Autonomous underwater vehicle spatial-temporal trajectory planning method and related equipment thereof

Abstract

The invention relates to the technical field of underwater robot navigation and path planning, and discloses an autonomous underwater vehicle spatial-temporal trajectory planning method and related equipment thereof. The method comprises the following steps: generating an initial reference navigation path of the autonomous underwater vehicle based on a space environment model of a target area, wherein the space environment model comprises an obstacle model in the target area and a starting point and an ending point of the autonomous underwater vehicle; based on the initial reference navigation path, an underwater safety corridor used for movement of the autonomous underwater vehicle is established in the space environment model, and the obstacle model is located on the outer side of the underwater safety corridor; and in the underwater safety corridor, carrying out space trajectory optimization processing and time trajectory optimization processing on the initial reference navigation path to generate a target space-time mobile navigation trajectory. Based on the method, the task execution capability, flexibility and safety of the AUV are improved.

Description

Technical Field

[0001] The present application relates to the technical field of underwater robot navigation and path planning, and in particular to a method for spatiotemporal trajectory planning of an autonomous underwater vehicle and related equipment. Background Art

[0002] Autonomous underwater vehicles (AUVs) need to deal with complex three-dimensional ocean environments, such as seabed topography, ocean currents, and suspended objects, when performing missions, which poses challenges to navigation safety and dynamic adaptability. Existing path planning methods mostly focus on generating spatial paths, ignoring dynamic environments and time constraints, resulting in problems such as discontinuous paths and difficulty in avoiding obstacles.

[0003] Although current related methods have introduced three-dimensional spatial constraints for optimization, these methods are mostly derived from the field of drones or land robots, and do not take into account the particularities of the underwater environment, such as ocean currents and the AUV's own motion characteristics, resulting in insufficient path smoothness and energy efficiency. In addition, the existing technology pays little attention to time optimization, which reduces the flexibility and robustness of the AUV in complex tasks. In summary, the current navigation path planning method of autonomous underwater vehicles cannot comprehensively consider the spatial constraints and time changes of the underwater environment, resulting in the planned navigation path being discontinuous, high energy consumption, and poor dynamic adaptability. Summary of the invention

[0004] An embodiment of the present invention provides a method for spatiotemporal trajectory planning of an autonomous underwater vehicle and related equipment, which at least solves the problem that the navigation path planning method of the autonomous underwater vehicle in the related art cannot comprehensively consider the spatial constraints and time changes of the underwater environment, resulting in discontinuous paths, high energy consumption, and poor dynamic adaptability.

[0005] According to a first aspect of an embodiment of the present invention, a method for spatiotemporal trajectory planning of an autonomous underwater vehicle is provided, comprising: Generate an initial reference navigation path for the autonomous underwater vehicle based on a spatial environment model of the target area, wherein the spatial environment model includes an obstacle model within the target area, a starting point and an end point of the autonomous underwater vehicle; Based on the initial reference navigation path, establishing an underwater safety corridor for movement of the autonomous underwater vehicle in the spatial environment model, wherein the obstacle model is located outside the underwater safety corridor; In the underwater safety corridor, the initial reference navigation path is subjected to spatial trajectory optimization processing and temporal trajectory optimization processing to generate a target spatiotemporal movement navigation trajectory.

[0006] According to a second aspect of an embodiment of the present invention, there is provided a device for planning a spatiotemporal trajectory of an autonomous underwater vehicle, comprising: A generation module, configured to generate an initial reference navigation path of the autonomous underwater vehicle based on a spatial environment model of the target area, wherein the spatial environment model includes an obstacle model in the target area, a starting point and an end point of the autonomous underwater vehicle; An establishing module, configured to establish an underwater safety corridor for movement of the autonomous underwater vehicle in the spatial environment model based on the initial reference navigation path, wherein the obstacle model is located outside the underwater safety corridor; The processing module is used to perform spatial trajectory optimization processing and temporal trajectory optimization processing on the initial reference navigation path in the underwater safety corridor to generate a target space-time movement navigation trajectory.

[0007] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor, and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to execute the method according to the first aspect.

[0008] According to a fourth aspect of an embodiment of the present invention, a non-transitory machine-readable medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method according to the first aspect.

[0009] Beneficial effects of the embodiments of the present invention: The spatiotemporal trajectory planning method for an autonomous underwater vehicle provided by an embodiment of the present invention generates an initial reference navigation path by modeling the spatial environment of the target area, and explicitly incorporates the starting point, end point and obstacle model in space of the AUV into the planning framework, which can effectively adapt to the requirements of a complex underwater environment. Compared with the prior art, the method not only focuses on the generation of spatial paths, but also combines the three-dimensional dynamic characteristics of the underwater environment, significantly improving the practical applicability of trajectory planning. By constructing an underwater safety corridor based on the initial reference navigation path, obstacles are completely isolated outside the safe area, ensuring the safety of AUV navigation and the continuity of the path. The design of the underwater safety corridor provides reliable boundary constraints for path optimization, so that the trajectory planning of the AUV in a complex environment has higher stability and adaptability. By combining spatial trajectory optimization with temporal trajectory optimization, the smoothness of the trajectory and the rationality of time allocation can be further improved. In summary, the method takes the underwater safety corridor as the core, comprehensively considers the spatial constraints and temporal change requirements of the underwater environment, solves many problems in the prior art, significantly improves the task execution capability, flexibility and safety of the AUV, and has outstanding technical effects and application value.

[0010] The details of one or more embodiments of the invention are set forth in the following drawings and description so that other features, objects, and advantages of the invention are more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other embodiments can be obtained based on these drawings without creative work.

[0012] Figure 1 A flowchart of a method for spatiotemporal trajectory planning of an autonomous underwater vehicle provided in an embodiment of the present invention.

[0013] Figure 2 A flowchart of a method for constructing a spatial environment model provided by an embodiment of the present invention.

[0014] Figure 3 A schematic diagram of an initial reference navigation path provided by an embodiment of the present invention.

[0015] Figure 4 A schematic diagram of an underwater safety corridor provided in an embodiment of the present invention.

[0016] Figure 5 A schematic diagram of an underwater safety corridor for removing an obstacle model provided in an embodiment of the present invention.

[0017] Figure 6 A schematic diagram of a curve showing the change of the position of a target space-time mobile navigation trajectory over time provided by an embodiment of the present invention.

[0018] Figure 7 A schematic diagram of a curve showing the change in speed of a target space-time moving navigation trajectory over time provided by an embodiment of the present invention.

[0019] Figure 8 A schematic diagram of a curve showing the acceleration of a target space-time mobile navigation trajectory changing with time provided by an embodiment of the present invention.

[0020] Fig. 9 A schematic diagram of a first target space-time moving navigation trajectory provided by an embodiment of the present invention.

[0021] Fig.10 A schematic diagram of a second target space-time moving navigation trajectory provided by an embodiment of the present invention.

[0022] Fig.11 A schematic diagram of a third target space-time moving navigation trajectory provided by an embodiment of the present invention.

[0023] Fig.12 A schematic diagram of a fourth target space-time moving navigation trajectory provided by an embodiment of the present invention.

[0024] Fig.13 A schematic diagram of a fifth target space-time moving navigation trajectory provided by an embodiment of the present invention.

[0025] Fig.14 A schematic diagram of a sixth target space-time moving navigation trajectory provided by an embodiment of the present invention.

[0026] Fig.15 A schematic structural diagram of a spatiotemporal trajectory planning device for an autonomous underwater vehicle provided in an embodiment of the present invention.

[0027] Fig.16 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] Embodiments of the present embodiment will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present embodiment are shown in the accompanying drawings, it should be understood that the present embodiment can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein, which are instead provided for a more thorough and complete understanding of the present embodiment. It should be understood that the drawings and embodiments of the present embodiment are only for exemplary purposes and are not intended to limit the scope of protection of the present embodiment.

[0029] Autonomous underwater vehicles (AUVs) have important application value in the fields of ocean exploration, resource exploration, and environmental monitoring. However, due to the complexity of the underwater environment, including the dynamic changes of seabed topography, suspended matter, and ocean currents, existing AUV path planning methods face many challenges. Traditional methods usually focus on generating two-dimensional or three-dimensional spatial paths, and fail to fully consider dynamic environmental factors and time constraints, resulting in problems such as discontinuous navigation paths, high energy consumption, and insufficient dynamic adaptability. At the same time, existing navigation path planning methods are mostly derived from the fields of drones or land robots, and have not been effectively designed for the particularity of the underwater environment, making it difficult to meet the navigation needs of AUVs in complex mission scenarios.

[0030] To solve the above problems, an embodiment of the present invention provides a method for spatiotemporal trajectory planning of an autonomous underwater vehicle, which isolates the navigable area of ​​the AUV from obstacles by establishing an underwater safety corridor, and combines spatial trajectory optimization with temporal trajectory optimization to generate a smooth and energy-optimized target navigation trajectory. This method comprehensively considers the spatial constraints and temporal dynamic changes of the underwater environment, and can effectively improve the path continuity, safety and mission execution efficiency of the AUV, thereby overcoming the shortcomings of the existing technology and providing a new technical solution for the efficient operation of the AUV.

[0031] Figure 1 Flow chart of a method for planning the spatiotemporal trajectory of an autonomous underwater vehicle provided by an embodiment of the present invention. Figure 1 As shown, the method includes the following steps.

[0032] Step S101, generating an initial reference navigation path of the autonomous underwater vehicle based on a spatial environment model of the target area, wherein the spatial environment model includes an obstacle model in the target area, a starting point and an end point of the autonomous underwater vehicle.

[0033] Step S102: Based on the initial reference navigation path, an underwater safety corridor for the autonomous underwater vehicle to move is established in the space environment model, and the obstacle model is located outside the underwater safety corridor.

[0034] Step S103, in the underwater safety corridor, the initial reference navigation path is optimized in space and time to generate a target space-time movement navigation trajectory.

[0035] Firstly, an initial reference navigation path of the autonomous underwater vehicle is generated according to the spatial environment model of the target area.

[0036] In this embodiment, an autonomous underwater vehicle (AUV) refers to an autonomous navigation device that can perform tasks in an underwater environment. AUV has high maneuverability and self-decision-making capabilities, and can complete tasks such as surveying, detection, and inspection in complex environments. The planning of its motion trajectory directly affects the efficiency and safety of performing tasks.

[0037] Spatiotemporal navigation trajectory planning for autonomous underwater vehicles refers to trajectory planning that takes both spatial position and time dimensions into consideration. Compared with simple spatial navigation path planning, spatiotemporal navigation trajectory planning not only needs to optimize the spatial smoothness of the navigation path, but also needs to optimize the time distribution of each path point to meet the task time constraints and dynamic environment adaptation requirements.

[0038] The spatial environment model of the target area in this embodiment is a three-dimensional modeling of the environment within the AUV mission area, including information such as the shape and position of obstacles, as well as the starting and end points of the AUV. Through the construction of the environmental model, the feasible navigation area within the mission area can be clearly defined. The initial reference navigation path is an initial path generated based on the spatial environment model and the starting and end points of the AUV. This trajectory has not been optimized and may have problems such as sharp turns and path discontinuity, and is only used as a basis for further optimization.

[0039] The construction of the space environment model can include the construction of the obstacle model and the construction of the task requirement model.

[0040] Specifically, obstacle modeling can include three-dimensional modeling of terrain obstacles and suspended obstacles. Terrain obstacles need to be constructed through their topological center points, geometric parameters (such as height, length, width), etc.; suspended obstacles are modeled with their center point coordinates and scaling factors in all directions. The obstacle model can accurately reflect the three-dimensional obstacle distribution in the target area and provide a reliable basis for subsequent path generation. Mission requirement modeling can be used to define the mission start and end positions of autonomous underwater vehicles, and at the same time form path planning constraints in combination with mission requirements (such as key points or areas that must be passed).

[0041] Then, based on the spatial environment model and task constraints, an initial reference navigation path is generated through a path planning algorithm. In this embodiment, the path planning algorithm may include but is not limited to: Informed RRT* (Fast Random Tree Optimization): Rapid exploration of a set of feasible path points in space, suitable for initial path generation in complex environments; A* algorithm: Prioritizes the generation of low-cost paths, suitable for simpler spatial environments between the starting point and the end point; Hybrid heuristic planning algorithm: Combines dynamic factors such as ocean currents to optimize the distribution of path points.

[0042] An underwater safety corridor is constructed around the initial reference navigation path to ensure the safety and feasibility of navigation. The underwater safety corridor in this embodiment is a restricted and safe underwater space area established around the initial reference navigation path. Its purpose is to completely isolate the navigable area from obstacles to ensure the navigation safety of the AUV. The underwater safety corridor consists of multiple connected safety areas, such as a convex polyhedron structure, and redundant areas need to be reduced through optimization.

[0043] Finally, in the underwater safety corridor, the initial reference navigation path is processed by spatial trajectory optimization and temporal trajectory optimization to generate the target space-time moving navigation trajectory.

[0044] In this embodiment, the spatial trajectory optimization process is to optimize the geometry of the initial path to make the path smoother and meet the spatial constraints (such as avoiding obstacles). After optimization, the sharp turns and mutation points of the path are smoothed, thereby reducing the energy consumption of the AUV. The time trajectory optimization process is based on the optimized spatial trajectory, and the time allocation between the path points is adjusted to ensure that the speed, acceleration and jump of the AUV are within the controllable range while minimizing the time cost of executing the task. The target space-time mobile navigation trajectory is the final trajectory after space and time optimization. The target trajectory meets the mission requirements of the AUV and achieves smoothness, energy efficiency and time optimization on the basis of ensuring navigation safety.

[0045] In an optional embodiment, before generating the initial reference navigation path of the autonomous underwater vehicle based on the spatial environment model of the target area, it is necessary to construct a spatial environment model. In this embodiment, the obstacle model includes a terrain obstacle model and a suspended obstacle model.

[0046] The underwater topography is a complex three-dimensional structure, formed mainly by crustal movement, and has certain similarities with land topography. Figure 2 Flow chart of a method for constructing a spatial environment model provided by an embodiment of the present invention. Figure 2 As shown, the method includes the following steps.

[0047] Step S201: based on the topological center coordinates, height parameters and terrain obstacles of the terrain Axis direction and The attenuation in the axial direction is used to construct the terrain obstacle model.

[0048] Step S202, based on the center coordinates of the suspended obstacle and the Axis direction, Axis direction and The suspended obstacle model is constructed based on the scaling factors corresponding to the axis directions.

[0049] In this embodiment, the underwater terrain is a complex three-dimensional structure, mainly formed by crustal movement, and has certain similarities with land terrain. Terrain obstacles can be used to represent each terrain unit with its topological center point coordinates, indicating the position of the terrain on a two-dimensional plane; the height parameter of the terrain obstacle can reflect the altitude or depth characteristics of the terrain unit in the vertical direction (z axis); Axis direction and The falloff in the axis direction can be used to control the steepness of the terrain. A smaller falloff means a steeper terrain, while a larger falloff means a flatter terrain.

[0050] In practical applications, the terrain obstacle model can be constructed using the following formula (1): (1) in, For the The topological center coordinates of the terrain obstacles, is the height parameter of the terrain obstacle, , Respectively Terrain obstacles in Axis and The amount of attenuation in the axial direction affects the steepness of the underwater terrain. is the number of terrain obstacles.

[0051] In this embodiment, underwater suspended objects are usually irregularly distributed spheres or ellipsoids, such as mud and sand, which have a significant impact on the navigation of the AUV. The suspension position of the suspended obstacle can be represented by its center coordinates; the geometric size of the suspended object in different directions can be controlled by the scaling factor, so that the suspended object can be modeled as an ellipsoid to adapt to the shape characteristics of different suspended objects.

[0052] In practical applications, the suspended obstacle model can be constructed using the following formula (2): (2) in, is the center coordinate of the suspended obstacle, , , For suspended obstacles axis, axis, Scaling factor along the axis.

[0053] In an optional embodiment, when generating an initial reference navigation path for an autonomous underwater vehicle based on a spatial environment model of a target area, a plurality of path points may be determined in the spatial environment model based on the starting point and end point of the autonomous underwater vehicle through an Informed RRT* algorithm so as to generate an initial reference navigation path based on the plurality of path points.

[0054] In this embodiment, the initial position and target position of the AUV are defined as the starting point and the end point, respectively. and end point , the Informed RRT* algorithm takes the starting point and end point As the core, a path tree is recursively constructed to connect two points, and finally a reference path is output.

[0055] In order to improve the efficiency of path planning, we can first construct an ellipsoidal sampling space between the starting point and the end point. The foci of the ellipsoid are the starting point and the end point. and end point , the axis length is determined by the distance between the two points. The ellipsoid sampling space in this embodiment constrains the sampling range of the path points, concentrates the sampling process on the potential path area, reduces the generation of invalid sampling points, and can improve the efficiency of the algorithm.

[0056] In the ellipsoid sampling space, the algorithm performs target-oriented random sampling. Specifically, a new candidate path point is randomly generated each time, and the connection cost between it and the nearest path point in the path tree is calculated. The candidate path point can be represented by three-dimensional coordinates. In practical applications, in order to ensure that the path point gradually moves toward the target position, the direction close to the end point is preferentially selected during the sampling process to form a trend of path convergence.

[0057] After the candidate path points are generated, the path points are checked for safety in combination with the terrain and obstacle information of the target area. Specifically, if the newly generated path point overlaps with the obstacle model, the point is discarded and resampled. If the path point passes the collision test, that is, it is located in the safe area, the path point is included in the path tree and becomes a new valid node. This process ensures that the path point is always outside the obstacle model, improving the feasibility and safety of the path.

[0058] Each time a valid path point is included in the path tree, the structure of the path tree is updated. Specifically, the connection cost from all nodes in the current path tree to the new path point is calculated. The path tree is locally adjusted according to the cost minimization principle so that the path tree gradually tends to the global optimum. Through the dynamic update and optimization of the path points, it gradually converges to an optimal path from the starting point to the end point.

[0059] Finally, the Informed RRT* algorithm outputs an initial reference navigation path from the starting point to the end point. The initial reference navigation path can be expressed based on the following formula (3): (3) The number of path points is , each path point contains three-dimensional position information .

[0060] Figure 3 A schematic diagram of an initial reference navigation path provided by an embodiment of the present invention. Figure 3 As shown, the black sphere in the figure is the end point, and the cube is the starting point and the intermediate path point.

[0061] In this embodiment, the construction of the ellipsoid sampling space constrains the range of random sampling, greatly reduces invalid point sampling, and improves the execution efficiency of the algorithm; by combining the obstacle model for collision detection, it ensures that the path points are always located in the safe area, effectively avoiding the risk of overlap between the path and obstacles; the dynamic update and cost optimization mechanism of the path tree make the generated reference path have good feasibility, providing a high-quality initial path for subsequent steps.

[0062] In an optional embodiment, when establishing an underwater safety corridor for the movement of an autonomous underwater vehicle in a spatial environment model based on an initial reference navigation path, a convex polyhedron containing adjacent path points can first be generated based on adjacent path points in the initial reference navigation path. Then, obstacle detection is performed on the convex polyhedron based on an obstacle model, and the detection result is output. If the detection result shows that the obstacle model is located within the convex polyhedron, the convex polyhedron is regenerated so that the obstacle model is located outside the convex polyhedron. Finally, a redundant detection is performed on the multiple convex polyhedrons generated based on the initial reference navigation path to remove the redundant parts of the convex polyhedron, and an underwater safety corridor is generated based on the convex polyhedron.

[0063] In this embodiment, according to the path point sequence in the initial reference navigation path , for any adjacent path point and Defining path segments A convex polyhedron is constructed on each path segment to represent the local area of ​​the underwater safety corridor.

[0064] Convex polyhedra can be defined by the following set of linear inequalities (4): (4) in, is the face normal vector matrix of a convex polyhedron, with each row corresponding to one face; is any point in three-dimensional space; is the location information of each face, based on the path points and and safe distance Calculated.

[0065] The six faces of the convex polyhedron are determined by the minimum and maximum coordinate values ​​of the path points in three-dimensional space, combined with the safety distance The definition of is shown in the following formula (5): , (5) in, and Indicates that the end points of the path segment are The maximum and minimum values ​​along the axis, and Indicates that the end points of the path segment are The maximum and minimum values ​​along the axis, and Indicates that the end points of the path segment are Maximum and minimum values ​​in the axis direction, safety distance Defined as the minimum safe separation between a path segment and an obstacle model, used to increase the safety margin.

[0066] To ensure that there are no obstacles in the safety corridor, it is necessary to perform obstacle validity detection on the convex polyhedron. Whether it is inside a convex polyhedron is determined by the following formula (6): (6) If the detection result shows that the obstacle point is located in the convex polyhedron, the algorithm will resample the points on the path segment to adjust the boundary of the convex polyhedron until the newly generated convex polyhedron can completely eliminate the obstacle. This step ensures that the obstacle-free area is cleared in each convex polyhedron, thereby constructing a safe underwater channel.

[0067] In scenes with dense obstacles, the path segments can be refined to improve the resolution of the safety corridor. , by setting the step size The path segments are refined to obtain new path segments. A convex polyhedron is generated on each new path segment, and obstacle validity detection is performed on each convex polyhedron to ensure that there are no obstacle points in the safety corridor. The step length calculation formula (7) is: (7) in: is the scale factor, which controls the refinement of the path segment (usually 0.2); is the Euclidean distance of the path segment.

[0068] After completing the construction of the convex polyhedrons of all path segments, the redundancy of adjacent convex polyhedrons is detected, unnecessary areas are removed, and a compact underwater safety corridor is optimized. The optimized underwater safety corridor is shown in formula (8): (8) In this embodiment, the optimized underwater safety corridor has the following characteristics: no redundant convex polyhedrons, high space utilization; each convex polyhedron is closely connected to ensure the continuity of the AUV motion trajectory; obstacles are completely isolated to meet the requirements of safe navigation. In this embodiment, the schematic diagram of the underwater safety corridor generated based on the above method is as follows Figure 4 The schematic diagram of the underwater safety corridor after removing the obstacle model is shown in Figure 5 shown.

[0069] Through the above method, the constructed underwater safety corridor ensures that the AUV can safely pass through a three-dimensional complex environment, while optimizing space utilization and path compactness. The segmented generation and optimization of convex polyhedrons make the entire underwater safety corridor both flexible and ensure navigation safety, effectively solving the problem that path planning in existing technologies is difficult to adapt to complex dynamic obstacles.

[0070] In an optional embodiment, in the underwater safety corridor, when performing spatial trajectory optimization processing and temporal trajectory optimization processing on the initial reference navigation path to generate the target space-time movement navigation trajectory, the following steps may be performed: First, the initial reference navigation path can be optimized in space based on the Bezier curve to generate a first space-time moving trajectory. Specifically, based on the quadratic programming algorithm, the acceleration of the trajectory can be minimized while satisfying the constraints to generate a smooth first space-time moving trajectory. In this embodiment, the control points of the Bezier curve meet the following constraints: state constraints of the starting point and the end point, including position, speed and acceleration; the control points are all located in the underwater safety corridor; the speed and acceleration of the trajectory meet the preset range.

[0071] Then, based on the optimized first spatiotemporal movement trajectory, the time allocation of each trajectory segment between adjacent path points is optimized to minimize the trajectory time cost and jerk, thereby generating a target spatiotemporal movement navigation trajectory.

[0072] In the process of AUV trajectory optimization, Bezier curves can be used to represent the trajectory of each path. Bezier curves are very suitable for path planning and adjustment in underwater environments due to their smoothness and easy control. Specifically, the AUV trajectory can be divided into The Bezier curve segment represents the The expression of the Bezier curve of the segment is shown in the following formula (9): , (9) in, For Bezier curves in parameters The trajectory point at is the Bezier basis function, indicating the Control point to trajectory point The weight of influence; For the The coordinates of the control points determine the shape of the Bezier curve; is the order of the Bezier curve, and the number of control points is ; is the normalized time parameter, and its value range is .

[0073] The specific expression of the Bezier basis function is shown in the following formula (10): (10) in, To indicate from Select from the elements The number of combinations of elements, is the normalized time parameter, and its value range is .

[0074] Therefore, in order to ensure the safety of AUV when performing tasks in complex marine environments, the control points of the Bezier curve must be constrained within the defined underwater safety corridor.

[0075] In trajectory optimization, multiple constraints need to be met to ensure that the AUV's motion is both smooth and safe in an underwater environment. These constraints include: initial and terminal state constraints, collision avoidance constraints, and velocity and acceleration constraints.

[0076] Initial and final state constraints: The starting and ending points of the trajectory must satisfy specific state constraints, including position, velocity, and acceleration. Assume that the starting state of the AUV is , , The end state is , , , then the state constraint condition of the starting point is as shown in the following formula (11): (11) in, is the Bezier curve in time The position at which the curve starts. is the specific coordinate value of the starting point, indicating the initial position of the autonomous underwater vehicle; is the Bezier curve in time The first-order derivative at time represents the velocity vector at the starting point; is the specific value of the initial speed, indicating the moving speed of the autonomous underwater vehicle at the starting point; is the Bezier curve in time The second-order derivative at represents the acceleration vector at the starting point; is the specific value of the initial acceleration, which represents the acceleration of the autonomous underwater vehicle at the starting point.

[0077] The state constraint of the endpoint is shown in the following formula (12): (12) in, is the Bezier curve in time The position at which the curve ends. is the specific coordinate value of the end point position, indicating the end point position of the autonomous underwater vehicle; is the Bezier curve in time The first-order derivative at represents the velocity vector at the end point; is the specific value of the terminal velocity, indicating the moving speed of the autonomous underwater vehicle at the terminal point; is the Bezier curve in time The second-order derivative at represents the acceleration vector at the end point; is the specific value of the terminal acceleration, which represents the acceleration of the autonomous underwater vehicle at the terminal point.

[0078] The state constraints at the start and end points can ensure that the states of the trajectory at the start and end points meet the task requirements, avoiding inappropriate paths or failure to reach the target.

[0079] Collision avoidance constraints: In order to ensure that the AUV trajectory is always within the underwater safety corridor, the control points of each Bezier curve Must be located in the corresponding underwater safety corridor This can be expressed by the following linear inequality constraint (13): (13) in, Indicates The face normal matrix of a convex polyhedron, For the trajectory The coordinate vectors of the control points of the Bezier curve, Indicates The offset or position vector of a convex polyhedron.

[0080] The collision avoidance constraint can ensure that all control points are in a safe area, thus preventing the AUV from colliding with obstacles.

[0081] Velocity and acceleration constraints: In order to ensure the dynamic feasibility of the AUV, the velocity and acceleration of the trajectory must meet certain constraints. For example, the maximum velocity is set to , the maximum acceleration is , then for each path segment, the following constraints must be satisfied: , , (14) in, To represent the trajectory Segment in time The velocity vector at time , To represent the trajectory Segment in time The acceleration vector at time .

[0082] Velocity and acceleration ensure that the AUV’s trajectory does not result in excessive acceleration or deceleration that is inconsistent with physical limitations, thereby improving navigation stability.

[0083] The trajectory optimization goal of AUV is to minimize jerk, that is, the rate of change of acceleration. Jerk describes the smoothness of acceleration. Minimizing jerk can significantly reduce the sudden acceleration generated by AUV during underwater navigation, thereby improving the smoothness and energy efficiency of navigation. The objective function can be expressed as: (15) in, Represents the value of the optimization objective function, which is used to measure the smoothness of the trajectory; represents the number of trajectory segments; To indicate the The third-order derivative of the segment trajectory (i.e., jerk). By integrating the square of the jerk, a quantity that measures the smoothness of the trajectory is obtained. The goal is to make the motion trajectory of the AUV smoother, reduce mechanical vibration, and improve navigation stability and mission execution efficiency through optimization.

[0084] In addition, through the representation of control points, this objective function can be further discretized into the weighted sum of control points: (16) in, Represents the value of the optimization objective function, which is used to measure the smoothness of the trajectory; represents the number of trajectory segments; Indicates Segment trajectory in time The trajectory point of Represents trajectory points The transpose of Represents the weight matrix, which is used to adjust the weights of different directions or dimensions in trajectory smoothness optimization.

[0085] By adjusting the control points, the jerk can be minimized, resulting in a smoother trajectory.

[0086] The final trajectory optimization problem is formalized as a quadratic programming problem (QP), the goal of which is to minimize the objective function , while satisfying the above constraints. The mathematical expression of the optimization problem is shown in the following formula (17): (17) Among them, the constraints include the state requirements of the starting point and the end point, the collision avoidance requirements, and the speed and acceleration limits. They can be solved by common quadratic programming solvers or other numerical optimization methods. The result of the solution will obtain a smooth trajectory with minimum energy consumption and minimum jitter, ensuring the efficient and safe operation of the AUV in complex underwater environments.

[0087] Based on the above method, the trajectory planning of the AUV is optimized in both space and time dimensions. Bezier curves are used to describe each path segment, and the control points are subject to multiple constraints, such as collision avoidance, speed and acceleration limits, and state constraints at the start and end points. Finally, by minimizing the jerk, the optimized trajectory is not only smooth, but also effectively improves the dynamic adaptability and mission execution efficiency of the AUV.

[0088] In an optional embodiment, based on the optimized first spatiotemporal movement trajectory, time allocation of each trajectory segment between adjacent path points is optimized to minimize trajectory time cost and jerk, and when generating a target spatiotemporal movement navigation trajectory, the following steps are included: First, the time of each trajectory segment is preliminarily allocated according to the trajectory length corresponding to each trajectory segment between adjacent path points and the maximum speed of the autonomous underwater vehicle.

[0089] Then, the time allocation is iteratively adjusted through the optimization algorithm so that the time allocation of each trajectory segment meets the constraints of speed, acceleration and jump, and minimizes the time cost.

[0090] In this embodiment, the core goal of time trajectory optimization is to optimize the time allocation of each segment of the trajectory so that the AUV can complete the task in the shortest time or at the lowest cost while satisfying the physical constraints of motion such as speed, acceleration and jump. Specifically, the optimized trajectory should have the following characteristics: reasonable time allocation and smooth path; optimal energy consumption and high execution efficiency; satisfying dynamic environmental constraints and improving task adaptability. By adjusting the time allocation on each segment of the trajectory, the time optimization of the entire trajectory can be achieved.

[0091] Before optimization, the time of the AUV on each trajectory segment is initially allocated. The initial time allocation is based on the length of the trajectory segment and the maximum speed of the AUV. Assume that The length of the segment trajectory is , its initial time The calculation formula is shown in the following formula (18): (18) in, For the The duration of the segment trajectory; For the The end point of the path segment, indicating the The spatial coordinates of the end point of the segment path; For the The starting point of the path segment, indicating the The spatial coordinates of the starting point of the segment path; is the maximum speed of the AUV.

[0092] This method effectively provides a preliminary time allocation for each trajectory segment while ensuring that the time of the trajectory segment is proportional to its length. The initial time allocation provides a reasonable starting point for subsequent optimization.

[0093] The objective function of time optimization consists of two parts: the time cost term and the motion smoothness term. The objective function is defined as: (19) in, is the dynamic smoothness cost function, which means minimizing the rate of change (jump) of acceleration in each segment of the trajectory to ensure the smoothness of the trajectory; is the time cost term, and the goal is to minimize the total time cost while ensuring the physical constraints; is a weight factor used to balance the weight of time cost and motion smoothness.

[0094] In this embodiment, in order to ensure the practical feasibility of the AUV during the time optimization process, the following constraints need to be met: Speed ​​constraint: The speed of the trajectory cannot exceed the maximum speed of the AUV ; Acceleration constraint: The acceleration must be within the physically controllable range; Jerk constraint: The jerk (rate of change of acceleration) should be within a reasonable range to avoid excessive motion mutations; Trajectory smoothness constraint: The time-optimized trajectory needs to match the space-optimized trajectory to ensure overall smoothness.

[0095] Time optimization is an iterative adjustment process that continuously adjusts the time allocation until it converges to the optimal solution. The optimization process includes the following steps: Initial calculation: Allocate according to the current time , calculate the velocity, acceleration and jump of each trajectory; Cost calculation: According to the objective function , evaluate the overall cost of the current time allocation; Time adjustment: adjust the time allocation of each segment according to the gradient of the cost function , while ensuring that the constraints are satisfied; Iterative update: Repeat the above process until the optimization result converges to the optimal time allocation.

[0096] The final time optimization result is the target time allocation that meets the following requirements: the time cost of each trajectory is minimized; the trajectory smoothness is optimized and the jump fluctuation is minimized; and the constraints of speed, acceleration and jump are met.

[0097] Through time optimization, the trajectory of the AUV can achieve dynamic adaptability and high efficiency, which is specifically manifested in: improved execution efficiency: time optimization reduces the ineffective movement time of the AUV in the mission; reduced energy consumption: unnecessary sudden acceleration and deceleration are avoided through smooth trajectory and reasonable time allocation; improved safety: the optimized trajectory meets all physical constraints to ensure the safe operation of the AUV; enhanced dynamic adaptability: real-time adjustment can be made in complex marine environments to ensure the optimal trajectory.

[0098] In summary, through scientific and reasonable time allocation and iterative adjustment, not only the mission execution capability of AUV is significantly improved, but also the problem of insufficient time optimization in the existing technology is overcome.

[0099] In an optional embodiment, the target spatiotemporal navigation trajectory is an optimal trajectory obtained by alternating iterative calculation of spatial optimization results and temporal optimization results after multiple spatial trajectory optimization processes and temporal trajectory optimization processes.

[0100] In this embodiment, the initial reference navigation path is optimized in the joint solution space by alternating iterative calculations of spatial trajectory optimization and temporal trajectory optimization combined with the coordinate descent method. The specific steps include: Based on the initial trajectory, the spatial trajectory and the temporal trajectory are optimized in turn.

[0101] In each optimization, the positions and time allocations of the control points are adjusted respectively so that the trajectory can satisfy the path smoothness, velocity and acceleration constraints while minimizing the time cost.

[0102] Through alternating iterations, the optimal solution of the joint solution space is gradually approached, ensuring that the AUV has the highest efficiency and safety when completing tasks in underwater environments.

[0103] Based on the above embodiments, spatial trajectory optimization is based on Bezier curves, and the control points are adjusted using a quadratic programming algorithm. The optimization objectives include: path smoothness, by adjusting the position of the control points and the curve shape, eliminating sharp turns and path mutations, making the trajectory more continuous; spatial constraints, the control points must be located within the underwater safety corridor to ensure that the trajectory does not intersect with obstacles; energy efficiency, the optimized trajectory should minimize the path length, thereby reducing the energy consumption of the AUV.

[0104] The time trajectory optimization is centered on the time allocation between path points and is adjusted based on the following goals: time optimality, minimizing the time cost of the trajectory by optimizing the time allocation; dynamic constraints, ensuring that the changes in speed, acceleration, and jump are within the allowable range of the AUV to avoid unnecessary intense movements; trajectory consistency, after the optimized time allocation is combined with the spatial trajectory, consistent dynamic performance should be maintained.

[0105] During the optimization process, in order to accurately evaluate the dynamic characteristics of the trajectory, the velocity and acceleration need to be accurately calculated: For the trajectory Segment path, its speed The calculation formula is as follows: (20) in, For the Segment path at time speed, is the speed coefficient associated with the Bezier curve, For the The control points of the Bezier curve of the segment path.

[0106] By accurately calculating the speed, the time allocation between trajectory points can be dynamically adjusted during the time optimization process to ensure that the speed is always within the preset range.

[0107] For the trajectory Segment path, its acceleration The calculation formula is: (twenty one) in, Indicates Segment path at time The acceleration of is the acceleration coefficient associated with the Bezier curve, For the The control points of the Bezier curve of the segment path.

[0108] Accurate calculation of acceleration helps to limit sudden acceleration changes and optimize time allocation to make the trajectory smoother.

[0109] In this embodiment, when spatial optimization and time optimization are alternately iterated, the following steps can be performed: initializing the trajectory, generating an initial trajectory based on the target area and the starting point and the end point; spatial optimization, adjusting the control point positions, optimizing the trajectory smoothness and path length, and satisfying the underwater safety corridor constraints; time optimization, adjusting the time allocation according to the optimized spatial trajectory so that the speed and acceleration meet the constraints; iterative update, repeating the above two steps, and gradually approaching the optimal solution of the joint solution space; termination condition, when the optimization converges or reaches the preset optimization accuracy, outputting the optimal trajectory.

[0110] After alternating optimization, the target space-time mobile navigation trajectory has the following characteristics: the spatial trajectory is continuous without mutation points; the speed and acceleration are within the safe range, which is consistent with the AUV's motion capabilities; the time cost is minimal and the task completion efficiency is high; the trajectory completely avoids obstacles and is always within the underwater safety corridor.

[0111] In this embodiment, it can be verified by experiments with different starting points, end points and seabed terrain conditions. For example, when the starting point is (−20, 20, 0), the end points are (−6, −23, 6), (20, −20, 4), (20, 15, 6), and the number of terrain obstacles is 10, 20 and 30 respectively, a smooth and efficient optimal trajectory can be generated. In the experiment, the maximum speed is 2 m / s and the maximum acceleration is 2 m / s. 2 ,The curves of the position, velocity and acceleration of the trajectory changing with time show that ,the optimization results meet all the constraints, verifying the effectiveness of the ,scheme.

[0112] In this embodiment, the starting point is (-20, 20, 0), the end point is (20, -20, 4), the maximum speed is 2m / s, and the maximum acceleration is 2m / s 2 As an example, the curve diagram of the target space-time mobile navigation trajectory position changing with time is as follows Figure 6 As shown in the figure, the curve diagram of the speed of the target space-time moving navigation trajectory changing with time is as follows Figure 7 As shown in the figure, the curve diagram of the acceleration of the target space-time mobile navigation trajectory changing with time is as follows Figure 8 shown.

[0113] This embodiment significantly improves the task execution efficiency and robustness of AUV in complex underwater environments through space-time joint optimization and dynamic characteristic control, and has high practical application value.

[0114] The spatiotemporal trajectory planning method for an autonomous underwater vehicle provided by an embodiment of the present invention is described below with reference to the accompanying drawings.

[0115] In this embodiment, it is assumed that in the same spatial environment model, a starting point Q, an end point 1, an end point 2, and an end point 3 are set. Based on the above three end points, a total of three target space-time mobile navigation trajectories are generated by the autonomous underwater vehicle space-time trajectory planning method provided by the embodiment of the present invention. Among them, the schematic diagram of the first target space-time mobile navigation trajectory between the starting point Q and the end point 1 is as follows Fig. 9 As shown, the schematic diagram of the second target space-time moving navigation trajectory between the starting point Q and the end point 2 is as follows Fig.10 As shown, the schematic diagram of the third target space-time mobile navigation trajectory between the starting point Q and the end point 3 is as follows Fig.11 shown.

[0116] like Fig. 9 As shown in the figure, the AUV's first target space-time navigation trajectory is short and avoids some high terrain obstacles. Since the end point is located in the middle and lower area of ​​the environment, the trajectory shows a significant downward trend when approaching the end point.

[0117] like Fig.10 As shown in Figure 1, the AUV's second target space-time navigation trajectory is longer and the path crosses a more complex obstacle area. The end point is distributed on a lower plane, and the trajectory gradually adjusts its height to adapt to the terrain when approaching the end point.

[0118] like Fig.11 As shown in the figure, the end point of the AUV's third target space-time mobile navigation trajectory is located in the upper area of ​​the environment. Compared with the first target space-time mobile navigation trajectory and the second target space-time mobile navigation trajectory, the trajectory has a slight increase in height when approaching the end point. This shows that the planning method can adaptively adjust the Z-axis component of the trajectory according to the height change of the end point position.

[0119] In summary, under different endpoint settings, the performance of the AUV's target spatiotemporal mobile navigation trajectory in a complex seabed environment has significant differences, but as a whole, it can meet the core goals of planning, that is, to ensure the smoothness, safety, and dynamic adaptability of the trajectory.

[0120] In this embodiment, it is assumed that the number of obstacle models is adjusted for the same spatial environment model to generate three different spatial environment models. The same starting point and end point are set, and a total of three target space-time mobile navigation trajectories are generated by the autonomous underwater vehicle space-time trajectory planning method provided by the embodiment of the present invention. Among them, the fourth target space-time mobile navigation trajectory, the fifth target space-time mobile navigation trajectory, and the sixth target space-time mobile navigation trajectory generated based on the above three different spatial environment models are respectively as follows: Fig. 9 , Fig.10 and Fig.11 shown.

[0121] By analyzing the above three figures, it can be seen that under the same spatial environment model, as the number of obstacle models increases, the autonomous underwater vehicle spatiotemporal trajectory planning method can dynamically adjust the planned trajectory according to the complexity of different environments to achieve the optimization of path safety, smoothness and energy efficiency. The following is a detailed analysis of the trajectory characteristics combined with specific diagrams: like Fig. 9 As shown in the figure, there are fewer obstacle models and the spatial environment is relatively open. The planned trajectory is relatively linear, avoiding limited obstacle models, and the path is short and smooth. In a simple environment, this method can plan an efficient target trajectory with the lowest energy consumption and the shortest time.

[0122] like Fig.10 As shown in the figure, the number of obstacle models is moderate and the complexity of the spatial environment has increased. The planned trajectory shows a certain degree of tortuosity in space, and by avoiding more obstacles, the continuity and smoothness of the trajectory can still be maintained. In a complex environment, the spatiotemporal trajectory planning method makes full use of the underwater safety corridor mechanism to effectively avoid obstacles and find a balance between path smoothness and energy efficiency.

[0123] like Fig.11 As shown in the figure, the number of obstacle models is the largest and the spatial environment is extremely complex. The planned trajectory is more flexible and shows obvious tortuosity. At the same time, it strictly follows the boundary of the underwater safety corridor on the path to ensure that the obstacles are completely outside the safety corridor. In a highly complex environment, this method can dynamically adjust the spatiotemporal trajectory parameters to ensure that the autonomous underwater vehicle can safely pass through narrow areas while ensuring the smoothness and robustness of the path.

[0124] In summary, the method provided by the embodiment of the present invention can adapt to spatial environments of different complexities and generate safe and reliable trajectories by constructing underwater safety corridors and combining trajectory optimization in time and space. As the number of obstacle models increases, the smoothness and energy efficiency of the trajectory are taken into account, while avoiding the path discontinuity problem caused by the increase in obstacles. The method can optimize the speed and acceleration parameters in environments of different complexities, maximize the operating efficiency of the autonomous underwater vehicle, and show excellent adaptability and robustness.

[0125] Based on the above-mentioned autonomous underwater vehicle spatiotemporal trajectory planning method provided by the embodiment of the present invention, the embodiment of the present invention also provides an autonomous underwater vehicle spatiotemporal trajectory planning device, such as Fig.15 As shown, the autonomous underwater vehicle spatiotemporal trajectory planning device includes a generation module 1501, a creation module 1502 and a processing module 1503.

[0126] The generation module 1501 is used to generate an initial reference navigation path of the autonomous underwater vehicle based on the spatial environment model of the target area, where the spatial environment model includes an obstacle model in the target area, and a starting point and an end point of the autonomous underwater vehicle.

[0127] The establishing module 1502 is used to establish an underwater safety corridor for the movement of the autonomous underwater vehicle in the spatial environment model based on the initial reference navigation path, and the obstacle model is located outside the underwater safety corridor.

[0128] The processing module 1503 is used to perform spatial trajectory optimization processing and temporal trajectory optimization processing on the initial reference navigation path in the underwater safety corridor to generate a target space-time movement navigation trajectory.

[0129] According to an embodiment of the present invention, the obstacle model includes a terrain obstacle model and a suspended obstacle model. Accordingly, the establishment module 1502 is also used to generate a terrain obstacle model based on the topological center point coordinates, height parameters and terrain obstacle parameters of the terrain obstacle. Axis direction and The terrain obstacle model is constructed based on the attenuation in the axial direction; and the center coordinates of the suspended obstacle and the Axis direction, Axis direction and The suspended obstacle model is constructed based on the scaling factors corresponding to the axis directions.

[0130] According to an embodiment of the present invention, the generation module 1501 is specifically used to determine multiple path points in the spatial environment model based on the starting point and the end point of the autonomous underwater vehicle through the Informed RRT* algorithm, so as to generate an initial reference navigation path based on the multiple path points.

[0131] According to an embodiment of the present invention, a module 1502 is established, which is specifically used to generate a convex polyhedron containing adjacent path points based on adjacent path points in an initial reference navigation path; perform obstacle detection on the convex polyhedron based on an obstacle model, and output the detection result; if the detection result shows that the obstacle model is located within the convex polyhedron, regenerate the convex polyhedron so that the obstacle model is located outside the convex polyhedron; perform redundancy detection on multiple convex polyhedrons generated based on the initial reference navigation path to remove redundant parts of the convex polyhedron, and generate an underwater safety corridor based on the convex polyhedron.

[0132] According to an embodiment of the present invention, the processing module 1503 is specifically used to perform spatial trajectory optimization processing on the initial reference navigation path based on the Bezier curve to generate a first space-time mobile trajectory; based on the optimized first space-time mobile trajectory, perform time trajectory optimization processing on the time allocation of each trajectory segment between adjacent path points to minimize the trajectory time cost and acceleration, and generate a target space-time mobile navigation trajectory; wherein the control points of the Bezier curve meet the following constraints: state constraints of the starting point and the end point, including position, speed and acceleration; the control points are all located in the underwater safety corridor; the speed and acceleration of the trajectory meet the preset range.

[0133] According to an embodiment of the present invention, the processing module 1503 is specifically configured to minimize the jerk of the trajectory based on a quadratic programming algorithm while satisfying constraint conditions, so as to generate a smooth first spatiotemporal movement trajectory.

[0134] According to an embodiment of the present invention, the processing module 1503 is specifically used to preliminarily allocate the time of each trajectory segment according to the trajectory length corresponding to each trajectory segment between adjacent path points and the maximum speed of the autonomous underwater vehicle; and iteratively adjust the time allocation through an optimization algorithm so that the time allocation of each trajectory segment satisfies the constraints of speed, acceleration and jump, and minimizes the time cost.

[0135] According to an embodiment of the present invention, the target spatiotemporal mobile navigation trajectory is an optimal trajectory obtained by alternating iterative calculation of spatial optimization results and temporal optimization results after multiple spatial trajectory optimization processes and temporal trajectory optimization processes.

[0136] An embodiment of the present invention further provides an electronic device, comprising: at least one processor; and a memory in communication with the at least one processor. The memory stores a computer program executable by the at least one processor, and when the at least one processor executes the computer program, the electronic device executes the method of the embodiment of the present invention.

[0137] An embodiment of the present invention further provides a non-transitory machine-readable medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method of the embodiment of the present invention.

[0138] An embodiment of the present invention further provides a computer program product, including a computer program, wherein the computer program, when executed by a processor of a computer, is used to enable the computer to execute the method of the embodiment of the present invention.

[0139] refer to Fig.16, a block diagram of an electronic device that can be used as a server or client of an embodiment of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, 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.

[0140] like Fig.16 As shown, the electronic device includes a computing unit 1601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1602 or a computer program loaded from a storage unit 1608 to a random access memory (RAM) 1603. In RAM 1603, various programs and data required for the operation of the electronic device can also be stored. The computing unit 1601, ROM 1602, and RAM 1603 are connected to each other via a bus 1604. An input / output (I / O) interface 1605 is also connected to the bus 1604.

[0141] Multiple components in the electronic device are connected to the I / O interface 1605, including: an input unit 1606, an output unit 1607, a storage unit 1608, and a communication unit 1609. The input unit 1606 can be any type of device that can input information to the electronic device, and the input unit 1606 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device. The output unit 1607 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1608 can include but is not limited to a disk, an optical disk. The communication unit 1609 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0142] The computing unit 1601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1601 include, but are not limited to, a CPU, a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1601 performs the various methods and processes described above. For example, in some embodiments, the method embodiments of the present invention may be implemented as a computer program, which is tangibly contained in a machine-readable medium, such as a storage unit 1608. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via ROM 1602 and / or communication unit 1609. In some embodiments, the computing unit 1601 may be configured to perform the above method in any other appropriate manner (e.g., by means of firmware).

[0143] The computer programs for implementing the methods of the embodiments 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 or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of an embodiment of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable signal medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. 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.

[0145] It should be noted that the term "including" and its variations used in the embodiments of the present invention are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "multiple" mentioned in the embodiments of the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

[0146] The various steps described in the method implementation methods provided in the embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method implementation methods may include additional steps and / or omit the steps shown. The scope of protection of the present invention is not limited in this respect.

[0147] The term "embodiment" in this specification refers to specific features, structures or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. The various embodiments in this specification are described in a related manner, and the same or similar parts between the various embodiments refer to each other. In particular, for the device, equipment, and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment.

[0148] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the attached claims.

Claims

1. A method for spatiotemporal trajectory planning of an autonomous underwater vehicle, comprising: Generate an initial reference navigation path for the autonomous underwater vehicle based on a spatial environment model of the target area, wherein the spatial environment model includes an obstacle model within the target area, a starting point and an end point of the autonomous underwater vehicle; Based on the initial reference navigation path, establishing an underwater safety corridor for movement of the autonomous underwater vehicle in the spatial environment model, wherein the obstacle model is located outside the underwater safety corridor; In the underwater safety corridor, the initial reference navigation path is subjected to spatial trajectory optimization processing and temporal trajectory optimization processing to generate a target spatiotemporal movement navigation trajectory.

2. The method according to claim 1, characterized in that The obstacle model includes a terrain obstacle model and a suspended obstacle model; the method further includes: Based on the topological center coordinates, height parameters and the terrain obstacles Axis direction and The terrain obstacle model is constructed based on the attenuation in the axial direction; Based on the central coordinates of the suspended obstacle, the suspended obstacle Axis direction, Axis direction and The suspended obstacle model is constructed by using scaling factors corresponding to the respective axis directions.

3. The method according to claim 1, characterized in that The generating of an initial reference navigation path of the autonomous underwater vehicle based on the spatial environment model of the target area comprises: Based on the starting point and the end point of the autonomous underwater vehicle, a plurality of waypoints are determined in the spatial environment model by an Informed RRT* algorithm, so as to generate the initial reference navigation path based on the plurality of waypoints.

4. The method according to claim 3, characterized in that The step of establishing an underwater safety corridor for movement of the autonomous underwater vehicle in the spatial environment model based on the initial reference navigation path comprises: Based on the adjacent path points in the initial reference navigation path, generating a convex polyhedron including the adjacent path points; Performing obstacle detection on the convex polyhedron based on the obstacle model, and outputting the detection result; If the detection result indicates that the obstacle model is located within the convex polyhedron, regenerating the convex polyhedron so that the obstacle model is located outside the convex polyhedron; Redundancy detection is performed on the multiple convex polyhedrons generated based on the initial reference navigation path to remove redundant parts of the convex polyhedrons, and the underwater safety corridor is generated based on the convex polyhedrons.

5. The method according to claim 3, characterized in that: In the underwater safety corridor, the initial reference navigation path is subjected to spatial trajectory optimization processing and temporal trajectory optimization processing to generate a target spatiotemporal movement navigation trajectory, including: Performing spatial trajectory optimization processing on the initial reference navigation path based on a Bezier curve to generate a first spatiotemporal movement trajectory; Based on the optimized first spatiotemporal movement trajectory, time allocation of each trajectory segment between adjacent path points is optimized to minimize trajectory time cost and jerk, thereby generating the target spatiotemporal movement navigation trajectory; Among them, the control points of the Bezier curve meet the following constraints: state constraints of the starting point and the end point, including position, speed and acceleration; the control points are all located in the underwater safety corridor; the speed and acceleration of the trajectory meet the preset range.

6. The method according to claim 5, characterized in that The performing spatial trajectory optimization processing on the initial reference navigation path based on the Bezier curve to generate a first spatiotemporal movement trajectory includes: Based on the quadratic programming algorithm, the jerk of the trajectory is minimized while satisfying the constraint conditions to generate a smooth first spatiotemporal movement trajectory.

7. The method according to claim 5, characterized in that The step of performing time trajectory optimization processing on the time allocation of each segment of the trajectory between adjacent path points based on the optimized first time-space movement trajectory to minimize the trajectory time cost and jerk, and generating the target time-space movement navigation trajectory, includes: Preliminarily allocating time for each trajectory segment based on the trajectory length corresponding to each trajectory segment between adjacent path points and the maximum speed of the autonomous underwater vehicle; The time allocation is iteratively adjusted through the optimization algorithm to make the time allocation of each trajectory meet the constraints of speed, acceleration and jump, and minimize the time cost.

8. The method according to claim 5, characterized in that The target spatiotemporal navigation trajectory is an optimal trajectory obtained by alternating and iterative calculation of spatial optimization results and temporal optimization results after multiple spatial trajectory optimization processes and temporal trajectory optimization processes.

9. An electronic device, comprising: A processor, and a memory storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the method according to any one of claims 1 to 8.

10. A non-transitory machine-readable medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 8.

Images