Map updating method, path planning method, related device, equipment and medium

Abstract

The invention discloses a map updating method, a path planning method, a related device, equipment and a medium, and the map updating method comprises the steps: obtaining the probability distribution of each obstacle region, and obtaining the real-time pose of a robot and the real-time measurement value of an observation point in a physical space; obtaining a physical distance between the observation point and the center point of the obstacle area based on the real-time pose, the real-time measurement value and the center coordinate of the obstacle area; based on a comparison result between each physical distance and a distance threshold value, determining whether the observation point belongs to an obstacle area and a specific obstacle area to which the observation point belongs; and responding to the observation point belonging to the obstacle area, updating the probability distribution of the obstacle area to which the observation point belongs based on the observation point, and drawing a virtual line for guiding the robot to avoid the obstacle in the map data based on the real-time pose and the real-time measurement value. According to the scheme, obstacle modeling can be carried out through instantaneous measurement so as to support the robot to effectively avoid obstacles in the moving process.

Description

Technical Field

[0001] This application relates to the field of robotics technology, and in particular to a map updating method, a path planning method, and related devices, equipment, and media. Background Technology

[0002] Robot motion control relies heavily on map data, and obstacle modeling is particularly important in this process because it enables robots to effectively avoid obstacles during movement.

[0003] Currently, existing obstacle avoidance technologies mainly include geometric ranging, optical imaging, waveform analysis, and threshold judgment. These technologies all suffer from a major problem: they cannot model obstacles through instantaneous measurements. Therefore, how to model obstacles through instantaneous measurements to support robots in effectively avoiding obstacles during movement has become an urgent problem to be solved. Summary of the Invention

[0004] The main technical problem addressed in this application is to provide a map updating method, a path planning method, and related devices, equipment, and media that can model obstacles through instantaneous measurements to support robots in effectively avoiding obstacles during movement.

[0005] To address the aforementioned technical problems, the first aspect of this application provides a map updating method, comprising: acquiring the probability distribution of each obstacle region, and acquiring the robot's real-time pose and real-time measurement values ​​of observation points in the physical space; wherein, the probability distribution represents the probability value of any point in the physical space belonging to an obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region; based on the real-time pose, real-time measurement values, and center coordinates of the obstacle region, obtaining the physical distance between the observation point and the center point of the obstacle region; based on the comparison results between each physical distance and a distance threshold, determining whether the observation point belongs to an obstacle region and the specific obstacle region to which it belongs; in response to the observation point belonging to an obstacle region, updating the probability distribution of the obstacle region to which the observation point belongs based on the observation point, and drawing a virtual line in the map data based on the real-time pose and real-time measurement values ​​to guide the robot to avoid obstacles.

[0006] To address the aforementioned technical problems, a second aspect of this application provides a path planning method, comprising: acquiring map data; wherein the map data is obtained by the map update method described in the first aspect; and performing path planning based on the map data to obtain the robot's motion path.

[0007] To address the aforementioned technical problems, a third aspect of this application provides a map updating device, comprising: a parameter acquisition module, a distance calculation module, a subordination determination module, and an update drawing module. The parameter acquisition module is used to acquire the probability distribution of each obstacle region, and to acquire the robot's real-time pose and real-time measurement values ​​of observation points in the physical space; wherein, the probability distribution represents the probability value of any point in the physical space belonging to an obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region; the distance calculation module is used to obtain the physical distance between the observation point and the center point of the obstacle region based on the real-time pose, real-time measurement values, and the center coordinates of the obstacle region; the subordination determination module is used to determine whether the observation point belongs to an obstacle region and the specific obstacle region it belongs to based on the comparison results between each physical distance and a distance threshold; the update drawing module is used to update the probability distribution of the obstacle region to which the observation point belongs based on the observation point in response to the observation point belonging to an obstacle region, and to draw virtual lines in the map data based on the real-time pose and real-time measurement values ​​to guide the robot to avoid obstacles.

[0008] To address the aforementioned technical problems, a fourth aspect of this application provides a path planning device, comprising: a map acquisition module and a motion planning module. The map acquisition module is used to acquire map data, wherein the map data is obtained from the map updating device described in the third aspect. The motion planning module is used to perform path planning based on the map data to obtain the motion path of the robot.

[0009] To address the aforementioned technical problems, the fifth aspect of this application provides an electronic device comprising at least a memory and a processor coupled to each other. The memory stores at least program instructions, and the processor executes the program instructions to implement the map update method in the first aspect or the path planning method in the second aspect.

[0010] To address the aforementioned technical problems, a sixth aspect of this application provides a computer-readable storage medium storing program instructions executable by a processor. These program instructions are used to implement the map update method of the first aspect or the path planning method of the second aspect.

[0011] The above scheme obtains the probability distribution of each obstacle region, the robot's real-time pose, and real-time measurements of observation points in the physical space. The probability distribution represents the probability that any point in the physical space belongs to an obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region. Based on the real-time pose, real-time measurements, and the center coordinates of the obstacle region, the physical distance between the observation point and the center point of the obstacle region is obtained. Then, based on the comparison results of each physical distance with a distance threshold, it is determined whether the observation point belongs to an obstacle region and its specific obstacle region. In response to the observation point belonging to an obstacle region, the probability distribution of the obstacle region to which the observation point belongs is updated, and... Based on real-time pose and measurements, virtual lines are drawn in the map data to guide the robot in obstacle avoidance. This allows for two main advantages: firstly, maintaining a separate probability distribution for each obstacle region during map updates to determine if an observation point belongs to an obstacle region; and secondly, updating the probability distribution of the corresponding obstacle region if it does. This dynamic maintenance of probability distributions facilitates obstacle modeling through instantaneous measurements. Secondly, combining real-time pose and measurements with virtual lines in the map data provides explicit data to better guide the robot in obstacle avoidance. Therefore, obstacle modeling through instantaneous measurements enables effective obstacle avoidance by the robot during movement. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating an embodiment of the map updating method of this application; Figure 2a This is a schematic diagram of a process of one embodiment of the map updating method of this application; Figure 2b This is a schematic diagram of another embodiment of the map updating method of this application; Figure 2c This is a schematic diagram of an embodiment of the virtual line lifetime of this application; Figure 3 This is a flowchart illustrating an embodiment of the path planning method of this application; Figure 4 This is a schematic diagram of the framework of an embodiment of the map updating device of this application; Figure 5 This is a schematic diagram of the framework of an embodiment of the path planning device of this application; Figure 6 This is a schematic diagram of the framework of an embodiment of the electronic device of this application; Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0013] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0014] In the following description, specific details such as particular system architectures, interfaces, and technologies are presented for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of this application.

[0015] In this paper, the terms "system" and "network" are often used interchangeably. The term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the slash " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this paper indicates two or more objects.

[0016] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the map updating method of this application. Specifically, it may include the following steps: Step S11: Obtain the probability distribution of each obstacle area, and obtain the robot's real-time pose and real-time measurement values ​​of the observation points in the physical space.

[0017] In this embodiment, the probability distribution can characterize the probability value that any point in the physical space belongs to the obstacle region, and the mean of the probability distribution can characterize the center coordinates of the obstacle region. As a possible implementation example, the probability distribution can specifically be a normal distribution, and the standard deviation of the probability distribution can characterize the positional uncertainty. Of course, the above example is merely one possible example of the probability distribution; other possible distribution forms of the probability distribution are not limited here, nor will they be listed one by one. Taking a normal distribution as an example, the probability distribution can be expressed as:

[0018] In the above formula, μ x μ y Let x and y represent the mean along the X-axis and Y-axis, respectively; in other words, they can also be represented as the coordinates of the center along the X-axis and Y-axis. Let x and y represent the coordinates of any point along the X-axis and Y-axis, respectively, and σ represent the standard deviation.

[0019] In one implementation scenario, the probability distribution of each obstacle region can be continuously adjusted during map updates, as detailed in the relevant descriptions below, which will not be elaborated upon here. Furthermore, in the initial stage, an obstacle region can be initialized, and its probability distribution can also be randomly initialized. Taking a normal probability distribution as an example, the mean and standard deviation of the probability distribution can be initialized to 0. Of course, the above example is merely a case study of probability distribution initialization in the initial stage; other possible scenarios will not be illustrated here.

[0020] In one implementation scenario, in addition to the probability distribution, each obstacle region can also maintain its own parameters such as the number of detections and update time. For ease of aggregation, each obstacle region can maintain its own statistical data. The probability distribution of an obstacle region can be included in its statistical data, and the statistical data can also include parameters such as the number of detections and update time. It should be noted that the number of detections represents the number of times an observation point is assigned to an obstacle region, and the update time represents the time when the observation point was last detected in the obstacle region.

[0021] In one implementation scenario, the robot's real-time pose can be sensed by sensors within the robot, such as accelerometers. The specific sensors used for sensing real-time pose are not limited here. As one possible implementation example, the real-time pose may specifically include the robot's position coordinates and its facing direction; or, as another possible implementation example, the real-time pose may specifically include the robot's pose change relative to the previous moment. In this case, after each sensing, the data can be continuously superimposed on the previous sensing data to obtain the robot's position coordinates, facing direction, and other parameter information at the time of the current measurement. It should be noted that the above examples are merely a few possible examples of real-time pose; other possible scenarios for real-time pose will not be listed here.

[0022] In one implementation scenario, real-time measurements of observation points in physical space represent the straight-line distance between the robot and the observation points. Please refer to [reference needed]. Figure 2a , Figure 2a This is a schematic diagram illustrating an embodiment of the map updating method of this application. For example... Figure 2a As shown, real-time measurements of observation points in physical space can be obtained by a single-point dToF sensor in the robot; the sensor used to sense the real-time measurements is not limited here. It should be noted that, when using a single-point dToF sensor to measure real-time measurements, this embodiment of the present disclosure can achieve probabilistic modeling on a single-point dToF sensor, which traditionally requires an area array sensor. This helps reduce the hardware cost of map updates, and because it eliminates the need to process complex point cloud data, it also facilitates implementation on low-computing-power platforms.

[0023] In one implementation scenario, as a possible example of practical application, the robot's real-time pose and real-time measurement values ​​of observation points in the physical space can be acquired at preset detection cycles. For example, the robot can acquire real-time pose and real-time measurement values ​​at a frequency of 10Hz.

[0024] Step S12: Based on the real-time pose, real-time measurement values, and center coordinates of the obstacle area, obtain the physical distance between the observation point and the center point of the obstacle area.

[0025] In one implementation scenario, as mentioned earlier, the real-time pose can directly or indirectly include the robot's position coordinates (see the aforementioned descriptions for details). Based on this, the position coordinates of the observation point can be determined by combining the real-time measurement values ​​and the robot's position coordinates. For example, starting from the robot's position coordinates, a point can be determined at the real-time measurement value forward (i.e., in the measurement direction from the robot to the observation point), thus obtaining the position coordinates of the observation point. After obtaining the position coordinates of the observation point, the physical distance between the observation point and the center point of the obstacle area can be calculated based on the position coordinates of the observation point and the center coordinates of the obstacle area. For example, the difference between the X-axis coordinate value of the observation point and the X-axis coordinate value of the center coordinates of the obstacle area can be obtained, as can the difference between the Y-axis coordinate value of the observation point and the Y-axis coordinate value of the center coordinates of the obstacle area. Taking the root of the sum of the squares of these two differences yields the physical distance between the observation point and the center point of the obstacle area.

[0026] In one implementation scenario, please refer to Figure 2b , Figure 2b This is a schematic diagram illustrating another embodiment of the map updating method of this application. For example... Figure 2b As shown, after obtaining the real-time pose and real-time measurement values, the real-time measurement values ​​can be evaluated to determine whether to proceed with the physical distance calculation step. For example, if the real-time measurement value is greater than (or not less than) the obstacle detection threshold (i.e., the robot is far from the observation point), the physical distance calculation step can be skipped, and the evaluation can be performed again after the next acquisition of real-time pose and measurement values. Conversely, if the real-time measurement value is not greater than (or less than) the obstacle detection threshold (i.e., the robot is close to the observation point), the physical distance calculation step can be performed, and the evaluation can be performed again after the next acquisition of real-time pose and measurement values. This process can be repeated, allowing for the evaluation of the real-time measurement values ​​after each acquisition to determine whether to calculate the physical distance.

[0027] Step S13: Based on the comparison results between each physical distance and the distance threshold, determine whether the observation point belongs to the obstacle area and the specific obstacle area it belongs to.

[0028] In one implementation scenario, as a possible example, the distance threshold can be set to a constant value. That is, a constant value can be set as the distance threshold for any obstacle area. For example, the constant value of the distance threshold can be the same for different obstacle areas; or, for another example, the constant value of the distance threshold can be different for different obstacle areas; or, for yet another example, the constant value of the distance threshold can be the same for some obstacle areas and different for some obstacle areas, without any limitation here.

[0029] In another implementation scenario, unlike the aforementioned implementation, as another possible example, the distance threshold can also adaptively change with the standard deviation of the probability distribution. Specifically, each obstacle region can have its own distance threshold, and the distance threshold of each obstacle region can be positively correlated with the standard deviation of its probability distribution. That is, for any obstacle region, the larger the standard deviation of its probability distribution, the larger its distance threshold; conversely, the smaller the standard deviation of its probability distribution, the smaller its distance threshold. This setting allows the distance threshold to be adaptively adjusted during map updates. As multiple observations are merged, the standard deviation gradually converges, and the smaller the standard deviation, the more stringent the merging. For example, the distance threshold can be set to a preset multiple of the standard deviation. This preset multiple can be set according to the confidence interval of the probability distribution. For example, when a 99.7% confidence interval needs to be covered, the preset multiple can be set to 3, in which case the distance threshold can be 3 times the standard deviation. Of course, the above example is only one possible example in practical applications; other possible situations are not limited here, nor will they be listed one by one. For ease of description, the distance threshold can be denoted as kσ, where k represents the preset multiple.

[0030] It should be noted that in practical applications, each obstacle region can be selected sequentially as the current region, and a distance threshold for determining whether an observation point belongs to the current region can be obtained (e.g., as mentioned earlier, the distance threshold can be obtained based on the standard deviation of the probability distribution of the current region). Based on this, the observation point's belonging to the current region can be determined by comparing the physical distance between the observation point and the center point of the current region with the distance threshold. For example, if the physical distance between the observation point and the center point of the current region is not greater than the distance threshold (i.e., the physical distance D is not greater than the distance threshold kσ), the observation point belongs to the current region; or, for another example, if the physical distance between the observation point and the center point of the current region is greater than the distance threshold, the observation point does not belong to the current region. Furthermore, if it is determined that the observation point does not belong to the current region, the process of sequentially selecting each obstacle region as the current region can be repeated until the specific obstacle region to which the observation point belongs is determined or it is determined that the observation point does not belong to any obstacle region.

[0031] Step S14: In response to the observation point belonging to the obstacle area, update the probability distribution of the obstacle area to which the observation point belongs based on the observation point, and draw a virtual line in the map data based on the real-time pose and real-time measurement value to guide the robot to avoid obstacles.

[0032] In one implementation scenario, please refer to [link / reference]. Figure 2b When an observation point belongs to an obstacle region, the probability distribution of the obstacle region to which the observation point belongs can be updated based on the observation point. As mentioned earlier, when the probability distribution is a normal distribution, the probability distribution of the observation point involves two parameters: mean and standard deviation. Therefore, the mean and standard deviation of the probability distribution can be updated separately based on the observation point. The updates for the mean and standard deviation are explained below: When updating the mean of the probability distribution of the obstacle region to which the observation point belongs based on the observation point, as a possible implementation example, the mean of the probability distribution of the obstacle region to which the observation point belongs (i.e., the new center coordinates) can be obtained by averaging the center coordinates of the obstacle region to which the observation point belongs and the position coordinates of the observation point. More specifically, the coordinates in the X-axis direction of the center coordinates of the obstacle region to which the observation point belongs and the X-axis direction of the position coordinates of the observation point can be averaged to obtain the coordinates in the X-axis direction of the new center coordinates, and the coordinates in the Y-axis direction of the center coordinates of the obstacle region to which the observation point belongs and the Y-axis direction of the position coordinates of the observation point can be averaged to obtain the coordinates in the Y-axis direction of the new center coordinates. Combining the coordinates in the X-axis direction and the Y-axis direction of the new center coordinates, the new center coordinates, i.e., the new mean of the probability distribution of the obstacle region to which the observation point belongs, can be obtained. Alternatively, as another possible implementation example, the number of times the obstacle region to which the observation point belongs can be obtained as the first weight, and 1 can be used as the second weight. Based on this, a new mean (i.e., new center coordinates) of the probability distribution of the obstacle region to which the observation point belongs can be obtained by weighting the center coordinates of the obstacle region to which the observation point belongs and the position coordinates of the observation point, respectively, using the first weight and the second weight. More specifically, the X-axis coordinates of the center coordinates of the obstacle region to which the observation point belongs and the X-axis coordinates of the position coordinates of the observation point can be weighted and averaged respectively, based on the first weight and the second weight, to obtain the new X-axis coordinates of the center coordinates. Similarly, the Y-axis coordinates of the center coordinates of the obstacle region to which the observation point belongs and the Y-axis coordinates of the position coordinates of the observation point can be weighted and averaged respectively, based on the first weight and the second weight, to obtain the new Y-axis coordinates of the center coordinates. Thus, by combining the new X-axis and Y-axis coordinates of the center coordinates, the new center coordinates, i.e., the new mean of the probability distribution of the obstacle region to which the observation point belongs, can be obtained. It should be noted that the position coordinates of the observation point are obtained from real-time pose and real-time measurement values, which can be referred to the aforementioned relevant descriptions and will not be repeated here. For ease of description, we can denote the number of times the obstacle region to which the observation point belongs is detected as n (excluding the current detection). Then, the new mean (i.e., the new center coordinates) of the probability distribution of the obstacle region to which the observation point belongs can be expressed as:

[0033] In the above formula, μ old This represents the center coordinates (i.e., the original mean) of the obstacle region to which the observation point belongs. new μ represents the position coordinates of the observation point. newThis represents the new center coordinates (i.e., the new mean) of the obstacle region to which the observation point belongs. The above method uses a weighted average of the center coordinates of the obstacle region to which the observation point belongs and the position coordinates of the observation point, respectively, using a first weight and a second weight, to obtain a new mean of the probability distribution of the obstacle region to which the observation point belongs. This weighted average can update the mean of the probability distribution of the obstacle region as detections continue.

[0034] When updating the standard deviation of the probability distribution of the obstacle region to which the observation point belongs based on the observation point, as a possible implementation example, the ratio of the square of the physical distance between the observation point and the center point of the obstacle region to which the observation point belongs to the target number of occurrences can be obtained as a reference variance. Based on this, the variance of the probability distribution of the obstacle region to which the observation point belongs and the reference variance can be averaged to obtain the new variance of the probability distribution of the obstacle region to which the observation point belongs. It should be noted that the target number of occurrences is obtained by adding 1 to the number of detections in the obstacle region to which the observation point belongs. In other words, the target number of occurrences can be understood as the number of detections including the current detection. Furthermore, when the probability distribution is a normal distribution, the square of the standard deviation can be converted into the variance, and the square root of the variance can be converted into the standard deviation. Alternatively, as another possible implementation example, the number of detections in the obstacle region to which the observation point belongs can be obtained as the first weight, and 1 can be used as the second weight. The ratio of the square of the physical distance between the observation point and the center point of the obstacle region to which the observation point belongs to the target number of occurrences can also be obtained as a reference variance. It should be noted that the relationship between the target number of occurrences and the standard deviation and variance can be referred to the aforementioned relevant descriptions, and will not be repeated here. Based on this, a weighted average can be calculated using the first weight and the second weight to take the variance and reference variance of the probability distribution of the obstacle region to which the observation point belongs, respectively, to obtain a new variance of the probability distribution of the obstacle region to which the observation point belongs. For ease of description, the number of detections can be denoted as n, and the number of targets can be denoted as n+1. Then, the new variance of the probability distribution of the obstacle region to which the observation point belongs can be expressed as:

[0035] In the above formula, μ old This represents the center coordinates (i.e., the original mean) of the obstacle region to which the observation point belongs. new σ represents the position coordinates of the observation point. 2 new D represents the new variance of the obstacle region to which the observation point belongs. 2 / (n+1) represents the reference variance, σ 2 oldThis represents the original variance of the obstacle region to which the observation point belongs. The above method, by weighting the variance of the probability distribution of the obstacle region to which the observation point belongs based on the first weight and the second weight respectively, yields a new variance of the probability distribution of the obstacle region to which the observation point belongs. This weighted average can update the variance of the probability distribution of the obstacle region as detections continue.

[0036] In one implementation scenario, as mentioned earlier, the probability distribution of obstacle regions can be included in the statistical data of obstacle regions, and the statistical data of obstacle regions can also include the detection frequency and update time of obstacle regions. Therefore, in addition to updating the mean and standard deviation when the observation point is detected as belonging to an obstacle region, the detection frequency and update time of the statistical data of the obstacle region to which the observation point belongs can also be updated. For example, when updating the detection frequency, the detection frequency of the obstacle region to which the observation point belongs can be incremented by 1. As another example, when updating the update time, the update time can be updated to the detection time when the observation point is detected as belonging to an obstacle region.

[0037] In one implementation scenario, to draw a virtual line in the map data, the virtual line can be drawn at the real-time measured value directly in front of the robot's real-time pose in the map data. Specifically, as mentioned earlier, the robot's position coordinates can be obtained based on the real-time pose. The virtual line can be drawn at the position measured value directly in front of the robot (i.e., the robot's observation direction), starting from the position coordinates. For example, the virtual line can be perpendicular to the observation direction. Furthermore, the center of the virtual line can be the end point. The two endpoints of the virtual line can be denoted as ll and lr, respectively. It should be noted that the length of the virtual line is determined based on the robot's body width. For example, the length of the virtual line can be positively correlated with the robot's body width; that is, the larger the robot's body width, the larger the length of the virtual line can be, and vice versa. This method, drawing a virtual line at the real-time measured value directly in front of the robot's real-time pose in the map data, with the length of the virtual line determined based on the robot's body width, can ensure that the robot can smoothly avoid obstacles.

[0038] In one implementation scenario, as a possible example, virtual lines can exist in map data for a long time.

[0039] In another implementation scenario, distinct from the aforementioned implementation methods, please refer to the following as another possible example. Figure 2a and Figure 2bA virtual line can exist in the map data within its lifetime; once its lifetime expires, the virtual line disappears from the map data. Specifically, to obtain the lifetime of a virtual line, its lifetime in the map data can be predicted based on a time factor, a base time, and the number of times the obstacle area to which the observation point belongs. It should be noted that the lifetime is positively correlated with the number of times the obstacle area to which the observation point belongs is detected. That is, the more times it is detected, the longer the lifetime, and vice versa. In addition, the time factor and base time can be set according to the actual application, such as by setting empirical values, etc. The specific values ​​of the time factor and base time are not limited here. For example, the detection count can be updated based on the number of times the obstacle region to which the observation point belongs, resulting in a new detection count for that obstacle region (as mentioned earlier, this can be obtained by adding 1 to the previous detection count). Then, a prediction is made based on this new detection count to obtain the additional time, which is positively correlated with the new detection count (e.g., the additional time can be obtained by predicting the new detection count using a positive correlation function such as the natural logarithm). Finally, the additional time is scaled based on a time factor and then summed with the base time to obtain the virtual line's lifetime in the map data. For ease of description, the virtual line's lifetime in the map data can be represented as H_time: H_time = b + t * ln(1 + n) In the above formula, ln represents the natural logarithm, 1+n represents the new number of detections, b represents the base time, and t represents the time factor. Of course, the above example is only one possible way to calculate survival time in practical applications; other possible calculation methods are not limited here, nor will they be listed one by one. As can be seen from the above calculation, the more times an obstacle area is detected, the longer the virtual line's survival time. This means that the more times an obstacle is seen by the dToF sensor, the longer its survival time on the map data (e.g., for static obstacles, allowing them to remain on the map for a long time is more beneficial for path planning). Conversely, when an obstacle is seen by the dToF sensor less often, its survival time on the map data will be shorter (e.g., for dynamic obstacles, allowing them to quickly disappear from the map data after obstacle avoidance planning is more beneficial for path planning). Please refer to [further details needed]. Figure 2c , Figure 2c This is a schematic diagram of an embodiment of the virtual line lifetime of this application. For example... Figure 2c As shown, the horizontal axis represents the number of detections, and the vertical axis represents the survival time. Figure 2c It is evident that survival time increases gradually with the number of detections. Of course, Figure 2c The diagram shown is merely one possible representation of survival time and detection frequency; other possible scenarios will not be illustrated here.

[0040] In one implementation scenario, please refer to [link / reference]. Figure 2a As a possible example in practical applications, due to the resource limitations of the computing platform, the statistical data for each obstacle region needs to be cleaned up in a timely manner. Specifically, the importance of an obstacle region can be determined based on the number of times it is detected and its update time, with the importance being positively correlated with the number of detections and the update time. For example, the importance can be expressed as: Importance = α * Update time + β * Number of detections In the above formula, α and β represent the weighting factors for update time and detection frequency, respectively. Based on this, data cleaning can be performed on statistical data of at least one obstacle region, according to its importance. As mentioned earlier, the statistical data can include probability distribution, detection frequency, and update time. For example, the obstacle regions can be sorted according to their importance, and when data cleaning is required, less important obstacle regions can be cleaned first. This method, by determining the importance of obstacle regions based on their detection frequency and update time, and then selecting at least one obstacle region's statistical data for data cleaning based on its importance, can prioritize and promptly clean less important obstacle regions when data cleaning is needed.

[0041] It should be noted that in practical applications, there may be situations where the observation point does not belong to any obstacle area. In this case, a new obstacle area can be created, and the observation point can then belong to the new obstacle area. The detection count of the new obstacle area is initialized to 1. Of course, the mean of the probability distribution of the new obstacle area (i.e., the center coordinates) can be initialized to the location coordinates of the observation point, and the standard deviation of its probability distribution can be initialized to 0. Furthermore, regardless of whether the observation point belongs to an obstacle area, the aforementioned steps can be repeated when a new observation point appears, thus continuously updating the map data based on observations.

[0042] The above scheme obtains the probability distribution of each obstacle region, the robot's real-time pose, and real-time measurements of observation points in the physical space. The probability distribution represents the probability that any point in the physical space belongs to an obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region. Based on the real-time pose, real-time measurements, and the center coordinates of the obstacle region, the physical distance between the observation point and the center point of the obstacle region is obtained. Then, based on the comparison results of each physical distance with a distance threshold, it is determined whether the observation point belongs to an obstacle region and its specific obstacle region. In response to the observation point belonging to an obstacle region, the probability distribution of the obstacle region to which the observation point belongs is updated, and... Based on real-time pose and measurements, virtual lines are drawn in the map data to guide the robot in obstacle avoidance. This allows for two main advantages: firstly, maintaining a separate probability distribution for each obstacle region during map updates to determine if an observation point belongs to an obstacle region; and secondly, updating the probability distribution of the corresponding obstacle region if it does. This dynamic maintenance of probability distributions facilitates obstacle modeling through instantaneous measurements. Secondly, combining real-time pose and measurements with virtual lines in the map data provides explicit data to better guide the robot in obstacle avoidance. Therefore, obstacle modeling through instantaneous measurements enables effective obstacle avoidance by the robot during movement.

[0043] Please see Figure 3 , Figure 3 This is a flowchart illustrating an embodiment of the path planning method of this application. Specifically, it may include the following steps: Step S31: Obtain map data.

[0044] In this embodiment of the disclosure, the map data is obtained by the process steps in the above-described map update method embodiment. For details, please refer to the aforementioned map update method embodiment, which will not be repeated here.

[0045] Step S32: Perform path planning based on map data to obtain the robot's motion path.

[0046] Specifically, path planning algorithms such as Dijkstra's algorithm, A* algorithm, D* algorithm, fast probing random number algorithm, and ant colony optimization algorithm can be used to plan paths from map data to obtain the robot's movement path. The specific process of path planning is not limited here; for details, please refer to the technical details of the aforementioned path planning algorithms, which will not be elaborated upon here. As a possible implementation example, the robot can continuously update the map data during movement using the aforementioned disclosed embodiments. In parallel, when path planning is required, the robot can perform path planning based on the latest map data to move according to the planned path. That is, the map update process of the aforementioned disclosed embodiments and the path planning process of this disclosed embodiment can be parallel processes, rather than the latter requiring the former to complete completely before execution; the latter can be executed in parallel during the execution of the former.

[0047] The above scheme acquires map data, and the map data is obtained through the process steps in the above map update method embodiment. Therefore, the map data can support obstacle modeling through instantaneous measurement, and then path planning is performed based on the map data to obtain the robot's movement path, which can support the robot to effectively avoid obstacles during movement.

[0048] Please see Figure 4 , Figure 4 This is a schematic diagram of the framework of an embodiment of the map updating device of this application. The map updating device 40 includes: a parameter acquisition module 41, a distance calculation module 42, a subordination determination module 43, and an update drawing module 44. The parameter acquisition module 41 is used to acquire the probability distribution of each obstacle region, and to acquire the real-time pose of the robot and the real-time measurement value of the observation point in the physical space; wherein, the probability distribution represents the probability value of any point in the physical space belonging to the obstacle region, and the mean of the probability distribution represents the center coordinate of the obstacle region; the distance calculation module 42 is used to obtain the physical distance between the observation point and the center point of the obstacle region based on the real-time pose, the real-time measurement value, and the center coordinate of the obstacle region; the subordination determination module 43 is used to determine whether the observation point belongs to the obstacle region and the specific obstacle region it belongs to based on the comparison results between each physical distance and a distance threshold; the update drawing module 44 is used to update the probability distribution of the obstacle region to which the observation point belongs based on the observation point in response to the observation point belonging to the obstacle region, and to draw a virtual line in the map data to guide the robot to avoid obstacles based on the real-time pose and the real-time measurement value.

[0049] In the above scheme, the map updating device 40 acquires the probability distribution of each obstacle region, and obtains the robot's real-time pose and real-time measurement values ​​of the observation points in the physical space. The probability distribution represents the probability value of any point in the physical space belonging to an obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region. Based on the real-time pose, real-time measurement values, and center coordinates of the obstacle region, the physical distance between the observation point and the center point of the obstacle region is obtained. Based on the comparison results between each physical distance and a distance threshold, it is determined whether the observation point belongs to an obstacle region and the specific obstacle region it belongs to. Then, in response to the observation point belonging to an obstacle region, the probability distribution of the obstacle region to which the observation point belongs is updated. Based on real-time pose and measurements, virtual lines are drawn in the map data to guide the robot in obstacle avoidance. Therefore, during map updates, a probability distribution can be maintained for each obstacle region to determine whether an observation point belongs to an obstacle region. If an observation point belongs to an obstacle region, the probability distribution of that region is further updated accordingly. This dynamic maintenance of the probability distribution of each obstacle region facilitates obstacle modeling through instantaneous measurements. Furthermore, combining real-time pose and measurements to draw virtual lines in the map data allows for more explicit obstacle avoidance guidance. Thus, obstacle modeling through instantaneous measurements enables effective obstacle avoidance by the robot during movement.

[0050] In some disclosed embodiments, the probability distribution is a normal distribution. The subordinate determination module 43 includes a region selection submodule, which is used to sequentially select each obstacle region as the current region. The subordinate determination module 43 includes a threshold calculation submodule, which is used to obtain a distance threshold for determining whether the observation point belongs to the current region based on the standard deviation of the probability distribution of the current region. The distance threshold is positively correlated with the standard deviation. The subordinate determination module 43 includes a loop iteration submodule, which is used to determine whether the observation point belongs to the current region based on the comparison between the physical distance between the observation point and the center point of the current region and the distance threshold for determining whether the observation point belongs to the current region. If it is determined that the observation point does not belong to the current region, the module returns to the step of sequentially selecting each obstacle region as the current region until the specific obstacle region to which the observation point belongs is determined or the observation point does not belong to any obstacle region.

[0051] In some disclosed embodiments, the update drawing module 44 includes a weight acquisition submodule, which is used to acquire the number of times the obstacle region to which the observation point belongs is detected, as the first weight, and 1 as the second weight; the update drawing module 44 includes a first weighting module, which is used to perform a weighted average of the center coordinates of the obstacle region to which the observation point belongs and the position coordinates of the observation point based on the first weight and the second weight, respectively, to obtain a new mean value of the probability distribution of the obstacle region to which the observation point belongs; wherein, the position coordinates are obtained from the real-time pose and the real-time measurement value.

[0052] In some disclosed embodiments, the update drawing module 44 includes a weight acquisition submodule, used to acquire the number of times the obstacle region to which the observation point belongs is detected, as a first weight, and 1 as a second weight. The update drawing module 44 includes a variance calculation submodule, used to acquire the ratio of the square of the physical distance between the observation point and the center point of the obstacle region to which the observation point belongs to the target number, as a reference variance; wherein, the target number is obtained by adding 1 to the number of times the obstacle region to which the observation point belongs is detected. The update drawing module 44 includes a second weighting submodule, used to perform a weighted average of the variance of the probability distribution of the obstacle region to which the observation point belongs and the reference variance based on the first weight and the second weight, respectively, to obtain a new variance of the probability distribution of the obstacle region to which the observation point belongs.

[0053] In some disclosed embodiments, the update drawing module 44 includes a dashed line drawing submodule for drawing a virtual line at the real-time measurement value directly in front of the robot's real-time pose in the map data; wherein the length value of the virtual line is determined based on the robot's body width.

[0054] In some disclosed embodiments, the map update device 40 includes a time calculation module for predicting the survival time of the virtual line in the map data based on a time factor, a base time, and the number of times the obstacle area to which the observation point belongs; wherein the survival time is positively correlated with the number of times it is detected.

[0055] In some disclosed embodiments, the time calculation module includes a count update submodule, used to update the count based on the number of detections in the obstacle area to which the observation point belongs, to obtain a new number of detections in the obstacle area to which the observation point belongs; the time calculation module includes a time prediction submodule, used to predict based on the new number of detections, to obtain an additional time; wherein, the additional time is positively correlated with the new number of detections; the time calculation module includes a time overlay submodule, used to scale the additional time based on a time factor and then sum it with the base time to obtain the survival time of the virtual line in the map data.

[0056] In some disclosed embodiments, the map update device 40 includes an importance measurement module for obtaining the importance of an obstacle region based on the number of times the obstacle region is detected and the update time; wherein the importance is positively correlated with the number of times the obstacle is detected and the update time; the map update device 40 includes a data cleaning module for selecting at least one obstacle region for data cleaning based on the importance of each obstacle region; wherein the statistical data includes probability distribution, number of times the obstacle is detected, and update time.

[0057] In some disclosed embodiments, the map updating device 40 includes a region creation module for creating a new obstacle region in response to an observation point not belonging to any obstacle region; wherein the observation point belongs to the new obstacle region, and the detection count of the new obstacle region is initialized to 1.

[0058] In some disclosed embodiments, the probability distribution is a normal distribution, and the standard deviation of the probability distribution characterizes the location uncertainty; and / or, the real-time measurement value is obtained by a single-point dToF sensor; and / or, the probability distribution of the obstacle region is included in the statistical data of the obstacle region, and the statistical data of the obstacle region also includes the number of times the obstacle region is detected and the update time.

[0059] Please see Figure 5 , Figure 5 This is a schematic diagram of the framework of an embodiment of the path planning device of this application. The path planning device 50 includes: a map acquisition module 51 and a motion planning module 52. The map acquisition module 51 is used to acquire map data; wherein, the map data is obtained by the map updating device in the above-described map updating device embodiment; the motion planning module 52 is used to perform path planning based on the map data to obtain the robot's motion path.

[0060] The above scheme acquires map data, and the map data is obtained by the map updating device in the above map updating device embodiment. Therefore, the map data can support obstacle modeling through instantaneous measurement, and then path planning is performed based on the map data to obtain the robot's movement path, which can support the robot to effectively avoid obstacles during movement.

[0061] Please see Figure 6 , Figure 6This is a schematic diagram of a framework of an embodiment of the electronic device of this application. The electronic device 60 includes at least a memory 61 and a processor 62 coupled to each other. The memory 61 stores at least program instructions, and the processor 62 executes the program instructions to implement the steps in any of the map update method embodiments described above, or the steps in the path planning method embodiments described above. For details, please refer to the foregoing disclosed embodiments, which will not be repeated here. The electronic device 60 may include, but is not limited to, mobile devices such as robots; the specific type of the electronic device 60 is not limited here. Furthermore, the electronic device 60 may also include, but is not limited to, single-point dToF sensors (not shown), etc.; the electronic components included in the electronic device 60 will not be listed individually here.

[0062] Specifically, processor 62 controls itself and memory 61 to implement the steps in any of the map update method embodiments described above, or the steps in the path planning method embodiments described above. Processor 62 can also be referred to as a CPU (Central Processing Unit). Processor 62 may be an integrated circuit chip with signal processing capabilities. Processor 62 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 62 can be implemented using integrated circuit chips.

[0063] In the above scheme, the electronic device 60 acquires the probability distribution of each obstacle region, and obtains the robot's real-time pose and real-time measurement values ​​of the observation points in the physical space. The probability distribution represents the probability value that any point in the physical space belongs to an obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region. Based on the real-time pose, real-time measurement values, and center coordinates of the obstacle region, the physical distance between the observation point and the center point of the obstacle region is obtained. Based on the comparison results between each physical distance and a distance threshold, it is determined whether the observation point belongs to an obstacle region and the specific obstacle region it belongs to. Then, in response to the observation point belonging to an obstacle region, the probability distribution of the obstacle region to which the observation point belongs is updated based on the observation point. Based on real-time pose and real-time measurement values, virtual lines are drawn in the map data to guide the robot in avoiding obstacles. Therefore, during map updates, each obstacle region can maintain its own probability distribution to determine whether an observation point belongs to an obstacle region. If an observation point belongs to an obstacle region, the probability distribution of that region is further updated accordingly, dynamically maintaining the probability distribution of each obstacle region. This facilitates obstacle modeling through instantaneous measurements. Furthermore, combining real-time pose and real-time measurement values ​​to draw virtual lines in the map data allows for more explicit data guidance for obstacle avoidance. Thus, obstacle modeling through instantaneous measurements enables the robot to effectively avoid obstacles during movement. In addition, the map data is obtained through the process steps described in the map update method embodiment. Therefore, the map data supports obstacle modeling through instantaneous measurements, and path planning based on the map data yields the robot's movement path, enabling the robot to effectively avoid obstacles during movement.

[0064] Please see Figure 7 , Figure 7 This is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of this application. The computer-readable storage medium 70 stores program instructions 71 that can be executed by a processor. The program instructions 71 are used to implement the steps in any of the above-described map update method embodiments or the steps in any of the above-described path planning method embodiments.

[0065] In the above scheme, the computer-readable storage medium 70 acquires the probability distribution of each obstacle region, and obtains the robot's real-time pose and real-time measurement values ​​of the observation points in the physical space. The probability distribution represents the probability value of any point in the physical space belonging to an obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region. Based on the real-time pose, real-time measurement values, and center coordinates of the obstacle region, the physical distance between the observation point and the center point of the obstacle region is obtained. Based on the comparison results between each physical distance and a distance threshold, it is determined whether the observation point belongs to an obstacle region and the specific obstacle region it belongs to. Then, in response to the observation point belonging to an obstacle region, the probability of the obstacle region to which the observation point belongs is updated. The probability distribution is calculated, and virtual lines are drawn in the map data based on real-time pose and real-time measurement values ​​to guide the robot in avoiding obstacles. Therefore, during map updates, the probability distribution of each obstacle region can be maintained separately to determine whether an observation point belongs to an obstacle region. If an observation point belongs to an obstacle region, the probability distribution of that region is further updated accordingly. This dynamic maintenance of the probability distribution of each obstacle region facilitates obstacle modeling through instantaneous measurements. Furthermore, combining real-time pose and real-time measurement values ​​to draw virtual lines in the map data allows for more explicit data-driven obstacle avoidance guidance. Thus, obstacle modeling through instantaneous measurements enables effective obstacle avoidance by the robot during movement. In addition, the map data is obtained through the process steps described in the map update method embodiment. Therefore, the map data supports obstacle modeling through instantaneous measurements, and path planning based on the map data yields the robot's motion path, enabling effective obstacle avoidance during movement.

[0066] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0067] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0069] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0070] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0071] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0072] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

Claims

1. A map update method characterized by comprising: The method comprises: obtaining a probability distribution of each obstacle region, and obtaining a real-time pose of the robot and a real-time measurement value of an observation point in a physical space; wherein the probability distribution represents a probability value of any point in the physical space belonging to the obstacle region, and a mean value of the probability distribution represents a center coordinate of the obstacle region; based on the real-time pose, the real-time measurement value and the center coordinate of the obstacle region, obtaining a physical distance between the observation point and the center point of the obstacle region; based on a comparison result between each of the physical distances and a distance threshold, determining whether the observation point belongs to the obstacle region and a specific obstacle region to which the observation point belongs; in response to the observation point belonging to the obstacle region, updating the probability distribution of the obstacle region to which the observation point belongs based on the observation point, and based on the real-time pose and the real-time measurement value, drawing a virtual line in map data for guiding the robot to avoid obstacles.

2. The method of claim 1, wherein, The probability distribution is a normal distribution, and the determination of whether the observation point belongs to the obstacle region and the specific obstacle region to which the observation point belongs based on the comparison result between each of the physical distances and the distance threshold comprises: selecting each of the obstacle regions in turn as a current region; obtaining a distance threshold for determining whether the observation point belongs to the current region based on a standard deviation of the probability distribution of the current region; wherein the distance threshold is positively correlated with the standard deviation; based on a comparison result between the physical distance between the observation point and the center point of the current region and the distance threshold for determining whether the observation point belongs to the current region, determining whether the observation point belongs to the current region, and returning to the step of selecting each of the obstacle regions in turn as a current region if it is determined that the observation point does not belong to the current region, until a specific obstacle region to which the observation point belongs is determined or it is determined that the observation point does not belong to any of the obstacle regions.

3. The method of claim 1, wherein, The updating of the probability distribution of the obstacle region to which the observation point belongs based on the observation point comprises: obtaining a detection frequency of the obstacle region to which the observation point belongs as a first weight, and taking 1 as a second weight; performing a weighted average on the center coordinate of the obstacle region to which the observation point belongs and a position coordinate of the observation point based on the first weight and the second weight respectively, to obtain a new mean value of the probability distribution of the obstacle region to which the observation point belongs; wherein the position coordinate is obtained from the real-time pose and the real-time measurement value.

4. The method of claim 1, wherein, The probability distribution is a normal distribution, and the updating of the probability distribution of the obstacle region to which the observation point belongs based on the observation point comprises: obtaining a detection frequency of the obstacle region to which the observation point belongs as a first weight, and taking 1 as a second weight, and obtaining a ratio between a square value of a physical distance between the observation point and the center point of the obstacle region to which the observation point belongs and a target number as a reference variance; wherein the target number is obtained by adding 1 to the detection frequency of the obstacle region to which the observation point belongs. Based on the first weight and the second weight, the variance of the probability distribution of the obstacle region to which the observation point belongs and the reference variance are weighted and averaged respectively to obtain a new variance of the probability distribution of the obstacle region to which the observation point belongs.

5. The method of claim 1, wherein, The step of drawing virtual lines in the map data based on the real-time pose and the real-time measurement values ​​to guide the robot in avoiding obstacles includes: A virtual line is drawn at the location of the real-time measurement value directly in front of the real-time pose in the map data; wherein the length of the virtual line is determined based on the width of the robot's body.

6. The method of claim 1, wherein, The method further includes: Based on the time factor, the base time, and the number of times the obstacle area to which the observation point belongs is detected, the survival time of the virtual line in the map data is predicted; wherein, the survival time is positively correlated with the number of detections.

7. The method of claim 6, wherein, The prediction of the virtual line's survival time in the map data based on the time factor, base time, and the number of times the obstacle region to which the observation point belongs is calculated, includes: The number of detections is updated based on the number of times the observation point is located in the obstacle region, resulting in a new number of detections for the obstacle region to which the observation point is located. Based on the new number of detections, an additional time is obtained through prediction; wherein the additional time is positively correlated with the new number of detections. The additional time is scaled based on the time factor and then summed with the base time to obtain the lifespan of the virtual line in the map data.

8. The method of claim 1, wherein, The method further includes: The importance of the obstacle region is determined based on the number of times it is detected and the update time; wherein, the importance is positively correlated with the number of times it is detected and the update time. Based on the importance of each of the obstacle regions, at least one of the obstacle regions is selected for data cleaning using statistical data; wherein, the statistical data includes the probability distribution, the number of detections, and the update time.

9. The method of claim 1, wherein, The method further includes: In response to the observation point not belonging to any of the obstacle regions, a new obstacle region is created; wherein the observation point belongs to the new obstacle region, and the detection count of the new obstacle region is initialized to 1.

10. The method according to any one of claims 1 to 9, characterized in that, The probability distribution is a normal distribution, and the standard deviation of the probability distribution represents the location uncertainty. And / or, the real-time measurement value is obtained by a single-point dToF sensor; And / or, the probability distribution of the obstacle region is included in the statistical data of the obstacle region, and the statistical data of the obstacle region also includes the number of times the obstacle region was detected and the update time.

11. A path planning method characterized by, include: Acquire map data; wherein the map data is obtained by the map update method according to any one of claims 1 to 10; Based on the map data, path planning is performed to obtain the robot's movement path.

12. A map update device characterized by comprising: include: The parameter acquisition module is used to acquire the probability distribution of each obstacle region, and to acquire the robot's real-time pose and the real-time measurement values ​​of the observation points in the physical space; wherein, the probability distribution represents the probability value of any point in the physical space belonging to the obstacle region, and the mean of the probability distribution represents the center coordinates of the obstacle region; a distance calculation module, configured to obtain a physical distance between the observation point and a center point of the obstacle region based on the real-time pose, the real-time measurement value, and a center coordinate of the obstacle region; a belonging determination module, configured to determine whether the observation point belongs to the obstacle region and a specific obstacle region based on a comparison result between each of the physical distances and a distance threshold; an update drawing module, configured to update a probability distribution of the obstacle region to which the observation point belongs based on the observation point in response to the observation point belonging to the obstacle region, and draw a virtual line for guiding the robot to avoid the obstacle in the map data based on the real-time pose and the real-time measurement value.

13. A path planning device characterized by comprising: comprising: a map acquisition module, configured to acquire map data; wherein the map data is obtained by the map update method of claim 12; a motion planning module, configured to perform path planning based on the map data to obtain a motion path of the robot.

14. An electronic device, comprising: at least comprising a memory and a processor coupled with each other, the memory at least storing program instructions, and the processor being configured to execute the program instructions to implement the map update method of any one of claims 1 to 10 or the path planning method of claim 11.

15. A computer-readable storage medium, characterized in that, the memory storing program instructions capable of being executed by the processor, and the program instructions being configured to implement the map update method of any one of claims 1 to 10 or the path planning method of claim 11.

Images