Mobile path determination method, apparatus, and electronic device

Abstract

The application discloses a mobile path determination method and device and electronic equipment, and relates to the field of mobile equipment. The method first acquires task information and a wireless signal quality map of the equipment, the task information including a mobile starting point, a mobile ending point and a task type, and the wireless signal quality map including probability distribution parameters of signal quality of wireless access points stored in grids; at least one candidate path from the mobile starting point to the mobile ending point is determined according to the mobile starting point, the mobile ending point, the task type and the probability distribution parameters of all wireless access points of all grids; the path length, the time consumption, the number of wireless access point switching and the proportion of a preset signal area of each candidate path are acquired, the comprehensive score of the candidate path is determined, and the candidate path with the minimum comprehensive score is selected as the target mobile path of the equipment. The application embodiment improves the continuity and stability of wireless communication of the determined mobile path.

Description

Technical Field

[0001] This application belongs to the field of mobile equipment technology, and particularly relates to a method, apparatus and electronic device for determining a movement path. Background Technology

[0002] In industrial warehousing and logistics centers, mobile equipment such as automated guided vehicles (AGVs) or autonomous mobile robots typically communicate with the scheduling system via wireless networks. Due to the large warehouse area and dense metal shelving, the coverage of a single wireless access point is limited, requiring equipment to switch between multiple wireless access points during movement.

[0003] Existing methods for determining mobile paths first plan multiple candidate paths, then filter or rank them based on indicators such as average distance to wireless access points along the path, load, and number of connections. In other words, current technologies only perform post-hoc comparison and selection among multiple predetermined paths. This can lead to situations where some sections of the final selected path have poor wireless signal quality or the device experiences repeated switching of wireless access points during its journey. This significantly impacts data transmission and command interaction, resulting in poor continuity and stability of wireless communication for the mobile path determined by existing methods. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for determining a mobile path, in order to solve the problem that the wireless communication continuity and stability of the mobile path determined by the existing mobile path determination method is poor.

[0005] In a first aspect, embodiments of this application provide a method for determining a movement path, the method comprising: Acquire the device's task information and wireless signal quality map. The task information includes the starting point of movement, the ending point of movement, and the task type. The wireless signal quality map includes multiple grids, and each grid stores the probability distribution parameters of the signal quality of the wireless access points covering that grid in that grid. Based on the probability distribution parameters of the mobile origin, mobile destination, task type, and all wireless access points in all grids, determine at least one candidate path from the mobile origin to the mobile destination. Obtain the path length, time, number of wireless access point switching times, and proportion of preset signal areas for each candidate path; The comprehensive score of the candidate path is determined based on the path length, time, number of wireless access point switching, and preset signal area ratio. The candidate path with the lowest comprehensive score is the target movement path of the device.

[0006] Secondly, embodiments of this application provide a movement path determination device, the device comprising: The acquisition module is used to acquire the device's task information and wireless signal quality map. The task information includes the starting point of movement, the ending point of movement, and the task type. The wireless signal quality map includes multiple grids, and each grid stores the probability distribution parameters of the signal quality of the wireless access points covering that grid in that grid. The determination module is used to determine at least one candidate path from the mobile origin to the mobile destination based on the probability distribution parameters of the mobile origin, mobile destination, task type, and all wireless access points of all grids. The acquisition module is also used to acquire the path length, time, number of wireless access point switching times, and proportion of preset signal areas for each candidate path; The determination module is also used to determine the comprehensive score of the candidate path based on the path length, time, number of wireless access point switching, and preset signal area ratio. The candidate path with the lowest comprehensive score is the target mobile path of the device.

[0007] Thirdly, embodiments of this application provide an electronic device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the movement path determination method as described in the first aspect.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the movement path determination method as described in the first aspect.

[0009] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the movement path determination method as described in the first aspect.

[0010] This application provides a method, apparatus, and electronic device for determining a mobile path. The method first acquires the device's task information and a wireless signal quality map. The task information includes the starting point, ending point, and task type. The wireless signal quality map includes multiple grids, each storing probability distribution parameters of the signal quality of wireless access points covering that grid. Based on the starting point, ending point, task type, and probability distribution parameters of all wireless access points in all grids, at least one candidate path from the starting point to the ending point is determined. For each candidate path, the path length, time taken, number of wireless access point handovers, and proportion of a preset signal area are acquired. A comprehensive score for the candidate path is determined based on the path length, time taken, number of wireless access point handovers, and proportion of the preset signal area, and the candidate path with the lowest comprehensive score is selected as the target mobile path. By dividing the work area into grids and using the mean to represent the overall signal quality and variance to represent signal fluctuation and stability, the method can comprehensively and accurately reflect the actual signal quality status of each wireless access point in different areas. Furthermore, signal quality parameters, including mean and variance, are incorporated during the candidate path generation stage. This proactively avoids areas with poor signal and frequent access point switching from the very beginning of the candidate path formation process, fundamentally reducing the probability of problematic communication segments appearing in the candidate paths. Finally, a comprehensive score is calculated based on multiple indicators to select the optimal path. This approach balances equipment mobility efficiency while further filtering for the optimal mobile path that ensures communication continuity and stability. It addresses the issue of existing technologies easily selecting paths with poor signal quality and repeated access point switching, thereby improving communication continuity and stability and ensuring normal data transmission and command interaction for mobile devices during operation. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of the structure of the system for determining the movement path provided in the embodiments of this application; Figure 2 This is a flowchart illustrating the movement path determination method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating a method for obtaining a wireless signal quality map provided in an embodiment of this application; Figure 4 This is a flowchart illustrating a method for determining a candidate path provided in an embodiment of this application; Figure 5 This is a flowchart illustrating an optimal wireless access point handover method provided in an embodiment of this application; Figure 6 This is a flowchart illustrating the overall process of a method for determining a movement path provided in an embodiment of this application. Figure 7 This is a schematic diagram of the structure of a movement path determination device provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0013] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0014] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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 limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0015] In industrial warehousing and logistics centers, mobile devices such as Automated Guided Vehicles (AGVs) or Autonomous Mobile Robots (AMRs) typically communicate with the scheduling system via Wi-Fi. Due to the large warehouse area and dense metal shelving, the coverage of a single Access Point (AP) is limited, requiring robots to switch between multiple APs during movement. The current mainstream AP switching scheme involves first planning multiple candidate paths, then filtering or ranking them based on metrics such as average distance to APs along the path, load, and number of connections. This scheme is essentially "path posterior filtering." Network quality is used for comparison among discrete candidate paths, rather than as an optimization objective for continuous spatial path search; Wi-Fi related quantities are not jointly minimized with kinematic costs such as distance and time within the same optimization framework. Furthermore, techniques for creating gridded Wi-Fi maps to assist mobile robot navigation divide the environment into grids and store wireless-related information. Typically, the wireless metrics for each grid are treated as static or quasi-static scalar statistics (such as the mean), resulting in weak explicit modeling of observation noise, spatiotemporal evolution, and uncertainties.

[0016] The "path post-hoc filtering" mode only compares WiFi-related quantities among multiple generated paths and cannot participate in node expansion decisions during path search, thus failing to achieve local fine-tuning of path geometry. For example, offsetting by 0.5 meters at the boundary between two AP coverage areas could avoid a handover, but if such an offset path does not exist in the pre-generated candidate path set, this optimization opportunity will not be captured. The "static scalar" representation of grid maps, which only stores the mean, cannot reflect observational uncertainties, cannot be automatically updated when the environment changes (requiring manual recalibration), and cannot provide the planner with probabilistic information such as "this area has low credibility and should be handled conservatively." In a warehouse environment, frequent shelf adjustments and crowd gatherings cause continuous changes in the wireless environment, and static maps become severely inaccurate after a few days.

[0017] To address the problems of existing technologies, this application discloses a method, apparatus, and electronic device for determining a mobile path. The method first acquires the device's task information and a wireless signal quality map. The task information includes the starting point, ending point, and task type. The wireless signal quality map comprises multiple grids, each storing probability distribution parameters of the signal quality of wireless access points covering that grid. Based on the starting point, ending point, task type, and probability distribution parameters of all wireless access points across all grids, at least one candidate path from the starting point to the ending point is determined. For each candidate path, the path length, time taken, number of wireless access point handovers, and proportion of a preset signal area are acquired. A comprehensive score for the candidate path is determined based on the path length, time taken, number of wireless access point handovers, and proportion of the preset signal area, and the candidate path with the lowest comprehensive score is selected as the target mobile path. By dividing the work area into grids and using the mean to represent the overall signal quality and the variance to represent signal fluctuation and stability, the method can comprehensively and accurately reflect the actual signal quality status of each wireless access point in different areas. Furthermore, signal quality parameters, including mean and variance, are incorporated during the candidate path generation stage. This proactively avoids areas with poor signal and frequent access point switching from the very beginning of the candidate path formation process, fundamentally reducing the probability of problematic communication segments appearing in the candidate paths. Finally, a comprehensive score is calculated based on multiple indicators to select the optimal path. This approach balances equipment mobility efficiency while further filtering for the optimal mobile path that ensures communication continuity and stability. It addresses the issue of existing technologies easily selecting paths with poor signal quality and repeated access point switching, thereby improving communication continuity and stability and ensuring normal data transmission and command interaction for mobile devices during operation.

[0018] The following section first introduces the system for determining a mobile path, which is applied to the method for determining a mobile path, as provided in the embodiments of this application.

[0019] Figure 1 A schematic diagram of the structure of a movement path determination system according to an embodiment of this application is shown. Figure 1 As shown, the system may include: Task-aware scheduler 101, path planner 102, wireless signal quality map 103, path prediction engine 104, and robot execution layer 105. The task-aware scheduler 101 determines the corresponding roaming strategy based on the task type and dynamically adjusts the cost weights in path planning. Then, it passes the adjusted weights and task information to the path planner 102. When searching for a path, the path planner 102 queries the posterior mean and variance of wireless access points in each grid from the wireless signal quality map 103 to jointly calculate costs such as distance, time, number of handovers, and the proportion of weak signal areas, generate an optimized path, and output it to the path prediction engine 104. The path prediction engine 104 generates a handover plan based on the optimized path and the wireless signal quality map 103, which includes the handover point location and the target access point sequence, and sends the plan to the robot execution layer 105. During the movement operation, the robot execution layer 105 performs speed-adaptive pre-authentication and rapid reassociation according to the handover plan, and feeds back the real-time signal quality observations collected along the way to the wireless signal quality map 103 to update the corresponding posterior mean and variance, thus forming a complete closed-loop collaboration from task scheduling, path planning, map updating to execution feedback.

[0020] The method for determining the movement path provided in the embodiments of this application is described below.

[0021] Figure 2 A flowchart illustrating a method for determining a movement path according to an embodiment of this application is shown. Figure 2 As shown, the method may include the following steps: S201 to S204.

[0022] S201, Obtain the device's task information and wireless signal quality map. The task information includes the starting point of movement, the ending point of movement, and the task type. The wireless signal quality map includes multiple grids, and each grid stores the probability distribution parameters of the signal quality of the wireless access points covering that grid in that grid.

[0023] The task information describes the work the device needs to perform, including its origin, destination, and the nature of the task. The wireless signal quality map is a graph recording the signal quality received from various wireless access points at each location. The probability distribution parameters are statistical characteristics describing the possible values ​​of signal quality.

[0024] In some embodiments, the wireless signal quality map can be a Bayesian grid map, a wireless signal quality map constructed based on a Gaussian process global regression model, a wireless signal quality map constructed based on a neural network implicit field, or a wireless signal quality map constructed based on particle filtering, etc.

[0025] In some embodiments, before the device begins to move, it first acquires the task information and a wireless signal quality map. This map divides the entire working environment into several equally sized grids. For each grid, the map stores the probability distribution parameters of the signal quality of all searchable wireless access points within that grid area.

[0026] In one example, a warehouse robot receives a task to move goods from the inbound to the outbound port; the task type is handling. Simultaneously, the system loads a pre-built wireless signal quality map, dividing the warehouse into 0.5m x 0.5m grids. For a given signal, the mean signal quality near the shelving area is -75dBm, with a large variance, indicating significant signal fluctuations; in the grids of open aisles, the mean is approximately -55dBm, with a small variance, indicating a stable and strong signal.

[0027] This embodiment of the application acquires task information and a wireless signal quality map containing probability distribution parameters. This step enables subsequent path planning to utilize complete statistical information on signal quality, rather than just an average value. The probability distribution reflects the fluctuations in signal quality in the real environment caused by various factors. This refined information input lays a data foundation for generating more reliable candidate paths with better communication quality, avoiding the pitfalls of misjudging regional signal quality due to the use of a single mean.

[0028] S202, based on the mobile origin, mobile destination, task type, and probability distribution parameters of all wireless access points in all grids, determine at least one candidate path from the mobile origin to the mobile destination.

[0029] Candidate paths refer to multiple different routes that can be taken from the starting point to the end point, each route consisting of a series of consecutive grids or waypoints.

[0030] In some embodiments, after obtaining the starting point, ending point, task type, and a map containing the probability distribution parameters of signal quality for each wireless access point in all grids, a preset search algorithm is used to perform path searching to generate one or more feasible paths from the starting point to the ending point. This search process comprehensively considers the requirements of the task type, such as whether the task has high requirements for communication reliability or time, and the probability distribution parameters of wireless access points in each grid traversed by the path. When evaluating each extension step, the search algorithm uses the probability distribution information stored in the grid to determine the signal quality and stability of the area, thus tending to select grids with better overall wireless environment to form the path, and finally outputs at least one candidate path for further evaluation.

[0031] This application's embodiments use the probability distribution of wireless signal quality as a crucial basis during the path generation stage, rather than generating paths based on distance first and then filtering them using signal quality afterwards. This approach, intervening at the source of the search, proactively avoids areas with poor signal quality, ensuring that the generated candidate paths naturally possess a better communication foundation. Compared to the two-step approach of planning followed by filtering in existing technologies, this avoids the problem of high-quality signal paths not existing in the candidate path set, thus guaranteeing the communication quality of candidate paths from the source.

[0032] In some implementations, path search algorithms are used to determine at least one candidate path from the starting point to the ending point of the movement. These algorithms may include Rapidly-exploring Random Tree star (RRT) and Probabilistic Roadmap Method (PRM).

[0033] In some embodiments, when determining candidate paths, the weight of signal quality cost in subsequent path searches can be adaptively adjusted based on the cumulative signal quality fluctuations of the currently traversed paths. If the first half of the path has experienced multiple signal fluctuations, the stability requirements for the second half of the path are increased, resulting in a more balanced signal quality across the entire path. For example, when a robot is performing a long-distance transport task, if it has already passed through an area with significant signal fluctuations in the first 200 meters, and the system detects a large cumulative communication quality fluctuation, it will automatically increase the stability requirements for the second half of the path when searching for the remaining paths, selecting a path with smaller signal quality fluctuations.

[0034] S203, obtain the path length, time, number of wireless access point switching times, and proportion of preset signal areas for each candidate path.

[0035] Here, path length is the total geometric distance of the candidate path. Travel time is the estimated travel time based on the device's speed and path geometry. Access point handover count is the estimated number of times the device needs to switch from one access point to another while traveling along the candidate path. Preset signal zone ratio is the percentage of the path's length in which the signal quality is below a certain preset threshold.

[0036] In some embodiments, for each generated candidate path, the path length is determined based on the geometric distance from the starting point to the ending point; the travel time is estimated based on the device's motion speed model and the path length; the number of times the optimal access point changes is counted based on the analysis of the optimal wireless access point at each location along the path; and the proportion of the path length falling into the specified region is calculated based on a predefined signal quality threshold. This describes the performance of the candidate path from different dimensions.

[0037] This application extracts the path length, time, number of wireless access point handovers, and proportion of preset signal areas for candidate paths, enabling subsequent multi-target comprehensive comparisons. Compared to existing technologies that only focus on distance or time, or only on a single network indicator, this application also considers the number of handovers and the proportion of weak signal coverage. The former reflects the risk of interruption during movement, while the latter reflects the quality of continuous communication. The combination of these two indicators can more comprehensively characterize the wireless communication quality of the path, avoiding extreme cases such as "strong average signal but frequent handovers" or "few handovers but weak signal throughout."

[0038] S204. The comprehensive score of the candidate path is determined based on the path length, time, number of wireless access point handovers, and preset signal area ratio. The candidate path with the lowest comprehensive score is the target mobile path of the device.

[0039] The overall score is a numerical value that combines path length, time, number of handovers, and the proportion of weak signal areas according to certain rules, used to compare the merits of different paths. The target movement path is the optimal path selected after comprehensive comparison, which the device will actually move along.

[0040] In some embodiments, after obtaining the length, time, number of handovers, and proportion of weak signal areas for each candidate path, each metric is normalized, weights are assigned to different metrics, and finally, a weighted sum is obtained to obtain a comprehensive score. Since the path length, time, number of handovers, and proportion of weak signal areas are all better the lower they are, the path with the lower comprehensive score means better overall performance. Finally, the comprehensive score of all candidate paths is calculated, and the path with the lowest score is selected as the final target movement path.

[0041] In some embodiments, the formula for calculating the overall score can be:

[0042] in, This is the normalization term for the path length. For the normalized term of expected time consumption, For AP handover count, The proportion of weak signal areas, This represents the proportion of abnormal areas. - Preset weights for each parameter.

[0043] This application embodiment uses a multi-index weighted comprehensive scoring method to quantitatively weigh path length, time consumption, number of handovers, and proportion of weak signal areas, thereby selecting the most balanced path overall. This ensures that the final output target movement path is the solution with the best overall performance among all candidate sets, thus significantly improving the communication continuity and stability during device movement.

[0044] In summary, this application embodiment obtains a wireless signal quality map containing the probability distribution parameters of wireless access point signal quality within each grid, and incorporates four indicators—path length, time consumption, number of wireless access point handovers, and proportion of weak signal areas—into a comprehensive scoring system. Finally, it selects the path with the lowest comprehensive score as the target movement path. This ensures travel efficiency while effectively avoiding signal fluctuation areas using probability distribution parameters, and directly reduces the risk of communication interruption and continuous communication quality deterioration during movement by using the number of handovers and the proportion of weak signal areas. It achieves optimal synergy between travel efficiency and wireless communication continuity, significantly improving the communication reliability of mobile devices during operation.

[0045] In some embodiments, such as Figure 3 As shown, the probability distribution parameters include the mean and variance. Obtaining a wireless signal quality map can include S301 to S304.

[0046] S301, acquire the map of the current working area of ​​the device, and divide the map of the current working area of ​​the device into multiple two-dimensional grids with a preset resolution.

[0047] The preset resolution is the side length of each grid cell. The two-dimensional grid is a planar division of the actual working area into neatly arranged small squares.

[0048] In some embodiments, a fixed spatial sampling interval, i.e. a preset resolution, is first determined, and then the entire working area of ​​the device is gridded in both the horizontal and vertical directions according to the interval to form a series of continuous and non-overlapping square grid units, each grid unit covering a fixed-size area in the actual physical space.

[0049] In one example, a warehouse environment is 60 meters long and 40 meters wide. If the grid resolution is set to 0.2 meters, then it is divided into 300 grids horizontally and 200 grids vertically, for a total of 60,000 grids. Each grid represents an actual area of ​​40 square centimeters.

[0050] This application's embodiments discretize a continuous space into a finite number of grids by using a preset resolution, making the data structure of the wireless signal quality map regular and indexable, greatly reducing storage and computational complexity. Simultaneously, the resolution can be adjusted in different scenarios to balance map accuracy and resource consumption; for example, a coarser resolution can be used in open areas to save memory, while a finer resolution can be used in areas with drastic signal changes to improve positioning accuracy.

[0051] In some embodiments, when dividing the grid, an adaptive non-uniform grid division strategy can be adopted based on the distribution density of wireless access points and the signal attenuation characteristics of the environment. In areas with dense wireless access points or large signal gradients, the resolution can be automatically increased (the grid is smaller), while in areas with sparse wireless access points or gentle signals, the resolution can be automatically decreased (the grid is larger), thereby further compressing the amount of data while maintaining map accuracy.

[0052] The embodiments of this application solve the redundant storage problem caused by fixed uniform grids and achieve a dynamic optimal balance between map accuracy and storage efficiency.

[0053] S302, for each wireless access point covering the grid in each grid, obtain the signal quality, preset prior probability distribution parameters and preset noise variance of the wireless access point at the location corresponding to the grid. The preset prior probability distribution parameters include the prior mean and the prior variance.

[0054] Here, signal quality refers to the actual signal strength of the wireless access point measured by the device at a certain location. The preset prior probability distribution parameters are the range (prior mean) and probability (prior variance) of the signal quality of the wireless access point in that grid, pre-set before this measurement or from the previous measurement. The preset noise variance is the inherent error fluctuation of the measuring device itself.

[0055] The embodiments of this application simultaneously acquire signal quality, preset prior probability distribution parameters, and preset noise variance, enabling subsequent processing to combine historical experience with current measurement results, rather than relying solely on a single measurement value that may contain random errors, thereby improving the robustness and accuracy of signal quality estimation.

[0056] S303, determine the mean and variance of the signal quality of the wireless access point in the corresponding grid based on the signal quality, preset noise variance, prior mean, and prior variance.

[0057] The mean represents the signal quality value of the wireless access point for that grid. The variance represents the degree of uncertainty of that signal quality value.

[0058] In some embodiments, the acquired signal quality, prior mean, prior variance, and preset noise variance are substituted into the Bayesian update formula to calculate a new posterior mean and posterior variance.

[0059] In some embodiments, observation In position Quality measured at wireless access point a .Will Associated with the overlay raster set For the unit Using the conjugate model as an example, if The unknown mean under Gaussian noise Given the noise variance Then a priori The formulas for calculating the posterior mean and variance are as follows:

[0060] in, Let be the posterior mean of the signal quality of a wireless access point in grid c. For the observation information of the t-th observation, This is the a priori precision, which is the reciprocal of the a priori variance. The observation accuracy is the reciprocal of the observation noise variance. This is the prior mean.

[0061] The embodiments of this application fuse the measured signal quality with the prior probability distribution parameters, neither over-relying on potentially distorted single measurements nor entirely relying on prior data; at the same time, the output variance can directly reflect the reliability of the current estimate, providing a quantitative basis for risk decisions in subsequent path planning.

[0062] S304. Construct a wireless signal quality map based on the mean and variance of the signal quality of all wireless access points in all grids.

[0063] In some embodiments, the posterior mean and posterior variance calculated for each wireless access point in each grid are stored according to the spatial location of the grid and the identifier of the wireless access point, forming a complete data structure map that can be quickly queried. Each location in this map contains the expected signal quality value of the corresponding wireless access point at that location and its uncertainty measure.

[0064] In some embodiments, the environment is divided into resolutions. A two-dimensional grid, each cell Related Locations For any AP With quality indicators (Such as effective throughput, negative RSSI, or comprehensive score), instead of being represented by a single-point mean, a parameterized distribution is maintained. , It is a collection of historical observation data.

[0065] In summary, this embodiment divides the working area into regular grids and, for each wireless access point in each grid, fuses the signal quality, preset prior probability distribution parameters, and preset noise variance to calculate the posterior mean and posterior variance of the AP in that grid. Each grid not only stores the signal quality value of the wireless access point but also the uncertainty of this estimate. This allows subsequent path planning to distinguish between areas with stable but moderate signal quality and areas with large signal fluctuations but high signal quality, thereby making more informed detour or passage decisions. Furthermore, the map can be iteratively updated with the continuous arrival of new observation data, without the need for manual recalibration, automatically adapting to environmental changes, thus providing a refined probabilistic environmental perception foundation for the entire mobile path determination method.

[0066] In some embodiments, the method may further include: Obtain the last observation time for each wireless access point in each grid; where the last observation time is the moment when the system last measured the signal of the wireless access point at that grid location; For each wireless access point in each grid, if the time difference between the current time and the last valid observation time exceeds a preset threshold, a time decay factor is determined based on the time difference and a preset time constant; where the preset time constant is a preset parameter that controls the rate of decay; and the time decay factor is a value between 0 and 1 used to scale the variance. The variance after time decay is determined based on the time decay factor and the variance of the wireless access point in the corresponding grid. The variance updated after time decay is the current variance of the wireless access point in the corresponding grid.

[0067] In some embodiments, the system can record a timestamp for each grid cell in the wireless signal quality map and for each wireless access point covering that grid. This timestamp represents the specific moment when the device last passed through the grid and measured the signal quality of the access point. For each wireless access point corresponding to each grid, the system first calculates the time difference between the current time and the last recorded observation time, and compares this difference with a preset threshold. When the time difference exceeds the threshold, an attenuation factor is calculated according to a preset exponential attenuation formula. The larger the time difference or the smaller the time constant, the closer the attenuation factor is to 0, indicating a lower reliability of the outdated data. The time attenuation factor is multiplied by the reciprocal of the variance of the wireless access point in the corresponding grid to obtain the time-attenuated updated variance. Finally, the calculated time-attenuated updated variance is written back and replaces the original variance value of the wireless access point in the corresponding grid in the wireless signal quality map.

[0068] In some embodiments, a time constant is introduced. If the time difference between the current moment and the last valid observation time of a certain unit is... For prior variance or effective sample size For exponential decay, the formula for calculating time decay updates can be:

[0069] Among them, after time decay This represents the number of effective samples after attenuation. This is the attenuation factor.

[0070] This application's embodiments record the last observation time of each wireless access point in each grid, and calculate an exponential attenuation factor based on the time difference between the current time and the last observation, as well as a preset time constant. This attenuation factor is then applied to the corresponding variance to obtain an updated variance that amplifies over time. This mechanism allows the wireless signal quality map to automatically forget historical observation data; that is, the longer a grid has not been observed, the larger its variance, indicating a less reliable estimate of the signal quality in that area, thereby improving the long-term robustness of the device in dynamic environments.

[0071] In some embodiments, the method may further include: Obtain the mean and variance of the wireless access points of the target grid adjacent to the target grid, where the target grid is the grid whose signal quality of the wireless access points has not been obtained; the target adjacent grid is the grid adjacent to the target grid whose signal quality of the wireless access points has been obtained. For each wireless access point in all target neighboring grids, determine the mean and variance of the signal quality of the wireless access point in the target grid based on at least one mean and variance of the wireless access point in all target neighboring grids.

[0072] In some embodiments, when certain grid cells exist in the wireless signal quality map, and because the robot has never traversed these locations or conducted signal measurements at those locations, resulting in no stored posterior mean and variance of any wireless access points, the system identifies these grids as target grids. Then, it retrieves all spatially adjacent grids from the map that have been measured and have stored mean and variance, designating these grids as target neighbor grids, and extracts the mean and variance data of each wireless access point within them for subsequent use. For each wireless access point, the system collects the mean and variance of that access point from all target neighbor grids, and then calculates the predicted mean and predicted variance of that access point in the target grid using a spatial interpolation algorithm.

[0073] In some embodiments, for grids that are not directly observed or are sparsely observed Use this grid as the query grid and leverage adjacent observed cells. The posterior mean and variance of the query raster. Give the predicted mean With prediction variance The calculation formula can be:

[0074] The commonly used kernel is the square exponent kernel: = , The signal quality at position x, Calculated for Gaussian distribution, Let x be the expected signal quality value at location x. Let x be the covariance function (kernel function), representing the correlation of signal quality between any two locations x and x′. To query the spatial location coordinates of a raster, The position of the adjacent observed grid cells. For signal variance, For preset length scale parameters, For noise variance, Let Kronecker function be used.

[0075] This application's embodiments identify unobserved grids as target grids and use the mean and variance of the same wireless access point in adjacent observed grids to infer the mean and variance of the signal quality of that access point in the target grid. This mechanism enables the wireless signal quality map to achieve full-area coverage, obtaining reasonable signal quality estimates even in areas never reached by the device. By interpolating using the mean and variance of adjacent grids, a comprehensive and reliable environmental information foundation is provided for subsequent joint optimization path planning.

[0076] In some embodiments, such as Figure 4 As shown, based on the mobile origin, mobile destination, task type, mean and variance of all wireless access points in all grids, at least one candidate path from the mobile origin to the mobile destination is determined, which may include: S401 and S402.

[0077] S401, based on the task type, determine the corresponding distance cost weight, time cost weight, handover cost weight, and signal quality cost weight.

[0078] The distance cost weight is the importance coefficient of path length in the total cost. The time cost weight is the importance coefficient of travel time in the total cost. The handover cost weight is the importance coefficient of the number of wireless access point handovers in the total cost. The signal quality cost weight is the importance coefficient of the proportion of weak signal areas in the total cost.

[0079] In some embodiments, the type of the current task is first identified, and then the specific values ​​of four weight coefficients are determined according to the pre-defined task type and weight mapping relationship: distance cost weight controls the importance of path length, time cost weight controls the importance of travel time, handover cost weight controls the importance of access point handover times, and signal quality cost weight controls the importance of the proportion of weak signal areas. The allocation of these four weights is different under different task types. For example, for tasks that require high-definition video backhaul, the signal quality cost weight will be set higher, while for urgent and time-sensitive tasks, the time cost weight will be set higher.

[0080] The embodiments of this application enable the path selection preference to be automatically adjusted according to the actual communication needs of the task, realizing the synergy between task semantics and path planning. Tasks that require high bandwidth and low latency will actively choose paths with good signal quality, even if they need to take a detour; while time-sensitive tasks can tolerate signal fluctuations in exchange for faster arrival, thereby significantly improving the success rate of task completion and communication reliability.

[0081] S402, Starting from the grid where the starting point of the movement is located, select adjacent grids in sequence and extend towards the grid where the ending point of the movement is located to obtain at least one candidate path; Specifically, when selecting adjacent grids of the current grid, the path length, travel time, number of wireless access point handovers, and preset signal area ratio of each first path are determined based on the selected grids and each grid to be selected, and at least one first path is formed. The path cost of each first path is determined based on the path length, distance cost weight, travel time, time cost weight, number of wireless access point handovers, handover cost weight, preset signal area ratio, and signal quality cost weight. The grid to be selected corresponding to the first path with a path cost less than a set threshold is the next grid of the corresponding path branch.

[0082] In some embodiments, starting from the grid where the starting point is located, the starting grid is taken as the first node of the current path. Then, in each step, a grid is selected from the set of adjacent grids of the grid at the end of the current path using a preset path search algorithm and added to the path. For each selected adjacent grid, the system temporarily appends the adjacent grid to the end of the currently selected path to form a temporary complete path. Then, the total length of this temporary path, the expected total travel time, the total number of optimal access point handovers along the route from the starting point to the current location, and the road segments with signal quality below a preset threshold are calculated. The four indicators are: length as a percentage of the total path length; then, each indicator is multiplied by its corresponding weight, and the four products are added together to obtain the total cost of the temporary path; finally, the cost of the temporary paths corresponding to all adjacent grids is compared, and the grids with the lowest cost are selected as the target grids for the next extension, extending the path one grid towards the endpoint; this process is repeated until the end grid of the current path coincides with the grid of the endpoint or a preset termination condition is met; by recording the selection of each extension, one or more complete path sequences from the starting grid to the ending grid are finally obtained.

[0083] In some embodiments, let the length of the path arc segment e be... The expected travel time is Define path Total cost:

[0084] in, For distance cost weights, For length , As a time cost weight, For time , To switch cost weights, For the number of wireless access point handovers, As the signal quality cost weight, This is the preset signal area ratio.

[0085] Discretize the path into a point series {p} according to the sampling resolution Based on the Bayesian map, the optimal AP for each point is queried, and the number of changes in the optimal AP between adjacent sampling points is counted. The formula for calculating the number of wireless access point handovers is:

[0086] in, The expected cost of a single switch.

[0087] Let the total path length be... For each edge e, the length of the weak signal region traversed by that edge is obtained from the map. The weak signal region is defined as the region where the quality index at the sampling points is below the threshold. The cumulative arc length. The formula for calculating the preset signal area ratio is:

[0088] Where, when L=0, let This calculation formula represents the proportion of the arc length of the weak signal area to the total path length, causing the planner to tend to avoid blind and weak areas.

[0089] This application's embodiments dynamically determine the cost weights of distance, time, handover, and signal quality based on the task type. Starting from the starting grid and extending progressively towards the ending grid, the algorithm calculates the length, time, number of handovers, and proportion of weak signal areas in each step of the temporary complete path. These are then weighted and summed to obtain the path cost value. Finally, adjacent grids with a cost value below a set threshold are selected as the next extension direction. The number of handovers and the proportion of weak signal areas accumulate as the path extends, enabling the search algorithm to identify potential path branches with excessive cumulative handovers or weak signal areas and abandon them promptly. Therefore, it can proactively discover and retain locally optimal paths that significantly reduce handovers or weak signals by taking a short detour, thus achieving proactive protection of communication quality at the source of path generation.

[0090] In some embodiments, the cost weight mapping table corresponding to the task type is shown in Table 1. For task types that are sensitive to uplink bandwidth and latency, such as visual guidance or real-time image backhaul, the system will increase the signal quality cost weight and appropriately increase the handover cost weight to reduce unnecessary access point handovers. For task types that are mainly control plane data and can tolerate short-term signal degradation, such as simple handling or point-to-point transportation, the system will reduce the signal quality cost weight and prioritize the distance cost weight and time cost weight to shorten the distance and travel time. For task types with intermittent burst characteristics, such as inspection or high-density barcode scanning, the system adopts a medium signal quality cost weight and supports dynamic recalculation of weights by road segment.

[0091] Table 1 Cost Weight Mapping Table

[0092] In some embodiments, when the task type is a preset task type, when selecting adjacent grids, the grids covered by the initial wireless access point connected to the mobile origin are selected.

[0093] The preset task type is a predefined special task that requires disabling or restricting wireless access point switching. The initial wireless access point is the wireless access point that the device connects to at the point of origin of movement.

[0094] In some embodiments, when the device is currently performing a pre-defined, critical task that requires extremely high communication continuity and does not allow any roaming handover, during each step of the path planning process, only grids covered by the signal of the initial wireless access point connected to the starting point of movement are eligible to be selected as the next grid on the path. In other words, the entire candidate path must always remain within the coverage area of ​​the initial wireless access point to ensure that the device does not trigger any access point handover during its entire journey.

[0095] This application embodiment avoids wireless access point switching during critical operations by imposing initial wireless access point coverage constraints on the path under specific task types. This eliminates the risk of brief packet loss, latency jitter, or even connection interruption that may occur during the switching process, and significantly improves the execution security of critical tasks.

[0096] In one example, the wireless access point handover classification for task types is shown in Table 2. Task types are divided into four levels based on their criticality. For tasks such as emergency stop recovery, elevator docking, and obstacle avoidance, the level is set to CRITICAL, and a roaming strategy prohibiting handover is adopted, i.e., locking the current access point. For tasks such as picking up goods, precise alignment, and charging docking, the level is set to HIGH, and a conservative handover strategy is adopted, for example, setting the roaming interval to 15 dB and the hysteresis time to 500 ms. For normal cruising tasks, the level is set to NORMAL, and a standard strategy is adopted, for example, setting the roaming interval to 8 dB and the hysteresis time to 200 ms. For idle waiting or charging tasks, the level is set to LOW, and an aggressive optimization strategy is adopted, for example, setting the roaming interval to 3 dB and actively searching for the optimal access point.

[0097] Table 2. Hierarchical Table of Wireless Access Point Handover by Task Type

[0098] In some embodiments, such as Figure 5 As shown, the method may further include: S501 to S504.

[0099] S501, sample the target movement path according to the preset spatial interval to obtain multiple sampling points.

[0100] The preset spatial interval is a pre-defined sampling distance. The sampling points are located at preset intervals along the target movement path, forming a series of discrete points from the starting point to the ending point.

[0101] In some embodiments, after determining the target movement path, the system collects a series of position coordinate points from the starting point of the path along the geometric direction of the path until the end point, according to a pre-set fixed spatial distance, thereby discretizing the continuous path curve into an ordered sequence of sampling points, each sampling point corresponding to a specific coordinate in the actual physical space.

[0102] This application embodiment discretizes the continuous path, transforming the subsequent wireless access point analysis into the processing of a finite number of discrete locations. This allows for the querying of the optimal access point for each sampled point, thereby transforming the continuous roaming problem into a statistical problem of an ordered state sequence.

[0103] S502 determines the optimal wireless access point for each sampling point based on the mean and variance of the signal quality of the wireless access point at the corresponding location in the wireless signal quality map.

[0104] In some embodiments, the grid cell to which the sampling point belongs is determined based on the coordinates of the sampling point, and then the posterior mean and posterior variance of all wireless access points stored in the grid are extracted from the wireless signal quality map; for each wireless access point, its posterior mean is used as the best estimate of the signal quality, and the posterior mean of all access points is compared, and the wireless access point with the largest variance and the largest mean is selected as the optimal wireless access point for the sampling point.

[0105] This application utilizes the mean and variance in a wireless signal quality map as the criteria for determining the optimal wireless access point for each location. The mean itself incorporates historical observation data from multiple observations, making it more stable and reliable than a single instantaneous measurement. Simultaneously, incorporating the posterior variance effectively prevents high-variance wireless access points, due to outdated data or inaccurate inferences, from being incorrectly recommended as the optimal wireless access point, thereby improving communication reliability.

[0106] S503, based on the optimal wireless access point of all sampling points, determines the wireless access point handover information, including the handover point location and the optimal wireless access point; the handover point location is the location of the sampling point when the optimal wireless access point changes.

[0107] The handover information records the instruction set needed for the device to switch to which wireless access point at which locations during its movement. The handover point location is the spatial coordinate of the sampling point where the optimal wireless access point changes along the movement path.

[0108] In some embodiments, the optimal wireless access points of all sampling points are arranged into a sequence according to the path order. Then, the optimal wireless access point identifiers of two adjacent sampling points are compared in turn. Whenever the optimal access points of two adjacent sampling points are different, the position between these two sampling points is recorded as a switching point, and the changed access point is recorded as the target access point of the switching point. Finally, an ordered switching plan from the starting point to the ending point is output, which includes the location coordinates of each switching point and the target wireless access point to be switched to at that point.

[0109] This application's embodiments transform the optimal wireless access point of discrete sampling points into a mapping between specific handover locations and target wireless access points, enabling the device to know in advance which wireless access point it should hand over to at which location. Compared to traditional passive roaming triggered by signal strength thresholds, this path pre-calculation-based handover plan eliminates the latency and decision uncertainty of wireless access point handover.

[0110] S504, based on the target movement path, performs a movement operation on the device, and according to the wireless access point switching information, switches to the corresponding optimal wireless access point at the switching point location during the movement of the device.

[0111] In some embodiments, the device begins to travel along a determined target path and monitors its own position in real time during the journey. When it detects that the distance between the current location and a certain handover point in the handover information is less than a preset threshold, the device actively initiates the deassociation with the current access point and performs an association operation with the target wireless access point specified by that handover point in the handover information, thereby completing an access point handover. The device continues to travel along the path and processes subsequent handover points in sequence until it reaches the destination.

[0112] The embodiments of this application apply the pre-calculated handover plan directly to the actual movement process. The device does not need to spend time scanning surrounding wireless access points, measuring signal strength and making comparison decisions during the movement. Instead, it directly performs the handover at the precise location according to the plan. Therefore, the handover delay is extremely low and there will be no false handover or missed handover due to signal fluctuations.

[0113] In some embodiments, switching to the corresponding optimal wireless access point at the switching point location during device movement based on wireless access point switching information may include: The device can obtain the distance and speed from its current location to the next switching point in real time, and determine the estimated arrival time based on the distance and speed. If the expected arrival time is less than a set threshold, a pre-authentication request is sent to the optimal wireless access point corresponding to the next handover point location; wherein, the pre-authentication request is a request to complete authentication and key negotiation with the target access point in advance; If the device receives a successful authentication message from the optimal wireless access point corresponding to the next handover point location, and the device has reached the next handover point location, it connects to the optimal wireless access point corresponding to the successfully authenticated next handover point location.

[0114] In some embodiments, while traveling along the target path, the device continuously acquires its precise location coordinates using its own positioning system, and simultaneously reads the location coordinates of the next yet-to-be-reached switching point from the switching information, calculating the distance between the two points. It also acquires its current speed in real time using a speed sensor, and then divides the distance value by the current speed value to obtain an estimated time value, representing the time required to travel from the current location to the next switching point. This value is compared with a pre-set time threshold; if the estimated arrival time is less than the threshold, it means the device will reach the next switching point in a very short time. At this point, the system immediately sends a pre-authentication request frame to the target wireless access point corresponding to the next switching point via the wireless network interface. This request frame aims to complete security authentication and key negotiation at the access point in advance, so that the device can quickly associate upon arrival without needing to perform a complete authentication process on-site. Once the device has sent a pre-authentication request to the target access point and successfully received an authentication success confirmation message from the target access point, the device continues to travel along the path and continuously monitors its own position. Once it detects that the distance between the current position and the next handover point is less than a preset arrival accuracy threshold, the device immediately sends a reassociation request frame to the target access point. This request frame carries the key information negotiated during the pre-authentication phase. After verification by the target access point, a data connection is quickly established. The device then disconnects from the old access point, completing a full access point handover.

[0115] This application embodiment dynamically calculates the estimated arrival time by acquiring the distance between the device's current location and the next handover point, as well as its current speed, in real time. If this time is less than a set threshold, a pre-authentication request is sent to the target access point in advance. Finally, upon receiving successful authentication information and actually arriving at the handover point, a re-association connection is performed. Separating pre-authentication from re-association allows the device to perform only a lightweight re-association operation upon arrival at the handover point, without needing to undergo the time-consuming full authentication process. This improves the smoothness and communication continuity of mobile devices when handover across wireless access points.

[0116] In some embodiments, the overall process for path prediction and wireless access point handover can be as follows: AP location registration. Load the location information {bssid, x, y, coverage_radius} of each AP, and construct a spatial index (such as K-dimensional tree KD-tree or region tree R-tree) to quickly query candidate APs near any point on the path. Wherein, bssid is the identifier of the wireless access point, x and y are the physical coordinate positions of the wireless access point in the environment map, and coverage_radius is the signal coverage radius.

[0117] Path and wireless access point mapping and handover plan generation. Sample the optimal mobile path P* at a fixed spacing (e.g., 0.2m) along the path direction to obtain a point sequence {pi}, query the optimal wireless access point best_ap(pi) for each sampling point through the Bayesian map, record AP change points, and generate an ordered handover plan switch_plan=[(switch_point_1,target_ap_1),(switch_point_2,target_ap_2),...]. Each handover point corresponds to the position where the optimal AP changes on the path. switch_point_k is the k-th handover point, that is, the spatial position where the optimal AP changes on the path. target_ap_k is the target AP of the k-th handover point, that is, the AP that needs to be switched and connected after reaching the handover point.

[0118] Speed-adaptive pre-authentication. For each handover point in the handover plan, calculate the remaining distance d from the current position to the next handover point and the current speed v in real time, and obtain the estimated arrival time t=d / v. When t<Tpreauth (pre-authentication window threshold), initiate an 802.11r FT pre-authentication request for fast roaming protocol or a custom pre-authentication handshake to the target AP; when the robot reaches the handover point, it only needs to execute Reassociation, thereby reducing the actual handover delay from hundreds of milliseconds to tens of milliseconds.

[0119] In some embodiments, the overall process of determining the mobile path of the present application is as follows Figure 6As shown, the process may include: S601, firstly, system initialization is performed, loading the wireless access point location table and the wireless network quality map to provide basic data for subsequent path planning, roaming decisions, and spatial interpolation. S602, after receiving task information, the current task type is identified, and distance cost weight, time cost weight, handover cost weight, and signal quality cost weight are set according to the preset task-weight mapping relationship, thereby realizing the linkage between task semantics and path planning parameters. S603, then, through joint optimization of the path and the wireless network quality map (considering the path length, expected time, number of wireless access point handovers along the path, and the proportion of weak signal area length in each step of the path search), one or more candidate paths are generated from the starting point to the destination, and the optimal mobile path with the minimum comprehensive cost is output. S604, on this optimal mobile path, sampling is performed at preset spatial intervals, and the optimal wireless access point is determined based on the posterior mean and variance of each sampling point in the wireless signal quality map. The changes in the optimal access point positions of adjacent sampling points are compared, thereby calculating the handover point position and the corresponding optimal wireless access point sequence, and generating a specific handover plan. S605: The device travels along the optimal path, entering a cycle, and collects device status (location, speed, current access point signal quality, etc.) in real time. It determines whether handover is allowed based on the task level (e.g., handover is prohibited for critical tasks). If the estimated arrival time from the next handover point is less than a preset threshold, a pre-authentication request is sent to the target access point, and a fast reassociation operation is performed upon actual arrival at the handover point. S606: After the handover is executed, it is determined whether the handover was successful. S607: If the handover is successful, the device collects observation data along the route (including location, access point identifier, and measured signal quality). The posterior mean and variance of the corresponding access point in the corresponding grid are corrected using Bayesian update rules. Simultaneously, a time decay factor is applied to reduce the weight of outdated data, enabling the wireless network quality map to adapt to environmental changes. S608 Finally, check if there is a path change (e.g., path replanning due to temporary obstacle avoidance) or a sudden change in the environment (e.g., a sharp increase in variance in a certain area of ​​the wireless signal quality map or the triggering of an abnormal area marker); if the above changes occur, return to S603 to replan the optimal path; if no changes occur and the task is not completed, continue to execute the cycle from S605 to S608; if the task is completed, the process ends.

[0120] In summary, this application's embodiments directly incorporate WiFi switching costs and quality costs into the path planning cost function, enabling the planner to proactively change the path geometry during the search process to bypass weak signal areas. Unlike traditional static grid maps that only store the mean, Bayesian probabilistic grid maps maintain the posterior probability distribution of quality variables for each grid cell, combining time decay and Gaussian process space inference to achieve uncertainty perception and environmental adaptation. The task-network requirement mapping maps task types to weight parameters in the path cost function, allowing visual guidance tasks and simple transport tasks within the same framework to obtain different path preferences, achieving consistency in task semantics between the planning and execution layers.

[0121] Figure 7 This application illustrates a movement path determination device 700 provided in an embodiment of the present application. The device may include: The acquisition module 701 is used to acquire the device's task information and wireless signal quality map. The task information includes the starting point of movement, the ending point of movement, and the task type. The wireless signal quality map includes multiple grids, and each grid stores the probability distribution parameters of the signal quality of the wireless access points covering the grid in that grid. The determination module 702 is used to determine at least one candidate path from the mobile origin to the mobile destination based on the mobile origin, mobile destination, task type, and probability distribution parameters of all wireless access points in all grids. The acquisition module 701 is also used to acquire the path length, time, number of wireless access point switching times, and proportion of preset signal areas for each candidate path; The determination module 702 is also used to determine the comprehensive score of the candidate path based on the path length, time, number of wireless access point switching, and preset signal area ratio of the candidate path, wherein the candidate path with the lowest comprehensive score is the target mobile path of the device.

[0122] In some embodiments, the movement path determining device 700 may further include: The segmentation module is used to obtain a map of the current working area of ​​the device and divide the map of the current working area of ​​the device into multiple two-dimensional grids with a preset resolution; The acquisition module 701 is also used to acquire, for each wireless access point covering the grid in each grid, the signal quality, preset prior probability distribution parameters and preset noise variance of the wireless access point at the location corresponding to the grid, the preset prior probability distribution parameters including the prior mean and the prior variance. The determination module 702 is also used to determine the mean and variance of the signal quality of the wireless access point in the corresponding grid based on the signal quality, the preset noise variance, the prior mean, and the prior variance; The module is used to build a wireless signal quality map based on the mean and variance of the signal quality of all wireless access points in all grids.

[0123] In some embodiments, the acquisition module 701 is further configured to acquire the last observation time of each wireless access point in each grid; The determination module 702 is also used to determine a time decay factor based on the time difference and a preset time constant for each wireless access point in each grid when the time difference between the current time and the last valid observation time exceeds a preset threshold. The determination module 702 is further configured to determine the time-attenuation updated variance based on the time attenuation factor and the variance of the wireless access point in the corresponding grid; the time-attenuation updated variance is the current variance of the wireless access point in the corresponding grid.

[0124] In some embodiments, the determining module 702 is further configured to: Obtain the mean and variance of the wireless access points of the target grid adjacent to the target grid, where the target grid is the grid whose signal quality of the wireless access points has not been obtained; the target adjacent grid is the grid adjacent to the target grid whose signal quality of the wireless access points has been obtained. For each wireless access point in all target neighboring grids, determine the mean and variance of the signal quality of the wireless access point in the target grid based on at least one mean and variance of the wireless access point in all target neighboring grids.

[0125] In some embodiments, the movement path determining device 700 may further include: The determination module 702 is also used to determine the corresponding distance cost weight, time cost weight, handover cost weight and signal quality cost weight according to the task type; The selection module is used to start from the grid where the movement originates, sequentially select adjacent grids and extend towards the grid where the movement ends, to obtain at least one candidate path; Specifically, when selecting adjacent grids of the current grid, the path length, travel time, number of wireless access point handovers, and preset signal area ratio of each first path are determined based on the selected grids and each grid to be selected, and at least one first path is formed. The path cost of each first path is determined based on the path length, distance cost weight, travel time, time cost weight, number of wireless access point handovers, handover cost weight, preset signal area ratio, and signal quality cost weight. The grid to be selected corresponding to the first path with a path cost less than a set threshold is the next grid of the corresponding path branch.

[0126] In some embodiments, the selection module is further configured to, when selecting adjacent grids, select the grid covered by the initial wireless access point connected to the mobile origin when the task type is a preset task type.

[0127] In some embodiments, the movement path determining device 700 may further include: The sampling module is used to sample the target movement path according to a preset spatial interval to obtain multiple sampling points; The determination module 702 is also used to determine the optimal wireless access point for each sampling point based on the mean and variance of the signal quality of the wireless access point at the corresponding location of each sampling point in the wireless signal quality map. The determination module 702 is also used to determine wireless access point handover information, including the handover point location and the optimal wireless access point, based on the optimal wireless access point of all sampling points; the handover point location is the location of the sampling point when the optimal wireless access point changes. The switching module is used to perform a movement operation on the device based on the target movement path, and to switch to the corresponding optimal wireless access point at the switching point location during the movement of the device according to the wireless access point switching information.

[0128] In some embodiments, the movement path determining device 700 may further include: The acquisition module 701 is also used to acquire the distance and current speed from the current position of the device to the next switching point in real time, and to determine the estimated arrival time based on the distance and current speed; The sending module is used to send a pre-authentication request to the optimal wireless access point corresponding to the next handover point location if the expected arrival time is less than a set threshold. The connection module is used to connect to the optimal wireless access point corresponding to the next handover point location after receiving authentication success information from the optimal wireless access point corresponding to the next handover point location and the device has reached the next handover point location.

[0129] It should be noted that the movement path determination device 700 is a device corresponding to the movement path determination method described above. All implementation methods in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0130] Figure 8 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0131] Electronic devices may include a processor 801 and a memory 802 storing computer program instructions.

[0132] Specifically, the processor 801 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0133] Memory 802 may include mass storage for data or instructions. For example, and not limitingly, memory 802 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 802 may include removable or non-removable (or fixed) media, or memory 802 may be non-volatile solid-state memory. Memory 802 may be internal or external to the integrated gateway disaster recovery device.

[0134] In one example, memory 802 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the movement path determination method according to this disclosure.

[0135] The processor 801 reads and executes computer program instructions stored in the memory 802 to achieve... Figure 2 The method for determining the movement path in the illustrated embodiment.

[0136] In one example, the electronic device may also include a communication interface 803 and a bus 804. For example, Figure 8 As shown, the processor 801, memory 802, and communication interface 803 are connected through bus 804 and complete communication with each other.

[0137] The communication interface 803 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0138] Bus 804 includes hardware, software, or both, that couples components of an electronic device together. For example, and not as a limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 804 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0139] Furthermore, in conjunction with the movement path determination methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the movement path determination methods in the above embodiments.

[0140] This application also provides a computer program product, including a computer program, which, when executed, implements any of the movement path determination methods described in the above embodiments.

[0141] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0142] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or text segments used to perform the required tasks. Programs or text segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Text segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0143] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0144] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0145] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for determining a movement path, characterized in that, The method includes: The task information and wireless signal quality map of the device are obtained. The task information includes the starting point of movement, the ending point of movement and the task type. The wireless signal quality map includes multiple grids. Each grid stores the probability distribution parameters of the signal quality of the wireless access points covering the grid in the grid. Based on the probability distribution parameters of the mobile origin, mobile destination, task type, and all wireless access points of all grids, at least one candidate path is determined from the mobile origin to the mobile destination. Obtain the path length, time, number of wireless access point switching times, and proportion of preset signal areas for each candidate path; The comprehensive score of the candidate path is determined based on the path length, time, number of wireless access point switching, and preset signal area ratio. The candidate path with the lowest comprehensive score is the target mobile path of the device.

2. The method for determining a movement path according to claim 1, characterized in that, The probability distribution parameters include the mean and variance. Obtaining a wireless signal quality map includes: Obtain a map of the device's current working area and divide the map of the device's current working area into multiple two-dimensional grids with a preset resolution; For each wireless access point covering the grid in each grid, the signal quality, preset prior probability distribution parameters, and preset noise variance of the wireless access point at the corresponding position in the grid are obtained. The preset prior probability distribution parameters include the prior mean and the prior variance. The mean and variance of the signal quality of the wireless access point in the corresponding grid are determined based on the signal quality, preset noise variance, prior mean, and prior variance. A wireless signal quality map is constructed based on the mean and variance of the signal quality of all wireless access points in all grids.

3. The method for determining a movement path according to claim 2, characterized in that, The method further includes: Obtain the last observation time for each wireless access point in each grid; For each wireless access point in each grid, if the time difference between the current time and the last valid observation time exceeds a preset threshold, a time decay factor is determined based on the time difference and a preset time constant. The variance after time decay is determined based on the time decay factor and the variance of the wireless access point in the corresponding grid; the variance after time decay is the current variance of the wireless access point in the corresponding grid.

4. The method for determining a movement path according to claim 2, characterized in that, The method further includes: Obtain the mean and variance of the wireless access points of the target grid adjacent to the target grid, wherein the target grid is a grid for which the signal quality of the wireless access points has not been acquired; and the target adjacent grid is a grid adjacent to the target grid for which the signal quality of the wireless access points has been acquired. For each wireless access point in all target neighboring grids, determine the mean and variance of the signal quality of the wireless access point in the target grid based on at least one mean and variance of the wireless access point in all target neighboring grids.

5. The method for determining a movement path according to any one of claims 1-4, characterized in that, The step of determining at least one candidate path from the mobile origin to the mobile destination based on the mobile origin, mobile destination, task type, and the mean and variance of all wireless access points in all grids includes: Based on the task type, determine the corresponding distance cost weight, time cost weight, handover cost weight, and signal quality cost weight; Starting from the grid where the starting point of the movement is located, adjacent grids are selected in sequence and the movement is gradually extended towards the grid where the ending point of the movement is located to obtain at least one candidate path; Specifically, when selecting adjacent grids of the current grid, the path length, travel time, number of wireless access point handovers, and preset signal area ratio of each first path are determined based on the selected grids and at least one first path formed by each grid to be selected. The path cost of each first path is determined based on the path length, distance cost weight, travel time, time cost weight, number of wireless access point handovers, handover cost weight, preset signal area ratio, and signal quality cost weight. The grid to be selected corresponding to the first path with a path cost less than a set threshold is the next grid of the corresponding path branch.

6. The method for determining a movement path according to claim 5, characterized in that, When the task type is a preset task type, when selecting adjacent grids, the grid covered by the initial wireless access point connected to the mobile origin is selected.

7. The method for determining a movement path according to any one of claims 1-4 or 6, characterized in that, The method further includes: The target movement path is sampled according to a preset spatial interval to obtain multiple sampling points; The optimal wireless access point for each sampling point is determined based on the mean and variance of the signal quality of the wireless access point at the corresponding location in the wireless signal quality map. Based on the optimal wireless access point of all sampling points, determine wireless access point switching information, including the switching point location and the optimal wireless access point; the switching point location is the location of the sampling point when the optimal wireless access point changes. Based on the target movement path, the device is moved, and according to the wireless access point switching information, it is switched to the corresponding optimal wireless access point at the switching point location during the movement of the device.

8. The method for determining a movement path according to claim 7, characterized in that, The step of switching to the corresponding optimal wireless access point at the switching point location during the movement of the device based on the wireless access point switching information includes: The distance and current speed from the current location of the device to the next switching point are obtained in real time, and the estimated arrival time is determined based on the distance and current speed. If the estimated arrival time is less than a set threshold, a pre-authentication request is sent to the optimal wireless access point corresponding to the next handover point location. Upon receiving authentication success information from the optimal wireless access point corresponding to the next handover point location, and upon reaching the next handover point location, the device connects to the optimal wireless access point corresponding to the successfully authenticated next handover point location.

9. A movement path determination device, characterized in that, The device includes: The acquisition module is used to acquire the device's task information and wireless signal quality map. The task information includes the starting point of movement, the ending point of movement, and the task type. The wireless signal quality map includes multiple grids, and each grid stores the probability distribution parameters of the signal quality of the wireless access points covering the grid in that grid. The determination module is used to determine at least one candidate path from the mobile origin to the mobile destination based on the mobile origin, mobile destination, task type, and probability distribution parameters of all wireless access points in all grids. The acquisition module is also used to acquire the path length, time, number of wireless access point switching times, and proportion of preset signal areas for each candidate path; The determining module is also used to determine the comprehensive score of the candidate path based on the path length, time, number of wireless access point switching, and preset signal area ratio of the candidate path, wherein the candidate path with the lowest comprehensive score is the target mobile path of the device.

10. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the movement path determination method as described in any one of claims 1-8.

Images