Control method of mobile robot, mobile robot, equipment and storage medium

Abstract

The invention provides a control method of a mobile robot, the mobile robot, equipment and a storage medium. The method comprises the steps that in the moving process of the mobile robot, whether an obstacle which cannot bypass exists in the advancing direction or not is detected; if the obstacle which cannot be bypassed exists in the advancing direction, target obstacle crossing position identification is carried out on the obstacle which cannot be bypassed; obtaining the form information of an obstacle which the mobile robot needs to cross when the mobile robot is located at the target obstacle crossing position; determining a target obstacle crossing strategy according to the obstacle form information; and through the target obstacle crossing strategy, the mobile robot is controlled to cross the non-bypassing obstacle. In the mode, appropriate obstacle crossing position recognition is carried out only for the obstacle which cannot be bypassed in the advancing direction, the obstacle crossing strategy is determined and obstacle crossing control is carried out according to the obstacle form of the obstacle crossing position, unnecessary obstacle crossing control can be reduced, loss of an obstacle crossing mechanism and energy can be reduced, and the obstacle crossing strategy of the mobile robot is more reasonable and more accurate.

Description

Technical Field

[0001] The present disclosure relates to the field of robot technology, and in particular to a control method for a mobile robot, a mobile robot, a device, and a storage medium. Background Art

[0002] With the development of robotics technology, robots that complete tasks based on mobility have acquired preliminary obstacle-crossing capabilities, such as cleaning robots and delivery robots.

[0003] However, most of the current obstacle control of mobile robots simply identifies the height of obstacles, and activates the obstacle-crossing mechanism when the obstacle is above a certain threshold to perform obstacle-crossing operations. This method is somewhat blind, and the activation timing of the obstacle-crossing mechanism is inaccurate, which easily causes energy waste and component loss of the robot. Summary of the invention

[0004] In view of this, an object of the present disclosure is to provide a control method of a mobile robot, a mobile robot, a device and a storage medium to improve the accuracy of the obstacle crossing strategy of the mobile robot.

[0005] In a first aspect, an embodiment of the present disclosure provides a control method for a mobile robot, the method comprising: during the movement of the mobile robot, detecting whether there is an uncircumventable obstacle in the direction of travel; if there is an uncircumventable obstacle in the direction of travel, identifying a target obstacle traversing position of the uncircumventable obstacle; obtaining morphological information of an obstacle that needs to be traversed when the mobile robot is in the target obstacle traversing position; determining a target obstacle traversing strategy based on the obstacle morphological information; and controlling the mobile robot to traverse the uncircumventable obstacle through the target obstacle traversing strategy.

[0006] In a second aspect, an embodiment of the present disclosure provides a mobile robot, comprising: a detection module, for detecting whether there is an insurmountable obstacle in the direction of travel during the movement of the mobile robot; an identification module, for identifying a target obstacle traversing position of the insurmountable obstacle if there is an insurmountable obstacle in the direction of travel; an acquisition module, for acquiring morphological information of an obstacle that needs to be traversed when the mobile robot is in the target obstacle traversing position; a determination module, for determining a target obstacle traversing strategy based on the obstacle morphological information; and a control module, for controlling the mobile robot to traverse the insurmountable obstacle through the target obstacle traversing strategy.

[0007] In a third aspect, an embodiment of the present disclosure provides a device including a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the above-mentioned mobile robot control method.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the control method of the mobile robot.

[0009] The embodiments of the present disclosure bring the following beneficial effects:

[0010] The control method, mobile robot, device and storage medium of the mobile robot described above perform appropriate obstacle crossing position identification for obstacles that cannot be circumvented in the direction of travel, determine obstacle crossing strategies and perform obstacle crossing control based on the obstacle shape at the obstacle crossing position, thereby reducing unnecessary obstacle crossing control, reducing the loss of obstacle crossing mechanisms and energy, and making the obstacle crossing strategy of the mobile robot more reasonable and accurate.

[0011] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or understood by practicing the present disclosure. The purpose and other advantages of the present disclosure are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0012] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 is a flow chart of an embodiment of a control method for a mobile robot in an embodiment of the present disclosure;

[0015] Figure 2 is a schematic diagram of a control method for a mobile robot in an embodiment of the present disclosure;

[0016] Figure 3 is a flow chart of another embodiment of the control method of the mobile robot in the embodiment of the present disclosure;

[0017] Figure 4 is a flow chart of another embodiment of the control method of the mobile robot in the embodiment of the present disclosure;

[0018] Figure 5 is a flow chart of another embodiment of the control method of the mobile robot in the embodiment of the present disclosure;

[0019] Figure 6 A schematic diagram of a mobile robot provided in an embodiment of the present disclosure;

[0020] Figure 7 A schematic diagram of a device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0022] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] For ease of understanding, the specific process of the embodiment of the present disclosure is described below. Figure 1 , an embodiment of the control method of the mobile robot in the embodiment of the present disclosure includes:

[0024] Step S10: During the movement of the mobile robot, detecting whether there is an obstacle that cannot be circumvented in the direction of travel;

[0025] It is understandable that the mobile robot is equipped with sensors that can be used to collect environmental information and can collect information about obstacles in the environment. For example, cameras, lidars, ultrasonic sensors, infrared sensors, etc. can all be used to perceive obstacles in the environment. The mobile robot can be installed with one or more of them. The information collected by different sensors can be fused to make the detection of obstacles more accurate.

[0026] In this embodiment, the environmental information collected by the environmental perception sensor installed on the mobile robot can be used to detect whether there are obstacles that cannot be circumvented in the direction of travel of the mobile robot. If there are obstacles that cannot be circumvented, the target obstacle crossing position can be identified to cross the obstacles that cannot be circumvented in the environment, which can reduce the obstacle crossing consumption of the mobile robot. For example, the camera installed on the mobile robot can be used to collect images, and the collected images can be used to identify obstacles that cannot be circumvented in the direction of travel and / or the target obstacle crossing position.

[0027] It should be noted that non-circumventable obstacles refer to obstacles for which there is no circumventable path. By detecting non-circumventable obstacles, the blind triggering of the obstacle crossing mechanism of the mobile robot can be reduced. Activating the obstacle crossing mechanism not only wastes energy, but also increases unnecessary losses of the obstacle crossing mechanism, thereby reducing the service life of the mobile robot.

[0028] It can be understood that, for a certain obstacle, if there is a path in the environment that can bypass the obstacle, then the obstacle does not belong to an uncircumventable obstacle, and the mobile robot preferably chooses the bypass path to pass. By detecting uncircumventable obstacles, this embodiment can reduce the occurrence of blind obstacle crossing, reduce energy waste and unnecessary loss of the mobile robot, and increase the service life of the mobile robot.

[0029] In one embodiment, a vision module installed on the mobile robot can be used to detect whether there are any non-circumventable obstacles in the direction of travel of the mobile robot. Specifically, obstacle detection can be performed on the images captured by the vision module first, and then it can be determined based on the obstacle detection result whether there are any obstacles in the direction of travel and whether there is a circumventable path for the existing obstacles. If there are any obstacles in the direction of travel and there is no circumventable path for the existing obstacles, it can be determined that there are any non-circumventable obstacles in the direction of travel.

[0030] Step S20: if there is an obstacle that cannot be circumvented in the direction of travel, identify the target obstacle position of the obstacle that cannot be circumvented;

[0031] In this embodiment, the target obstacle crossing position is an obstacle crossing position that meets preset conditions. The preset conditions can be determined according to actual application scenarios such as different types of mobile robots or the operating environment of the mobile robot. For example, the preset conditions can be the position with the highest probability of crossing the obstacle, the position with the lowest energy consumption for crossing the obstacle, the position with the lowest obstacle, the edge position of the obstacle, the position that can accommodate the size of the mobile robot body, etc. It can be judged by a single condition or by combining multiple conditions, and the specific conditions are not limited here.

[0032] It can be understood that the target obstacle crossing position is the position where the mobile robot starts to execute the target obstacle crossing strategy. By identifying the obstacle crossing position, the mobile robot can cross the obstacle at the appropriate position, reducing the difficulty of obstacle crossing and the probability of obstacle crossing failure. For example, an inappropriate obstacle crossing position may cause the mobile robot to be entangled or stuck. Therefore, the identification of the obstacle crossing position is also a reflection of the improvement of the mobile robot's obstacle crossing ability, which can assist in the determination of the obstacle crossing strategy and make the obstacle crossing strategy more in line with the actual scenario.

[0033] Step S30, obtaining information on the shape of obstacles that the mobile robot needs to cross when it is at a target obstacle crossing position;

[0034] In this embodiment, the obstacle morphological information that the mobile robot needs to cross refers to the local morphological information of the non-circumventable obstacle that the mobile robot needs to cross when crossing the non-circumventable obstacle at the target obstacle crossing position, specifically the local morphological information of the surface of the non-circumventable obstacle that can accommodate the mobile robot to cross.

[0035] For example, the local shape of a non-circumventable obstacle can be Figure 2-Figure 4 As shown, Figure 2 This is a partial diagram of a balcony slide rail. Figure 3 This is a partial diagram of a wooden strip. Figure 4 is a schematic diagram of the local shape of a wire, assuming Figure 2-Figure 4 They are all images collected by the visual module when the mobile robot is at the target obstacle crossing position, containing information on the local shape of the obstacle to be crossed, and are not specifically limited here.

[0036] In one embodiment, obstacle information can be extracted from the overall morphological information of non-circumventable obstacles, or it can be obtained by identifying the morphology of obstacles that need to be crossed at the target obstacle crossing position through a visual module installed on the mobile robot. Obstacle morphological information can also be collected through or in combination with other sensors installed on the mobile robot, and the specific details are not limited here.

[0037] Step S40: determining a target obstacle crossing strategy according to obstacle morphology information;

[0038] In this embodiment, a specific target obstacle crossing strategy can be determined based on the local morphological information of the non-circumventable obstacle that needs to be crossed, wherein the target obstacle crossing strategy is used to indicate the obstacle crossing control parameters of the obstacle crossing mechanism, and the obstacle crossing control parameters are used to indicate the obstacle crossing control method for the mobile robot, specifically including whether to enable the parameters of the obstacle crossing mechanism and the parameters of the obstacle crossing control for the obstacle crossing mechanism.

[0039] As an example and not a limitation, for a mobile robot that lifts to overcome obstacles, the target obstacle crossing strategy may include control parameters such as lifting height, lifting timing, lifting duration, heading angle, drive wheels, etc., which are not specifically limited here.

[0040] As another example, for a mobile robot that can overcome obstacles through driving wheels, the target obstacle-overcoming strategy may include control parameters of the driving wheels, control parameters of the auxiliary obstacle-overcoming mechanism, etc., which are not specifically limited here.

[0041] In one embodiment, the target obstacle crossing strategy can be determined based on one or more of the obstacle's morphological attributes such as obstacle height, width, depth, hardness, deformation difficulty, displacement difficulty, and self-weight in the obstacle morphological information, so that the obstacle crossing strategy of the mobile robot is more accurate.

[0042] Step S50: Control the mobile robot to cross the non-circumventable obstacle through the target obstacle crossing strategy.

[0043] It is understandable that after determining the target obstacle crossing strategy, the mobile robot can be controlled to cross the obstacle to cross the above-mentioned non-circumventable obstacle and complete the obstacle crossing control. In one embodiment, if the mobile robot fails to successfully cross the above-mentioned non-circumventable obstacle after being controlled to cross the obstacle by the target obstacle crossing strategy, then a stronger obstacle crossing strategy can be set based on the target obstacle crossing strategy, and the mobile robot can be controlled to cross the obstacle again until the obstacle crossing strategy used is the strongest obstacle crossing strategy, or the conditions for canceling the obstacle crossing are met, and the obstacle crossing is stopped.

[0044] In one implementation, if the mobile robot fails to overcome an obstacle, an obstacle failure prompt may be provided, such as the mobile robot sounding a warning sound or sending an obstacle failure prompt message to the terminal, etc., which is not limited to the specifics here.

[0045] The control method for the mobile robot provided in the above-mentioned embodiment performs appropriate obstacle crossing position identification for obstacles that cannot be circumvented in the direction of travel, determines the obstacle crossing strategy and performs obstacle crossing control according to the obstacle shape at the obstacle crossing position, which can reduce unnecessary obstacle crossing control, reduce the loss of obstacle crossing mechanism and energy, and make the obstacle crossing strategy of the mobile robot more reasonable and accurate.

[0046] Next, the identification of non-circumventable obstacles and target obstacle surmounting positions is described in detail.

[0047] In one embodiment, the mobile robot is equipped with a vision module, which can simulate the visual function of the human eye, allowing the mobile robot to obtain image information of the surrounding environment and perform analysis and processing. The vision module can include a variety of sensors to achieve more comprehensive visual perception, such as cameras, optical sensors, inertial measurement units (IMU), etc.

[0048] In one embodiment, during the movement of the mobile robot, when detecting whether there is an obstacle that cannot be circumvented in the direction of travel, it includes: during the movement of the mobile robot, detecting obstacles in the direction of travel by using a visual module to obtain obstacle detection results; and determining whether there is an obstacle that cannot be circumvented in the direction of travel based on the obstacle detection results.

[0049] In this embodiment, obstacles in the direction of travel of the mobile robot are detected by a visual module to obtain obstacle detection results, wherein the obstacle detection results can be used to indicate whether there are obstacles in the direction of travel of the mobile robot. Further, when determining whether there are obstacles that cannot be circumvented in the direction of travel according to the obstacle detection results, if the obstacle detection results indicate that there are obstacles in the direction of travel of the mobile robot, a bypass path can be planned for the detected obstacle, and if there is a bypassable path, the detected obstacle is determined to be a circumventable obstacle, otherwise, the detected obstacle is determined to be a non-circumventable obstacle.

[0050] In one embodiment, the obstacle detection result can also be used to indicate whether there is an insurmountable obstacle in the direction of travel of the mobile robot. It can be understood that the visual module can capture environmental images, and perform obstacle recognition on the captured environmental images through an artificial intelligence model to obtain obstacle information, wherein the obstacle information can be used to indicate whether the obstacle is an insurmountable obstacle.

[0051] As an example and not limitation, the artificial intelligence model for obstacle detection is trained with sample data. For example, the sample data may include images marked with non-circumventable obstacles and / or circumventable obstacles. Through training with the sample data, the artificial intelligence model can be used to detect non-circumventable obstacles and / or circumventable obstacles.

[0052] Among them, the basic structure / algorithm of the artificial intelligence model can be any algorithm in the yolo (You Only LookOnce) series of target detection algorithms, a deep learning model including a residual neural network (ResNet), a deep learning model including an Inception structure, a deep learning model including a visual geometry group (VGG) structure, etc., and the specifics are not limited here.

[0053] In one embodiment, the obstacle detection result is used to indicate whether there is an obstacle in the direction of travel and the type of the obstacle; when determining whether there is an uncircumventable obstacle in the direction of travel based on the obstacle detection result, if the obstacle detection result indicates that there is an obstacle in the direction of travel and the type of the obstacle is an uncircumventable obstacle, then it is determined that there is an uncircumventable obstacle in the direction of travel; if the obstacle detection result indicates that there is an obstacle in the direction of travel and the type of the obstacle is a circumventable obstacle, a bypass path planning is performed to obtain a bypass path planning result; if the bypass path planning result indicates that there is no circumventable path, then it is determined that there is an uncircumventable obstacle in the direction of travel.

[0054] In this embodiment, the obstacle detection result includes the type of obstacle, which is divided into circumventable obstacles and non-circumventable obstacles. According to the type of obstacle, it is possible to easily and quickly determine whether the obstacle in the direction of travel is a non-circumventable obstacle. For example, door thresholds, steps, balcony rails, etc. are non-circumventable obstacles, and table and chair legs, carpet folds, wires, etc. are circumventable obstacles, which are not limited here.

[0055] It should be noted that different placement states of circumventable obstacles may also cause the obstacles to be non-circumventable. For example, the placement of electric wires causes the electric wires to be non-circumventable. Therefore, if the obstacle detection result indicates that the type of obstacle existing in the direction of travel is a circumventable obstacle, then a bypass path planning is performed to verify whether there is a circumventable path for the circumventable obstacle, so as to avoid missed detection of non-circumventable obstacles due to different placement states of circumventable obstacles, thereby improving the accuracy of the mobile robot's obstacle surmounting.

[0056] In this embodiment, if there is no circumventable path for the circumventable obstacle, the obstacle in the direction of travel can be determined as a non-circumventable obstacle. It should be noted that bypass path planning is only performed for obstacles of the identified circumventable obstacle type, rather than for all obstacles, which can reduce computing costs and improve detection efficiency.

[0057] In one embodiment, if there is an uncircumventable obstacle in the direction of travel, then identifying the target obstacle surmounting position of the uncircumventable obstacle includes: if there is an uncircumventable obstacle in the direction of travel, then identifying the morphology of the uncircumventable obstacle to obtain the overall morphological information of the uncircumventable obstacle; wherein the overall morphological information includes the height distribution of the uncircumventable obstacle from the supporting surface; and determining the target obstacle surmounting position of the uncircumventable obstacle based on the overall morphological information.

[0058] In this embodiment, when identifying the target obstacle crossing position, the overall morphology of the non-circumventable obstacle is firstly identified to obtain the overall morphological information of the non-circumventable obstacle, including the height distribution of the non-circumventable obstacle from its supporting surface, usually the distribution of the height of the non-circumventable obstacle from the ground.

[0059] It is understandable that the height of obstacles is usually not uniform and may be uneven. By determining the target obstacle crossing position through the height distribution of the non-circumventable obstacles, the best obstacle crossing position of the non-circumventable obstacles, i.e., the target obstacle crossing position, can be found. For example, the obstacle surface to be crossed by the mobile robot at the target obstacle crossing position may be the surface containing the lowest position of the non-circumventable obstacles, the surface with the smallest height change, the surface with the lowest average height and containing the lowest position, etc., and the specifics are not limited here.

[0060] It should be noted that the surface of the obstacle to be crossed by the mobile robot at the target obstacle crossing position is a surface that can accommodate the mobile robot crossing. Specifically, it is described from the perspective of looking down at the mobile robot. Assuming that the moving direction of the mobile robot is the Y-axis direction, then the length of the obstacle surface to be crossed in the X-axis direction must be greater than or equal to the length of the mobile robot's body in the X-axis direction when it crosses the non-circumventable obstacle. This means that the surface of the obstacle to be crossed by the mobile robot at the target obstacle crossing position is a surface that can accommodate the mobile robot crossing.

[0061] In one embodiment, when determining the target obstacle traversing position of a non-circumventable obstacle based on the overall morphological information, the obstacle surface to be traversed with the lowest reference height among the non-circumventable obstacles is determined based on the height distribution in the overall morphological information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be traversed using a specified algorithm; and the supporting surface within the specified range of the obstacle surface to be traversed is determined as the target obstacle traversing position of the non-circumventable obstacle.

[0062] In this embodiment, the reference heights of different obstacle-crossable surfaces are calculated by a specified algorithm, wherein the obstacle-crossable surface refers to a surface that can accommodate the mobile robot to cross. The reference height calculated by the specified algorithm may be the average height, minimum height, maximum height, etc. of the obstacle-crossable surface. Taking the average height as an example, the obstacle surface to be crossed with the lowest reference height is the obstacle-crossable surface with the lowest average height, and taking the minimum height as an example, the obstacle surface to be crossed with the lowest reference height is the obstacle-crossable surface with the lowest minimum height. No specific limitation is made here.

[0063] It is understandable that the support surface within the specified range of the obstacle surface to be crossed can be used as the target obstacle crossing position for the mobile robot to cross the obstacle. Specifically, the specified range can be the range of the size of the mobile robot body when viewed from above, or it can be a range larger than the size of the body when viewed from above, which is not limited here.

[0064] In one embodiment, when obtaining the morphological information of the obstacle that the mobile robot needs to cross, it can be directly extracted from the overall morphological information of the non-circumventable obstacle, or it can be obtained through visual module recognition. It should be noted that the surface of the obstacle to be crossed can be a partial or complete surface of the non-circumventable obstacle, and the specific details are not limited here.

[0065] Next, the control method of the mobile robot is described in detail.

[0066] In one embodiment, the obstacle morphology information is used to indicate: local morphology information of the surface of the obstacle to be crossed of a non-circumventable obstacle; when determining a target obstacle crossing strategy based on the obstacle morphology information, if the target obstacle crossing position intersects with the edge of the non-circumventable obstacle, then identifying a first angle between the surface within a preset range of the edge of the non-circumventable obstacle and the supporting surface; if the first angle is less than or equal to the preset angle, then determining that the target obstacle crossing strategy is direct passage; if the first angle is greater than the preset angle, then determining the target obstacle crossing strategy based on the obstacle morphology information.

[0067] It can be understood that if the target obstacle crossing position intersects with the edge of the non-circumventable obstacle, then the first angle between the surface within a certain range of the edge of the non-circumventable obstacle and the supporting surface of the obstacle can be identified. If the first angle is less than or equal to a certain threshold, it means that there is no need to activate the obstacle crossing mechanism and the obstacle can be crossed directly with the help of friction. At this time, the target obstacle crossing strategy instructs the mobile robot to pass directly.

[0068] In addition, if the first angle is greater than a certain threshold, it means that the probability of the mobile robot directly passing over the obstacle is low, and it is necessary to combine the support surface material information and the obstacle shape information to evaluate the obstacle crossing strategy and obtain the target obstacle crossing strategy.

[0069] In one embodiment, when determining a target obstacle crossing strategy based on obstacle morphology information, a reference height of the obstacle surface to be crossed between the mobile robot and the non-circumventable obstacle is obtained from the obstacle morphology information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be crossed using a specified algorithm; based on the reference height, the obstacle crossing control parameters of the mobile robot are determined to obtain the target obstacle crossing strategy.

[0070] In this embodiment, the reference height of the obstacle surface to be crossed is obtained from the obstacle morphology information, wherein the reference height is calculated in the same manner as the reference height calculation method described above, and the details are not repeated here. In one embodiment, after determining the reference height of the obstacle surface to be crossed, it can be determined whether to enable the obstacle crossing mechanism of the mobile robot. If enabled, the specific obstacle crossing control parameters of the mobile robot are further determined based on the reference height and / or other environmental parameters (such as support surface material information), thereby obtaining a target obstacle crossing strategy for controlling the mobile robot to cross obstacles.

[0071] In one embodiment, when determining the obstacle control parameters of the mobile robot according to the reference height and obtaining the target obstacle crossing strategy, the corresponding obstacle crossing strength can be determined according to the reference height, and then the obstacle crossing control parameters of the corresponding obstacle crossing strength can be determined as the obstacle crossing control parameters of the target obstacle crossing strategy.

[0072] In one embodiment, when determining the obstacle control parameters of the mobile robot according to the reference height and obtaining the target obstacle crossing strategy, it includes: performing material identification on the support surface within the specified range of the target obstacle crossing position to obtain the support surface material information of the target obstacle crossing position; obtaining the first friction parameter of the support surface of the target obstacle crossing position according to the support surface material information; obtaining the corresponding obstacle crossing height range according to the friction strength type in the first friction parameter; wherein the obstacle crossing height range is used to indicate a first surmountable height range corresponding to at least one obstacle strength corresponding to the friction strength type; determining the target surmountable height range to which the reference height belongs from the first surmountable height range; determining the obstacle crossing control parameter corresponding to the obstacle strength according to the obstacle strength corresponding to the target surmountable height range, and obtaining the target obstacle crossing strategy.

[0073] It is understandable that when the mobile robot overcomes an obstacle, support surfaces of different materials will also have an impact on the obstacle-overcoming decision of the mobile robot, among which the most important is the impact of the friction information of the support surface in the support surface material information on the obstacle-overcoming decision. Therefore, in one embodiment, the support surface material information may be the friction information for indicating the support surface, wherein the friction information may be the range, level, or value of the friction, etc., which is not limited here.

[0074] In one embodiment, the material information of the support surface within the specified range of the target obstacle crossing position can also be identified by a visual module installed on the mobile robot, and can also be identified by information collected by other sensors, such as ultrasonic sensors, etc., which are not specifically limited here. It can be understood that when performing material identification on the support surface within the specified range of the target obstacle crossing position to obtain the material information of the support surface at the target obstacle crossing position, the material identification of the support surface within the specified range of the target obstacle crossing position can be performed by an artificial intelligence model, and specifically, the artificial intelligence model can be used to perform image recognition to obtain the material information of the support surface at the target obstacle crossing position, wherein the image can be collected by a visual module or camera installed on the mobile robot.

[0075] In this implementation, the first friction parameter of the support surface can be obtained according to the support surface material information, and the first friction parameter can include the friction strength type, friction strength level or friction value, etc. Specifically, in one implementation, the friction value in the first friction parameter can be calculated according to the friction calculation formula corresponding to the support surface material information, and the friction strength type or friction strength level in the first friction parameter can also be determined according to the friction mapping relationship corresponding to the support surface material information.

[0076] As an example but not limitation, the friction strength types can be divided into three types, namely high strength, medium strength and low strength. The materials corresponding to these three types of friction strength can be carpet, wood and ceramic tile, among which carpet has the highest friction strength and ceramic tile has the lowest friction strength. The specific details are not limited here.

[0077] In this embodiment, different friction strength types correspond to different obstacle height ranges. Different obstacle height ranges can adopt obstacle crossing strategies with different obstacle crossing strengths, where the obstacle height range represents the obstacle height range that can be crossed by different obstacle crossing strengths under the action of the friction force of the corresponding friction strength type.

[0078] For easier understanding, please refer to Figure 5 It can be seen that, assuming that the friction strength types are divided into three types: high friction strength, medium friction strength and low friction strength, then the obstacle height range corresponding to each friction strength type can include the first surmountable height ranges corresponding to the three obstacle strengths, among which the obstacle strength and friction strength type can be divided according to specific needs and are not limited here.

[0079] by Figure 5Taking it as an example, the first passable height ranges corresponding to the three obstacle-crossing strengths from low to high corresponding to the high-intensity friction strength type can include: "less than 3 cm", "3 cm - 4.5 cm", and "greater than 4.5 cm". The first passable height ranges corresponding to the three obstacle-crossing strengths corresponding to the medium-intensity friction strength type can include: "less than 2.5 cm", "2.5 cm - 4 cm", and "greater than 4 cm". The first passable height ranges corresponding to the three obstacle-crossing strengths corresponding to the low-intensity friction strength type can include: "less than 2 cm", "2 cm - 4.5 cm", and "greater than 4.5 cm".

[0080] Figure 5 In the example, the obstacle-crossing height ranges are sorted from low to high according to the obstacle-crossing strength. For example, for the high-intensity friction strength type, an obstacle height of "less than 3 cm" can adopt the obstacle-crossing strategy with the lowest obstacle-crossing strength, an obstacle height of "3 cm - 4.5 cm" can adopt the obstacle-crossing strategy with medium obstacle-crossing strength, and an obstacle height of "greater than 4.5 cm" can adopt the obstacle-crossing strategy with the highest obstacle-crossing strength. The division of the friction strength type, the obstacle-crossing height range, and the obstacle-crossing strength corresponds to each other, and no specific limitation is made.

[0081] Furthermore, assuming that the reference height of the surface of the obstacle to be crossed is 5 cm, the material of the support surface is carpet, and the corresponding friction strength type is high friction strength. Then, since 5 > 4.5, it belongs to the target passable height range of "greater than 4.5 cm", and the corresponding obstacle-crossing strength is high obstacle-crossing strength. Therefore, the obstacle-crossing control parameter of the high obstacle-crossing strength is determined as the obstacle-crossing control parameter of the target obstacle-crossing strategy, and the target obstacle-crossing strategy is the obstacle-crossing strategy of the high obstacle-crossing strength.

[0082] Specifically, by way of example and not limitation, the target obstacle-crossing strategy with low obstacle-crossing strength can be to not activate the obstacle-crossing mechanism of the mobile robot and directly pass by relying on friction; the target obstacle-crossing strategy with medium obstacle-crossing strength can be to activate the obstacle-crossing mechanism of the mobile robot to cross the obstacle; the target obstacle-crossing strategy with high obstacle-crossing strength can be to activate the obstacle-crossing mechanism of the mobile robot and at the same time control the driving wheels of the mobile robot to cross one side driving wheel first and then the other side driving wheel.

[0083] It can be understood that the reference height of the surface of the obstacle to be crossed is the obstacle height. According to the obstacle-crossing strength corresponding to the target passable height range to which the reference height belongs, the preset obstacle-crossing strategy corresponding to the corresponding obstacle-crossing strength can be determined as the target obstacle-crossing strategy. For example, assuming that the obstacle height is 4 cm and the material of the support surface is woolen blanket, 4 cm belongs to the obstacle-crossing height range of "3 cm - 4.5 cm" corresponding to the high-intensity friction strength type, and the obstacle-crossing strategy corresponding to this obstacle-crossing height range with medium obstacle-crossing strength can be determined as the target obstacle-crossing strategy.

[0084] In one embodiment, obstacle overcoming strategies of different obstacle overcoming strengths may be differentiated according to the lifting height of the obstacle overcoming mechanism, or may be differentiated according to other obstacle overcoming control parameters of the obstacle overcoming mechanism, such as the control mode of the obstacle overcoming mechanism, etc., which are not specifically limited here.

[0085] In one embodiment, after controlling the mobile robot to cross an insurmountable obstacle through a target obstacle crossing strategy, if the mobile robot fails to cross the insurmountable obstacle within a preset time period, the obstacle crossing strategy strength is upgraded or the obstacle crossing fallback strategy is enabled according to the obstacle crossing strength of the target obstacle crossing strategy.

[0086] It is understandable that if the mobile robot is controlled to overcome obstacles through the target obstacle crossing strategy, and the mobile robot still fails to overcome the obstacle within a certain period of time, the strength of the obstacle crossing strategy can be upgraded according to the obstacle crossing strength of the target obstacle crossing strategy. If the target obstacle crossing strategy is already the obstacle crossing strategy with the highest obstacle crossing strength, the obstacle crossing back-off strategy is enabled to make the mobile robot return to the target obstacle crossing position or other reference position. After the back-off, it can find a path to bypass the obstacle again to avoid problems such as the robot tipping over due to forced obstacle crossing.

[0087] In one embodiment, when controlling the mobile robot to overcome obstacles, the robot's tilt angle and motion state can be monitored in real time by using an accelerometer and a gyroscope installed on the mobile robot to identify whether the mobile robot is at risk of tilting or tipping over before or during obstacle overcoming. If so, the robot can be adjusted in posture or backed off before or during obstacle overcoming to avoid instability of the robot due to activation of the obstacle overcoming component.

[0088] In one embodiment, after the mobile robot is controlled to cross the non-circumventable obstacle through the target obstacle crossing strategy, if the mobile robot crosses the non-circumventable obstacle, the obstacle crossing strategy used by the mobile robot when crossing the non-circumventable obstacle is recorded.

[0089] It can be understood that if the mobile robot successfully overcomes an insurmountable obstacle through the current obstacle crossing strategy, then the current obstacle crossing strategy and the corresponding obstacle crossing position can be recorded. The next time the mobile robot needs to overcome the same insurmountable obstacle, the recorded obstacle crossing strategy and the corresponding obstacle crossing position can be directly obtained to perform obstacle crossing control, thereby improving the obstacle crossing efficiency of the mobile robot.

[0090] For example, assuming that the material of the supporting surface is a material with high friction strength, such as carpet, if the reference height of the obstacle surface to be crossed is less than 2.5, a low obstacle crossing strength obstacle crossing strategy is used as the target obstacle crossing strategy, that is, direct passage, and the moment when the mobile robot starts to cross the obstacle is recorded. If the obstacle crossing control process exceeds the preset time, such as 5 seconds, and the mobile robot still fails to cross the obstacle successfully, it can return to the target obstacle crossing position or other reference position, and then upgrade the obstacle crossing strategy of the next obstacle crossing strength as the target obstacle crossing strategy, that is, enable the obstacle crossing mechanism to cross the obstacle, and record the medium obstacle crossing strength obstacle crossing strategy used when crossing the non-circumventable obstacle. When executing the task next time, the medium obstacle crossing strength obstacle crossing strategy is directly used to cross the obstacle, thereby improving efficiency.

[0091] Corresponding to the above method embodiment, see Figure 6 A schematic diagram of a mobile robot is shown, the mobile robot comprising: a detection module 60, used to detect whether there is an uncircumventable obstacle in the direction of travel during the movement of the mobile robot; an identification module 62, used to identify the target obstacle traversing position of the uncircumventable obstacle if there is an uncircumventable obstacle in the direction of travel; an acquisition module 64, used to obtain the morphological information of the obstacle that needs to be traversed when the mobile robot is in the target obstacle traversing position; a determination module 66, used to determine the target obstacle traversing strategy based on the obstacle morphological information; and a control module 68, used to control the mobile robot to traverse the uncircumventable obstacle through the target obstacle traversing strategy.

[0092] The above-mentioned mobile robot will only identify the appropriate obstacle crossing position for obstacles that cannot be circumvented in the direction of travel, determine the obstacle crossing strategy and perform obstacle crossing control according to the obstacle shape at the obstacle crossing position, which can reduce unnecessary obstacle crossing control, reduce the loss of obstacle crossing mechanism and energy, and make the obstacle crossing strategy of the mobile robot more reasonable and accurate.

[0093] Optionally, the above-mentioned detection module 60 includes: a detection unit, used to detect obstacles in the traveling direction through a visual module installed on the mobile robot during the movement of the mobile robot, and obtain an obstacle detection result; a determination unit, used to determine whether there is an uncircumventable obstacle in the traveling direction based on the obstacle detection result.

[0094] Optionally, the obstacle detection result is used to indicate whether there is an obstacle in the direction of travel and the type of the obstacle; the above-mentioned determination unit is specifically used to: if the obstacle detection result indicates that there is an obstacle in the direction of travel, and the type of the obstacle is a non-circumventable obstacle, then determine that there is a non-circumventable obstacle in the direction of travel; if the obstacle detection result indicates that there is an obstacle in the direction of travel, and the type of the obstacle is a circumventable obstacle, then perform a bypass path planning to obtain a bypass path planning result; if the bypass path planning result indicates that there is no circumventable path, then determine that there is a non-circumventable obstacle in the direction of travel.

[0095] Optionally, the above-mentioned identification module 62 includes: an identification unit, which is used to perform morphological recognition on the non-circumventable obstacle if there is one in the direction of travel, and obtain the overall morphological information of the non-circumventable obstacle; wherein the overall morphological information includes the height distribution of the non-circumventable obstacle from the supporting surface; and a positioning unit, which is used to determine the target obstacle crossing position of the non-circumventable obstacle based on the overall morphological information.

[0096] Optionally, the above-mentioned positioning unit is specifically used to: determine the obstacle surface to be crossed with the lowest reference height among the non-circumventable obstacles according to the height distribution in the overall morphological information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be crossed by a specified algorithm; and determine the supporting surface within a specified range of the obstacle surface to be crossed as the target obstacle crossing position of the non-circumventable obstacle.

[0097] Optionally, the obstacle morphology information is used to indicate: local morphology information of the obstacle surface to be crossed of the non-circumventable obstacle; the above-mentioned determination module 66 is also used to: if the target obstacle crossing position intersects with the edge of the non-circumventable obstacle, identify the first angle between the surface within a preset range of the edge of the non-circumventable obstacle and the supporting surface; if the first angle is less than or equal to the preset angle, determine that the target obstacle crossing strategy is direct passage; if the first angle is greater than the preset angle, determine the target obstacle crossing strategy according to the obstacle morphology information.

[0098] Optionally, the above-mentioned determination module 66 also includes: a calculation unit, used to obtain a reference height of the obstacle surface to be crossed between the mobile robot and the non-circumventable obstacle from the obstacle morphology information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be crossed using a specified algorithm; and a decision-making unit, used to determine the obstacle crossing control parameters of the mobile robot according to the reference height to obtain a target obstacle crossing strategy.

[0099] Optionally, the above-mentioned policy-making unit is specifically used to: perform material identification on the support surface within the specified range of the target obstacle crossing position to obtain material information of the support surface of the target obstacle crossing position; obtain a first friction parameter of the support surface of the target obstacle crossing position based on the support surface material information; obtain a corresponding obstacle crossing height range based on the friction strength type in the first friction parameter; wherein the obstacle crossing height range is used to indicate a first surmountable height range corresponding to at least one obstacle strength corresponding to the friction strength type; determine the target surmountable height range to which the reference height belongs from the first surmountable height range; determine the obstacle control parameter corresponding to the obstacle strength based on the obstacle strength corresponding to the target surmountable height range, and obtain the target obstacle crossing strategy.

[0100] Optionally, the above-mentioned device also includes: a fault-tolerant module, which is used to upgrade the obstacle crossing strategy strength or enable the obstacle crossing fallback strategy according to the obstacle crossing strength of the target obstacle crossing strategy if the mobile robot fails to cross the non-circumventable obstacle within a preset time period.

[0101] Optionally, the above-mentioned device also includes: a recording module, which is used to record the obstacle crossing strategy adopted by the mobile robot when crossing the non-circumventable obstacle if the mobile robot crosses the non-circumventable obstacle.

[0102] This embodiment also provides a device, including a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the control method of the mobile robot. The device can be a server or a terminal device.

[0103] See also Figure 7 As shown, the device includes a processor 100 and a memory 101. The memory 101 stores machine executable instructions that can be executed by the processor 100. The processor 100 executes the machine executable instructions to implement the above-mentioned mobile robot control method.

[0104] Further, Figure 7 The device shown further includes a bus 102 and a communication interface 103 , and the processor 100 , the communication interface 103 and the memory 101 are connected via the bus 102 .

[0105] The memory 101 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0106] The processor 100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 100. The above processor 100 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and completes the steps of the method of the above embodiment in combination with its hardware, for example:

[0107] During the movement of the mobile robot, it is detected whether there is an uncircumventable obstacle in the direction of travel; if there is an uncircumventable obstacle in the direction of travel, a target obstacle traversing position of the uncircumventable obstacle is identified; the morphological information of the obstacle that needs to be traversed when the mobile robot is in the target obstacle traversing position is obtained; according to the obstacle morphological information, a target obstacle traversing strategy is determined; and the mobile robot is controlled to traverse the uncircumventable obstacle through the target obstacle traversing strategy.

[0108] In this method, only obstacles that cannot be circumvented in the direction of travel are appropriately identified. According to the shape of the obstacle at the obstacle position, the obstacle crossing strategy is determined and obstacle crossing control is performed. This can reduce unnecessary obstacle crossing control, reduce the loss of obstacle crossing mechanism and energy, and make the obstacle crossing strategy of the mobile robot more reasonable and accurate.

[0109] Optionally, the step of detecting whether there are any non-circumventable obstacles in the direction of travel during the movement of the mobile robot includes: during the movement of the mobile robot, performing obstacle detection in the direction of travel by a visual module installed on the mobile robot to obtain an obstacle detection result; and determining whether there are any non-circumventable obstacles in the direction of travel based on the obstacle detection result.

[0110] Optionally, the obstacle detection result is used to indicate whether there is an obstacle in the direction of travel and the type of the obstacle; the step of determining whether there is an uncircumventable obstacle in the direction of travel based on the obstacle detection result includes: if the obstacle detection result indicates that there is an obstacle in the direction of travel and the type of the obstacle is an uncircumventable obstacle, then determining that there is an uncircumventable obstacle in the direction of travel; if the obstacle detection result indicates that there is an obstacle in the direction of travel and the type of the obstacle is a circumventable obstacle, performing a bypass path planning to obtain a bypass path planning result; if the bypass path planning result indicates that there is no circumventable path, then determining that there is an uncircumventable obstacle in the direction of travel.

[0111] Optionally, if there is an uncircumventable obstacle in the direction of travel, the step of identifying the target obstacle surmounting position of the uncircumventable obstacle includes: if there is an uncircumventable obstacle in the direction of travel, performing morphological identification on the uncircumventable obstacle to obtain overall morphological information of the uncircumventable obstacle; wherein the overall morphological information includes the height distribution of the uncircumventable obstacle from a supporting surface; and determining the target obstacle surmounting position of the uncircumventable obstacle based on the overall morphological information.

[0112] Optionally, the step of determining a target obstacle traversing position of the non-circumventable obstacle based on the overall morphology information includes: determining an obstacle surface to be traversed with the lowest reference height in the non-circumventable obstacle based on the height distribution in the overall morphology information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be traversed using a specified algorithm; and determining a supporting surface within a specified range of the obstacle surface to be traversed as the target obstacle traversing position of the non-circumventable obstacle.

[0113] Optionally, the obstacle morphology information is used to indicate: local morphology information of the obstacle surface to be crossed of the non-circumventable obstacle; the step of determining the target obstacle circumventing strategy based on the obstacle morphology information includes: if the target obstacle circumventing position intersects with the edge of the non-circumventable obstacle, identifying a first angle between a surface within a preset range of the edge of the non-circumventable obstacle and a supporting surface; if the first angle is less than or equal to a preset angle, determining that the target obstacle circumventing strategy is direct passage; if the first angle is greater than a preset angle, determining the target obstacle circumventing strategy based on the obstacle morphology information.

[0114] Optionally, the step of determining a target obstacle crossing strategy based on the obstacle morphology information includes: obtaining a reference height of the obstacle surface to be crossed between the mobile robot and the non-circumventable obstacle from the obstacle morphology information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be crossed using a specified algorithm; and determining the obstacle crossing control parameters of the mobile robot based on the reference height to obtain the target obstacle crossing strategy.

[0115] Optionally, the step of determining the obstacle crossing control parameters of the mobile robot according to the reference height to obtain a target obstacle crossing strategy includes: performing material identification on the supporting surface within a specified range of the target obstacle crossing position to obtain material information of the supporting surface of the target obstacle crossing position; obtaining a first friction parameter of the supporting surface of the target obstacle crossing position according to the supporting surface material information; obtaining a corresponding obstacle crossing height range according to a friction strength type in the first friction parameter; wherein the obstacle height range is used to indicate a first surmountable height range corresponding to at least one obstacle strength corresponding to the friction strength type; determining from the first surmountable height range the target surmountable height range to which the reference height belongs; and determining the obstacle crossing control parameters of the corresponding obstacle strength according to the obstacle strength corresponding to the target surmountable height range to obtain a target obstacle crossing strategy.

[0116] Optionally, after the step of controlling the mobile robot to cross the non-circumventable obstacle through the target obstacle crossing strategy, the method further includes: if the mobile robot fails to cross the non-circumventable obstacle within a preset time period, upgrading the obstacle crossing strategy strength or enabling an obstacle crossing fallback strategy according to the obstacle crossing strength of the target obstacle crossing strategy.

[0117] Optionally, after the step of controlling the mobile robot to cross the non-circumventable obstacle through the target obstacle crossing strategy, the method further includes: if the mobile robot crosses the non-circumventable obstacle, recording the obstacle crossing strategy adopted by the mobile robot when crossing the non-circumventable obstacle.

[0118] This embodiment further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the control method of the mobile robot, for example:

[0119] During the movement of the mobile robot, it is detected whether there is an uncircumventable obstacle in the direction of travel; if there is an uncircumventable obstacle in the direction of travel, a target obstacle traversing position of the uncircumventable obstacle is identified; the morphological information of the obstacle that needs to be traversed when the mobile robot is in the target obstacle traversing position is obtained; according to the obstacle morphological information, a target obstacle traversing strategy is determined; and the mobile robot is controlled to traverse the uncircumventable obstacle through the target obstacle traversing strategy.

[0120] In this method, only obstacles that cannot be circumvented in the direction of travel are appropriately identified. According to the shape of the obstacle at the obstacle position, the obstacle crossing strategy is determined and obstacle crossing control is performed. This can reduce unnecessary obstacle crossing control, reduce the loss of obstacle crossing mechanism and energy, and make the obstacle crossing strategy of the mobile robot more reasonable and accurate.

[0121] Optionally, the step of detecting whether there are any non-circumventable obstacles in the direction of travel during the movement of the mobile robot includes: during the movement of the mobile robot, performing obstacle detection in the direction of travel by a visual module installed on the mobile robot to obtain an obstacle detection result; and determining whether there are any non-circumventable obstacles in the direction of travel based on the obstacle detection result.

[0122] Optionally, the obstacle detection result is used to indicate whether there is an obstacle in the direction of travel and the type of the obstacle; the step of determining whether there is an uncircumventable obstacle in the direction of travel based on the obstacle detection result includes: if the obstacle detection result indicates that there is an obstacle in the direction of travel and the type of the obstacle is an uncircumventable obstacle, then determining that there is an uncircumventable obstacle in the direction of travel; if the obstacle detection result indicates that there is an obstacle in the direction of travel and the type of the obstacle is a circumventable obstacle, performing a bypass path planning to obtain a bypass path planning result; if the bypass path planning result indicates that there is no circumventable path, then determining that there is an uncircumventable obstacle in the direction of travel.

[0123] Optionally, if there is an uncircumventable obstacle in the direction of travel, the step of identifying the target obstacle surmounting position of the uncircumventable obstacle includes: if there is an uncircumventable obstacle in the direction of travel, performing morphological identification on the uncircumventable obstacle to obtain overall morphological information of the uncircumventable obstacle; wherein the overall morphological information includes the height distribution of the uncircumventable obstacle from a supporting surface; and determining the target obstacle surmounting position of the uncircumventable obstacle based on the overall morphological information.

[0124] Optionally, the step of determining a target obstacle traversing position of the non-circumventable obstacle based on the overall morphology information includes: determining an obstacle surface to be traversed with the lowest reference height in the non-circumventable obstacle based on the height distribution in the overall morphology information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be traversed using a specified algorithm; and determining a supporting surface within a specified range of the obstacle surface to be traversed as the target obstacle traversing position of the non-circumventable obstacle.

[0125] Optionally, the obstacle morphology information is used to indicate: local morphology information of the obstacle surface to be crossed of the non-circumventable obstacle; the step of determining the target obstacle circumventing strategy based on the obstacle morphology information includes: if the target obstacle circumventing position intersects with the edge of the non-circumventable obstacle, identifying a first angle between a surface within a preset range of the edge of the non-circumventable obstacle and a supporting surface; if the first angle is less than or equal to a preset angle, determining that the target obstacle circumventing strategy is direct passage; if the first angle is greater than a preset angle, determining the target obstacle circumventing strategy based on the obstacle morphology information.

[0126] Optionally, the step of determining a target obstacle crossing strategy based on the obstacle morphology information includes: obtaining a reference height of the obstacle surface to be crossed between the mobile robot and the non-circumventable obstacle from the obstacle morphology information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be crossed using a specified algorithm; and determining the obstacle crossing control parameters of the mobile robot based on the reference height to obtain the target obstacle crossing strategy.

[0127] Optionally, the step of determining the obstacle crossing control parameters of the mobile robot according to the reference height to obtain a target obstacle crossing strategy includes: performing material identification on the supporting surface within a specified range of the target obstacle crossing position to obtain material information of the supporting surface of the target obstacle crossing position; obtaining a first friction parameter of the supporting surface of the target obstacle crossing position according to the supporting surface material information; obtaining a corresponding obstacle crossing height range according to a friction strength type in the first friction parameter; wherein the obstacle height range is used to indicate a first surmountable height range corresponding to at least one obstacle strength corresponding to the friction strength type; determining from the first surmountable height range the target surmountable height range to which the reference height belongs; and determining the obstacle crossing control parameters of the corresponding obstacle strength according to the obstacle strength corresponding to the target surmountable height range to obtain a target obstacle crossing strategy.

[0128] Optionally, after the step of controlling the mobile robot to cross the non-circumventable obstacle through the target obstacle crossing strategy, the method further includes: if the mobile robot fails to cross the non-circumventable obstacle within a preset time period, upgrading the obstacle crossing strategy strength or enabling an obstacle crossing fallback strategy according to the obstacle crossing strength of the target obstacle crossing strategy.

[0129] Optionally, after the step of controlling the mobile robot to cross the non-circumventable obstacle through the target obstacle crossing strategy, the method further includes: if the mobile robot crosses the non-circumventable obstacle, recording the obstacle crossing strategy adopted by the mobile robot when crossing the non-circumventable obstacle.

[0130] The computer program products of the mobile robot control method, mobile robot, device and storage medium provided in the embodiments of the present disclosure include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments, which will not be repeated here.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system and mobile robot described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0132] In addition, in the description of the embodiments of the present disclosure, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present disclosure can be understood according to specific circumstances.

[0133] If the functions are implemented in the form of software functional units 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 disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0134] In the description of the present disclosure, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the mobile robot or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present disclosure. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0135] Finally, it should be noted that the above embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above embodiments, those skilled in the art should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A control method for a mobile robot, characterized in that: The method comprises: During the movement of the mobile robot, detecting whether there is an obstacle that cannot be circumvented in the direction of travel; If there is an obstacle that cannot be circumvented in the direction of travel, the target obstacle circumvention position of the obstacle is identified; Obtaining information on the shape of obstacles that the mobile robot needs to cross when it is at the target obstacle crossing position; Determining a target obstacle crossing strategy according to the obstacle morphology information; The mobile robot is controlled to cross the non-circumventable obstacle through the target obstacle crossing strategy.

2. The method according to claim 1, characterized in that The step of detecting whether there is an obstacle that cannot be circumvented in the moving direction of the mobile robot during its movement includes: During the movement of the mobile robot, obstacle detection in the moving direction is performed by a visual module installed on the mobile robot to obtain an obstacle detection result; According to the obstacle detection result, it is determined whether there is an unavoidable obstacle in the traveling direction.

3. The method according to claim 2, characterized in that The obstacle detection result is used to indicate whether there is an obstacle in the traveling direction and the type of the obstacle; The step of determining whether there is an unavoidable obstacle in the direction of travel according to the obstacle detection result comprises: If the obstacle detection result indicates that there is an obstacle in the direction of travel, and the type of the obstacle is an obstacle that cannot be circumvented, determining that there is an obstacle that cannot be circumvented in the direction of travel; If the obstacle detection result indicates that there is an obstacle in the direction of travel, and the type of the obstacle is a circumventable obstacle, then a bypass path planning is performed to obtain a bypass path planning result; If the detour path planning result indicates that there is no detour path, it is determined that there is an unavoidable obstacle in the direction of travel.

4. The method according to claim 1, characterized in that: If there is an obstacle that cannot be circumvented in the direction of travel, the step of identifying the target obstacle circumvention position of the obstacle that cannot be circumvented includes: If there is an obstacle that cannot be circumvented in the direction of travel, the morphology of the obstacle that cannot be circumvented is identified to obtain overall morphological information of the obstacle that cannot be circumvented; wherein the overall morphological information includes the height distribution of the obstacle from the support surface; A target obstacle surmounting position of the non-circumventable obstacle is determined according to the overall morphological information.

5. The method according to claim 4, characterized in that The step of determining the target obstacle surmounting position of the non-circumventable obstacle according to the overall morphological information comprises: Determine, according to the height distribution in the overall morphology information, the obstacle surface to be crossed with the lowest reference height among the non-circumventable obstacles; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be crossed using a specified algorithm; The support surface within the specified range of the surface of the obstacle to be crossed is determined as the target obstacle crossing position of the non-circumventable obstacle.

6. The method according to claim 1, characterized in that The obstacle shape information is used to indicate: local shape information of the obstacle surface to be crossed of the non-circumventable obstacle; The step of determining a target obstacle crossing strategy according to the obstacle morphology information comprises: If the target obstacle crossing position intersects with the edge of the non-circumventable obstacle, identifying a first angle between a surface within a preset range of the edge of the non-circumventable obstacle and a supporting surface; If the first angle is less than or equal to the preset angle, determining the target obstacle crossing strategy to be direct passage; If the first angle is greater than a preset angle, a target obstacle crossing strategy is determined according to the obstacle shape information.

7. The method according to claim 1, characterized in that The step of determining a target obstacle crossing strategy according to the obstacle morphology information comprises: Acquire a reference height of the obstacle surface to be crossed between the mobile robot and the non-circumventable obstacle from the obstacle morphology information; wherein the reference height is obtained by calculating the height distribution of the obstacle surface to be crossed using a specified algorithm; According to the reference height, the obstacle crossing control parameters of the mobile robot are determined to obtain a target obstacle crossing strategy.

8. The method according to claim 7, characterized in that The step of determining the obstacle crossing control parameters of the mobile robot according to the reference height to obtain a target obstacle crossing strategy comprises: Performing material identification on the support surface within the specified range of the target obstacle crossing position to obtain material information of the support surface at the target obstacle crossing position; Acquire a first friction parameter of the support surface at the target obstacle crossing position according to the support surface material information; According to the friction strength type in the first friction parameter, a corresponding obstacle crossing height range is obtained; wherein the obstacle crossing height range is used to indicate a first surmountable height range corresponding to at least one obstacle crossing strength corresponding to the friction strength type; Determine, from the first traversable altitude range, a target traversable altitude range to which the reference altitude belongs; According to the obstacle crossing intensity corresponding to the target surmountable height range, an obstacle crossing control parameter corresponding to the obstacle crossing intensity is determined to obtain a target obstacle crossing strategy.

9. The method according to claim 1, characterized in that: After the step of controlling the mobile robot to cross the non-circumventable obstacle by using the target obstacle crossing strategy, the method further includes: If the mobile robot fails to cross the non-circumventable obstacle within a preset time period, the obstacle crossing strategy strength is upgraded or the obstacle crossing fallback strategy is activated according to the obstacle crossing strength of the target obstacle crossing strategy.

10. The method according to claim 1, characterized in that After the step of controlling the mobile robot to cross the non-circumventable obstacle by using the target obstacle crossing strategy, the method further includes: If the mobile robot crosses the non-circumventable obstacle, the obstacle crossing strategy adopted by the mobile robot when crossing the non-circumventable obstacle is recorded.

11. A mobile robot, characterized in that: The mobile robot comprises: A detection module, used to detect whether there is an obstacle that cannot be circumvented in the moving direction of the mobile robot during its movement; An identification module, configured to identify a target obstacle surmounting position of an obstacle that cannot be circumvented if there is one in the direction of travel; An acquisition module, used to acquire information on the shape of obstacles that the mobile robot needs to cross when it is at the target obstacle crossing position; A determination module, used to determine a target obstacle crossing strategy according to the obstacle morphology information; The control module is used to control the mobile robot to cross the non-circumventable obstacle through the target obstacle crossing strategy.

12. A device, characterized in that: It comprises a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the control method of the mobile robot according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the control method of the mobile robot according to any one of claims 1 to 10.

Images