Control method and system of embodied robot and embodied robot

Abstract

This application relates to the field of embodied robot control technology, and more particularly to a control method, system, and embodied robot. The method comprises: identifying a target obstacle during the embodied robot's movement and obtaining information about the target obstacle's height; determining a current obstacle surmounting height threshold for the target obstacle based on the embodied robot's historical number of obstacle avoidance attempts; and controlling the embodied robot to avoid or surmount the target obstacle based on the current obstacle surmounting height threshold and the height information. As a result, the present application can more intelligently handle low obstacles and enhance obstacle surmounting capabilities.

Description

Technical Field

[0001] The present application relates to the technical field of embodied robot control, and in particular to a control method and system for an embodied robot and the embodied robot. Background Art

[0002] In existing technology, robots (such as sweeping robots) typically use sensors to identify obstacles. This can be achieved using a variety of sensors, with line lasers being an increasingly popular method for intelligent obstacle avoidance. Line lasers can detect objects at any height below their mounting height, and their distance measurement is relatively accurate. This allows them to avoid obstacles closer to the robot, improving its ability to avoid obstacles.

[0003] However, in actual use, it was found that the robot based on line laser was too sensitive to obstacle detection, which weakened the robot's obstacle crossing ability. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a control method and system for an embodied robot, and the embodied robot, which can handle low obstacles more intelligently and enhance the obstacle-crossing capability.

[0005] In a first aspect, an embodiment of the present application provides a control method for an embodied robot, comprising:

[0006] Identifying a target obstacle during the movement of the embodied robot and obtaining height information of the target obstacle;

[0007] Determining a current obstacle crossing height threshold for the target obstacle based on a historical number of obstacle avoidance attempts by the embodied robot;

[0008] The embodied robot is controlled to avoid or overcome the target obstacle according to the current obstacle crossing height threshold and the height information.

[0009] In some embodiments, determining the current obstacle crossing height threshold for the target obstacle based on the historical number of obstacle avoidances performed by the embodied robot on the target obstacle includes:

[0010] If the number of historical obstacle avoidance attempts of the embodied robot to avoid the target obstacle is greater than a preset number threshold, the current obstacle crossing height threshold is adjusted from the first obstacle crossing height threshold to the second obstacle crossing height threshold; otherwise, the current obstacle crossing height threshold is maintained at the first obstacle crossing height threshold;

[0011] The second obstacle clearance height threshold is greater than the first obstacle clearance height threshold.

[0012] In some embodiments, the height information includes multiple actual height values, and controlling the embodied robot to avoid or overcome the target obstacle based on the current obstacle crossing height threshold and the height information includes:

[0013] If the maximum actual height value in the height information is greater than or equal to the current obstacle crossing height threshold, the embodied robot is controlled to avoid the target obstacle and the historical obstacle avoidance times are updated; otherwise, the embodied robot is controlled to cross the target obstacle.

[0014] In some embodiments, after obtaining the height information of the target obstacle, the method further includes:

[0015] When the distance between the embodied robot and the target obstacle is greater than the obstacle avoidance distance, if any of the actual height values ​​in the height information is greater than or equal to the first obstacle crossing height threshold, storing the position information of the target obstacle;

[0016] The controlling the embodied robot to avoid the target obstacle includes:

[0017] When it is determined based on the position information of the target obstacle that the embodied robot has traveled to a distance from the target obstacle that is less than or equal to the obstacle avoidance distance, the embodied robot is controlled to avoid the target obstacle.

[0018] In some embodiments, the embodied robot is provided with a line laser sensor, and identifying a target obstacle during the movement of the embodied robot and obtaining height information of the target obstacle includes:

[0019] identifying the target obstacle by the line laser sensor during the movement of the embodied robot;

[0020] Obtaining actual distance measurement values ​​corresponding to the target obstacle collected by the line laser sensor at different sampling angles;

[0021] According to each of the sampling angles and the corresponding actual distance measurement value, the height information of the target obstacle is obtained by utilizing the mapping relationship between the sampling angle, the sampling point height value and the sampling distance measurement value obtained in advance.

[0022] In some embodiments, the height information includes multiple actual height values, and obtaining the height information of the target obstacle according to each sampling angle and the corresponding actual distance value using a pre-calibrated mapping relationship between the sampling angle, the sampling point height value, and the sampling distance value includes:

[0023] For each of the sampling angles, searching for all sampling ranging values ​​associated with the sampling angle in the mapping relationship, and obtaining a set of sampling ranging values ​​corresponding to each of the sampling angles;

[0024] Selecting, from the set of sampled ranging values, a maximum sampled ranging value and a minimum sampled ranging value in the ranging interval in which the actual ranging value is located;

[0025] According to the maximum sampled ranging value and the minimum sampled ranging value in the ranging interval, searching for the associated sampling point height values ​​in the mapping relationship to obtain a height interval;

[0026] The actual height value corresponding to each sampling angle is obtained according to the sampled ranging value in the ranging interval corresponding to each sampling angle, the sampling point height value in the height interval, and the actual ranging value, so as to obtain the height information of the target obstacle.

[0027] In some embodiments, the mapping relationship is represented by a ranging truth table, and a method for constructing the ranging truth table includes:

[0028] The line laser sensor is used to measure the distance of a plurality of calibration planes at different heights from each sampling angle to obtain respective sampling distance measurement values; wherein the sampling angle is selected from the maximum detection angle range of the line laser sensor;

[0029] For each of the calibration planes, taking the height value between the calibration plane and a reference plane determined with reference to the embodied robot as the height value of the sampling point;

[0030] The sampled ranging values ​​associated with each sampling angle under the condition of each sampling point height value are stored to obtain a ranging truth table.

[0031] In some embodiments, before storing the sampled ranging values ​​associated with each sampling angle under the condition of each sampling point height value, the method further includes:

[0032] Calculating, according to the installation height and installation angle of the line laser sensor, a theoretical distance measurement value when the line laser sensor measures the distance of each calibration plane from each sampling angle;

[0033] For each calibration plane, the sampling distance value associated with each sampling angle is corrected according to the adjustment coefficient and the theoretical distance value corresponding to each sampling angle.

[0034] In some embodiments, the following formula is used to correct the sampled ranging value associated with each sampling angle:

[0035] final_value=λ×theory_value+(1-λ)×sample_value

[0036] Among them, final_value is the corrected sampling distance value, theory_value is the theoretical distance value, sample_value is the sampling distance value corresponding to the sampling point height value; λ is the adjustment coefficient, wherein the value of the adjustment coefficient is in the interval [0, 1].

[0037] In a second aspect, an embodiment of the present application provides an embodied robot system, the system comprising:

[0038] An obstacle height determination module is used to identify target obstacles during the movement of the embodied robot and obtain height information of the target obstacles;

[0039] An obstacle crossing height determination module, configured to determine a current obstacle crossing height threshold for the target obstacle based on a historical number of obstacle avoidance attempts by the embodied robot to avoid the target obstacle;

[0040] The travel control module is used to control the embodied robot to avoid or overcome the target obstacle according to the current obstacle crossing height threshold and the height information.

[0041] In a third aspect, an embodiment of the present application provides an embodied robot, comprising a line laser sensor, a processor, and a memory; wherein the memory stores a computer program, and the processor is used to execute the computer program to implement a control method for an embodied robot provided in the first aspect of the present application.

[0042] The embodiments of the present application have the following beneficial effects:

[0043] This application identifies target obstacles during the movement of an embodied robot and obtains the height information of the target obstacle; determines the current obstacle crossing height threshold for the target obstacle based on the historical number of obstacle avoidance attempts by the embodied robot; and controls the embodied robot to avoid or overcome the target obstacle based on the current obstacle crossing height threshold and the height information. This application adjusts the current obstacle crossing height threshold based on the historical number of obstacle avoidance attempts, and then controls the embodied robot to avoid or overcome the obstacle based on the current obstacle crossing height threshold and the height information. This application effectively solves the problem of weakened obstacle crossing capabilities of robots based on line lasers in the prior art by limiting the historical number of obstacle avoidance attempts. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A schematic diagram showing the detection range of a linear laser sensor in an embodied robot system according to an embodiment of the present application is shown;

[0046] Figure 2 A flow chart showing a control method of an embodied robot according to an embodiment of the present application is shown;

[0047] Figure 3 A schematic diagram of the mapping relationship in the control method of the embodied robot according to an embodiment of the present application is shown;

[0048] Figure 4 A schematic diagram illustrating the calculation of the height of a target obstacle in a certain sampling angle direction in the control method of the embodied robot according to an embodiment of the present application is shown;

[0049] Figure 5 An oblique view of laser point cloud data collected on each height calibration plane in the control method of the embodied robot according to an embodiment of the present application is shown;

[0050] Figure 6 A side view of laser point cloud data collected from each height calibration plane in the control method of the embodied robot according to an embodiment of the present application is shown;

[0051] Figure 7 A schematic diagram illustrating calculation of the sampling ranging value corresponding to each sampling angle direction in a frame of line laser data at a certain sampling point height in the control method of the embodied robot according to an embodiment of the present application is shown;

[0052] Figure 8 A schematic diagram showing a process in which an embodied robot detects a target obstacle during movement in a control method for an embodied robot according to an embodiment of the present application is shown;

[0053] Figure 9 A schematic diagram showing a low obstacle detected by a laser before the machine moves forward in the control method of the embodied robot according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0055] The components of the embodiments of the present application generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but rather merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort are within the scope of protection of the present application.

[0056] Hereinafter, the terms "including", "having" and their cognates used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the aforementioned items, and should not be understood as excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the aforementioned items or adding the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the aforementioned items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and should not be understood as indicating or implying relative importance.

[0057] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as in the context of the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0058] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0059] In actual use, it is found that some low obstacles often cause the embodied robot to trigger the obstacle detection of the line laser and cannot pass through, which weakens the obstacle-crossing ability of the embodied robot. Therefore, the present application provides a control method, system and embodied robot for an embodied robot. The main idea of ​​the present application is to switch the obstacle crossing height threshold for the obstacle after avoiding the same obstacle a certain number of times, so as to allow attempts to pass through low objects that were originally considered "obstacles", thereby improving the obstacle-crossing ability.

[0060] First, the present application provides an embodied robot. Exemplarily, the embodied robot includes a line laser sensor, a processor and a memory. The line laser sensor is installed on the embodied robot. The memory stores a computer program. The processor runs the computer program to enable the embodied robot to execute the control method of the embodied robot of the embodiment of the present application or the functions of each module in the control device of the embodied robot.

[0061] Among them, the line laser sensor is used to scan the point cloud information of the target obstacles around the embodied robot. Figure 1 (a) and Figure 1 As shown in (b), the black circle indicates the line laser sensor, and the black rectangle indicates the target obstacle. The line laser sensor is installed on the front side of the embodied robot. The line laser sensor emits a flat line laser downward at a certain angle; the maximum detection viewing angle range of the line laser sensor is theta°. For example, theta can be 120°, that is, the detection viewing angle range is ±60°.

[0062] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), 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. The general-purpose processor can be a microprocessor or any conventional processor, etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0063] The memory may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), and electrically erasable programmable read-only memory (EEPROM). The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving an execution instruction.

[0064] It can be understood that the embodied robots of the present application include but are not limited to cleaning robots (sweeping robots, mopping robots and sweeping and mopping robots), companion robots, humanoid robots, etc.

[0065] The control method of the embodied robot is described below with reference to some specific embodiments. The control method of the embodied robot is applied to the embodied robot.

[0066] Figure 2 A flow chart of a control method of an embodied robot according to an embodiment of the present application is shown. Exemplarily, the control method of the embodied robot includes the following steps:

[0067] S100, identifying a target obstacle while the embodied robot is moving, and obtaining height information of the target obstacle.

[0068] The target obstacle can be any object in a home environment that blocks the movement of the embodied robot, such as a table, chair, or door threshold. In this embodiment of the application, a line laser sensor is used to scan the front. When the line laser sensor detects the target obstacle, point cloud information of the target obstacle is obtained. The target obstacle can be identified based on the point cloud information, and the height information of the target obstacle can be further identified based on the point cloud information.

[0069] Exemplarily, when the embodied robot receives a work instruction, it plans a travel path according to the map corresponding to the home environment to perform the work task corresponding to the work instruction. The embodied robot receives line laser data in real time while moving along the planned path. When a target obstacle is detected, the height information of the detected target obstacle is calculated based on the line laser data of the target obstacle.

[0070] S200 , determining a height threshold for crossing the target obstacle based on the historical number of times the embodied robot avoids the target obstacle.

[0071] The historical obstacle avoidance times are the times the embodied robot avoids the target obstacle while performing the current task.

[0072] For example, when the embodied robot is in a closed scene with multiple obstacles around it, when a target obstacle among the multiple obstacles is detected for the first time by the line laser sensor, and the height of the target obstacle is higher than the first obstacle crossing height threshold set by default, the embodied robot performs obstacle avoidance processing on the target obstacle to try to bypass the target obstacle, and at the same time increases the historical obstacle avoidance times by 1. Since the embodied robot is in the closed scene, after trying to bypass the target obstacle, the target obstacle will be detected again in the same position. At this time, the obstacle crossing height threshold is determined based on the historical obstacle avoidance times of the target obstacle.

[0073] Furthermore, to facilitate storage of historical obstacle avoidance counts, embodiments of the present application also construct a count map. It is understood that the count map is generated based on the global map, and the corresponding historical obstacle avoidance counts are updated in the count map based on the current location of the target obstacle. It is understood that when comparing the historical obstacle avoidance counts with a preset count threshold, it is necessary to retrieve the corresponding historical obstacle avoidance counts from the count map based on the target obstacle's location information.

[0074] When the number of historical obstacle avoidance times is less than or equal to the preset number threshold, if the maximum value of the actual height values ​​of the target obstacle is greater than or equal to the first obstacle height threshold, the number of historical obstacle avoidance times is obtained from the number map based on the current position information of the target obstacle, and the historical obstacle avoidance times is controlled to be incremented by one and synchronously written back to the number map.

[0075] In other words, if the application still cannot pass through the target obstacle after several attempts to bypass it, in order to prevent the embodied robot from being unable to complete the current work task, it is necessary to adjust the obstacle crossing height threshold.

[0076] In some embodiments, the current obstacle crossing height threshold may be determined based on a pre-established correspondence between the number of historical obstacle avoidance attempts and the obstacle crossing height threshold.

[0077] In some embodiments, the embodied robot stores multiple obstacle height thresholds, and based on the historical number of obstacle avoidance attempts of the embodied robot against the target obstacle, determines the current obstacle height threshold for the target obstacle from the multiple obstacle height thresholds.

[0078] Exemplarily, the current obstacle crossing height threshold includes a first obstacle crossing height threshold and a second obstacle crossing height threshold.

[0079] S300: Control the embodied robot to avoid or overcome the target obstacle based on the obstacle crossing height threshold and height information.

[0080] In an embodiment of the present application, the size of the obstacle crossing height threshold is adjusted based on the number of historical obstacle avoidance times, and whether to avoid or cross the obstacle is determined based on the obstacle crossing height threshold and the height information of the target obstacle. If an obstacle cannot be passed after avoiding the same position a certain number of times, the obstacle crossing height threshold for the obstacle is switched to allow attempts to pass through low objects that were originally considered "obstacles", thereby improving the obstacle crossing ability of the embodied robot.

[0081] In one embodiment, a line laser sensor is provided on the embodied robot.

[0082] In step S100, a target obstacle is identified during the movement of the embodied robot, and height information of the target obstacle is obtained, which specifically includes the following steps S110-S120:

[0083] S110, identifying a target obstacle using a line laser sensor while the embodied robot is moving;

[0084] S120: Acquire actual distance values ​​corresponding to the target obstacle collected by the line laser sensor at different sampling angles, wherein the actual distance value is the distance between the emission point of the line laser and the sampling point.

[0085] S130: Confirm the height of the target obstacle based on the actual distance measurement value.

[0086] In some embodiments, confirming the height of the target obstacle based on the actual ranging value includes: obtaining the height information of the target obstacle based on each sampling angle and the corresponding actual ranging value using a mapping relationship between a pre-calibrated sampling angle, a sampling point height value, and a sampling ranging value.

[0087] In other words, given the sampling angle and the corresponding actual distance measurement value, the mapping relationship is used to obtain the height value of the sampling point, and the height information of the target obstacle is determined based on the height value of the sampling point.

[0088] In this embodiment, due to the inherent ranging errors and installation errors of the line laser sensor, these errors can lead to significant deviations in the measurement and calculation of obstacle heights. To address the problem of significant deviations in the measured obstacle heights caused by these errors, this application pre-calibrates the line laser data and calculates the target obstacle height information using the mapping relationship between the pre-calibrated sampling angle, sampling point height values, and sampled ranging values. This can improve the accuracy of determining the target obstacle height information, thereby improving the accuracy of the embodied robot's obstacle avoidance or traversal based on this height information.

[0089] In some embodiments, to facilitate querying the mapping relationship, the above mapping relationship is represented by a ranging truth table. For example, the ranging truth table is shown in Table 1, which includes m sampling angles within a range of ±60°, n calibration plane height values ​​h (sampling point height values), and the corresponding sampled ranging values ​​d.

[0090] Table 1 Distance measurement truth table

[0091]

[0092] In some embodiments, according to each sampling angle and the corresponding actual distance measurement value, the height information of the target obstacle is obtained by using a pre-calibrated mapping relationship between the sampling angle, the sampling point height value, and the sampling distance measurement value, including: for each sampling angle, if a sampling distance measurement value that is the same as the actual distance measurement value at the sampling angle is found in the mapping relationship, then the sampling point height value corresponding to the same sampling distance measurement value is used as the height value of the target obstacle at the sampling angle; if a sampling distance measurement value that is the same as the actual distance measurement value at the sampling angle is not found in the mapping relationship, then the following steps S131-S133 are executed:

[0093] S131: For each sampling angle, search for all sampling ranging values ​​associated with the sampling angle in the mapping relationship to obtain a sampling ranging value set corresponding to each sampling angle; and select the maximum sampling ranging value and the minimum sampling ranging value in the ranging interval where the actual ranging value is located from the sampling ranging value set.

[0094] like Figure 3 As shown in Table 2, each sampling angle in the mapping relationship corresponds to multiple sampling distance values, and the multiple sampling distance values ​​include a sampling distance value corresponding to each sampling height value. For example, when the sampling angle is 60°, the sampling distance values ​​d1, ..., and dn corresponding to the sampling height value h1 are determined, as shown in Table 2:

[0095] Table 2 Mapping relationship between 60° sampling angle, height value of each sampling point, and sampling distance value

[0096]

[0097] For each sampling angle, it is necessary to search for each sampling ranging value corresponding to the sampling angle in the mapping relationship, that is, each sampling ranging value measured at the sampling angle at different sampling heights, and each sampling ranging value constitutes the sampling ranging value set corresponding to the sampling angle. For example, when the sampling angle is 60°, the corresponding sampling ranging value set is {d1, d2, …, dn}; optionally, the two endpoint values ​​of the ranging interval (that is, the maximum sampling ranging value and the minimum sampling ranging value) can be selected from the corresponding sampling ranging value set according to the set interval size.

[0098] In some embodiments, a sampled distance value that is closest to the actual distance value and is larger than the actual distance value and a sampled distance value that is smaller than the actual distance value can be found in the sampled distance value set, and the two endpoint values ​​of the distance interval are determined based on these two sampled distance values. For example, the actual distance value corresponding to the sampling angle of 60° is L 1. Find the sampled distance value set {d1, d2, ..., dn} corresponding to 60° and the actual distance value L1 The first adjacent, and the sampling distance value d1 that is larger than the actual distance value, the sampling distance value d2 that is smaller than the actual distance value, obtain the actual distance value L 1 corresponds to the ranging interval [d1, d2], that is, L 1∈[d1, d2]. In this embodiment, by finding the sampled ranging value closest to the actual ranging value in the sampled ranging value set and determining the two endpoint values ​​of the ranging interval, the error in the subsequent calculation of the actual height value of the target obstacle can be reduced, thereby improving the detection accuracy of the target obstacle height information.

[0099] It should be noted that since the shapes of obstacles are different, the actual ranging values ​​collected at some sampling angles will be equal to 0. In some embodiments, before step S131, the sampling angles corresponding to the actual ranging values ​​​​equal to 0 are filtered out to obtain the sampling angles corresponding to the actual ranging values ​​​​greater than 0, and the filtered sampling angles are processed in step 131 and subsequent steps.

[0100] S132 , according to the maximum sampled ranging value and the minimum sampled ranging value in the ranging interval, respectively search for the associated sampling point height values ​​in the mapping relationship to obtain the height interval.

[0101] When the sampling angle is fixed, a sampling distance value in the mapping relationship has a unique corresponding sampling point height value. According to the maximum sampling distance value and the minimum sampling distance value in the ranging interval, the corresponding sampling point height values ​​are searched in the mapping relationship respectively, and the height interval is obtained according to the sampling point height value corresponding to the maximum sampling distance value and the sampling point height value corresponding to the minimum sampling distance value.

[0102] For example, taking the sampling angle of 60° as an example, according to Table 2, the sampling distance values ​​d1 and d2 corresponding to the ranging interval [d1, d2] are searched in the mapping relationship for the sampling point height values ​​h1 and h2 corresponding to d1 and d2 to obtain the height interval [h2, h1].

[0103] S133 , obtaining the actual height value corresponding to each sampling angle according to the sampled ranging value in the ranging interval corresponding to each sampling angle, the sampling point height value in the height interval, and the actual ranging value, so as to obtain the height information of the target obstacle.

[0104] For example, taking the sampling angle of 60° as an example, according to the sampling distance value in the distance interval [d1, d2] corresponding to the sampling angle 60°, the sampling point height value in the height interval [h2, h1] and the actual distance value L 1. Get the actual height value corresponding to the sampling angle of 60° to obtain the height information of the target obstacle. Figure 4As shown, the black circle is used to indicate the line laser sensor, and the black rectangle is used to indicate the target obstacle. If the ranging interval [d1, d2] is [OA, OB], the sampled ranging values ​​in the ranging interval are OA and OB, and the height interval is [hb, ha], the sampling point height values ​​in the height interval are hb and ha, the actual ranging value L 1=OC. Since OA, OB, OC, ha, and hb are all known, the height of the line laser sensor installation is also known (that is, the height ho of point O where the line laser sensor is installed). △OAE, △OCG, and △OBF are similar triangles with the same ratio of the sides. Therefore, hc can be calculated based on the proportional relationship of the similar triangles to obtain the actual height of the target obstacle at a sampling angle of 60°.

[0105] In some embodiments, for each sampling angle, when there are multiple sampled distance values ​​in the distance measurement interval and multiple sampled point height values ​​in the height interval, multiple actual height values ​​of the target obstacle at the sampling angle can be obtained, and the multiple actual height values ​​can be averaged to obtain a final actual height value of the target obstacle at the sampling angle, so that the determination of the actual height value is more accurate. For example, Figure 4 As shown in the figure, the actual height value 1 can be calculated according to the proportional relationship between △OAE and △OCG, and the actual height value 2 can be calculated according to the proportional relationship between △OCG and △OBF. The actual height values ​​1 and 2 are averaged, and the average value is used as the actual height value of the target obstacle at the sampling angle.

[0106] It should be noted that since the shape of the obstacle may be irregular, the actual height value corresponding to each sampling angle may be the same or different. Saving multiple actual height values ​​means that the height information of the target obstacle includes multiple actual height values ​​at different sampling angles.

[0107] The following describes a method for constructing a ranging truth table used to represent the above mapping relationship in this application.

[0108] It can be understood that this application calibrates the line laser data and obtains a distance measurement truth table after calibration. The process of calibrating the line laser data is the process of constructing the distance measurement truth table. To ensure the accuracy of the calibration, before constructing the distance measurement truth table, it is first necessary to use a calibration fixture to calibrate the line laser sensor installed horizontally in front of the embodied robot to determine whether the installation and distance measurement values ​​of the line laser sensor are within the allowable error range. The premise for subsequent calibration steps is that the installation and distance measurement of the line laser sensor are within the allowable error range.

[0109] The method for constructing the ranging truth table specifically includes the following steps S410-S430:

[0110] S410 , using a line laser sensor to measure distances to a plurality of calibration planes at different heights from each sampling angle, to obtain respective sampling distance measurement values.

[0111] The sampling angles are selected from the maximum detection angle range of the line laser sensor. Each sampling angle is a set of multiple angles within the maximum detection angle range of the line laser sensor, determined at a set interval. For example, if the maximum detection angle range of the line laser sensor is theta = 120°, i.e., a detection range of ±60°, and the angular resolution is set to angLe_resoLution = 0.5° (i.e., the set interval), then a total of 240 sampling angles are included.

[0112] The calibration planes are a number of equally spaced planes obtained by dividing the preset height range determined based on the reference plane into preset height intervals. The reference planes are planes determined with reference to the embodied robot. For example, the reference planes include, but are not limited to, planes determined based on multiple points at the lowest end of the embodied robot, such as the horizontal plane at the bottom surface of the embodied robot's drive wheels.

[0113] In other words, a reference plane is determined based on the embodied robot, and the interval within the preset height range above and below the reference plane is used as the detection space. The detection space is divided into several calibration planes using the preset height intervals. For example, Figure 5 As shown in the figure, the black oval represents the driving wheel of the embodied robot. The horizontal plane where the lower surface of the driving wheel of the embodied robot is located is used as the reference plane (i.e. Figure 5 The detection space is divided into sections 5 cm above and below the reference plane, with a preset height interval of 5 mm. Multiple calibration planes parallel to the reference plane are obtained by dividing the detection space into sections 5 cm above and below the reference plane.

[0114] S420 , for each calibration plane, taking the height value between the calibration plane and the reference plane determined by the reference embodied robot as the sampling point height value.

[0115] like Figure 5 and Figure 6As shown, the height of the overall detection space is calibrated using the robot's horizontal plane as the reference plane. The range H above and below the reference plane corresponds to an obstacle height range of ±H. The overall height of the detection space is 2H, with the initial height at -H. For example, the calibration plate is moved upward in 5mm intervals, serving as the calibration plane. Line laser detection data (line laser data) is recorded after each movement of the calibration plate. This line laser data includes the sampled ranging values ​​of the line laser at each sampling angle at the current calibration plate height. The points on the calibration plate where the line laser scans are located are referred to as sampling points. The height between the calibration plate and the reference plane is the sampling point height.

[0116] S430 , storing the sampled distance measurement values ​​associated with each sampling angle under the condition of each sampling point height value, and obtaining a distance measurement truth table.

[0117] Specifically, a file is generated in the form of a table to record each sampling angle, each sampling point height value, and the corresponding sampled distance value, to obtain a distance truth table.

[0118] Furthermore, in order to improve the accuracy, before step S430 storing the sampled distance values ​​associated with each sampling angle under the condition of each sampling point height value, the following steps S510-S520 are also included:

[0119] S510 , calculating, based on the installation height and installation angle of the line laser sensor, a theoretical distance measurement value when the line laser sensor measures the distance of each calibration plane from each sampling angle.

[0120] The installation height and installation angle of the line laser sensor refer to the height and angle at which the line laser sensor is installed on the embodied robot.

[0121] Based on the theoretical installation height and installation angle (tilt angle) of the line laser sensor, a frame of data at the corresponding height value of each calibration plane can be calculated. This frame of data includes the theoretical ranging value for each sampling angle, which corresponds one-to-one with the sampling point height value used in the above calibration. In this way, the theoretical ranging value from the line laser to each calibration plane at each sampling angle can be obtained.

[0122] For example, Figure 7As shown in the figure, the black circle represents the line laser sensor. The line laser sensor is mounted on the embodied robot at a height h, that is, the height of the line laser sensor from the ground is h. Line segment AB is composed of the sampling points scanned by the line laser on the calibration plate. To obtain the theoretical ranging value corresponding to the sampling points in line segment AB at each sampling angle, we need to find the ranging value in the direction of any sampling angle β with respect to the midline OC of ∠AOB in △AOB. Point O is the line laser emission point of the line laser sensor. Line segment AB is located on the calibration plane and includes the sampling points corresponding to each sampling angle. OC corresponds to the theoretical ranging value in the direction of the sampling angle 0° in the line laser sensor coordinate system, OA corresponds to the theoretical ranging value in the direction of the minimum sampling angle on the right side of the line laser coordinate system (for example, the minimum right angle is -60°), and OB corresponds to the theoretical ranging value in the direction of the maximum sampling angle on the left side of the line laser coordinate system (for example, the maximum left angle is +60°). The angle α is the angle between the sampling angle 0° direction of the line laser coordinate system and the calibration plane. The angles between other angle directions and the calibration plane are not α. According to α and h, the theoretical ranging value OC corresponding to the sampling angle 0° direction can be calculated, that is, OC=h / sin(α). Then, according to OC, the corresponding theoretical ranging values ​​of all angle directions in this line laser coordinate system can be calculated. For example, the theoretical ranging value of the sampling angle β direction is OD, OD = OC / cos(β) = (h / sin(α)) / cos(β); thus, the theoretical ranging value of each sampling angle direction can be calculated in turn.

[0123] S520 , for each calibration plane, correct the sampled ranging value of each associated sampling angle according to the adjustment coefficient and the theoretical ranging value corresponding to each sampling angle.

[0124] Exemplarily, the following formula is used to correct the sampled ranging value of each associated sampling angle:

[0125] final_value=λ×theory_value+(1-λ)×sample_value

[0126] Among them, final_value is the corrected sampling distance value, theory_value is the theoretical distance value, sample_value is the sampling distance value corresponding to the sampling point height value; λ is the adjustment coefficient, where the value of the adjustment coefficient is in the interval [0, 1].

[0127] For each calibration plate height, a set of theoretical distance values ​​(theory_value) and sampled distance values ​​(sample_value) are mapped one-to-one. The value of λ can be adjusted and selected based on the deviation between the theoretical and sampled distance values. The larger the λ value, the closer the final_value is to the theoretical distance value. Alternatively, the final_value can be randomly selected in the interval [0, 1]. Finally, a usable distance truth table is obtained. The distance truth value includes the corrected sampled distance value at each sampling angle at different heights.

[0128] In one embodiment, in order to improve the pass rate, in step S200, based on the historical number of times the embodied robot has avoided the target obstacle, determining the current obstacle crossing height threshold for the target obstacle includes:

[0129] If the historical number of obstacle avoidance attempts of the embodied robot to avoid the target obstacle is greater than a preset number threshold, the current obstacle crossing height threshold is adjusted from the first obstacle crossing height threshold to the second obstacle crossing height threshold; otherwise, the current obstacle crossing height threshold is maintained at the first obstacle crossing height threshold; wherein, the second obstacle crossing height threshold is greater than the first obstacle crossing height threshold.

[0130] The first obstacle height threshold and the second obstacle height threshold can be set according to the hardware conditions of the embodied robot (such as the size of the driving wheels).

[0131] In other words, in this embodiment of the present application, by default, the obstacle height threshold is the first obstacle height threshold. If the historical number of obstacle avoidance attempts exceeds a preset number threshold, the embodied robot's current obstacle height threshold for the target obstacle is adjusted to the second obstacle height threshold; this allows the embodied robot to control its movement based on the target obstacle's actual height and the second obstacle height threshold. In other words, if the embodied robot has avoided the target obstacle a predetermined number of times, i.e., if it still cannot overcome an obstacle in the same location after a certain number of attempts (e.g., a threshold area requiring attempts to pass), it is necessary to adjust the obstacle height threshold, i.e., raise the obstacle height threshold to improve its ability to overcome obstacles.

[0132] In one embodiment, the height information includes multiple actual height values. That is, for a target obstacle, the height information includes the actual height value corresponding to each sampling angle and the actual height values ​​corresponding to multiple moments. Figure 8 As shown, when the embodied robot moves to the target obstacle, it can scan the target obstacle at each sampling moment within a certain distance, but only the data scanned at the last time contains the maximum actual height value of the target obstacle.

[0133] Optionally, the method further includes: if the actual height value of the target obstacle is detected to be greater than or equal to a first height detection threshold, saving the actual height value of the target obstacle into the height information.

[0134] To ensure the accuracy of obstacle avoidance, in step S300, the embodied robot is controlled to avoid or overcome the target obstacle based on the obstacle height threshold and height information, including:

[0135] If the maximum actual height value in the height information is greater than or equal to the current obstacle crossing height threshold, the embodied robot is controlled to avoid the target obstacle and the historical obstacle avoidance times are updated; otherwise, the embodied robot is controlled to cross the target obstacle.

[0136] The maximum actual height value is the maximum value among the actual height values ​​of the target obstacle.

[0137] In other words, when the number of historical obstacle avoidance attempts is less than or equal to the preset number threshold, once it is detected that the maximum actual height value of the target obstacle is greater than or equal to the current obstacle crossing height threshold, it means that the target obstacle cannot be crossed based on the hardware conditions of the embodied robot itself, so the target obstacle is confirmed to be avoided and the number of historical obstacle avoidance attempts is updated at the same time; if the maximum actual height value of the target obstacle is less than the current obstacle crossing height threshold, it means that the target obstacle can be crossed based on the hardware conditions of the embodied robot itself, so the embodied robot is controlled to cross the obstacle and continue moving.

[0138] In some embodiments, after obtaining the height information of the target obstacle, the method further includes:

[0139] When the distance between the embodied robot and the target obstacle is greater than the obstacle avoidance distance, if any actual height value in the height information is greater than or equal to the first obstacle crossing height threshold, the position information of the target obstacle is stored.

[0140] Among them, the obstacle avoidance distance can be set according to the task type performed by the embodied robot. For example, if the embodied robot is a sweeping robot, in order to ensure the cleaning coverage of the sweeping robot and avoid missing sweeps, the obstacle avoidance distance needs to ensure that the sweeping robot does not miss sweeps while not colliding with obstacles.

[0141] Since the embodied robot will scan the target obstacle multiple times when approaching the target obstacle, and the height values ​​of the sampling points are different, once the calculated actual height value of the obstacle is detected to be greater than or equal to the first obstacle height threshold, the position information of the target obstacle is stored. Otherwise, the height of the obstacle will not block the embodied robot, so there is no need to record it.

[0142] like Figure 9As shown, the embodied robot cannot detect the target obstacle when the distance between the robot and the target obstacle is less than or equal to the obstacle avoidance distance. Specifically, due to the installation method of the line laser, when a relatively low target obstacle is detected, it is still a safe distance away from the embodied robot and no obstacle avoidance action is triggered. If the embodied robot continues to move forward, the target obstacle cannot be detected in real time at a certain distance. Therefore, by preserving the target obstacle's position information, it can be used to accurately determine the timing of triggering the obstacle avoidance action.

[0143] For example, embodiments of the present application utilize a local map to store the location information of target obstacles. As will be appreciated, if the actual height of the target obstacle is detected to be greater than or equal to a first height detection threshold, the location of the target obstacle is marked on the local map using a marker based on the target obstacle's location information. Furthermore, the local map is determined based on a set length threshold centered on the embodied robot.

[0144] For example, a local map of n×n area is created with the robot's current location as the center. The currently detected target obstacle is marked at the corresponding location in the local map based on its location information. The robot then continues to move along the pre-planned path. When it reaches the obstacle avoidance distance from the target obstacle marker, the robot performs an obstacle avoidance action (such as deceleration). Here, n is determined based on the robot's radius extending outward from the robot's center point and the distance between the laser line and the horizontal surface. For example, a local map of 2m×2m area is used.

[0145] Furthermore, to ensure the timeliness of obstacle detection, the method also includes: clearing the marker from the local map after a preset time period. In other words, the location information of the target obstacle needs to be cleared after a certain period of time. For example, if the time period exceeds 30 seconds, the location information of the target obstacle will be automatically cleared.

[0146] Furthermore, in order to ensure the safety of the embodied robot, the embodied robot is controlled to avoid or overcome target obstacles, including:

[0147] When it is determined based on the position information of the target obstacle that the embodied robot has traveled to a distance from the target obstacle that is less than or equal to the obstacle avoidance distance, the embodied robot is controlled to avoid the target obstacle.

[0148] Optionally, the distance between the embodied robot and the target obstacle may be calculated based on the position information of the target obstacle on the local map and the position of the embodied robot in the local map.

[0149] Specifically, the number of historical obstacle avoidance attempts is less than or equal to a preset number threshold, the maximum actual height value in the height information is greater than or equal to the current obstacle crossing height threshold, and the embodied robot is confirmed to have traveled to a distance from the target obstacle that is less than or equal to the obstacle avoidance distance based on the position information of the target obstacle. Only then will the number of obstacle avoidance attempts be updated and obstacle avoidance executed.

[0150] Exemplarily, if the distance between the embodied robot and the forward marker is determined to be less than or equal to the obstacle avoidance distance based on the local map, the embodied robot is controlled to avoid the target obstacle. However, if the distance between the embodied robot and the target obstacle is less than or equal to the obstacle avoidance distance, the target obstacle cannot be identified, and thus, the distance to the target obstacle can only be determined based on the local map.

[0151] The control method of the embodied robot of the present application is described below with reference to a specific example. In this example, the embodied robot is a household service robot:

[0152] S610, collecting actual distance measurement values ​​in all sampling angle directions in the line laser data at the current moment.

[0153] S620: For each sampling angle, find a set of sampling ranging values ​​corresponding to the sampling angle direction in the truth table, including sampling ranging values ​​corresponding to different sampling point height values ​​and sampling ranging values ​​corresponding to the same sampling point height value.

[0154] At step S630, the maximum and minimum sampled ranging values ​​in the ranging interval where the actual ranging value obtained by scanning is located are selected from the sampled ranging value set in step S620, and the corresponding height interval of the target obstacle is determined based on the ranging interval. Then, the actual height value of the target obstacle is accurately calculated based on the height interval.

[0155] S640: If the maximum actual height value of the target obstacle is greater than or equal to the first obstacle height threshold, a local map with an area size of 2m×2m is created with the current position of the home service robot as the center, and the target obstacle is marked on the local map with a marking point based on the currently detected position information of the target obstacle.

[0156] It should be noted that the location information of the target obstacle needs to be cleared after being retained on the local map for a certain period of time, for example, 30 seconds. If the location information exceeds 30 seconds, the target obstacle mark point will be automatically cleared.

[0157] S650: Control the home service robot to continue moving along the pre-planned path. When the robot reaches the obstacle avoidance distance from the marked point corresponding to the target obstacle, the robot performs an obstacle avoidance action (e.g., deceleration). Simultaneously, based on the location information of the target obstacle corresponding to the obstacle avoidance action, the robot updates the historical obstacle avoidance count for the target obstacle in the constructed count map.

[0158] Due to the installation method of the line laser, when a relatively low obstacle is detected, it is still a safe distance away from the home service robot and will not trigger any action. If the home service robot continues to move forward, the target obstacle cannot be detected in real time, so the timing of triggering the obstacle avoidance action can only be accurately judged by retaining the point cloud information of the target obstacle through the local map.

[0159] S660: During the subsequent movement, it is determined whether the obstacle avoidance height threshold needs to be switched based on the number of historical obstacle avoidance times recorded at the same position on the times map.

[0160] For example, in one embodiment, step S660 includes:

[0161] S661: Determine whether the number of historical obstacle avoidances corresponding to the position of the target obstacle is less than or equal to a preset number threshold.

[0162] S662: If the number of historical obstacle avoidance attempts corresponding to the target obstacle's position on the times map is less than or equal to the preset times threshold, the current obstacle crossing height threshold is not switched, and then a determination is made as to whether the maximum actual height value corresponding to the current position is greater than or equal to the first obstacle crossing height threshold. If the maximum actual height value of the target obstacle is greater than or equal to the first obstacle crossing height threshold, a collision signal is generated normally, and the historical obstacle avoidance attempts in the times map are updated.

[0163] S663, if the number of historical obstacle avoidance attempts corresponding to the position of the target obstacle on the frequency map is greater than the preset number threshold, it is necessary to switch the current obstacle crossing height threshold to the second obstacle crossing height threshold; and then determine whether the maximum actual height value corresponding to the current position is greater than or equal to the second obstacle crossing height threshold; if the maximum actual height value is greater than the second obstacle crossing height threshold, a collision signal is generated normally; if it is less than the second obstacle crossing height threshold, no collision signal is generated, and the home service robot continues to be controlled to move forward to determine whether the position of the next target obstacle can be crossed.

[0164] If a target obstacle detected by a line laser blocks the entire road section, the home service robot will continuously trigger line laser collision detection when it approaches the target obstacle, ultimately preventing it from passing. To address this situation, the embodiment of the present application switches the obstacle's current obstacle crossing height threshold after a certain number of attempts at the same obstacle location (such as a threshold area, where attempts to pass are required), thereby increasing navigation's passing capability. This is necessary. It should be noted that the current obstacle crossing height threshold is for the target obstacle encountered at the current location. If the next target obstacle is encountered, the judgment will be re-evaluated according to the method of the present application.

[0165] The present application also provides a control system for an embodied robot. Exemplarily, the control system for the embodied robot includes:

[0166] A height information determination module is used to identify target obstacles during the movement of the embodied robot and obtain the height information of the target obstacles;

[0167] An obstacle height threshold determination module is used to determine the current obstacle height threshold for the target obstacle based on the historical number of obstacle avoidance attempts by the embodied robot;

[0168] The travel control module is used to control the embodied robot to avoid or overcome the target obstacle based on the obstacle height threshold and height information.

[0169] Furthermore, the obstacle height threshold determination module is specifically configured to:

[0170] If the number of historical obstacle avoidance attempts of the embodied robot to avoid the target obstacle is greater than the preset number threshold, the current obstacle height threshold is adjusted from the first obstacle height threshold to the second obstacle height threshold; otherwise, the current obstacle height threshold is maintained at the first obstacle height threshold;

[0171] The second obstacle clearance height threshold is greater than the first obstacle clearance height threshold.

[0172] Furthermore, the height information includes a plurality of actual height values. After obtaining the height information of the target obstacle, the system further includes a position information storage module;

[0173] The position information storage module is used to store the position information of the target obstacle when the distance between the embodied robot and the target obstacle is greater than the obstacle avoidance distance and if any actual height value in the height information is greater than or equal to the first obstacle crossing height threshold.

[0174] Furthermore, the travel control module is specifically configured to control the embodied robot to avoid the target obstacle when it is determined based on the position information of the target obstacle that the distance between the embodied robot and the target obstacle is less than or equal to the obstacle avoidance distance.

[0175] Furthermore, the height information includes multiple actual height values, and the travel control module is also specifically used to: if the maximum actual height value in the height information is greater than or equal to the current obstacle crossing height threshold, then control the embodied robot to avoid the target obstacle and update the historical obstacle avoidance times; otherwise, control the embodied robot to cross the target obstacle.

[0176] Furthermore, the embodied robot is provided with a line laser sensor, and the height information determination module is specifically used to:

[0177] The target obstacle is identified by a line laser sensor during the movement of the embodied robot;

[0178] Obtain the actual distance measurement value corresponding to the target obstacle collected by the line laser sensor at different sampling angles;

[0179] According to each sampling angle and the corresponding actual distance measurement value, the height information of the target obstacle is obtained by using the mapping relationship between the pre-calibrated sampling angle, sampling point height value and sampling distance value.

[0180] Furthermore, the height information includes multiple actual height values. When the height information determination module obtains the height information of the target obstacle based on each sampling angle and the corresponding actual distance value, using a pre-calibrated mapping relationship between the sampling angle, the sampling point height value, and the sampling distance value, it is further configured to:

[0181] For each sampling angle, search for all sampling distance measurement values ​​associated with the sampling angle in the mapping relationship, and obtain the sampling distance measurement value set corresponding to each sampling angle;

[0182] Selecting the maximum sampled distance measurement value and the minimum sampled distance measurement value in the distance measurement interval where the actual distance measurement value is located from the sampled distance measurement value set;

[0183] According to each sampled distance measurement value in the distance measurement interval, the associated sampling point height value is searched in the mapping relationship to obtain the height interval;

[0184] According to the sampled distance measurement value in the distance measurement interval corresponding to each sampling angle, the sampling point height value in the height interval and the actual distance measurement value, the actual height value corresponding to each sampling angle is obtained to obtain the height information of the target obstacle.

[0185] Furthermore, the mapping relationship is represented by a ranging truth table, and the method for constructing the ranging truth table includes:

[0186] A line laser sensor is used to measure the distance of multiple calibration planes at different heights at each sampling angle to obtain each sampling distance value; wherein the sampling angle is selected from the maximum detection angle range of the line laser sensor;

[0187] For each calibration plane, the height value between the calibration plane and the reference plane determined by the reference embodied robot is used as the sampling point height value;

[0188] The sampled ranging values ​​associated with each sampling angle under the condition of each sampling point height value are stored to obtain a ranging truth table.

[0189] Furthermore, the system also includes a correction module; the correction module is used to:

[0190] Before storing the sampled distance values ​​associated with each sampling angle and each sampling point height value, the theoretical distance value when the line laser sensor measures the distance to each calibration plane from each sampling angle is calculated according to the installation height and installation angle of the line laser sensor;

[0191] For each calibration plane, the sampling distance value of each associated sampling angle is corrected according to the adjustment coefficient and the theoretical distance value corresponding to each sampling angle.

[0192] Furthermore, the following formula is used to correct the sampling distance value of each associated sampling angle:

[0193] final_value=λ×theory_value+(1-λ)×sample_value

[0194] Among them, final_value is the corrected sampling distance value, theory_value is the theoretical distance value, sample_value is the sampling distance value corresponding to the sampling point height value; λ is the adjustment coefficient, where the value of the adjustment coefficient is in the interval [0, 1].

[0195] It can be understood that the device of this embodiment corresponds to the control method of the embodied robot of the above embodiment, and the optional items in the above embodiment are also applicable to this embodiment, so they will not be repeated here.

[0196] This application also provides a computer-readable storage medium for storing the computer program used in the embodied robot. For example, the computer-readable storage medium may include, but is not limited to, a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, among other media capable of storing program code.

[0197] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or flowchart, and the combination of boxes in the structure diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0198] In addition, the functional modules or units in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0199] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a smart phone, personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0200] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A control method for an embodied robot, characterized in that: include: Identifying a target obstacle during the movement of the embodied robot and obtaining height information of the target obstacle; If the number of historical obstacle avoidance attempts by the embodied robot to avoid the target obstacle is greater than a preset number threshold, the current obstacle crossing height threshold is adjusted from the first obstacle crossing height threshold to the second obstacle crossing height threshold; otherwise, the current obstacle crossing height threshold is maintained at the first obstacle crossing height threshold; wherein the second obstacle crossing height threshold is greater than the first obstacle crossing height threshold; the historical obstacle avoidance attempt number is the number of times the embodied robot has avoided the target obstacle while performing the current task; The specific method of storing the historical obstacle avoidance times is as follows: generating a times map based on the global map, and updating the corresponding historical obstacle avoidance times in the times map based on the current position of the target obstacle; The embodied robot is controlled to avoid or overcome the target obstacle according to the current obstacle crossing height threshold and the height information.

2. The control method of the embodied robot according to claim 1, characterized in that: The height information includes a plurality of actual height values, and controlling the embodied robot to avoid or overcome the target obstacle according to the current obstacle crossing height threshold and the height information includes: If the maximum actual height value in the height information is greater than or equal to the current obstacle crossing height threshold, the embodied robot is controlled to avoid the target obstacle and the historical obstacle avoidance times are updated; otherwise, the embodied robot is controlled to cross the target obstacle.

3. The control method of the embodied robot according to claim 2, characterized in that: After obtaining the height information of the target obstacle, the method further includes: When the distance between the embodied robot and the target obstacle is greater than the obstacle avoidance distance, if any of the actual height values ​​in the height information is greater than or equal to the first obstacle crossing height threshold, storing the position information of the target obstacle; The controlling the embodied robot to avoid the target obstacle includes: When it is determined based on the position information of the target obstacle that the embodied robot has traveled to a distance from the target obstacle that is less than or equal to the obstacle avoidance distance, the embodied robot is controlled to avoid the target obstacle.

4. The control method of the embodied robot according to claim 1, characterized in that: The embodied robot is provided with a line laser sensor, and the identification of target obstacles during the movement of the embodied robot and obtaining height information of the target obstacles include: identifying the target obstacle by the line laser sensor during the movement of the embodied robot; Obtaining actual distance measurement values ​​corresponding to the target obstacle collected by the line laser sensor at different sampling angles; According to each of the sampling angles and the corresponding actual distance measurement value, the height information of the target obstacle is obtained by utilizing the mapping relationship between the sampling angle, the sampling point height value and the sampling distance measurement value obtained in advance.

5. The control method of the embodied robot according to claim 4, characterized in that: The height information includes a plurality of actual height values, and the height information of the target obstacle is obtained according to each sampling angle and the corresponding actual distance value by using a mapping relationship between a pre-calibrated sampling angle, a sampling point height value, and a sampling distance value, including: For each of the sampling angles, searching for all sampling ranging values ​​associated with the sampling angle in the mapping relationship, and obtaining a set of sampling ranging values ​​corresponding to each of the sampling angles; Selecting, from the set of sampled ranging values, a maximum sampled ranging value and a minimum sampled ranging value in the ranging interval in which the actual ranging value is located; According to the maximum sampled ranging value and the minimum sampled ranging value in the ranging interval, searching for the associated sampling point height values ​​in the mapping relationship to obtain a height interval; The actual height value corresponding to each sampling angle is obtained according to the sampled ranging value in the ranging interval corresponding to each sampling angle, the sampling point height value in the height interval, and the actual ranging value, so as to obtain the height information of the target obstacle.

6. The control method of the embodied robot according to claim 4, characterized in that: The mapping relationship is represented by a ranging truth table, and the method for constructing the ranging truth table includes: The line laser sensor is used to measure the distance of a plurality of calibration planes at different heights from each sampling angle to obtain respective sampling distance measurement values; wherein the sampling angle is selected from the maximum detection angle range of the line laser sensor; For each of the calibration planes, taking the height value between the calibration plane and a reference plane determined with reference to the embodied robot as the height value of the sampling point; The sampled ranging values ​​associated with each sampling angle under the condition of each sampling point height value are stored to obtain a ranging truth table.

7. The control method of the embodied robot according to claim 6, characterized in that: Before storing the sampled distance values ​​associated with each sampling angle under the condition of each sampling point height value, the method further includes: Calculating, according to the installation height and installation angle of the line laser sensor, a theoretical distance measurement value when the line laser sensor measures the distance of each calibration plane from each sampling angle; For each calibration plane, the sampling distance value associated with each sampling angle is corrected according to the adjustment coefficient and the theoretical distance value corresponding to each sampling angle.

8. The control method of the embodied robot according to claim 7, characterized in that: The following formula is used to correct the sampling distance value of each associated sampling angle: final_value=λ×theory_value+(1-λ)×sample_value Among them, final_value is the corrected sampling distance value, theory_value is the theoretical distance value, sample_value is the sampling distance value corresponding to the sampling point height value; λ is the adjustment coefficient, wherein the value of the adjustment coefficient is in the interval [0, 1].

9. An embodied robotic system, characterized in that: The system comprises: An obstacle height determination module is used to identify target obstacles during the movement of the embodied robot and obtain height information of the target obstacles; an obstacle height determination module, configured to adjust a current obstacle height threshold from a first obstacle height threshold to a second obstacle height threshold if the embodied robot has a history of avoiding the target obstacle greater than a preset number threshold, and otherwise maintain the current obstacle height threshold at the first obstacle height threshold; wherein the second obstacle height threshold is greater than the first obstacle height threshold; and the historical obstacle avoidance number is the number of times the embodied robot has avoided the target obstacle while performing the current task; The specific method of storing the historical obstacle avoidance times is as follows: generating a times map based on the global map, and updating the corresponding historical obstacle avoidance times in the times map based on the current position of the target obstacle; A travel control module is used to control the embodied robot to avoid or overcome the target obstacle according to the current obstacle crossing height threshold and the height information.

10. An embodied robot, characterized in that: The embodied robot includes a line laser sensor, a processor and a memory; wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the control method of the embodied robot according to any one of claims 1-8.

Images