Path planning method, system and equipment of data center inspection robot and medium

Abstract

The embodiment of the invention provides a path planning method, system and equipment for a data center inspection robot and a medium, and belongs to the field of robot navigation and automatic driving. The method comprises the following steps: acquiring an operation environment of the inspection robot, and carrying out regional division on a space where the operation environment is located to construct a topological graph; on the basis of the topological graph, path searching is carried out through an A * algorithm, an initial planning path is obtained, path smoothing processing is carried out on the initial planning path, and a target planning path is obtained; and calculating a local speed in combination with a dynamic window evaluation algorithm, so that the inspection robot meets a speed constraint condition and an angular speed constraint condition in a local adjustment process, and selecting an optimal planning path from the target planning paths according to a constructed target cost function. The safety of path planning is improved by utilizing the constructed topological graph, the optimal path is searched in combination with an A * algorithm, and the path length and the driving safety are both considered.

Description

Technical Field

[0001] The present invention relates to the technical fields of robot navigation and autonomous driving, and particularly to a path planning method, system, device and medium for a data center inspection robot. Background Art

[0002] Path planning is one of the key technologies in the fields of robot navigation and autonomous driving, aiming to generate an optimized path from a starting point to a target point. A mobile robot realizes the map representation of the working space through environmental modeling and completes global path planning according to the map. During the robot navigation process, it uses its own sensors to continuously perceive environmental obstacles and avoid them, meeting various constraints such as time, energy consumption, and safety.

[0003] However, the obstacles in the real environment are complex and changeable. Therefore, the robot also needs to rely on its own sensors to continuously perceive the environment and dynamically adjust the path to ensure safe and efficient obstacle avoidance.

[0004] Traditional path planning methods, such as the Dijkstra algorithm and the A* algorithm, perform well in static or less obstacle environments and can quickly plan the shortest path. However, in scenarios with dense obstacles or dynamically changing environments, they often struggle to quickly adapt to environmental changes, resulting in low path planning efficiency and even the inability to find a feasible path. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a path planning method, system, device and medium for a data center inspection robot, which is used to improve the safety of path planning according to the constructed topological graph, and combines the A* algorithm to search for the optimal path, taking into account both the path length and driving safety.

[0006] To achieve the above purpose, the embodiments of the present invention provide a path planning method for a data center inspection robot, including: Obtain the operating environment of the inspection robot, and divide the space where the operating environment is located into regions to construct a topological graph; Based on the topological graph, use the A* algorithm to perform path search to obtain an initial planned path, and perform path smoothing on the initial planned path to obtain a target planned path; Combine the dynamic window evaluation algorithm to calculate the local speed, so that the inspection robot meets the speed constraint conditions and angular velocity constraint conditions during the local adjustment process, and select the optimal planned path from the target planned path according to the constructed target cost function, where the optimal planned path selected by the target cost function minimizes the weighted sum of the distance from the current position of the inspection robot to the target point, the distance between the inspection robot and its nearest obstacle, and the current linear velocity and angular velocity of the inspection robot.

[0007] Optionally, obtaining the operating environment of the inspection robot and dividing the space where the operating environment is located to construct a topological map includes: Obtaining the obstacle contour in the operating environment of the inspection robot and determining the obstacle seed point set based on the obstacle contour; Using the Voronoi Diagram to divide the operating environment space of the inspection robot based on the obstacle seed point set to form multiple Voronoi regions; Taking the vertex of each Voronoi region as the connection node of the topological map, connecting the connection node with the vertices of adjacent Voronoi regions, and using the connecting line formed as the edge of the topological map to construct the topological map.

[0008] Optionally, the Voronoi region is defined as:

[0009] In the formula, is the Euclidean distance, q represents any point in the Voronoi region, represents the i-th seed point set, represents the j-th seed point.

[0010] Optionally, based on the topological map, using the A* algorithm for path search to obtain the initial planned path includes: using the following formula for path search: ; ; In the formula, represents the comprehensive evaluation value of the current node, representing the estimated minimum cost from the starting point to the target point, is the path cost from the starting point to the current node n, is the heuristic function, represents the coordinate of the current node, represents the coordinate of the target node.

[0011] Optionally, the objective function for smoothing the initial planned path is as follows:

[0012] In the formula, represents the th path point on the initial planned path P, represents the th path point on the initial planned path P, represents the th path point on the initial planned path P, represents the total number of path points on the initial planned path P.

[0013] Optionally, the speed constraint condition is characterized as:

[0014] In the formula, represents the minimum speed, represents the maximum speed; The angular velocity constraint condition is characterized as:

[0015] In the formula, represents the minimum angular velocity, represents the maximum angular velocity.

[0016] Optionally, the formula of the objective cost function is as follows:

[0017] In the formula, represents the distance from the current position of the inspection robot to the target point, represents the distance between the inspection robot and its nearest obstacle, respectively represent the current linear velocity and angular velocity of the inspection robot, respectively represent weights.

[0018] In a second aspect, the present invention further provides a path planning system for a data center inspection robot, including: An acquisition unit, configured to acquire the operating environment of the inspection robot, and divide the space where the operating environment is located into regions to construct a topological map; A smoothing processing unit, configured to perform path search based on the topological map by using the A* algorithm to obtain an initial planned path, and perform path smoothing processing on the initial planned path to obtain a target planned path; A path planning unit, configured to calculate local speeds in combination with the dynamic window evaluation algorithm, so that the inspection robot satisfies the speed constraint condition and the angular velocity constraint condition during the local adjustment process, and select an optimal planned path from the target planned path according to the constructed objective cost function, wherein the optimal planned path selected by the objective cost function minimizes the weighted sum of the distance from the current position of the inspection robot to the target point, the distance between the inspection robot and its nearest obstacle, and the current linear velocity and angular velocity of the inspection robot.

[0019] In a third aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of the path planning method for the data center inspection robot described above are implemented.

[0020] Fourthly, the present invention further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the path planning method of the data center patrol robot described above are implemented.

[0021] Through the above technical solutions, by combining the topological map and the A* search algorithm, while improving the path safety, the path planning efficiency is optimized, and the robot motion stability is improved by smoothing the path.

[0022] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification, and are used to explain the embodiments of the present invention together with the following specific implementation manners, but do not constitute a limitation to the embodiments of the present invention. In the drawings: Figure 1 is an implementation flowchart of a path planning method for a data center patrol robot provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the construction process of a topological map provided by an embodiment of the present invention; Figure 3 is a schematic structural diagram of a path planning system for a data center patrol robot provided by an embodiment of the present invention; Figure 4 is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To better understand the technical solutions of the present application, the following explains the professional terms involved in the present application: A*: The A* search algorithm, commonly known as the A-star algorithm, is a path finding and graph traversal algorithm, which is widely used in the field of path optimization. Its unique feature is that it introduces global information when checking each possible node in the shortest path, estimates the distance of the current node from the end point, and uses it as a measure of the possibility of the node being on the shortest route.

[0025] Voronoi diagram: The Voronoi diagram, also known as the Dirichlet tessellation, is a space partitioning algorithm established by the Russian mathematician Georgy Fedoseevich Voronoi. It is inspired by Descartes' idea of dividing space with convex domains. It has a wide range of applications in many fields such as geometry, crystallography, architecture, geography, meteorology, information systems, etc.

[0026] In the following detailed description, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather the present disclosure should be understood to cover all adjustments, equivalents, and / or alternative solutions that fall within the spirit and scope of the various embodiments of the present disclosure.

[0027] Hereinafter, the term "comprising" or "may comprise" that may be used in various embodiments of the present disclosure indicates the presence of the disclosed function or operation, and does not limit the addition of one or more functions or operations. Further, as used in various embodiments of the present disclosure, the terms "comprising", "having" and their cognates are only intended to indicate a specific feature, number, step, operation, or combination of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, or combinations of the foregoing items.

[0028] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the recited words. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0030] Refer to Figure 1 Shown is a flowchart of a path planning method for an inspection robot in a data center in a specific embodiment, including the following execution steps: Step 100: Obtain the operating environment of the inspection robot, and divide the space where the operating environment is located into regions to construct a topology map.

[0031] Specifically, refer to Figure 2 As shown, when executing step 100, the following steps may be specifically executed: S1000: Obtain the obstacle contour in the operating environment of the inspection robot, and determine an obstacle seed point set based on the obstacle contour.

[0032] Specifically, a camera or a depth camera is configured on the inspection robot to capture images or point cloud data of the target object. Before use, the sensor is calibrated to ensure that the sensor can accurately capture images or point cloud data of the target object. The inspection robot captures environmental images through a vision sensor and performs preprocessing, such as denoising and enhancing contrast, to improve the image quality. The preprocessed image is binarized to separate obstacles from the background, forming a binary image. In the binary image, the edge contours of the obstacles are extracted through Canny edge detection. Morphological operations are performed on the extracted obstacle contours to remove noise and small objects while retaining the general shape of the obstacles. Point cloud segmentation is used to separate the ground from the obstacles. Clustering processing is performed on the separated obstacle point clouds to form multiple point sets, and each point set represents an obstacle and its size range.

[0033] Exemplarily, continuous spatial obstacle contours obtained using lidar / vision sensors are used. Vertices are extracted from the convex polygon boundaries of each obstacle, and auxiliary points are inserted at the concave polygon depressions to ensure that the Voronoi edges can reflect the safety of narrow channels. The convex vertices and the midpoints of long straight walls are used as seed points.

[0034] S1001: Use the Voronoi Diagram to divide the operating environment space of the inspection robot based on the obstacle seed point set, forming multiple Voronoi regions.

[0035] Specifically, the Voronoi region is defined as:

[0036] In the formula, is the Euclidean distance, q represents any point in the Voronoi region, represents the i-th seed point set, represents the j-th seed point.

[0037] The Voronoi region defines all regions within the influence range of a point such that any point in the region is closer to than to other seed points

[0038] The Voronoi Diagram can accurately divide the operating environment space of the inspection robot into multiple Voronoi regions based on the set of obstacle seed points. The distance from all points within each Voronoi region to the generator of that region (i.e., the obstacle seed point) is shorter than the distance to other generators. This division method ensures that each region closely surrounds its corresponding obstacle seed point, thus achieving a fine division of the space. In the path planning of the inspection robot, the application of the Voronoi Diagram can significantly improve the efficiency and safety of the path. By dividing the Voronoi regions, the robot can more easily identify which regions are obstacle-dense areas and which regions are relatively empty. When planning the path, the robot can choose to bypass the obstacle-dense areas and move through the empty areas, thus avoiding collisions with obstacles and improving the safety of the path. At the same time, since the division of the Voronoi Diagram is based on distance, the robot can more easily find the path closest to the target point. This path is usually optimal because it can ensure that the robot deviates from the target direction as little as possible during movement.

[0039] During the actual operation of the inspection robot, the environment may change, such as the appearance of new obstacles or the disappearance of existing obstacles. The Voronoi Diagram can adapt to these changes dynamically. When the environment changes, only by recalculating or updating the Voronoi Diagram can a new space division result be obtained. This dynamic adaptability enables the inspection robot to operate efficiently in a complex and changing environment. In addition, the Voronoi Diagram also has high flexibility. It can perform different space divisions according to different sets of obstacle seed points, thus meeting the needs of the inspection robot in different scenarios. For example, in a narrow passage, the robot may require a more refined space division to avoid collisions with obstacles; while in an open area, the robot may require a more concise space division to improve the efficiency of path planning.

[0040] By using the Voronoi Diagram for spatial partitioning, the inspection robot can traverse the entire environmental space more efficiently. Within each Voronoi region, the robot can move along the region boundary to ensure coverage of the entire region. At the same time, since each region closely surrounds its corresponding obstacle seed point, the robot can more easily identify obstacles and take corresponding obstacle avoidance measures. In addition, the partitioning method of the Voronoi Diagram can also improve the accuracy of inspection. Within each Voronoi region, the robot can more easily locate the target point or obstacle, thus achieving precise perception and response to the environment. This precision is crucial for the inspection robot because it can ensure that the robot does not miss any important information or misjudge the position of obstacles when performing tasks.

[0041] S1002: Use the vertices of each Voronoi region as the connection nodes of the topological graph, connect these connection nodes with the vertices of adjacent Voronoi regions, and use the formed connecting lines as the edges of the topological graph to construct the topological graph.

[0042] Specifically, it includes the following steps: Step 1: Generate the Voronoi diagram: Given a set of points on a two-dimensional plane, such as the point set P = {A, B, C, D}, use the Voronoi diagram generation algorithm to generate the Voronoi diagram according to the input point set. The Voronoi diagram divides the plane into multiple regions, each region corresponding to an input point, and the distance from any point within the region to this point is less than the distance to other input points.

[0043] Step 2: Determine the vertices of the Voronoi diagram: In the generated Voronoi diagram, identify all the vertices. These vertices are usually the intersections of three or more Voronoi regions, or the intersections of Voronoi regions and the plane boundary.

[0044] Step 3: Construct the topological graph: Use each vertex of the Voronoi diagram as a node of the topological graph. For each vertex in the Voronoi diagram, find other vertices adjacent to it (i.e., vertices sharing the same edge). In the topological graph, establish connections between these adjacent vertices to form edges.

[0045] Finally, the obtained topological graph is an undirected graph containing multiple nodes and multiple edges, reflecting the spatial adjacency relationship of the vertices of the Voronoi diagram.

[0046] The topological map uses the vertices of Voronoi regions as connection nodes, which can accurately express the relationships between points, lines, and planes in space. Each Voronoi region represents a specific spatial range, and its vertices, as connection nodes, can clearly outline the boundary of the region. The topological map simplifies the complex spatial structure into the relationship between nodes and edges, making the expression of spatial relationships more intuitive and understandable. By observing the topological map, the adjacent relationships and spatial layouts between various Voronoi regions can be clearly seen. Moreover, in the topological map, the path planning problem can be transformed into the problem of finding the shortest path between nodes and edges. Using the shortest path algorithm in graph theory, the optimal path from the starting point to the ending point can be quickly found. The topological map can provide intelligent navigation services for inspection robots. The robot can find the optimal path in the topological map based on its current position and the target position, and move along this path. During the movement, the robot can also dynamically adjust the path planning according to the real-time perceived environmental information to ensure safe and efficient arrival at the destination.

[0047] Through the topological map, the sizes and shapes of each Voronoi region can be clearly seen. According to actual needs, these regions can be reasonably divided and combined to optimize the utilization of spatial resources. When the obstacles in the environment or the position of the inspection robot changes, the Voronoi Diagram can be recalculated and the topological map can be updated. By dynamically adjusting the topological map, the accuracy and real-time nature of the spatial division can be ensured, thereby improving the utilization rate of spatial resources.

[0048] Step 101: Based on the topological map, use the A* algorithm to perform path search to obtain an initial planned path, and perform path smoothing on the initial planned path to obtain a target planned path.

[0049] The path P searched by the A* algorithm on the Voronoi diagram consists of discrete path points. The initial path , since the path points are discrete, driving directly along this path will cause the robot to make non-smooth sharp turns. Therefore, path smoothing is required.

[0050] Specifically, based on the topological map, using the A* algorithm to perform path search to obtain an initial planned path includes: performing path search using the following formula: ; ; In the formula, represents the comprehensive evaluation value of the current node, represents the estimated minimum cost from the starting point to the target point, is the path cost from the starting point to the current node n, is the heuristic function, Indicates the coordinates of the current node. Indicates the coordinates of the target node.

[0051] More specifically, the goal of path smoothing optimization is to minimize the curvature change, that is, to reduce the sharp turns of the path. The objective function for the initial planning path smoothing is as follows:

[0052] In the formula, represents the first Waypoints, represents the first Waypoints, represents the first Waypoints, Represents the total number of path points on the initial planned path P.

[0053] The objective function is to calculate the second-order difference (discrete second-order derivative) between adjacent path points. If the path is collinear, the optimization term approaches 0, indicating that the path is straight. If there is a sharp turn in the path, the optimization term is large, and the optimization process will adjust the control points to make the path smoother. Take the minimum value.

[0054] The initial planned path may contain many turning points, resulting in an unsmooth path. Through path smoothing, unnecessary turning points can be removed to make the path more natural and smooth. In addition, a smooth path can reduce vibration and energy consumption during movement and improve movement efficiency. In the fields of robot navigation and autonomous driving, smooth path planning helps reduce mechanical wear and energy loss and extend the service life of equipment.

[0055] Step 102: Calculate the local speed in combination with the dynamic window evaluation algorithm so that the inspection robot meets the speed constraint and the angular velocity constraint during the local adjustment process, and select the optimal planning path from the target planning paths according to the constructed target cost function.

[0056] The optimal planning path selected by the target cost function minimizes the weighted sum of the distance from the current position of the inspection robot to the target point, the distance between the inspection robot and its nearest obstacle, and the current linear velocity and angular velocity of the inspection robot.

[0057] Specifically, the speed constraint condition is characterized as:

[0058] In the formula, Indicates the minimum speed, Represents the maximum speed; The angular velocity constraint condition is characterized as:

[0059] In the formula, Represents the minimum angular velocity, Represents the maximum angular velocity.

[0060] By considering the current speed and acceleration limits of the robot, the DWA algorithm can generate a feasible speed window and select an optimal speed pair (linear speed and angular velocity) from it to drive the robot.

[0061] Exemplarily, taking the inspection robot with two-wheel differential drive as an example, when the inspection robot moves linearly, its linear speed is calculated by the speeds of the left and right wheels. Among them, assuming the speed of the left wheel is V L , and the speed of the right wheel is V R , and the distance between the two wheels is H, then the formula for calculating the linear speed of the robot is as follows:

[0062] Among them, , and Are the derivatives of the position coordinates x, y, and z with respect to time t, respectively, representing the instantaneous speed components of the inspection robot in these directions.

[0063] Specifically, the formula of the target cost function is as follows:

[0064] In the formula, Represents the distance from the current position of the inspection robot to the target point, Represents the distance between the inspection robot and its nearest obstacle, Represent the current linear speed and angular velocity of the inspection robot respectively, Represent weights respectively.

[0065] It should be understood that The weights can be adjusted and set according to the specific application scenario. For example, in the application scenario that emphasizes the shortest path, the weight of the path length in the cost function can be increased; in the scenario that needs to avoid close obstacles, the weight of the obstacle distance in the cost function can be increased, so that the design of the target cost function has flexibility and can be adjusted and optimized according to the actual application scenario and requirements.

[0066] Exemplarily, Represents the distance from the current position of the inspection robot to the target point, The calculation formula for representing the distance between the patrol robot and its nearest obstacle can all adopt the following formula:

[0067] In the formula, represents the coordinate position of the patrol robot, represents the coordinate position of the target point.

[0068] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0069] By combining the Voronoi topological structure and the A search algorithm, this application optimizes the path planning efficiency while improving the path safety, and smooths the path through the Bezier curve to improve the motion stability of the robot, and can be widely applied to fields such as data center patrol, intelligent warehousing, and unmanned delivery.

[0070] As Figure 3 shown, the following is an embodiment of the path planning system of the data center patrol robot provided by the embodiments of the present disclosure. It belongs to the same inventive concept as the path planning method of the data center patrol robot in the above embodiments. For the details not described in detail in the embodiment of the path planning system of the data center patrol robot, reference can be made to the embodiments of the path planning method of the data center patrol robot above.

[0071] The path planning system of the data center patrol robot includes: An acquisition unit, configured to acquire the operating environment of the patrol robot, and divide the space where the operating environment is located into regions to construct a topological map; A smoothing processing unit, configured to perform path search based on the topological map by using the A* algorithm to obtain an initial planned path, and perform path smoothing processing on the initial planned path to obtain a target planned path; A path planning unit, configured to calculate the local speed by combining the dynamic window evaluation algorithm, so that the patrol robot satisfies the speed constraint condition and the angular velocity constraint condition during the local adjustment process, and select an optimal planned path from the target planned path according to the constructed target cost function, where the optimal planned path selected by the target cost function minimizes the weighted sum of the distance from the current position of the patrol robot to the target point, the distance between the patrol robot and its nearest obstacle, and the current linear speed and angular velocity of the patrol robot.

[0072] Figure 4 is a schematic hardware structure diagram of an electronic device for implementing various embodiments of the present invention.

[0073] The path planning method of the data center inspection robot provided by the embodiments of the present application can be applied to electronic devices. Those skilled in the art can understand that the structure of the electronic device involved in the embodiments of the present invention does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. In the embodiments of the present invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, 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 embodiments of the present application described herein and / or claimed.

[0074] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, keys, a camera, a display screen, and a SIM card interface, etc.

[0075] It can be understood that the structure schematically shown in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0076] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), etc., an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0077] Among them, the processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals according to the instruction operation code and timing signal to complete the control of fetching and executing instructions.

[0078] A memory can also be set in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can save the instructions or data that the processor has just used or recycled. If the processor needs to use the instruction or data again, it can directly call it from this memory. This avoids repeated accesses, reduces the waiting time of the processor, and thus improves the system efficiency.

[0079] The external memory interface can be used to connect to an external memory card, such as a MicroSD card, to implement the storage capacity expansion of the electronic device. The external memory card communicates with the processor through the external memory interface to achieve the data storage function. For example, files such as music and videos are saved in the external memory card.

[0080] The internal memory can be used to store computer-executable program codes, and the computer-executable program codes include instructions. The processor executes various functional applications and data processing of the electronic device by running the instructions stored in the internal memory. The internal memory can include a program storage area and a data storage area. The internal memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0081] The wireless communication function of the electronic device can be implemented through an antenna, a wireless communication module, a modulation and demodulation processor, a baseband processor, etc.

[0082] The wireless communication module can provide wireless communication solutions applied to the electronic device, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite systems (GNSSs), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0083] The electronic device can implement audio functions, etc. through an audio module, a speaker, a receiver, a microphone, a headphone interface, an application processor, etc.

[0084] An electronic device can implement a shooting function through an ISP, a camera, a video codec, a GPU, a display screen, an application processor, etc.

[0085] An electronic device can implement a display function through a GPU, a display screen, an application processor, etc.

[0086] The GPU is a microprocessor for image processing, connecting the display screen and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor may include one or more GPUs, which execute program instructions to generate or change display information.

[0087] The display screen is used to display images, videos, etc. The display screen includes a display panel.

[0088] In the storage medium provided in this application, there is a program product capable of implementing the path planning method of the data center inspection robot.

[0089] The path planning method of the data center inspection robot includes: obtaining the operating environment of the inspection robot, and dividing the space where the operating environment is located into regions to construct a topological map; based on the topological map, using the A* algorithm to perform path search to obtain an initial planned path, and performing path smoothing processing on the initial planned path to obtain a target planned path; combining the dynamic window evaluation algorithm to calculate the local speed, so that the inspection robot satisfies the speed constraint condition and the angular velocity constraint condition during the local adjustment process, and selecting the optimal planned path from the target planned path according to the constructed target cost function, where the optimal planned path selected by the target cost function makes the weighted sum of the distance from the current position of the inspection robot to the target point, the distance between the inspection robot and its nearest obstacle, and the current linear speed and angular velocity of the inspection robot the smallest.

[0090] In some possible implementation manners, the subject name path planning method and system of the data center inspection robot in the present disclosure may be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0091] The storage medium of the present disclosure may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable 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.

[0092] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A path planning method for a data center inspection robot, characterized in that: include: Obtain the operating environment of the inspection robot and divide the space where the operating environment is located into regions to construct a topological map; Based on the topological graph, an A* algorithm is used to perform path search to obtain an initial planned path, and path smoothing is performed on the initial planned path to obtain a target planned path; The local speed is calculated in combination with the dynamic window evaluation algorithm so that the inspection robot meets the speed constraints and angular velocity constraints during the local adjustment process, and the optimal planning path is selected from the target planning path according to the constructed target cost function, wherein the optimal planning path selected by the target cost function minimizes the distance from the current position of the inspection robot to the target point, the distance between the inspection robot and its nearest obstacle, and the weighted sum of the current linear velocity and angular velocity of the inspection robot.

2. The path planning method for a data center inspection robot according to claim 1, characterized in that: The step of obtaining the operating environment of the inspection robot and dividing the space where the operating environment is located into regions to construct a topological map includes: Obtaining the obstacle contour in the operating environment of the inspection robot, and determining the obstacle species point set based on the obstacle contour; The Voronoi Diagram is used to divide the inspection robot's operating environment space based on the obstacle seed point set to form multiple Voronoi regions. The topology graph is constructed by taking the vertex of each Voronoi region as the connection node of the topology graph, connecting the connection node with the vertex of the adjacent Voronoi region, and forming the connection line as the edge of the topology graph.

3. The path planning method for a data center inspection robot according to claim 2, characterized in that: The Voronoi region is defined as: In the formula, is the Euclidean distance, q represents any point in the Voronoi region, represents the i-th seed point set, represents the jth seed point.

4. The path planning method for a data center inspection robot according to claim 1, characterized in that: Based on the topological graph, the A* algorithm is used to search for a path to obtain an initial planned path, which includes: using the following formula to search for a path: ； ； In the formula, Represents the comprehensive evaluation value of the current node, indicating the estimated minimum cost from the starting point to the target point. is the path cost from the starting point to the current node n, is the heuristic function, Indicates the coordinates of the current node. Indicates the coordinates of the target node.

5. The path planning method for a data center inspection robot according to claim 1, characterized in that: The objective function for smoothing the initial planning path is as follows: In the formula, represents the first Waypoints, represents the first Waypoints, represents the first Waypoints, Represents the total number of path points on the initial planned path P.

6. The path planning method for a data center inspection robot according to claim 1, characterized in that: The speed constraint condition is characterized as: In the formula, Indicates the minimum speed, Indicates the maximum speed; The angular velocity constraint condition is characterized as: In the formula, represents the minimum angular velocity, Indicates the maximum angular velocity.

7. The path planning method for a data center inspection robot according to claim 1, characterized in that: The target cost function formula is as follows: In the formula, Indicates the distance from the current position of the inspection robot to the target point. Indicates the distance between the inspection robot and its nearest obstacle. They represent the current linear velocity and angular velocity of the inspection robot respectively. Represent weights respectively.

8. A path planning system for a data center inspection robot, characterized in that: include: An acquisition unit is used to acquire the operating environment of the inspection robot and divide the space where the operating environment is located into regions to construct a topological map; A smoothing processing unit, configured to perform path search based on the topological map using an A* algorithm to obtain an initial planned path, and perform path smoothing processing on the initial planned path to obtain a target planned path; A path planning unit is used to calculate the local speed in combination with the dynamic window evaluation algorithm so that the inspection robot satisfies the speed constraint and the angular velocity constraint during the local adjustment process, and selects the optimal planning path from the target planning path according to the constructed target cost function, wherein the optimal planning path selected by the target cost function minimizes the distance from the current position of the inspection robot to the target point, the distance between the inspection robot and its nearest obstacle, and the weighted sum of the current linear velocity and angular velocity of the inspection robot.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the path planning method of the data center inspection robot as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the path planning method for a data center inspection robot as described in any one of claims 1 to 7 are implemented.

Images