple continuous path points, and obtain the trajectory distance.

[0093] Step S142: Based on the selected multiple continuous path points, obtain the tangent directions of the path points at the beginning and end of the corresponding trajectory, calculate the tangent angle difference between the path points at the beginning and end, and convert the tangent angle difference into radians to obtain the tangent radian difference of the trajectory. The corresponding trajectory refers to the trajectory of the curve formed by the combination of line segments corresponding to the selected multiple continuous path points.

[0094] Step S143: Calculate the trajectory radius based on the ratio of the trajectory distance to the trajectory tangential arc difference, and then calculate the path curvature based on the trajectory radius. The path curvature and trajectory radius are reciprocals of each other. A smaller curvature corresponds to a larger trajectory radius. When the curvature radius approaches infinity, the planned path is a straight line.

[0095] Combine Figure 6 , the step S15 is specifically as follows:

[0096] Step S151: Collect the motion data of the unmanned boat and obtain a boat motion calibration table.

[0097] The step S151 is specifically as follows:

[0098] Collect the speed and angular velocity information of the unmanned vessel when the lateral throttle value increases in equal throttle steps at equal time intervals; the longitudinal throttle value is set to 0, the time interval can be set to 10 seconds, the throttle step size is set to 5, and the initial lateral throttle value is set to 0;

[0099] A ship motion calibration table for lateral throttle control is established based on the correspondence between each lateral throttle value at equal time intervals and the speed information and angular velocity information of the unmanned ship;

[0100] Collect the speed and angular velocity information of the unmanned vessel when the longitudinal throttle value increases in equal throttle steps at equal time intervals; the lateral throttle value is set to 0, the time interval can be set to 10 seconds, the throttle step size is set to 5, and the initial lateral throttle value is set to 0;

[0101] According to the corresponding relationship between the longitudinal throttle values ​​at equal time intervals and the speed information and angular velocity information of the unmanned ship, a ship motion calibration table for longitudinal throttle control is established.

[0102] By establishing a ship motion calibration table, the corresponding relationships between speed and throttle value and between angular velocity and throttle value can be obtained.

[0103] Step S152: Calculate the target speed of the unmanned vessel based on the calculated path curvature and the vessel motion calibration table. The target speed can be obtained by querying the vessel motion calibration table based on the path curvature.

[0104] Preferably, the speed of the unmanned boat at the end point is 0, then within the control cycle, the remaining distance from the unmanned boat to the end point can be calculated in real time, and the target speed corresponding to the natural gliding distance can be derived.

[0105] Specifically, the step S16 is as follows:

[0106] According to the target speed and real-time speed of the unmanned ship, the speed difference between the target speed and the real-time speed of the unmanned ship is calculated, the corresponding throttle value is calculated, and the corresponding control instruction is obtained.

[0107] The throttle value is calculated using the following formula (3):

[0108] thrust=P·(v d -v)+D·d(v d -v) / dt+I·∫(v d -v)dt (3)

[0109] Where thrust is the throttle output value, v d is the target speed of the unmanned ship, v is the real-time speed of the unmanned ship, P, I and D are the controller design parameters, and t is the time.

[0110] Figure 7 A flow chart of an autonomous warehousing method for an unmanned vessel is provided in accordance with another embodiment of the present invention. Figure 7 As shown, the step S11 further includes step S1101 after the step S11, and the remaining steps are similar to those in the above embodiment and will not be described in detail. The step S1101 added in this embodiment is described in detail below.

[0111] Step S1101, distance and angle verification: According to the GPS coordinates of the storage location, convert them from the geodetic coordinate system to the plane rectangular coordinate system; obtain the actual docking position of the unmanned boat, and calculate the Euclidean distance between the actual docking position of the unmanned boat and the storage location; obtain the heading angle of the unmanned boat, and calculate the angle difference between the heading angle of the unmanned boat and the direction angle of the storage location according to the direction angle of the storage location; determine whether the calculated Euclidean distance is less than the preset distance and whether the angle difference is less than 90°.

[0112] Among them, the Euclidean distance between the actual docking position of the unmanned boat and the storage location is calculated by converting the coordinate information of the actual docking position of the unmanned boat and the storage location into a plane rectangular coordinate system. The preset distance is determined according to the size of the water area. By verifying the distance and angle, the position and angle of the unmanned boat can be accurately controlled to improve the positioning accuracy, ensure that there will be no collision during navigation, and be stable and reliable.

[0113] Preferably, after the step of determining whether the calculated Euclidean distance is less than a preset distance and whether the angle difference is less than 90° in step S1101, the method further includes:

[0114] When the Euclidean distance is not less than the preset distance, the real-time docking position of the unmanned boat is adjusted. When the angle difference is not less than 90°, the bow angle of the unmanned boat is adjusted to adjust the heading angle.

[0115] In summary, the autonomous warehousing method of an unmanned boat of the present invention plans the path of the unmanned boat based on dynamic constraints to make the path planning more in line with practical applications, more accurate, improve positioning accuracy, make the control stable and reliable, and calculate the path curvature of the unmanned boat path, calculate the target speed of the unmanned boat according to the path curvature, and control the output instructions according to the real-time speed and target speed of the unmanned boat at each path point in the planned path to accurately control the movement of the unmanned boat.

[0116] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for autonomous warehousing of an unmanned vessel, characterized in that: The following steps are involved: Storage location mark: mark the GPS coordinates and direction angle of the storage location; Ship dynamic performance calculation: Drive the unmanned ship to follow specific actions and obtain the dynamic constraints of the unmanned ship; Warehouse entry path planning: planning the global warehouse entry path based on dynamic constraints; Path curvature calculation: Calculate the path curvature based on the path points of the planned global inbound path; Target speed calculation: Calculate the target speed of the unmanned ship at each path point based on the calculated path curvature; Control output calculation: Based on the real-time speed and target speed of the unmanned ship at each path point, the control output instruction is calculated in real time.

2. The autonomous warehousing method for an unmanned ship according to claim 1, characterized in that: The steps of calculating the ship's dynamic performance specifically include: Only longitudinal throttle is applied to drive the unmanned boat, and the speed corresponding to the maximum longitudinal throttle value is obtained as the maximum speed of the unmanned boat, and the maximum value of the acceleration values ​​corresponding to the maximum longitudinal throttle value is obtained as the maximum acceleration; When driving the unmanned boat, only the lateral throttle is applied, and the angular velocity corresponding to the maximum lateral throttle value is obtained as the maximum angular velocity of the unmanned boat; The unmanned boat is driven to apply longitudinal throttle and lateral throttle, and the turning radius corresponding to the maximum longitudinal throttle value and the maximum lateral throttle value is obtained as the maximum turning radius; The maximum speed, maximum acceleration, maximum angular velocity and maximum turning radius of the unmanned ship are recorded as the dynamic constraints of the unmanned ship.

3. The autonomous warehousing method for an unmanned ship according to claim 2, characterized in that: The steps of the warehousing path planning specifically include: Global path pre-planning: Based on the obtained dynamic constraints of the unmanned ship and combined with the prior safety zone information, a global entry path to bypass the obstacle zone is planned; Available route generation: Predict the local trajectory of the unmanned vessel and generate an available actual planned route.

4. The autonomous warehousing method for an unmanned ship according to claim 3, characterized in that: The step of generating available routes further includes: Route smoothing: Smoothing the generated available actual planned route.

5. The autonomous warehousing method for an unmanned ship according to claim 3, characterized in that: The steps of planning a global entry path around an obstacle zone in the global path pre-planning step by combining the prior safety zone information are specifically as follows: The drivable area is calculated and obtained, and a path search algorithm is used to quickly plan a global drivable path that bypasses the obstacle area based on the obtained drivable area; wherein the path search algorithm includes the Dijkstra search algorithm, the heuristic A* algorithm and the rapidly expanding random tree (RRT) algorithm.

6. The autonomous warehousing method for an unmanned ship according to claim 3, characterized in that: The steps of generating available routes specifically include: According to the initial position information, final position information, velocity information and acceleration information of the unmanned vessel, a local trajectory is generated by direct construction method; Verify the generated local trajectory; Generate an available actual planned route based on the verified and available local trajectory.

7. The autonomous warehousing method for an unmanned ship according to claim 6, characterized in that: The step of verifying the generated local trajectory specifically includes: Path point splitting: Split the generated local trajectory into several line segments and several path points according to the preset spacing; Curvature judgment: Set a sliding window of preset length, and slide each path point as the starting point to intercept a curve of preset length as a local curve, and judge whether the curvature of each local curve meets the standard.

8. The autonomous warehousing method for an unmanned ship according to claim 7, characterized in that: The step of calculating the path curvature specifically includes: According to the obtained path points, multiple continuous path points are selected, and the line segments corresponding to the selected multiple continuous path points are accumulated to obtain the trajectory distance; According to the selected multiple continuous path points, the tangent directions of the path points at the beginning and end of the corresponding trajectory are obtained, the angular difference between the tangent directions of the path points at the beginning and end of the corresponding trajectory is calculated, and the angular difference is converted into radians to obtain the tangent radian difference of the trajectory; The trajectory radius is calculated based on the ratio of the trajectory distance to the trajectory tangential arc difference, and the path curvature is calculated based on the trajectory radius; wherein the path curvature and the trajectory radius are reciprocals of each other.

9. The autonomous warehousing method for an unmanned ship according to claim 1, characterized in that: The steps of the storage location marking are specifically as follows: Control the unmanned boat to maintain a fixed position and angle at the berth for a preset period of time, calculate the average GPS coordinates and average angles of the unmanned boat during the preset period of time, obtain the position corresponding to the average GPS coordinates as the storage location, obtain the average angle as the storage location direction angle, and record and store the storage location and storage location direction angle.

10. The autonomous warehousing method for an unmanned ship according to claim 9, characterized in that: The step of location marking further includes the following steps: Distance and angle verification: Based on the GPS coordinates of the storage location, convert them from the geodetic coordinate system to the plane rectangular coordinate system; obtain the actual docking position of the unmanned boat, and calculate the Euclidean distance between the actual docking position of the unmanned boat and the storage location; obtain the heading angle of the unmanned boat, and calculate the angle difference between the heading angle of the unmanned boat and the direction angle of the storage location based on the direction angle of the storage location; determine whether the calculated Euclidean distance is less than the preset distance and whether the angle difference is less than 90°.

Images