Efficient low-power-consumption path planning method based on reciprocating underwater hull cleaning robot

Abstract

The invention relates to the technical field of underwater robot cleaning, and discloses a high-efficiency low-power-consumption path planning method based on a reciprocating underwater hull cleaning robot, and the method comprises the steps: generating a two-dimensional cleaning planning plane according to the surface contour point cloud data of a to-be-cleaned hull, carrying out safety constraint on the motion mode of the underwater ship body cleaning robot of the to-be-cleaned ship body to obtain a target cleaning robot, analyzing the cleaning path of the target cleaning robot in the two-dimensional cleaning planning plane, generating a reciprocating coverage path in the cleaning area of the to-be-cleaned ship body, and carrying out the cleaning of the to-be-cleaned ship body. And multi-cleaning-area sequential scheduling and path splicing are conducted on the back-and-forth coverage path, a whole-hull cleaning path is obtained, energy consumption self-adaptive adjustment is conducted on the whole-hull cleaning path, and a target cleaning path of the target cleaning robot is obtained. On the premise that coverage integrity is guaranteed, cleaning energy consumption is remarkably reduced, path execution efficiency is improved, and the self-adaptive capacity of an underwater ship body cleaning task to complex working conditions is enhanced.

Description

Technical Field

[0001] This invention relates to the field of underwater robot cleaning technology, and in particular to a high-efficiency, low-power path planning method for a reciprocating underwater hull cleaning robot. Background Technology

[0002] Currently, underwater hull cleaning robots widely employ a reciprocating path planning method for hull surface cleaning. This method is typically based on a geometric model of the hull surface, dividing it into several cleaning strips along the longitudinal direction or continuous curvature of the hull, and generating regular reciprocating paths within these strips to achieve comprehensive cleaning of the hull surface. This type of method is simple to operate, low in implementation cost, and can accomplish routine hull cleaning tasks to a certain extent, while also being easy to deploy on existing low-cost control systems.

[0003] However, existing rule-based path planning relies primarily on static geometric information, failing to adequately consider dynamic factors in the actual underwater environment, such as water flow disturbances, robot posture changes, and mechanical disturbances generated by wall-adhesion motion. In practical applications, this static planning method easily leads to the following problems: first, path redundancy or repeated coverage reduces cleaning efficiency; second, the robot frequently adjusts its posture during turning or reversing, increasing control complexity and energy consumption; and third, it lacks adaptability to environmental changes. When the hull drifts or deviates due to water flow, the cleaning path is difficult to adjust in time, thus affecting the cleaning effect and the robot's endurance.

[0004] To improve path planning efficiency and energy consumption, collaborative coverage and partitioned round-trip scheduling strategies from the UAV swarm field can be adopted. These methods achieve multi-agent collaborative coverage by dividing the coverage area and optimizing the scheduling order, reducing redundant coverage and idle travel, thereby improving overall efficiency. However, UAV coverage methods are typically applied to two-dimensional or weakly constrained spaces, while the hull surface is a complex three-dimensional curved surface with both adsorption mechanisms and normal motion constraints, making direct application of the algorithm difficult and limiting its direct application value in path planning for underwater hull cleaning robots.

[0005] Therefore, existing reciprocating underwater hull cleaning path planning relies solely on static geometric models and does not fully consider dynamic environmental factors such as water flow disturbances and robot posture changes, resulting in high energy consumption, low coverage efficiency, and poor adaptability. Summary of the Invention

[0006] This invention provides an efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot. Its main purpose is to solve the problems of high energy consumption, low coverage efficiency and poor adaptability in existing reciprocating underwater hull cleaning path planning methods that rely only on static geometric models and do not fully consider dynamic environmental factors such as water flow disturbance and robot posture changes.

[0007] To achieve the above objectives, this invention provides a high-efficiency, low-power path planning method for a reciprocating underwater hull cleaning robot, comprising: Acquire the surface contour point cloud data of the hull to be cleaned, and generate a two-dimensional cleaning planning plane based on the surface contour point cloud data; By applying safety constraints to the motion mode of the underwater hull cleaning robot to be cleaned, the target cleaning robot is obtained. The cleaning path of the target cleaning robot on the two-dimensional cleaning planning plane is analyzed to generate a round-trip coverage path within the cleaning area of ​​the hull to be cleaned. The round-trip coverage path is sequentially scheduled for multiple cleaning areas and spliced ​​together to obtain the full hull cleaning path. The energy consumption of the full-hull cleaning path is adaptively adjusted to obtain the target cleaning path of the target cleaning robot.

[0008] In a preferred embodiment, generating a two-dimensional cleaning planning plane based on the surface contour point cloud data includes: The surface contour point cloud data is denoised and resampled to obtain smooth surface contour data; Obtain the hull geometry features of the hull to be cleaned, and divide the surface contour smoothing data into several local areas to be cleaned based on the hull geometry features; Minimum distortion mapping is performed on the three-dimensional surface of each local area to be cleaned to obtain a two-dimensional local area to be cleaned. All the two-dimensional local areas to be cleaned are summarized into a two-dimensional cleaning planning plane.

[0009] In a preferred embodiment, the step of performing minimum distortion mapping on the three-dimensional surface of each of the local areas to be cleaned to obtain a two-dimensional local area to be cleaned includes: Extract the set of surface points of the local area to be cleaned from the surface contour smoothing data; The surface point set is mapped to a mapping point set according to the preset mapping target; Error analysis is performed on the mapping point set to generate vertex mapping error; When the vertex mapping error is greater than or equal to a preset error threshold, the mapping point set is optimized based on the vertex mapping error to obtain the target point set. When the vertex mapping error is less than a preset error threshold, the mapped point set is taken as the target point set; A two-dimensional local area to be cleaned is generated based on the target point set.

[0010] In a preferred embodiment, the step of safety-constraining the motion mode of the underwater hull cleaning robot to obtain the target cleaning robot includes: Obtain the cleaning task of the underwater hull cleaning robot, and select the adsorption mode of the underwater hull cleaning robot according to the cleaning task. Using the adsorption mode as the motion mode of the underwater hull cleaning robot, an adsorption cleaning robot is obtained. By constraining the rotational degrees of freedom of the adsorption cleaning robot, a constrained cleaning robot is obtained. The adsorption force data of the constrained cleaning robot is obtained, and the adsorption force data is monitored in real time to obtain the adsorption state of the constrained cleaning robot. The constrained cleaning robot is adjusted in real time according to the adsorption state to obtain the target cleaning robot.

[0011] In a preferred embodiment, the step of analyzing the cleaning path of the target cleaning robot on the two-dimensional cleaning planning plane to generate a round-trip coverage path within the cleaning area of ​​the hull to be cleaned includes: Obtain the effective cleaning width of the target cleaning robot, and generate the number of parallel cleaning strips based on each two-dimensional local area to be cleaned in the two-dimensional cleaning planning plane and the effective cleaning width; Based on the number of parallel cleaning strips, several parallel cleaning strips are generated along a preset main direction on the two-dimensional local area to be cleaned. The parallel cleaning strips are connected sequentially to obtain an initial reciprocating path; The initial round-trip path is subjected to wall-hugging constraint verification, and the initial round-trip path is locally fine-tuned based on the verification results to obtain the round-trip coverage path of the two-dimensional local area to be cleaned.

[0012] In a preferred embodiment, the step of sequentially scheduling and stitching multiple cleaning areas along the round-trip coverage path to obtain a full-hull cleaning path includes: The two-dimensional local area to be cleaned is used as the cleaning area node of the hull to be cleaned. A topology diagram of the cleaning area is constructed based on the round-trip coverage path of the two-dimensional local area to be cleaned and the nodes of the cleaning area. Based on the end strips of adjacent regions and the first strip of the next region in the topology diagram of the cleaning region, the transfer distance between cleaning regions and the attitude adjustment cost of the target cleaning robot are calculated. The inter-region scheduling cost function is obtained by weighting and combining the transfer distance, the attitude adjustment cost, and the preset round-trip direction reversal penalty cost. The cleaning zone sequence of the hull to be cleaned is generated according to the inter-regional scheduling cost function. The corresponding round-trip coverage paths are spliced ​​together one by one according to the order of the cleaning areas to obtain the initial global cleaning path. The path endpoints between adjacent cleaning areas in the initial global cleaning path are finely adjusted to connect the directions, thus obtaining the full hull cleaning path.

[0013] In a preferred embodiment, the step of calculating the transfer distance between cleaning areas and the attitude adjustment cost of the target cleaning robot based on the end strips of adjacent areas and the first strip of the next area in the topology diagram of the cleaning area includes: Two adjacent cleaning areas are selected one by one from the topology diagram of the cleaning area to obtain the first cleaning area and the second cleaning area. Extract the end strip of the first cleaning area and the first strip of the second cleaning area; Obtain the end pose information of the end strip and the start pose information of the first strip, and extract the end position point of the end pose information and the start position point of the start pose information; Calculate the transfer distance between the first cleaning area and the second cleaning area based on the end position point and the start position point; The posture adjustment angle of the target cleaning robot is generated based on the end-effector pose information and the starting pose information; The attitude adjustment cost of the target cleaning robot is calculated based on the attitude adjustment angle.

[0014] In a preferred embodiment, the step of adaptively adjusting the energy consumption of the full-hull cleaning path to obtain the target cleaning path of the target cleaning robot includes: Obtain the water flow direction and velocity of the water area where the hull to be cleaned is located, and generate the current cleaning energy consumption of each parallel cleaning strip based on the water flow direction and the water flow velocity; The main direction of each parallel cleaning strip is selected based on the current cleaning energy consumption; The starting and ending ends of the parallel cleaning strip are dynamically fine-tuned according to the main direction of the strip to obtain an adjusted cleaning strip. The path of the entire ship cleaning path is optimized by adjusting the cleaning strips to obtain the target cleaning path of the target cleaning robot.

[0015] In a preferred embodiment, generating the current cleaning energy consumption for each parallel cleaning strip based on the water flow direction and the water flow velocity includes: Extract the strip movement direction of each parallel cleaning strip in the two-dimensional local area to be cleaned; Calculate the angle between the direction of the strip's movement and the direction of the water flow; The cleaning state is obtained by analyzing the co-current and counter-current states of the parallel cleaning strips based on the included directional angle. The basic cleaning energy consumption of the parallel cleaning strip is obtained based on the cleaning status. An energy consumption correction coefficient is generated based on the water flow velocity and the directional angle. The energy consumption of the basic cleaning is corrected using the energy consumption correction coefficient to obtain the current cleaning energy consumption of the parallel cleaning strip.

[0016] This invention acquires point cloud data of the surface contour of the hull to be cleaned, and generates a two-dimensional cleaning planning plane based on this data. This transforms the complex three-dimensional geometry of the hull surface into a clearly structured and computationally efficient two-dimensional planning space, enabling the cleaning path planning to more accurately conform to the actual hull shape. Safety constraints are applied to the motion mode of the underwater hull cleaning robot to obtain the target cleaning robot. A clear feasibility boundary is established between path planning and actual execution, ensuring the cleaning robot maintains stable attachment and controllable motion in complex underwater environments. This effectively reduces the risk of detachment and operation interruption caused by drastic attitude changes, excessively rapid turns, or motion instability. The cleaning path of the target cleaning robot on the two-dimensional cleaning planning plane is analyzed to generate a reciprocating coverage path within the cleaning area of ​​the hull to be cleaned. This path planning fully integrates the robot's actual motion capabilities with the geometric features of the local area, achieving regular and orderly area coverage and effectively reducing ineffective turns and repetitive strokes. To reduce energy consumption and instability risks associated with attitude adjustments while ensuring continuous and complete cleaning trajectories within the cleaning area, the system employs multi-area sequential scheduling and path splicing for the reciprocating coverage path to obtain a full-hull cleaning path. This unifies previously independent local cleaning paths into a continuous full-hull cleaning path. By comprehensively considering the spatial relationships between areas and the cost of path transfer, it effectively reduces invalid movements and frequent attitude adjustments during area switching, thereby lowering overall energy consumption and improving path continuity. Furthermore, the system performs adaptive energy consumption adjustment on the full-hull cleaning path to obtain the target cleaning path for the target cleaning robot. Based on the actual energy consumption differences of different cleaning strips and areas, the path execution direction and connection sequence are dynamically corrected, effectively reducing the proportion of counter-current operations and high-energy-consuming movements. This reduces overall energy consumption while ensuring the integrity of the hull cleaning coverage, significantly lowering cleaning energy consumption, improving path execution efficiency, and enhancing the adaptability of underwater hull cleaning tasks to complex working conditions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating an efficient and low-power path planning method for a reciprocating underwater hull cleaning robot, as provided in an embodiment of the present invention.

[0019] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] This application provides an efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot. This method can be executed by software or hardware installed on a terminal device or server-side device. The server-side device includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be a standalone server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and demand forecasting platforms.

[0023] Reference Figure 1 The diagram shown is a flowchart illustrating an efficient and low-power path planning method for a reciprocating underwater hull cleaning robot according to an embodiment of the present invention. In this embodiment, the efficient and low-power path planning method for a reciprocating underwater hull cleaning robot includes: S1. Obtain the surface contour point cloud data of the hull to be cleaned, and generate a two-dimensional cleaning planning plane based on the surface contour point cloud data.

[0024] In this embodiment of the invention, the hull to be cleaned refers to the ship's body and its outer surface structure, which require underwater cleaning operations. The surface contour point cloud data is a discrete three-dimensional set of points collected by sensing devices, used to describe the spatial morphology of the ship's outer surface. The two-dimensional cleaning planning plane is a two-dimensional reference plane used for cleaning path planning, formed by mapping or unfolding the three-dimensional hull surface based on the hull surface contour point cloud data.

[0025] Specifically, generating a two-dimensional cleaning planning plane based on the surface contour point cloud data includes: The surface contour point cloud data is denoised and resampled to obtain smooth surface contour data; Obtain the hull geometry features of the hull to be cleaned, and divide the surface contour smoothing data into several local areas to be cleaned based on the hull geometry features; Minimum distortion mapping is performed on the three-dimensional surface of each local area to be cleaned to obtain a two-dimensional local area to be cleaned. All the two-dimensional local areas to be cleaned are summarized into a two-dimensional cleaning planning plane.

[0026] In this embodiment of the invention, anomaly detection and noise suppression are performed on the surface contour point cloud data to remove discrete noise points introduced by underwater sensing errors, suspended particle interference, or reflection anomalies. While preserving the overall geometric features of the hull and key curvature changes, the surface contour point cloud data is spatially homogenized and resampled to make the point distribution more regular and consistent, ultimately obtaining smooth surface contour data that can accurately characterize the hull shape and is suitable for subsequent cleaning planning.

[0027] Furthermore, geometric feature information that reflects the hull structure morphology, such as curvature changes, boundary orientation, and regional continuity, is extracted from the surface contour smoothing data. Based on the geometric features, a structural analysis is performed on the hull surface to be cleaned, dividing the overall hull surface into several local areas to be cleaned that are relatively consistent in geometric shape and have similar cleaning conditions.

[0028] In this embodiment of the invention, for each local area to be cleaned, a mapping method that preserves local geometric relationships and neighborhood topology is adopted to unfold the local area to be cleaned to a two-dimensional plane. During the mapping process, area distortion and angle distortion are constrained to minimize the geometric distortion introduced by the conversion from three-dimensional to two-dimensional, so as to accurately reflect the morphological characteristics of the original three-dimensional surface in two-dimensional space, making the two-dimensional local area to be cleaned both easy to calculate and able to realistically represent the surface structure of the ship.

[0029] Specifically, the step of performing minimum distortion mapping on the three-dimensional surface of each of the local areas to be cleaned to obtain a two-dimensional local area to be cleaned includes: Extract the set of surface points of the local area to be cleaned from the surface contour smoothing data; The surface point set is mapped to a mapping point set according to the preset mapping target; Error analysis is performed on the mapping point set to generate vertex mapping error; When the vertex mapping error is greater than or equal to a preset error threshold, the mapping point set is optimized based on the vertex mapping error to obtain the target point set. When the vertex mapping error is less than a preset error threshold, the mapped point set is taken as the target point set; A two-dimensional local area to be cleaned is generated based on the target point set.

[0030] In this embodiment of the invention, point cloud data corresponding to the local area to be cleaned is selected from the overall surface contour smoothing data to form a surface point set for characterizing the three-dimensional geometric shape of the local area to be cleaned. The surface point set completely preserves the spatial structure information of the local area to be cleaned.

[0031] Furthermore, with the goal of preserving the geometric features of the surface and the local neighborhood relationships, the three-dimensional surface point set is projected or unfolded into a two-dimensional constrained plane according to a predetermined mapping rule. During the mapping process, the distance between points, the angular relationship, or the curvature continuity are comprehensively considered so that the obtained mapped point set can reasonably reflect the structural features of the original three-dimensional surface in two-dimensional space.

[0032] In this embodiment of the invention, the positional relationship of the mapping point set in the two-dimensional plane is compared and analyzed with the expected mapping target or constraint conditions to obtain the degree of deviation of each mapping vertex in terms of position offset, boundary consistency or local shape preservation, thus forming the vertex mapping error used to measure the mapping quality.

[0033] Furthermore, when the vertex mapping error is detected to exceed the allowable error threshold range, the vertex positions in the mapping point set are iteratively corrected or reconstrained according to the vertex mapping error, so that the mapping result gradually approaches the preset mapping target; by adjusting multiple times to reduce the overall mapping distortion, a target point set that meets the error requirements is finally formed.

[0034] When the vertex mapping error is within the preset allowable error threshold range, it is determined that the current mapping result has met the accuracy requirements and no further adjustment is needed. The mapped point set is then directly determined as the target point set for subsequent processing.

[0035] In this embodiment of the invention, the corresponding regional boundary and internal structure are constructed on a two-dimensional plane according to the final determined target point set, forming a two-dimensional local area to be cleaned that can completely characterize the geometry of the local area.

[0036] Furthermore, according to the spatial positional relationship and relative connection order of each local area to be cleaned on the original hull surface, the obtained multiple two-dimensional local areas to be cleaned are uniformly arranged and spliced; during the summarization process, the adjacency relationship and boundary correspondence between the areas are maintained to form a unified two-dimensional cleaning planning plane covering the entire hull surface.

[0037] This invention acquires the surface contour point cloud data of the hull to be cleaned and generates a two-dimensional cleaning planning plane accordingly. This transforms the complex three-dimensional hull surface geometry into a clear and computationally efficient two-dimensional planning space, enabling the cleaning path planning to more accurately fit the actual hull shape. This reduces the computational complexity of three-dimensional path planning and minimizes coverage errors caused by geometric approximation.

[0038] S2. Apply safety constraints to the motion mode of the underwater hull cleaning robot to be cleaned to obtain the target cleaning robot.

[0039] In this embodiment of the invention, the underwater hull cleaning robot is an autonomous or semi-autonomous robot used to perform cleaning operations along the outer surface of a ship in an underwater environment. Motion mode refers to the movement methods and combinations adopted by the underwater hull cleaning robot during the cleaning task, including direction of travel, turning method, attitude adjustment method, and speed change characteristics.

[0040] Safety constraints are limitations set to ensure the stable operation of underwater hull cleaning robots in complex underwater environments. They constrain the range of motion, the magnitude of attitude changes, and the operating methods. The target cleaning robot is a model of a cleaning robot that meets the requirements of operational safety and path feasibility after motion mode safety constraints are applied to the existing underwater hull cleaning robot.

[0041] Specifically, the process of applying safety constraints to the motion mode of the underwater hull cleaning robot to obtain the target cleaning robot includes: Obtain the cleaning task of the underwater hull cleaning robot, and select the adsorption mode of the underwater hull cleaning robot according to the cleaning task. Using the adsorption mode as the motion mode of the underwater hull cleaning robot, an adsorption cleaning robot is obtained. By constraining the rotational degrees of freedom of the adsorption cleaning robot, a constrained cleaning robot is obtained. The adsorption force data of the constrained cleaning robot is obtained, and the adsorption force data is monitored in real time to obtain the adsorption state of the constrained cleaning robot. The constrained cleaning robot is adjusted in real time according to the adsorption state to obtain the target cleaning robot.

[0042] In this embodiment of the invention, the cleaning task to be performed is obtained. The cleaning task includes at least the location of the cleaning area, the attitude characteristics of the ship surface, and the cleaning operation requirements. Combining the differences in stability, maneuverability, and applicable surface morphology of different adsorption modes, an adsorption mode that matches the cleaning task is selected, thereby providing a suitable attachment method for subsequent cleaning operations.

[0043] Furthermore, the selected adsorption mode is introduced into the motion control logic of the cleaning robot, so that the robot performs motion planning based on the adsorption state when performing movement, turning and posture adjustment; by combining the adsorption mode with motion behavior, an adsorption cleaning robot that can stably adhere to the hull surface and perform cleaning actions is formed.

[0044] In this embodiment of the invention, to address the problem of excessive rotation or attitude instability that may occur in the adsorption cleaning robot during the attachment state, the rotation range and rotation rate around a specific axis are limited; by imposing constraints on the rotational degrees of freedom, the risk of desorption caused by attitude fluctuations is reduced, thereby improving the operational safety and control stability of the adsorption cleaning robot in complex underwater environments.

[0045] In this embodiment of the invention, adsorption force data generated by the constrained cleaning robot is continuously collected during the robot's operation, and the adsorption force data is analyzed in real time. By judging the magnitude and trend of the adsorption force data, it is determined whether the constrained cleaning robot is currently in a stable attachment state, thereby forming adsorption state information that reflects its operational safety.

[0046] Furthermore, based on the adsorption state obtained from real-time monitoring, the motion parameters, posture adjustment strategies, or adsorption control methods of the constrained cleaning robot are dynamically corrected; when insufficient adsorption force or abnormal fluctuations are detected, the motion behavior is adjusted in a timely manner to restore stable adhesion, thereby obtaining a target cleaning robot that can safely and stably perform cleaning tasks under different working conditions.

[0047] This invention establishes a clear feasibility boundary between path planning and actual execution by constraining the motion mode of the underwater hull cleaning robot to be cleaned. This ensures that the cleaning robot maintains stable attachment and controllable motion in complex underwater environments, effectively reducing the risk of detachment and the probability of operation interruption caused by drastic changes in attitude, excessively fast turning, or motion instability.

[0048] S3. Analyze the cleaning path of the target cleaning robot on the two-dimensional cleaning planning plane to generate a round-trip coverage path in the cleaning area of ​​the hull to be cleaned.

[0049] In this embodiment of the invention, the cleaning path is the movement trajectory of the target cleaning robot in a two-dimensional cleaning planning plane to complete the cleaning operation according to certain rules.

[0050] A reciprocating coverage path is a coverage movement path that achieves continuous and thorough cleaning of the surface of a cleaning area by moving back and forth through adjacent parallel paths within the cleaning area.

[0051] In detail, the analysis of the cleaning path of the target cleaning robot on the two-dimensional cleaning planning plane, and the generation of a round-trip coverage path within the cleaning area of ​​the hull to be cleaned, includes: Obtain the effective cleaning width of the target cleaning robot, and generate the number of parallel cleaning strips based on each two-dimensional local area to be cleaned in the two-dimensional cleaning planning plane and the effective cleaning width; Based on the number of parallel cleaning strips, several parallel cleaning strips are generated along a preset main direction on the two-dimensional local area to be cleaned. The parallel cleaning strips are connected sequentially to obtain an initial reciprocating path; The initial round-trip path is subjected to wall-hugging constraint verification, and the initial round-trip path is locally fine-tuned based on the verification results to obtain the round-trip coverage path of the two-dimensional local area to be cleaned.

[0052] In this embodiment of the invention, the actual cleaning width that the target cleaning robot can cover during a single journey in a stable operating state is determined; combined with the geometric dimensions of each two-dimensional local area to be cleaned in the two-dimensional cleaning planning plane, the number of parallel cleaning strips required without cleaning omissions or excessive overlap is calculated.

[0053] Furthermore, within the defined two-dimensional local area to be cleaned, the main cleaning direction that matches the area morphology is selected as the strip generation direction; according to the number of parallel cleaning strips obtained, multiple parallel cleaning strips are arranged at equal intervals along the strip generation direction, so that the parallel cleaning strips are evenly distributed within the area and cover the entire local area.

[0054] In this embodiment of the invention, the starting and ending ends of each parallel cleaning strip are connected sequentially according to the spatial relationship between adjacent parallel cleaning strips, so that the target cleaning robot can switch continuously between adjacent strips; by connecting the beginning and end alternately, an initial path with round-trip characteristics is formed, thereby reducing unnecessary empty travel and improving the continuity of path execution.

[0055] Furthermore, the initial reciprocating path is matched and verified with the wall-attaching motion constraints of the target cleaning robot to check whether the initial reciprocating path meets the requirements for stable attachment and safe movement at each position. When it is found that there is insufficient wall attachment or attitude adjustment risk in some path segments in the initial reciprocating path, the corresponding path nodes or turning positions are finely adjusted and corrected to finally form a reciprocating coverage path that meets the wall-attaching safety constraints and can completely cover the local area.

[0056] This invention analyzes the cleaning path of the target cleaning robot on a two-dimensional cleaning planning plane and generates a reciprocating coverage path within the cleaning area of ​​the hull to be cleaned. This allows the path planning to fully combine the robot's actual motion capabilities with the geometric features of the local area, achieving regular and orderly area coverage, effectively reducing ineffective turning and repeated strokes, lowering energy consumption and instability risks caused by attitude adjustments, and ensuring that the cleaning trajectory within the cleaning area is continuous and without omissions.

[0057] S4. Perform multi-cleaning area sequential scheduling and path splicing on the round-trip coverage path to obtain the full hull cleaning path.

[0058] In this embodiment of the invention, multi-cleaning area sequential scheduling is a process of rationally arranging the cleaning sequence of multiple local areas to be cleaned, taking into account the locational relationships and operational continuity of the areas. Path splicing connects the round-trip coverage paths generated in different local areas to be cleaned according to the scheduling order, forming a continuous and executable overall motion path.

[0059] The full hull cleaning path is a complete cleaning motion path that covers the entire hull surface by sequentially scheduling and splicing the cleaning paths of all local areas to be cleaned.

[0060] In detail, the step of sequentially scheduling and stitching multiple cleaning areas along the round-trip coverage path to obtain a full-hull cleaning path includes: The two-dimensional local area to be cleaned is used as the cleaning area node of the hull to be cleaned. A topology diagram of the cleaning area is constructed based on the round-trip coverage path of the two-dimensional local area to be cleaned and the nodes of the cleaning area. Based on the end strips of adjacent regions and the first strip of the next region in the topology diagram of the cleaning region, the transfer distance between cleaning regions and the attitude adjustment cost of the target cleaning robot are calculated. The inter-region scheduling cost function is obtained by weighting and combining the transfer distance, the attitude adjustment cost, and the preset round-trip direction reversal penalty cost. The cleaning zone sequence of the hull to be cleaned is generated according to the inter-regional scheduling cost function. The corresponding round-trip coverage paths are spliced ​​together one by one according to the order of the cleaning areas to obtain the initial global cleaning path. The path endpoints between adjacent cleaning areas in the initial global cleaning path are finely adjusted to connect the directions, thus obtaining the full hull cleaning path.

[0061] In this embodiment of the invention, each generated two-dimensional local area to be cleaned is abstractly represented, and each two-dimensional local area to be cleaned is corresponding to a cleaning area node. Combining the round-trip coverage path information corresponding to each cleaning area node, the spatial adjacency relationship and path connectivity relationship of different local cleaning areas on the hull surface are analyzed, and the connection edges between nodes are established accordingly, and finally a cleaning area topology diagram that can reflect the spatial association and transfer relationship between cleaning areas is formed.

[0062] In this embodiment of the invention, the step of calculating the transfer distance between cleaning areas and the attitude adjustment cost of the target cleaning robot based on the end strips of adjacent areas and the first strip of the next area in the topological relationship diagram of the cleaning area includes: Two adjacent cleaning areas are selected one by one from the topology diagram of the cleaning area to obtain the first cleaning area and the second cleaning area. Extract the end strip of the first cleaning area and the first strip of the second cleaning area; Obtain the end pose information of the end strip and the start pose information of the first strip, and extract the end position point of the end pose information and the start position point of the start pose information; Calculate the transfer distance between the first cleaning area and the second cleaning area based on the end position point and the start position point; The posture adjustment angle of the target cleaning robot is generated based on the end-effector pose information and the starting pose information; The attitude adjustment cost of the target cleaning robot is calculated based on the attitude adjustment angle.

[0063] In detail, in the constructed topology diagram of the cleaned areas, two cleaned areas with direct adjacent relationships are selected in sequence according to the connection relationship between adjacent cleaned areas, and the first and second cleaned areas that need to be evaluated for the area switching cost are identified.

[0064] For the selected adjacent cleaning areas, the last cleaning strip to be executed is determined from the round-trip coverage path corresponding to the first cleaning area, and the first cleaning strip to be executed is determined from the round-trip coverage path of the second cleaning area. By extracting the end strip and the first strip, the specific path position of the robot before and after the area switching is determined.

[0065] Read the spatial pose information of the target cleaning robot at the end of the end strip and at the beginning of the first strip, respectively, and extract the end position point and the start position point for distance calculation from the corresponding pose information.

[0066] Based on the coordinate relationship between the end point and the starting point in the planned space, the spatial distance required for the target cleaning robot to switch from the first cleaning area to the second cleaning area is calculated. This transfer distance is used to quantify the additional movement cost incurred during the area switching process. The calculation formula is as follows:

[0067] in, This indicates the transfer distance between the first cleaning area and the second cleaning area. Indicates the end position point. Indicates the starting position point. Indicates the directional difference adjustment coefficient. This indicates the angle between the end strip of the first cleaning zone and the first strip of the second cleaning zone.

[0068] By comparing the attitude parameters contained in the end-effector pose information and the initial pose information, the magnitude of the attitude change that the target cleaning robot needs to complete during the area switching process is analyzed; by converting the attitude change amount into attitude adjustment angle, the specific requirements of area switching on the attitude control of the target cleaning robot are clarified.

[0069] Using the attitude adjustment angle as a quantitative indicator to measure the degree of attitude change, and combining it with the motion characteristics and control constraints of the target cleaning robot, the energy consumption or control cost required to complete the attitude adjustment is evaluated; thus, the attitude adjustment cost for area scheduling optimization is obtained, and the calculation formula is as follows:

[0070] in, This represents the attitude adjustment cost between the first and second cleaning regions. This represents the attitude adjustment weighting coefficient. This indicates the angle between the end strip of the first cleaning zone and the first strip of the second cleaning zone. This represents the nonlinear amplification index.

[0071] In this embodiment of the invention, the transfer distance generated during the switching of cleaning areas is used as the basic cost term, the attitude adjustment cost under the wall-hugging motion condition is used as the motion cost term, and the penalty cost introduced when the reversal of the reciprocating cleaning direction is used as the continuity constraint term. The above cost terms are combined according to preset weights to form the inter-region scheduling cost function, and the calculation formula is as follows:

[0072]

[0073]

[0074] in, This represents the penalty coefficient for reversing direction. This indicates the directional consistency between the first and second cleaning areas. Indicates the direction of end strip cleaning. Indicates the cleaning direction of the first strip. This indicates the transfer distance between the first cleaning area and the second cleaning area. This represents the attitude adjustment cost between the first and second cleaning regions. This represents the penalty cost for reversing the round-trip direction between the first and second cleaning areas. This represents the weights of the transfer distance, attitude adjustment cost, and round-trip direction reversal penalty cost. This represents the inter-region scheduling cost function between the first and second cleaning regions.

[0075] Furthermore, with the goal of minimizing the overall scheduling cost, the scheduling cost function between regions is analyzed and optimized to determine the access order of each cleaning region, thereby minimizing the overall movement distance and attitude adjustment cost during the switching process of the cleaning region, and thus improving the execution efficiency of the whole hull cleaning task.

[0076] In this embodiment of the invention, according to the determined cleaning area order, the round-trip coverage path corresponding to each cleaning area is selected in sequence and connected according to the area access order; by splicing the round-trip coverage paths, a continuous cleaning trajectory covering multiple areas is formed, and an initial global cleaning path covering the entire hull is obtained.

[0077] Furthermore, the connection positions of adjacent area path segments in the initial global cleaning path are checked, and the directional consistency and motion continuity of the path endpoints are analyzed. When there are sudden changes in direction or the cost of attitude adjustment is high, the connection endpoints are locally oriented and the path is fine-tuned to make the overall path smoother and more continuous, and finally a fully executable hull cleaning path is formed.

[0078] This invention utilizes multi-cleaning area sequential scheduling and path splicing to perform round-trip coverage paths generated within each cleaning area. This can unify previously independent local cleaning paths into continuous full-hull cleaning paths. By comprehensively considering the spatial relationship between areas and the cost of path transfer, it effectively reduces invalid movement and frequent attitude adjustments during area switching, lowers overall energy consumption, and improves path continuity, thereby significantly improving the overall efficiency of hull cleaning operations.

[0079] S5. Perform adaptive energy consumption adjustment on the full hull cleaning path to obtain the target cleaning path of the target cleaning robot.

[0080] In this embodiment of the invention, adaptive energy consumption adjustment is a process of dynamically optimizing path parameters or execution methods based on the target cleaning robot's motion state and environmental factors to reduce energy consumption, while maintaining the integrity of the path coverage.

[0081] The target cleaning path is the final cleaning motion path obtained after adaptive energy consumption adjustment of the cleaning path for the entire hull. It meets the cleaning coverage requirements, has better energy consumption performance, and can be directly executed by the target cleaning robot.

[0082] Specifically, the step of adaptively adjusting the energy consumption of the entire hull cleaning path to obtain the target cleaning path for the target cleaning robot includes: Obtain the water flow direction and velocity of the water area where the hull to be cleaned is located, and generate the current cleaning energy consumption of each parallel cleaning strip based on the water flow direction and the water flow velocity; The main direction of each parallel cleaning strip is selected based on the current cleaning energy consumption; The starting and ending ends of the parallel cleaning strip are dynamically fine-tuned according to the main direction of the strip to obtain an adjusted cleaning strip. The path of the entire ship cleaning path is optimized by adjusting the cleaning strips to obtain the target cleaning path of the target cleaning robot.

[0083] In this embodiment of the invention, generating the current cleaning energy consumption for each parallel cleaning strip based on the water flow direction and the water flow velocity includes: Extract the strip movement direction of each parallel cleaning strip in the two-dimensional local area to be cleaned; Calculate the angle between the direction of the strip's movement and the direction of the water flow; The cleaning state is obtained by analyzing the co-current and counter-current states of the parallel cleaning strips based on the included directional angle. The basic cleaning energy consumption of the parallel cleaning strip is obtained based on the cleaning status. An energy consumption correction coefficient is generated based on the water flow velocity and the directional angle. The energy consumption of the basic cleaning is corrected using the energy consumption correction coefficient to obtain the current cleaning energy consumption of the parallel cleaning strip.

[0084] In detail, within the two-dimensional local area to be cleaned, each generated parallel cleaning strip is traversed and analyzed to obtain the travel direction information of each parallel cleaning strip in the two-dimensional cleaning planning plane. The strip movement direction is used to characterize the actual movement orientation of the target cleaning robot when performing the corresponding strip cleaning operation.

[0085] The direction of movement of each parallel cleaning strip is vectorized relative to the direction of water flow in the current water area. The angle between the direction of movement of the strip and the direction of water flow is obtained by the vector angle calculation method. The angle is used to quantitatively describe the relative relationship between the direction of robot movement and the direction of water flow.

[0086] Based on the magnitude and directional characteristics of the directional angle, it is determined whether the target cleaning robot is in a downstream state, a upstream state, or a lateral flow state when moving on the corresponding parallel cleaning strip; by distinguishing between downstream and upstream characteristics, a cleaning state reflecting the mode of water flow is formed.

[0087] For different cleaning states, the corresponding basic cleaning energy consumption is obtained from the preset energy consumption model or empirical parameters. The basic cleaning energy consumption is used to characterize the baseline energy consumption required for the robot to complete the cleaning operation on the strip without considering the change in water flow intensity.

[0088] By jointly analyzing the current water flow velocity and the angle between the direction of the strip movement and the direction of the water flow, an energy consumption correction coefficient is constructed that reflects the influence of water flow intensity and the direction of flow. The energy consumption correction coefficient is used to characterize the increase or decrease in cleaning energy consumption caused by water flow.

[0089] The energy consumption correction coefficient is applied to the corresponding basic cleaning energy consumption to make a weighted adjustment to the basic cleaning energy consumption. Through this weighted correction process, dynamic environmental factors such as water flow direction and flow velocity are introduced into the energy consumption assessment, and finally the current cleaning energy consumption of the parallel cleaning strip that can reflect the actual working conditions is obtained.

[0090] In this embodiment of the invention, the current cleaning energy consumption of the same parallel cleaning strip under different possible travel directions is compared and analyzed; under the premise of meeting the coverage requirements and motion constraints, the travel direction with lower energy consumption is selected as the main direction of the cleaning strip, so that the target cleaning robot can follow the water flow conditions as much as possible when performing cleaning operations, thereby reducing the overall energy consumption.

[0091] In this embodiment of the invention, after determining the main direction of the strip, the starting and ending positions of the parallel cleaning strip in the two-dimensional cleaning planning plane are adjusted to ensure directional consistency. By appropriately moving the endpoint positions or exchanging the start and end sequences, the actual execution direction of the cleaning strip is matched with the selected main direction of the strip, thereby forming an adjusted cleaning strip that is more in line with the water flow conditions.

[0092] Furthermore, the dynamically fine-tuned cleaning strips are incorporated into the entire hull cleaning path, updating and reconstructing the entire hull cleaning path. While maintaining the integrity of the entire hull coverage, the overall operating energy consumption under the action of water flow is reduced through strip direction optimization and path sequence coordination, ultimately forming a target cleaning path suitable for the current aquatic environment and directly executable by the target cleaning robot.

[0093] This invention adaptively adjusts the energy consumption of the entire hull cleaning path, incorporating dynamic environmental factors such as water flow direction, water flow velocity, and robot motion state into the path optimization process. This allows the cleaning path to no longer be generated solely based on static geometric relationships, but to dynamically correct the path execution direction and connection sequence according to the actual energy consumption differences of different cleaning strips and areas. This effectively reduces the proportion of countercurrent operations and high-energy-consuming movements, thereby reducing overall energy consumption while ensuring the integrity of the hull cleaning coverage.

[0094] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0095] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0096] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0097] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0098] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0099] In the embodiments provided in this disclosure, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0100] It should be noted that, in this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0101] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A high-efficiency, low-power path planning method based on a reciprocating underwater hull cleaning robot, characterized in that, The method includes: Acquire the surface contour point cloud data of the hull to be cleaned, and generate a two-dimensional cleaning planning plane based on the surface contour point cloud data; By applying safety constraints to the motion mode of the underwater hull cleaning robot to be cleaned, the target cleaning robot is obtained. The cleaning path of the target cleaning robot on the two-dimensional cleaning planning plane is analyzed to generate a round-trip coverage path within the cleaning area of ​​the hull to be cleaned. The round-trip coverage path is sequentially scheduled for multiple cleaning areas and spliced ​​together to obtain the full hull cleaning path. The energy consumption of the full-hull cleaning path is adaptively adjusted to obtain the target cleaning path of the target cleaning robot.

2. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 1, characterized in that, The step of generating a two-dimensional cleaning planning plane based on the surface contour point cloud data includes: The surface contour point cloud data is denoised and resampled to obtain smooth surface contour data; Obtain the hull geometry features of the hull to be cleaned, and divide the surface contour smoothing data into several local areas to be cleaned based on the hull geometry features; Minimum distortion mapping is performed on the three-dimensional surface of each local area to be cleaned to obtain a two-dimensional local area to be cleaned. All the two-dimensional local areas to be cleaned are summarized into a two-dimensional cleaning planning plane.

3. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 2, characterized in that, The step of performing minimum distortion mapping on the three-dimensional surface of each of the local areas to be cleaned to obtain a two-dimensional local area to be cleaned includes: Extract the set of surface points of the local area to be cleaned from the surface contour smoothing data; The surface point set is mapped to a mapping point set according to the preset mapping target; Error analysis is performed on the mapping point set to generate vertex mapping error; When the vertex mapping error is greater than or equal to a preset error threshold, the mapping point set is optimized based on the vertex mapping error to obtain the target point set. When the vertex mapping error is less than a preset error threshold, the mapped point set is taken as the target point set; A two-dimensional local area to be cleaned is generated based on the target point set.

4. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 1, characterized in that, The process of applying safety constraints to the motion mode of the underwater hull cleaning robot to obtain the target cleaning robot includes: Obtain the cleaning task of the underwater hull cleaning robot, and select the adsorption mode of the underwater hull cleaning robot according to the cleaning task. Using the adsorption mode as the motion mode of the underwater hull cleaning robot, an adsorption cleaning robot is obtained. By constraining the rotational degrees of freedom of the adsorption cleaning robot, a constrained cleaning robot is obtained. The adsorption force data of the constrained cleaning robot is obtained, and the adsorption force data is monitored in real time to obtain the adsorption state of the constrained cleaning robot. The constrained cleaning robot is adjusted in real time according to the adsorption state to obtain the target cleaning robot.

5. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 1, characterized in that, The step of analyzing the cleaning path of the target cleaning robot on the two-dimensional cleaning planning plane and generating a round-trip coverage path within the cleaning area of ​​the hull to be cleaned includes: Obtain the effective cleaning width of the target cleaning robot, and generate the number of parallel cleaning strips based on each two-dimensional local area to be cleaned in the two-dimensional cleaning planning plane and the effective cleaning width; Based on the number of parallel cleaning strips, several parallel cleaning strips are generated along a preset main direction on the two-dimensional local area to be cleaned. The parallel cleaning strips are connected sequentially to obtain an initial reciprocating path; The initial round-trip path is subjected to wall-hugging constraint verification, and the initial round-trip path is locally fine-tuned based on the verification results to obtain the round-trip coverage path of the two-dimensional local area to be cleaned.

6. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 5, characterized in that, The process of sequentially scheduling and stitching multiple cleaning areas along the round-trip coverage path to obtain a full-hull cleaning path includes: The two-dimensional local area to be cleaned is used as the cleaning area node of the hull to be cleaned. A topology diagram of the cleaning area is constructed based on the round-trip coverage path of the two-dimensional local area to be cleaned and the nodes of the cleaning area. Based on the end strips of adjacent regions and the first strip of the next region in the topology diagram of the cleaning region, the transfer distance between cleaning regions and the attitude adjustment cost of the target cleaning robot are calculated. The inter-region scheduling cost function is obtained by weighting and combining the transfer distance, the attitude adjustment cost, and the preset round-trip direction reversal penalty cost. The cleaning zone sequence of the hull to be cleaned is generated according to the inter-regional scheduling cost function. The corresponding round-trip coverage paths are spliced ​​together one by one according to the order of the cleaning areas to obtain the initial global cleaning path. The path endpoints between adjacent cleaning areas in the initial global cleaning path are finely adjusted to connect the directions, thus obtaining the full hull cleaning path.

7. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 6, characterized in that, The step of calculating the transfer distance between cleaning areas and the attitude adjustment cost of the target cleaning robot based on the end strips of adjacent areas and the first strip of the next area in the topology diagram of the cleaning area includes: Two adjacent cleaning areas are selected one by one from the topology diagram of the cleaning area to obtain the first cleaning area and the second cleaning area. Extract the end strip of the first cleaning area and the first strip of the second cleaning area; Obtain the end pose information of the end strip and the start pose information of the first strip, and extract the end position point of the end pose information and the start position point of the start pose information; Calculate the transfer distance between the first cleaning area and the second cleaning area based on the end position point and the start position point; The posture adjustment angle of the target cleaning robot is generated based on the end-effector pose information and the starting pose information; The attitude adjustment cost of the target cleaning robot is calculated based on the attitude adjustment angle.

8. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 1, characterized in that, The step of adaptively adjusting the energy consumption of the full-hull cleaning path to obtain the target cleaning path of the target cleaning robot includes: Obtain the water flow direction and velocity of the water area where the hull to be cleaned is located, and generate the current cleaning energy consumption of each parallel cleaning strip based on the water flow direction and the water flow velocity; The main direction of each parallel cleaning strip is selected based on the current cleaning energy consumption; The starting and ending ends of the parallel cleaning strip are dynamically fine-tuned according to the main direction of the strip to obtain an adjusted cleaning strip. The path of the entire ship cleaning path is optimized by adjusting the cleaning strips to obtain the target cleaning path of the target cleaning robot.

9. The efficient and low-power path planning method based on a reciprocating underwater hull cleaning robot as described in claim 8, characterized in that, The step of generating the current cleaning energy consumption for each parallel cleaning strip based on the water flow direction and the water flow velocity includes: Extract the strip movement direction of each parallel cleaning strip in the two-dimensional local area to be cleaned; Calculate the angle between the direction of the strip's movement and the direction of the water flow; The cleaning state is obtained by analyzing the co-current and counter-current states of the parallel cleaning strips based on the included directional angle. The basic cleaning energy consumption of the parallel cleaning strip is obtained based on the cleaning status. An energy consumption correction coefficient is generated based on the water flow velocity and the directional angle. The energy consumption of the basic cleaning is corrected using the energy consumption correction coefficient to obtain the current cleaning energy consumption of the parallel cleaning strip.

Images