A mobile robot repositioning method, a mobile robot system, and an electronic device

Abstract

Embodiments of the present application provide a mobile robot repositioning method, a mobile robot system and an electronic device. The method is applied to the technical field of mobile robots, and comprises: obtaining description information of a specified sound wave received by a mobile robot as first description information; wherein the description information represents characteristic information of the specified sound wave when it reaches the mobile robot; determining a pose corresponding to the first description information as a first pose based on a pre-constructed correspondence between description information and poses; wherein the correspondence between the description information and the poses is constructed based on description information of the specified sound wave received by the mobile robot in different poses; and determining a current pose of the mobile robot with the first pose as an initial pose. Through the present solution, the repositioning efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mobile robots, and in particular to a mobile robot repositioning method, a mobile robot system, and an electronic device. BACKGROUND

[0002] The mobile robot repositioning refers to determining a mobile robot pose in a pre-constructed environment map.

[0003] In related technologies, a global iterative search is usually used for repositioning. In simple terms, when the method provided by the related technology is used for repositioning, a random pose is generated as an initial pose, and a global iterative search is performed on the environment map starting from the initial pose.

[0004] It can be seen that, starting from a randomly generated pose as an initial pose, a global iterative search is undoubtedly low in efficiency. SUMMARY

[0005] The embodiments of the present application aim to provide a mobile robot repositioning method, a mobile robot system, and an electronic device to improve the repositioning efficiency. The specific technical solutions are as follows.

[0006] In a first aspect, the embodiments of the present application provide a mobile robot repositioning method, which comprises:

[0007] Obtaining description information of a specified sound wave received by a mobile robot as first description information, wherein the description information represents feature information of the specified sound wave when it reaches the mobile robot;

[0008] Determining a pose corresponding to the first description information as a first pose based on a pre-constructed correspondence between description information and poses, wherein the correspondence between description information and poses is constructed based on description information of the specified sound wave received by the mobile robot in different poses;

[0009] Determining a current pose of the mobile robot with the first pose as an initial pose.

[0010] Optionally, before the step of obtaining description information of a specified sound wave received by a mobile robot as first description information, the method further comprises:

[0011] Judging whether the mobile robot is in an extreme environment, wherein the extreme environment is an environment that is not suitable for repositioning;

[0012] If the mobile robot is not in the extreme environment, the step of obtaining description information of a specified sound wave received by the mobile robot as first description information is performed.

[0013] Optionally, after determining whether the mobile robot is in an extreme environment, the method further comprises:

[0014] If the mobile robot is in the extreme environment, controlling the mobile robot to move to a non-extreme environment; wherein the non-extreme environment is an environment suitable for repositioning;

[0015] After the mobile robot moves to the non-extreme environment, performing the step of obtaining the description information of the specified sound wave received by the mobile robot as first description information.

[0016] Optionally, the step of controlling the mobile robot to move to a non-extreme environment comprises:

[0017] Obtaining the description information of the specified sound wave received by the mobile robot when the mobile robot is in the extreme environment as second description information;

[0018] Determining the pose corresponding to the second description information as a second pose based on the correspondence between the description information and the pose;

[0019] Controlling the mobile robot to move to the non-extreme environment based on the second pose.

[0020] Optionally, the step of determining whether the mobile robot is in an extreme environment comprises:

[0021] Obtaining an image collected by the mobile robot;

[0022] Determining whether the mobile robot is in an extreme environment based on the obtained image.

[0023] Optionally, the step of determining whether the mobile robot is in an extreme environment based on the obtained image comprises:

[0024] Extracting feature points contained in the obtained image;

[0025] When the proportion of the number of specified feature points in the extracted feature points is greater than a first threshold value, determining that the mobile robot is in an extreme environment, otherwise, determining that the mobile robot is in a non-extreme environment;

[0026] wherein the specified feature point is a feature point whose proportion of similar feature points is greater than a second threshold value among the extracted feature points; and the similar feature point of each feature point is a feature point whose distance from the feature point is less than a specified distance in a feature space.

[0027] Optionally, the step of controlling the mobile robot to move to the non-extreme environment based on the second pose comprises:

[0028] determine a moving path for moving the mobile robot to the non-extreme environment based on the second pose;

[0029] control the mobile robot to move according to the moving path.

[0030] Optionally, the correspondence between the description information and the pose is constructed in the following manner, comprising:

[0031] for each position to which the mobile robot moves in the mapping stage, acquire description information of the specified sound wave received by the mobile robot at the position, and determine a current pose of the mobile robot, and combine the position and the determined pose as a pose corresponding to the acquired description information.

[0032] Optionally, the description information comprises a time difference of arrival of the specified sound wave; wherein the time difference of arrival is a time difference between which two sound wave receiving devices in the mobile robot receive the specified sound wave.

[0033] the determination of the current pose of the mobile robot comprises:

[0034] determine a pose angle of the mobile robot relative to a sound line of the specified sound wave based on the time difference of arrival in the acquired description information and a relative distance between the different sound wave receiving devices in the mobile robot.

[0035] determine the pose of the mobile robot based on the pose angle and a pose of a specified sound emitting device; wherein the specified sound emitting device is a device that emits the specified sound wave.

[0036] Optionally, the mobile robot comprises two sound wave receiving devices.

[0037] the determination of the pose angle of the mobile robot relative to the sound line of the received sound wave based on the time difference of arrival in the acquired description information and the relative distance between the different sound wave receiving devices in the mobile robot comprises:

[0038] determine the pose angle of the mobile robot relative to the sound line of the specified sound wave by using the following formula:

[0039]

[0040] wherein φ is the pose angle of the mobile robot relative to the sound line of the specified sound wave, Δt is the time difference of arrival in the acquired description information, and L is the relative distance between the two sound wave receiving devices in the mobile robot.

[0041] Optionally, in the correspondence between the description information and the pose, each description information is classified into multiple categories according to a corresponding position in a feature space.

[0042] The correspondence between the description information and the pose is constructed based on the description information received by the mobile robot at different poses.

[0043] From the multiple categories, a category to which the first description information belongs is determined as a target category.

[0044] From each description information belonging to the target category, a description information matched with the first description information is determined, and a pose corresponding to the determined description information is determined as the pose corresponding to the first description information.

[0045] Optionally, the current pose of the mobile robot is determined by taking the first pose as an initial pose.

[0046] The pose of the mobile robot is determined as a third pose by taking the first pose as an initial pose of a first repositioning algorithm, wherein the first repositioning algorithm is at least one of an image repositioning algorithm and a laser radar repositioning algorithm.

[0047] The pose of the mobile robot is determined as the current pose of the mobile robot by taking the third pose as an initial pose of a second repositioning algorithm.

[0048] The second repositioning algorithm is different from the first repositioning algorithm.

[0049] In a second aspect, an embodiment of the present application provides a mobile robot system, comprising:

[0050] An acoustic wave receiving module is configured to acquire description information of a specified acoustic wave received by a mobile robot as first description information, wherein the description information represents feature information of the specified acoustic wave when the specified acoustic wave reaches the mobile robot.

[0051] A processor is configured to determine a pose corresponding to the first description information as a first pose based on a pre-constructed correspondence between description information and a pose, and determine a current pose of the mobile robot by taking the first pose as an initial pose.

[0052] The correspondence between the description information and the pose is constructed based on the description information received by the mobile robot at different poses.

[0053] Optionally, the processor is further configured to determine whether the mobile robot is in an extreme environment before the sound wave receiving module performs the step of obtaining the description information of the specified sound wave received by the mobile robot as the first description information; if the mobile robot is not in the extreme environment, the sound wave receiving module is called to perform the step of obtaining the description information of the specified sound wave received by the mobile robot as the first description information; wherein the extreme environment is an environment that is not suitable for repositioning.

[0054] Optionally, the method further comprises:

[0055] a power module configured to drive the mobile robot to move to a non-extreme environment under the control of the processor.

[0056] The processor is further configured to control the power module to move if the mobile robot is in the extreme environment after the step of determining whether the mobile robot is in an extreme environment; and call the sound wave receiving module to perform the step of obtaining the description information of the specified sound wave received by the mobile robot as the first description information after the mobile robot moves to the non-extreme environment; wherein the non-extreme environment is an environment suitable for repositioning using the repositioning algorithm.

[0057] Optionally, the sound wave receiving module is further configured to obtain the description information of the specified sound wave received by the mobile robot in the extreme environment as the second description information.

[0058] The processor is configured to determine a pose corresponding to the second description information as a second pose based on the correspondence between the description information and the pose, and control the mobile robot to move to the non-extreme environment based on the second pose.

[0059] Optionally, the method further comprises an image acquisition module configured to acquire images, and the processor is further configured to acquire the images acquired by the image acquisition module and determine whether the mobile robot is in an extreme environment based on the acquired images.

[0060] Optionally, the processor is specifically configured to extract feature points contained in the acquired images; when the proportion of the number of specified feature points in the extracted feature points is greater than a first threshold value, it is determined that the mobile robot is in an extreme environment, otherwise, it is determined that the mobile robot is in a non-extreme environment; wherein the specified feature points are feature points whose proportion of similar feature points is greater than a second threshold value among the extracted feature points; and the similar feature points of each feature point are feature points whose distance from the feature point is less than a specified distance in a feature space.

[0061] Optionally, the processor is specifically configured to determine a moving path of the mobile robot to the non-extreme environment based on the second pose; and control the mobile robot to move according to the moving path.

[0062] Optionally, the processor is further configured to establish the correspondence between the description information and the pose in the following manner: for each position to which the mobile robot moves in the mapping stage, obtaining description information of the specified sound wave received by the mobile robot at the position, determining a current pose of the mobile robot, and merging the position and the determined pose as a pose corresponding to the obtained description information.

[0063] Optionally, the description information comprises a time difference of arrival of the specified sound wave; wherein the time difference of arrival is a time difference between which two sound wave receiving devices in the mobile robot receive the specified sound wave.

[0064] The processor is specifically configured to determine a pose angle of the mobile robot relative to a sound line of the specified sound wave based on the time difference of arrival in the obtained description information and a relative distance between the different sound wave receiving devices in the mobile robot; and determine a pose of the mobile robot based on the pose angle and a pose of a specified sound emitting device.

[0065] Optionally, the mobile robot comprises two sound wave receiving devices.

[0066] The processor is specifically configured to determine the pose angle of the mobile robot relative to the sound line of the specified sound wave by using the following formula:

[0067]

[0068] wherein φ is the pose angle of the mobile robot relative to the sound line of the specified sound wave, Δt is the time difference of arrival in the obtained description information, and L is the relative distance between the two sound wave receiving devices in the mobile robot.

[0069] Optionally, in the correspondence between the description information and the pose, each description information is classified into a plurality of categories according to a corresponding position in a feature space.

[0070] The processor is specifically configured to determine a category to which the first description information belongs as a target category from the plurality of categories; determine description information matching the first description information from each description information belonging to the target category; and determine a pose corresponding to the determined description information as a pose corresponding to the first description information.

[0071] Optionally, the processor is specifically configured to: determine the pose of the mobile robot as a third pose by taking the first pose as an initial pose of a first repositioning algorithm; and determine the pose of the mobile robot as a current pose of the mobile robot by taking the third pose as an initial pose of a second repositioning algorithm; wherein the first repositioning algorithm is at least one of an image repositioning algorithm and a laser radar repositioning algorithm; and the second repositioning algorithm is a repositioning algorithm different from the first repositioning algorithm among the image repositioning algorithm and the laser radar repositioning algorithm.

[0072] In a third aspect, an electronic device is provided, and the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus.

[0073] The memory is configured to store a computer program.

[0074] The processor is configured to execute the program stored in the memory, and implement the method steps of any one of the first aspect.

[0075] The embodiments of the present application have the following beneficial effects:

[0076] The mobile robot repositioning method, the mobile robot system and the electronic device provided by the embodiments of the present application can obtain the description information of the specified sound wave received by the mobile robot, and then determine the first pose corresponding to the first description information based on the correspondence between the description information and the pose constructed in advance, and determine the current pose of the mobile robot by taking the first pose as the initial pose. It can be seen that the embodiments of the present application can realize rough estimation of the pose of the mobile robot through the description information of the specified sound wave received by the mobile robot, and then take the first pose as the initial pose, so that the iterative search can start from the first pose, avoiding global search of the environment map. It can be seen that, compared with the global iterative search method, the embodiments of the present application can improve the efficiency of the mobile robot repositioning.

[0077] Of course, implementing any product or method of the present application does not necessarily require achieving all the advantages described above. BRIEF DESCRIPTION OF DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and other embodiments can also be obtained by those skilled in the art according to these drawings.

[0079] Figure 1A flowchart of the mobile robot repositioning method provided by the embodiment of the present application;

[0080] Figure 2 Another flowchart of the mobile robot repositioning method provided by the embodiment of the present application;

[0081] Figure 3 A schematic diagram of a repetitive texture provided by the embodiment of the present application;

[0082] Figure 4 A schematic diagram of a mobile robot movement provided by the embodiment of the present application;

[0083] Figure 5 A schematic diagram of a mobile robot sound wave receiving provided by the embodiment of the present application;

[0084] Figure 6 Another flowchart of the mobile robot repositioning method provided by the embodiment of the present application;

[0085] Figure 7 A schematic diagram of description information clustering provided by the embodiment of the present application;

[0086] Figure 8 Another flowchart of the mobile robot repositioning method provided by the embodiment of the present application;

[0087] Figure 9 A schematic diagram of a scene provided by the embodiment of the present application;

[0088] Figure 10 A schematic diagram of the structure of the mobile robot system provided by the embodiment of the present application;

[0089] Figure 11 A schematic diagram of the structure of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0090] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art based on the present application are within the scope of protection of the present application.

[0091] In order to improve the efficiency of repositioning, the embodiment of the present application provides a mobile robot repositioning method, a mobile robot system and an electronic device.

[0092] It should be noted that in specific applications, the embodiments of the present application can be applied to mobile robots, such as service robots or welcome robots. Alternatively, the mobile robot repositioning method provided by the embodiments of the present application can also be applied to other various electronic devices, such as smart phones, personal computers, servers, and other devices with data processing capabilities. It should be noted that when applied to other various electronic devices, the electronic device can communicate with the mobile robot, so that the description information of the specified sound wave received by the mobile robot can be obtained, and the mobile robot can be controlled to move. Moreover, the mobile robot repositioning method provided by the embodiments of the present application can be realized by software, hardware or a combination of software and hardware; wherein the above specified sound wave can be emitted by a specified sound emitting device.

[0093] Among them, the mobile robot repositioning method provided by the embodiments of the present application can include:

[0094] Obtain the description information of the specified sound wave received by the mobile robot as the first description information; wherein the description information represents the characteristic information of the specified sound wave when it reaches the mobile robot;

[0095] Determine the pose corresponding to the first description information as the first pose based on the pre-constructed correspondence between the description information and the pose; wherein the correspondence between the description information and the pose is constructed based on the description information of the specified sound wave received by the mobile robot in different poses;

[0096] Determine the current pose of the mobile robot with the first pose as the initial pose.

[0097] In the above scheme provided by the embodiments of the present application, the description information of the specified sound wave received by the mobile robot can be used to roughly estimate the pose of the mobile robot, and then the first pose is used as the initial pose, so that the iterative search can start from the first pose, avoiding global search of the environment map. Therefore, compared with the global iterative search method, the efficiency of the mobile robot repositioning can be improved.

[0098] The mobile robot repositioning method provided by the embodiments of the present application will be described in detail below in conjunction with the drawings of the specification.

[0099] As shown in Figure 1 The mobile robot repositioning method provided by the embodiments of the present application can include steps S101-S103, wherein:

[0100] S101, obtain the description information of the specified sound wave received by the mobile robot as the first description information;

[0101] The description information represents characteristic information when the specified sound wave reaches the mobile robot.

[0102] In the embodiment of the present application, when the mobile robot needs to be repositioned, the mobile robot can receive the specified sound wave emitted by the specified sound emitting device in the target scene where the mobile robot is located.

[0103] In one implementation, when the embodiment of the present application is applied to the mobile robot, after receiving the specified sound wave, the mobile robot can determine the description information of the received specified sound wave. In another implementation, when the embodiment of the present application is applied to the electronic device independent of the mobile robot, after the mobile robot receives the specified sound wave, the description information of the received specified sound wave can be determined by the mobile robot, and then the electronic device communicates with the mobile robot to obtain the description information of the received specified sound wave from the mobile robot.

[0104] The target scene can be an indoor scene where the mobile robot moves, such as a living room, a bedroom, an office, etc. The sound emitting device in the target scene can be pre-installed in the scene, which can actively or passively emit the specified sound wave to the target scene.

[0105] In one implementation, in order to more accurately estimate the first pose of the mobile robot, the specified sound wave can include multiple specified sound waves, so that the description information of each received specified sound wave of the mobile robot can be obtained.

[0106] In the case of including multiple specified sound waves, each specified sound wave can be emitted by a single specified sound emitting device, which means that multiple specified sound emitting devices are provided in the target scene. For example, three specified sound emitting devices are installed in the target scene, which respectively emit specified sound wave 1, specified sound wave 2 and specified sound wave 3 to the target scene, and the first description information can include the description information of the specified sound wave 1, the description information of the specified sound wave 2 and the description information of the specified sound wave 3.

[0107] In an implementation, the description information of each specified sound wave can include at least one of a time difference of arrival (TDOA) and a sound intensity of the sound wave. The TDOA of the sound wave can be a time difference between which two sound receivers in the mobile robot receive the specified sound wave. For example, the mobile robot can include two sound receivers, a sound receiver 1 and a sound receiver 2. The TDOA of the sound wave can be |T1-T2|, where T1 is a time at which the sound receiver 1 receives the specified sound wave, and T2 is a time at which the sound receiver 2 receives the specified sound wave. The sound intensity can be an average energy flow density of the specified sound wave at a current position of the mobile robot, and can be used to describe a strength of the sound. The sound intensity can be represented by a sound energy per unit area per unit time, and can be measured in W / m2. 2 .

[0108] When the description information includes both the TDOA and the sound intensity, the specified sound waves in the target scene can include a specified sound wave 1, a specified sound wave 2, and a specified sound wave 3. The description information of the specified sound waves received by the mobile robot at the current position can be {TDOA1, TDOA2, TDOA3, strength1, strength2, strength3}, where TDOA1, TDOA2, and TDOA3 are the TDOAs of the specified sound wave 1, the specified sound wave 2, and the specified sound wave 3, respectively, and strength1, strength2, and strength3 are the sound intensities of the specified sound wave 1, the specified sound wave 2, and the specified sound wave 3 at the current position of the mobile robot, respectively.

[0109] In S102, a pose corresponding to the first description information is determined as a first pose based on a pre-constructed correspondence between description information and poses.

[0110] The correspondence between the description information and the poses can be constructed based on the description information of the specified sound waves received by the mobile robot at different poses. Alternatively, the correspondence between the description information and the poses can be pre-constructed based on the description information of the specified sound waves received by the mobile robot at different poses. Optionally, the mobile robot can construct a soundprint map including the correspondence between the description information and the poses during a mapping stage. In the constructed soundprint map, each sampling position corresponds to a pose of the mobile robot at the position, and description information of the specified sound waves received by the mobile robot at the position and the corresponding pose. The construction of the correspondence between the description information and the poses will be described in detail in subsequent embodiments, and thus will not be described herein.

[0111] After the first description information is determined, in order to roughly determine the pose of the mobile robot, a pose corresponding to the first description information can be found from the correspondence between the description information and the pose as the pose of the mobile robot at the current position determined roughly.

[0112] S103, taking the first pose as an initial pose of repositioning, determining the current pose of the mobile robot.

[0113] After the first pose is determined, in order to accurately determine the pose of the mobile robot, the first pose can be taken as an initial pose of repositioning, and then the current pose of the mobile robot is determined to complete the entire repositioning process.

[0114] In the embodiments of the present application, the current pose of the mobile robot can be determined by using various repositioning methods, and optionally, any one of the following implementation manners can be used:

[0115] The first implementation manner is to take the first pose as an initial pose of image repositioning algorithm to determine the current pose of the mobile robot. The image repositioning algorithm is a repositioning algorithm taking an image as a search basis. Specifically, a database containing the correspondence between an image or an image texture feature and a pose is constructed in advance. When repositioning is needed, an image currently collected by the mobile robot is acquired, and then iterative search is performed in the database constructed in advance based on the image or the texture feature of the image to determine the pose corresponding to the image or the texture feature of the image as the repositioning result of the mobile robot. In the embodiments of the present application, the iterative search of the image or the texture feature of the image can be started from the first pose, so that the current pose of the mobile robot can be determined quickly and accurately.

[0116] The second implementation manner is to take the first pose as an initial pose of laser radar repositioning algorithm to determine the current pose of the mobile robot. The laser radar repositioning algorithm is a repositioning algorithm taking radar data as a search basis. Specifically, a database containing the correspondence between radar data and a pose is constructed in advance. When repositioning is needed, radar data currently collected by the mobile robot is acquired, and then iterative search is performed in the database constructed in advance based on the radar data to determine the pose corresponding to the radar data as the repositioning result of the mobile robot. In the embodiments of the present application, the iterative search of the radar data can be started from the first pose, so that the current pose of the mobile robot can be determined quickly and accurately.

[0117] The third implementation manner is to use the combination of the image repositioning algorithm and the laser radar repositioning algorithm to determine the current pose of the mobile robot, so as to make the application scope of the embodiments of the present application more extensive. The specific implementation process will be described in detail in subsequent embodiments, and will not be described here.

[0118] In the above scheme provided by the embodiment of the present application, the description information of the specified sound wave received by the mobile robot can be used to achieve rough estimation of the pose of the mobile robot, and then the first pose is used as the initial pose, so that the iterative search can start from the first pose, and global search of the environment map is avoided. It can be seen that, compared with the global iterative search method, the embodiment of the present application can improve the efficiency of the mobile robot repositioning.

[0119] In actual use, the target scene where the mobile robot is located can include an extreme environment, wherein the extreme environment is an environment that is not suitable for repositioning, for example, a region without gradient, texture, weak texture or repeated texture in the target scene, such as a long straight corridor, a wall, a window, a glass door, etc.

[0120] When the mobile robot is in the extreme environment, it means that it is impossible to use the method shown in the embodiment to accurately obtain the pose of the mobile robot. Figure 1 In order to solve the problem that the extreme environment is not suitable for repositioning, the embodiment of the present application further provides another mobile robot repositioning method, which can further include the following steps before step S101:

[0121] It is judged whether the mobile robot is in the extreme environment, and if the mobile robot is not in the extreme environment, step S101 is performed.

[0122] In this step, before performing step S101, the mobile robot can first judge whether it is in the extreme environment. When it is determined that the mobile robot is not in the extreme environment, it means that the current environment of the mobile robot is suitable for repositioning. At this time, after it is judged that the mobile robot is not in the extreme environment, step S101 can be directly performed.

[0123] Optionally, the environment data collected by various sensors carried by the mobile robot can be used to judge whether the mobile robot is in the extreme environment. For example, at least one of image data, radar data and ultrasonic data can be used to judge whether the mobile robot is in the extreme environment. The specific environment data to be used can be determined in combination with the types and requirements of the sensors included in the mobile robot.

[0124] In one method for judging whether the mobile robot is in the extreme environment based on images, the images collected by the mobile robot are acquired, and then it is determined whether the mobile robot is in the extreme environment based on the acquired images.

[0125] The image collected by the mobile robot can be an image collected by a camera in the mobile robot. Specifically, after the mobile robot is started, the camera in the mobile robot can collect images in real time. In the embodiment of the present application, the image collected by the mobile robot can be obtained in real time or periodically during the movement of the mobile robot.

[0126] After the image collected by the mobile robot is obtained, whether the mobile robot is in an extreme environment can be determined based on the obtained image. Optionally, feature points contained in the obtained image can be extracted, and then when the proportion of the number of specified feature points in the extracted feature points is greater than a first threshold, it is determined that the mobile robot is in an extreme environment, otherwise, it is determined that the mobile robot is in a non-extreme environment.

[0127] The specified feature point is a feature point whose proportion of similar feature points is greater than a second threshold in the extracted feature points. The similar feature point of each feature point is a feature point whose distance from the feature point in the feature space is less than a specified distance.

[0128] The feature point can be an image feature represented by a feature descriptor. The feature descriptor is a data structure for describing a feature. The dimension of a feature descriptor can be multi-dimensional. In the embodiment of the present application, at least one of a binary descriptor such as BRIEF (Binary Robust Independent Elementary Features), BRISK (Binary Robust Invariant Scalable Keypoints), FREAK (Fast Retina Keypoint), and a floating point descriptor such as SIFT (Scale-invariant feature transform) and SURF (Speeded Up Robust Features) can be used.

[0129] The following describes a repetitive texture. As shown in Figure 3 A repetitive texture image schematic diagram provided by the embodiment of the present application is shown. First, feature points contained in the image are extracted, then all the feature points are traversed, and for each feature point, the feature point and the remaining feature points are subjected to XOR operation to determine the similar feature points of the feature point, and then the same or different situation of each feature point and other feature points is counted. If the number n of feature points identical to the feature point a accounts for the proportion of the total number m of feature points greater than a first threshold Th1, the number of similarities sim is sim+1, and if the total number of similarities sim accounts for the proportion of the total number m of feature points greater than a threshold Th2, it is considered as a repetitive texture.

[0130] In the embodiment of the present application, the first threshold and the second threshold can be determined according to actual needs, or can be determined in combination with the descriptor used, which is all possible.

[0131] On this basis, based on the embodiment shown in Figure 1 As shown inFigure 2 As shown, the mobile robot repositioning method provided by another embodiment of the present application can further include S104-S105 before step S101, wherein:

[0132] S104, determining whether the mobile robot is in an extreme environment, if yes, executing step S105, if not, executing step S101;

[0133] The specific implementation of the step of determining whether the mobile robot is in an extreme environment is described in the foregoing embodiments, which will not be repeated again.

[0134] When determining whether the mobile robot is in an extreme environment, it indicates that the current environment of the mobile robot is not suitable for repositioning. To solve the problem that the extreme environment is not suitable for repositioning, step S105 can be executed in the embodiment of the present application.

[0135] When it is determined that the mobile robot is not in an extreme environment, it indicates that the current environment of the mobile robot is suitable for repositioning. At this time, after determining that the mobile robot is not in an extreme environment, step S101 can be directly executed.

[0136] S105, controlling the mobile robot to move to a non-extreme environment; after the mobile robot moves to the non-extreme environment, executing step S101.

[0137] In this step, when it is determined that the current environment of the mobile robot is not suitable for repositioning, the mobile robot can be controlled to move to a non-extreme environment.

[0138] The mobile robot can be moved to a non-extreme environment in various ways, such as randomly controlling the mobile robot to move, and determining whether the current environment is a non-extreme environment according to the image collected by the mobile robot, and stopping the moving process when it is determined that the current environment is a non-extreme environment.

[0139] Optionally, in order to more quickly move the mobile robot out of the extreme environment, in an implementation manner of the embodiment of the present application, when the mobile robot is in an extreme environment, the description information of the specified sound wave received can be taken as the second description information, and then the pose corresponding to the second description information is determined as the second pose based on the correspondence between the description information and the pose, and the pose corresponding to the second description information is determined as the second pose based on the correspondence between the description information and the pose.

[0140] The process of determining the second description information can refer to the process of determining the first description information, which will not be repeated here. In order to make the mobile robot quickly get rid of the current extreme environment, after the second description information is determined, the second description information can be used to determine the current rough pose of the mobile robot, that is, based on the correspondence between the description information and the pose, the pose corresponding to the second description information is determined as the second pose, and then based on the second pose, the moving path of the mobile robot moving to the non-extreme environment is determined, and the mobile robot is controlled to move according to the moving path.

[0141] For example, as shown in the figure, the embodiment of the application provides a motion schematic diagram. In the figure, the base station can be used as a sound emitting device in the target scene to emit a specified sound wave to the target scene. The circular icon containing two small circles represents a mobile robot in the target scene, and the two circular images inside represent sound wave receiving devices inside the mobile robot. The direction indicated by the vertical line at the lower end of the mobile robot is the front direction of the mobile robot. Figure 4 In the figure, the mobile robot is located at the position of the right-angle wall surface, and is in an extreme environment. At this time, the mobile robot can determine a moving path based on the specified sound wave emitted by the base station, and then move out of the current extreme environment according to the moving path. Figure 4

[0142] In the above scheme provided by the embodiment of the application, the repositioning efficiency can be improved. Further, when the mobile robot is in an extreme environment, the mobile robot can be moved to a non-extreme environment based on the description information, thereby improving the success rate of repositioning.

[0143] In one embodiment, the mobile robot repositioning method provided by another embodiment of the application can be constructed in the following manner to establish the correspondence between the description information and the pose, comprising:

[0144] For each position to which the mobile robot moves in the mapping stage, the description information of the specified sound wave received by the mobile robot at the position is obtained, and the pose of the mobile robot at the moving position is determined, and the position and the determined pose are combined as a pose corresponding to the obtained description information.

[0145] In the mapping stage, after the mobile robot faces a new scene, the stage of establishing map data such as a grid map, a topological map, and a semantic map of the new scene. In the mapping stage, the mobile robot will continue to move, and at each sampling period, it will collect environmental data based on various sensors carried by itself, and record the current pose of itself.

[0146] ​In the mapping stage of the embodiment, the mobile robot can obtain the description information of the specified sound wave received by the mobile robot at each position moved to, and then determine the pose of the mobile robot at the position, and finally combine the position and the determined pose as a pose corresponding to the obtained description information.

[0147] In the case where the description information includes the time difference of arrival of the specified sound wave, the above-mentioned determination of the pose of the mobile robot currently located can include steps 1-2:

[0148] Step 1: based on the time difference of arrival in the obtained description information and the relative distance between different sound receiving devices in the mobile robot, determine the attitude angle of the mobile robot relative to the sound line of the specified sound wave;

[0149] As shown in Figure 5 , a schematic diagram of a specified sound receiving device provided by the embodiment of the present application, Figure 5 The midpoint a is the intersection of the annotation lines, which has no actual meaning. Figure 5 In the above, S(k) represents the specified sound wave. The specified sound wave reaches the specified sound receiving devices o1 and o2 on the mobile robot in turn, and the time instants when the specified sound wave reaches the two specified sound receiving devices are denoted as t1 and t2, respectively. The time difference of arrival is Δt = t1-t2.

[0150] Further, according to the geometric relationship, we have:

[0151]

[0152] Further, we have:

[0153]

[0154] where φ is the attitude angle of the mobile robot relative to the sound line of the sound wave, Δt is the time difference of arrival, L is the relative distance between the two sound receiving devices in the mobile robot, and c is the speed of sound.

[0155] where the above-mentioned sound line is a geometric acoustic concept, ignoring the wave nature of sound, a straight line or curve representing the direction of sound energy propagation from the sound source, ignoring the wave nature of sound. The above-mentioned attitude angle is the relative pose of the mobile robot and the specified sound emitting device.

[0156] Step 2: based on the attitude angle and the pose of the specified sound emitting device, determine the pose of the mobile robot; wherein the specified sound emitting device is the device emitting the specified sound wave;

[0157] Once the attitude angle between the mobile robot and the designated sound-emitting device is determined, the attitude of the mobile robot can be determined based on this attitude angle and the attitude of the designated sound-emitting device. The attitude of the designated sound-emitting device can be stored as prior knowledge in the execution subject of this embodiment, or it can be obtained through communication between the execution subject and the designated sound-emitting device; either approach is acceptable.

[0158] After determining the attitude angle, the attitude of the specified sound-emitting device can be calculated and added to the attitude angle to obtain the attitude of the mobile robot.

[0159] In one embodiment, in order to accurately determine the pose of the mobile robot, multiple sound-emitting devices can be installed in the target scene, and different sound-emitting devices have different heights. Thus, the pose of the mobile robot can be comprehensively determined based on the attitude angle of the sound waves emitted by the mobile robot and the sound ray emitted by different designated sound-emitting devices.

[0160] The above-described solutions provided in the embodiments of the present invention can improve relocation efficiency and further provide a specific implementation process for the correspondence between description information and pose, thus providing a basis for improving relocation efficiency.

[0161] Optionally, in one implementation, the correspondence between the above-mentioned descriptive information and pose is divided into multiple categories according to the position they correspond to in the feature space.

[0162] At this time, Figure 1 Based on the illustrated embodiments, as Figure 6 As shown, in another embodiment of the mobile robot relocation method provided by the present invention, step S102 above may include S102a-S102b, wherein:

[0163] S102a, determine the category to which the first descriptive information belongs from multiple categories, and use it as the target category;

[0164] In this step, the correspondence between descriptive information and pose can be used to group descriptive information in the feature space whose Euclidean distance is within a certain threshold into the same cluster. Then, clustering can be used to determine the category to which the first descriptive information belongs in the feature space, which is then used as the target category. Specifically, the Euclidean distance between the first descriptive information and the centers of each cluster can be calculated, and the category corresponding to the cluster with the closest distance to the first descriptive information is taken as the target category.

[0165] S102b, from the description information belonging to the target category, determine the description information that matches the first description information, and take the pose corresponding to the determined description information as the pose corresponding to the first description information.

[0166] In this step, after the target category is found, each sub-description information in the cluster corresponding to the target category can be further traversed to find the description information most similar to the first description information, and the pose of the description information is taken as the pose corresponding to the first description information.

[0167] As shown in Figure 7 , an embodiment of the present application provides a clustering schematic diagram. The first description information currently collected is divided into a certain category by a clustering algorithm, such as Figure 7 , the category in which the star icon is located.

[0168] In the above scheme provided by the embodiment of the present application, the repositioning efficiency can be improved, and the description information matched with the first description information can be quickly determined in a clustering manner.

[0169] On the basis of the embodiment shown in Figure 1 , as shown in Figure 8 , the mobile robot repositioning method provided by another embodiment of the present application can include S103a-S103b, wherein:

[0170] S103a, taking the first pose as the initial pose of the first repositioning algorithm, determines the pose of the mobile robot as the third pose; wherein the first repositioning algorithm is at least one of an image repositioning algorithm and a laser radar repositioning algorithm;

[0171] S103b, taking the third pose as the initial pose of the second repositioning algorithm, determines the pose of the mobile robot as the current pose of the mobile robot.

[0172] In the above scheme provided by the embodiment of the present application, since the description information of the specified sound wave received by the mobile robot can be used to roughly estimate the pose of the mobile robot, and then the first pose is taken as the initial pose, the iterative search can start from the first pose, avoiding global search of the environment map. It can be seen that, compared with the global iterative search method, the embodiment of the present application can improve the efficiency of mobile robot repositioning.

[0173] In an embodiment, a mobile robot repositioning method combined with an actual scene is provided. As shown in Figure 9 , a scene schematic diagram provided by the embodiment of the present application is shown. First, the mobile robot constructs a high-precision map of the indoor environment through a first cleaning process. Under the same set of odometer, different maps are constructed by different sensors. Commonly used maps include grid maps, topological maps, semantic maps, and voiceprint maps. The corresponding odometer pose and map description are bound for retrieval in the repositioning process.

[0174] According to the map, the base station and the network camera of the mobile robot are calibrated, and the specific calibration method is as follows:

[0175] As shown in Figure 9 After the map is aligned, the map coordinate system of the high-precision map is OXY, wherein the OX direction is the 0-degree direction. The user can manually select two regular points A and B on the client, and the system automatically calculates the vector (AB)→. At the same time, the user can place a right-angle side of the base station close to the vector (AB)→, and after fixing the position, the system automatically calculates the coordinates o of the planar geometric center of the base station in the OXY plane according to the physical size of the base station. At the same time, the base station coordinate system oxy is established, which is used for sound source orientation.

[0176] Figure 9 The field of view of the camera is the intersection area of the lines of sight of the cameras installed at positions C and D, and the cameras installed at positions C and D can emit specified sound waves as specified sound emitting devices. For camera calibration, the user selects two positions C and D as initial positions, and simultaneously calibrates the relative poses of the two positions according to the calibration pattern provided by the mobile robot. At the same time, the pose transformation of one of the cameras relative to the mobile robot can be calculated, and the pose of the camera in the global map system can be solved according to the pose of the mobile robot in the global map system. The pose of the two cameras in the global map system is composed of the position and the pose. Since the calibration process is not the main presentation of the present scheme, it is briefly described.

[0177] In this embodiment, the voiceprint map is mainly composed of position, pose, time difference of arrival (TDOA), sound intensity 1, sound intensity 2, sound intensity 3, etc. This map can be stored in the form of a simple text document, and the text is as follows:

[0178] x, y, z, roll, pitch, yaw, TDOA1, TDOA2, TDOA3, strength1, strength2, strength3…

[0179] The first six positions are the pose of the mobile robot, and the last several positions are the description of the specified sound waves received by the pose. It describes the characteristic information and geometric information of the specified sound waves received by the mobile robot in the pose. Among them, the sound intensity is used to describe the strength of the sound, which represents the sound energy per unit area per unit time passing through the envelope. The unit is: W / m^2. The geometric information mainly includes the time difference of arrival TDOA, which is mainly related to the spatial pose of the mobile robot. The network camera and the sound emitting device in the base station emit a specific specified sound wave, and the specified sound wave receiving device installed inside the mobile robot receives and analyzes the specified sound wave.

[0180] When it is determined that the current scene is an extreme scene, the visual repositioning in this scene will fail, resulting in repositioning using a single sensor laser radar, which is time-consuming or fails due to no initial pose. In the present solution, a specified sound wave guiding motion can be started to explore the scene, and the mobile robot is moved to a non-extreme environment to restore the function of visual matching repositioning.

[0181] According to the mobile robot repositioning method provided by the above-mentioned embodiments of the present application, as shown in the figure, the present application further provides a mobile robot system, which comprises: Figure 10

[0182] The sound wave receiving module 1001 is configured to acquire description information of the specified sound wave received by the mobile robot as first description information, wherein the description information represents characteristic information of the specified sound wave when it reaches the mobile robot.

[0183] The processor 1002 is configured to determine a pose corresponding to the first description information as a first pose based on a pre-constructed correspondence between description information and pose, and determine the current pose of the mobile robot by taking the first pose as an initial pose.

[0184] The correspondence between the description information and the pose is constructed based on the description information of the specified sound wave received by the mobile robot in different poses, and the start point pose is the pose when the repositioning algorithm starts to perform iterative search.

[0185] Optionally, the processor is further configured to determine whether the mobile robot is in an extreme environment before the sound wave receiving module performs the step of acquiring the description information of the specified sound wave received by the mobile robot as the first description information, and if the mobile robot is not in the extreme environment, call the sound wave receiving module to perform the step of acquiring the description information of the specified sound wave received by the mobile robot as the first description information, wherein the extreme environment is an environment that is not suitable for repositioning.

[0186] Optionally, it further comprises a power module configured to drive the mobile robot to move to the non-extreme environment under the control of the processor.

[0187] The processor is further configured to control the power module to move if the mobile robot is in the extreme environment after determining whether the mobile robot is in the extreme environment, and call the sound wave receiving module to perform the step of acquiring the description information of the specified sound wave received by the mobile robot as the first description information after the mobile robot moves to the non-extreme environment, wherein the non-extreme environment is an environment suitable for repositioning using the repositioning algorithm. ​

[0188] Optionally, the sound wave receiving module is further configured to acquire, as second description information, description information of the specified sound wave received when the mobile robot is in the extreme environment.

[0189] The processor is configured to determine, based on a correspondence between the description information and a pose, a pose corresponding to the second description information as a second pose, and control the mobile robot to move to the non-extreme environment based on the second pose.

[0190] Optionally, the apparatus further comprises an image acquisition module configured to acquire an image, and the processor is further configured to acquire the image acquired by the image acquisition module, and determine whether the mobile robot is in an extreme environment based on the acquired image.

[0191] Optionally, the processor is specifically configured to extract feature points contained in the acquired image, and determine that the mobile robot is in an extreme environment when a proportion of a specified feature point in the extracted feature points is greater than a first threshold, and otherwise, determine that the mobile robot is in a non-extreme environment; the specified feature point is a feature point whose proportion of similar feature points is greater than a second threshold among the extracted feature points; and the similar feature point of each feature point is a feature point whose distance from the feature point is less than a specified distance in a feature space.

[0192] Optionally, the processor is specifically configured to determine a moving path of the mobile robot to the non-extreme environment based on the second pose, and control the mobile robot to move according to the moving path.

[0193] Optionally, the processor is further configured to construct the correspondence between the description information and the pose in the following manner: for each position to which the mobile robot moves in a mapping stage, acquire description information of the specified sound wave received by the mobile robot at the position, determine a current attitude of the mobile robot, and combine the position and the determined attitude as a pose corresponding to the acquired description information.

[0194] Optionally, the description information comprises a time difference of arrival of the specified sound wave; the time difference of arrival is a time difference between different sound wave receiving devices in the mobile robot receiving the specified sound wave.

[0195] The processor is specifically configured to determine the attitude angle of the mobile robot relative to the sound line of the specified sound wave based on the time difference of arrival in the obtained description information and the relative distance between different sound wave receiving devices in the mobile robot, and determine the attitude of the mobile robot based on the attitude angle and the attitude of the specified sound emitting device.

[0196] Optionally, the mobile robot comprises two sound wave receiving devices.

[0197] The processor is specifically configured to determine the attitude angle of the mobile robot relative to the sound line of the specified sound wave by using the following formula:

[0198]

[0199] Wherein, φ is the attitude angle of the mobile robot relative to the sound line of the specified sound wave, Δt is the time difference of arrival in the obtained description information, and L is the relative distance between the two sound wave receiving devices in the mobile robot.

[0200] Optionally, in the correspondence between the description information and the pose, each description information is divided into multiple categories according to the corresponding position in the feature space.

[0201] The processor is specifically configured to determine the category to which the first description information belongs from the multiple categories as a target category, determine the description information matched with the first description information from each description information belonging to the target category, and take the pose corresponding to the determined description information as the pose corresponding to the first description information.

[0202] Optionally, the processor is specifically configured to take the first pose as the initial pose of a first repositioning algorithm, determine the pose of the mobile robot as a third pose, and take the third pose as the initial pose of a second repositioning algorithm, determine the pose of the mobile robot as the current pose of the mobile robot, wherein the first repositioning algorithm is at least one of an image repositioning algorithm and a laser radar repositioning algorithm, and the second repositioning algorithm is a repositioning algorithm different from the first repositioning algorithm among the image repositioning algorithm and the laser radar repositioning algorithm.

[0203] In the above scheme provided by the embodiment of the application, the rough estimation of the pose of the mobile robot can be realized through the description information of the specified sound wave received by the mobile robot, and then the first pose is taken as the initial pose, so that the iterative search can start from the first pose, avoiding the global search of the environment map. It can be seen that, compared with the global iterative search method, the efficiency of the repositioning of the mobile robot can be improved.

[0204] The embodiment of the present application also provides an electronic device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus. Figure 11

[0205] The memory is used for storing a computer program.

[0206] The processor is used for executing the program stored in the memory, and the following steps are realized.

[0207] The description information of the specified sound wave received by the mobile robot is obtained as first description information, wherein the description information represents the characteristic information of the specified sound wave when the specified sound wave reaches the mobile robot.

[0208] The pose corresponding to the first description information is determined as a first pose based on a pre-constructed corresponding relationship between description information and pose, wherein the corresponding relationship between description information and pose is constructed based on the description information of the specified sound wave received by the mobile robot in different poses.

[0209] The current pose of the mobile robot is determined by taking the first pose as an initial pose.

[0210] The electronic device provided by the embodiment of the present application can realize rough estimation of the pose of the mobile robot by the description information of the specified sound wave received by the mobile robot, and then take the first pose as an initial pose, so that the iterative search can start from the first pose, and the global search of the environment map is avoided. Therefore, compared with the global iterative search mode, the embodiment of the present application can improve the efficiency of the repositioning of the mobile robot.

[0211] The communication bus mentioned in the above electronic device can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0212] The communication interface is used for communication between the above electronic device and other devices.

[0213] ​The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory can also be at least one storage device located remotely from the aforementioned processor.

[0214] The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0215] In yet another embodiment provided by the present application, a computer readable storage medium is also provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of any of the mobile robot repositioning methods described above.

[0216] In yet another embodiment provided by the present application, a computer program product containing instructions, which, when run on a computer, causes the computer to execute any of the mobile robot repositioning methods in the above embodiments.

[0217] In the embodiments described above, all or some of the steps can be implemented by software, hardware or firmware, or any combination thereof. When implemented by software, all or some of the steps can be implemented in the form of one or more computer programs. The computer program can be stored in any computer readable medium, and loaded into the computer system for execution. The computer readable medium includes: a computer storage medium and a computer communication medium. The computer storage medium includes: volatile media (such as random access memory (RAM) and others) and non-volatile media (such as read-only memory (ROM), floppy disks, CD-ROMs, optical disks, hard disks, etc.). The computer communication medium includes: computer networks and other media.

[0218] It should be noted that, in this document, the terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. In addition, the terms "comprise", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or other elements inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article or device that includes the element.

[0219] Each of the embodiments in the specification is described in a related manner, and the same or similar parts between each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for system, electronic device, computer readable storage medium, and computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0220] The above merely describes the preferred embodiments of the present application, but is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A mobile robot repositioning method characterized by, The method comprises: obtaining description information of a specified sound wave received by a mobile robot as first description information; wherein the description information represents characteristic information of the specified sound wave when it reaches the mobile robot; determining a pose corresponding to the first description information as a first pose based on a pre-constructed correspondence between description information and pose; wherein the correspondence between description information and pose is constructed based on description information of the specified sound wave received by the mobile robot in different poses; determining a current pose of the mobile robot using the first pose as an initial pose; in the correspondence between description information and pose, each description information is divided into multiple categories according to the corresponding position in the feature space; determining a pose corresponding to the first description information based on the pre-constructed correspondence between description information and pose comprises: determining a category to which the first description information belongs from the multiple categories as a target category; from each description information belonging to the target category, determining description information that matches the first description information, and determining a pose corresponding to the determined description information as a pose corresponding to the first description information.

2. The method of claim 1, wherein, Before the step of obtaining description information of a specified sound wave received by a mobile robot as first description information, the method further comprises: determining whether the mobile robot is in an extreme environment; wherein the extreme environment is an environment that is not suitable for repositioning; if the mobile robot is not in the extreme environment, performing the step of obtaining description information of a specified sound wave received by a mobile robot as first description information.

3. The method of claim 2, wherein, After determining whether the mobile robot is in an extreme environment, the method further comprises: if the mobile robot is in the extreme environment, controlling the mobile robot to move to a non-extreme environment; wherein the non-extreme environment is an environment suitable for repositioning; after the mobile robot moves to the non-extreme environment, performing the step of obtaining description information of a specified sound wave received by a mobile robot as first description information.

4. The method of claim 3, wherein, The step of controlling the mobile robot to move to a non-extreme environment comprises: obtaining description information of the specified sound wave received by the mobile robot when it is in the extreme environment as second description information; determining a pose corresponding to the second description information as a second pose based on the correspondence between description information and pose; controlling the mobile robot to move to the non-extreme environment based on the second pose.

5. The method of claim 2, wherein, The step of determining whether the mobile robot is in an extreme environment comprises: obtaining an image collected by the mobile robot; determining whether the mobile robot is in an extreme environment based on the obtained image.

6. The method of claim 5, wherein, The step of determining whether the mobile robot is in an extreme environment based on the obtained image comprises: extracting feature points contained in the obtained image; when the proportion of a specified feature point in the extracted feature points is greater than a first threshold value, determining that the mobile robot is in an extreme environment, otherwise, determining that the mobile robot is in a non-extreme environment. The specified feature point is a feature point in the extracted feature points, and a number of similar feature points of the feature point accounts for more than a second threshold value.

7. The method of claim 4, wherein, The method comprises: Based on the second pose, determining a movement path of the mobile robot to the non-extreme environment; According to the movement path, controlling the mobile robot to move.

8. The method according to any one of claims 1 to 7, characterized in that, The correspondence between the description information and the pose is constructed in the following manner: For each position to which the mobile robot moves in the mapping stage, the description information of the specified sound wave received by the mobile robot at the position is obtained, the attitude of the mobile robot at the position is determined, and the position and the determined attitude are combined as a pose corresponding to the obtained description information.

9. The method of claim 8, wherein, The description information includes a time difference of arrival of the specified sound wave; wherein the time difference of arrival is a time difference between different sound wave receiving devices in the mobile robot receiving the specified sound wave; The determination of the attitude of the mobile robot at the current position comprises: Based on the time difference of arrival in the obtained description information and the relative distance between different sound wave receiving devices in the mobile robot, the attitude angle of the mobile robot relative to the sound line of the specified sound wave is determined; Based on the attitude angle and the attitude of the specified sound emitting device, the attitude of the mobile robot is determined; wherein the specified sound emitting device is a device emitting the specified sound wave.

10. The method of claim 9, wherein, The mobile robot includes two sound wave receiving devices; Based on the time difference of arrival in the obtained description information and the relative distance between different sound wave receiving devices in the mobile robot, the attitude angle of the mobile robot relative to the sound line of the received sound wave is determined, comprising: The attitude angle of the mobile robot relative to the sound line of the specified sound wave is determined by the following formula: Wherein φ is the attitude angle of the mobile robot relative to the sound line of the specified sound wave, Δt is the time difference of arrival in the obtained description information, and L is the relative distance between the two sound wave receiving devices in the mobile robot.

11. The method according to any one of claims 1 to 7, characterized in that, The determination of the current pose of the mobile robot based on the first pose as the initial pose comprises: The first pose is taken as the initial pose of a first repositioning algorithm, the pose of the mobile robot is determined as a third pose, and the first repositioning algorithm is at least one of an image repositioning algorithm and a laser radar repositioning algorithm; The third pose is taken as the initial pose of a second repositioning algorithm, the pose of the mobile robot is determined as the current pose of the mobile robot; The second repositioning algorithm is different from the first repositioning algorithm among the image repositioning algorithm and the laser radar repositioning algorithm.

12. A mobile robot system, characterized by The method comprises: The sound wave receiving module is configured to acquire description information of a specified sound wave received by the mobile robot as first description information, wherein the description information represents characteristic information of the specified sound wave when the specified sound wave reaches the mobile robot. The processor is configured to determine a pose corresponding to the first description information as a first pose based on a pre-constructed correspondence between description information and poses; and determine a current pose of the mobile robot by taking the first pose as an initial pose. The correspondence between the description information and the poses is constructed based on description information of the specified sound wave received by the mobile robot in different poses. In the correspondence between the description information and the poses, each description information is classified into multiple categories according to a corresponding position in a feature space; the processor is specifically configured to determine a category to which the first description information belongs as a target category from the multiple categories; determine description information matching the first description information from each description information belonging to the target category; and determine a pose corresponding to the determined description information as a pose corresponding to the first description information.

13. The mobile robotic system of claim 12, wherein, The processor is further configured to determine whether the mobile robot is in an extreme environment before the sound wave receiving module performs the step of acquiring the description information of the specified sound wave received by the mobile robot as the first description information; and if the mobile robot is not in the extreme environment, call the sound wave receiving module to perform the step of acquiring the description information of the specified sound wave received by the mobile robot as the first description information; wherein the extreme environment is an environment that is not suitable for repositioning.

14. The mobile robotic system of claim 13, wherein, Further comprising: A power module configured to drive the mobile robot to move to a non-extreme environment under control of the processor. The processor is further configured to control the power module to move if the mobile robot is in the extreme environment after determining whether the mobile robot is in the extreme environment; and call the sound wave receiving module to perform the step of acquiring the description information of the specified sound wave received by the mobile robot as the first description information after the mobile robot moves to the non-extreme environment; wherein the non-extreme environment is an environment suitable for repositioning using a repositioning algorithm.

15. The mobile robotic system of claim 14, wherein, The sound wave receiving module is further configured to acquire description information of the specified sound wave received by the mobile robot when the mobile robot is in the extreme environment as second description information. The processor is configured to determine a pose corresponding to the second description information as a second pose based on the correspondence between the description information and the poses; and control the mobile robot to move to the non-extreme environment based on the second pose.

16. The mobile robotic system of claim 13, wherein, Further comprising an image acquisition module configured to acquire images; and the processor is further configured to acquire images acquired by the image acquisition module; and determine whether the mobile robot is in an extreme environment based on the acquired images.

17. The mobile robotic system of claim 16, wherein, The processor is specifically configured to extract feature points contained in the acquired image; when a proportion of a specified feature point in the extracted feature points is greater than a first threshold, it is determined that the mobile robot is in an extreme environment, otherwise, it is determined that the mobile robot is in a non-extreme environment; wherein the specified feature point is a feature point whose proportion of similar feature points is greater than a second threshold among the extracted feature points; and the similar feature point of each feature point is a feature point whose distance from the feature point is less than a specified distance in a feature space.

18. The mobile robotic system of claim 15, wherein, The processor is specifically configured to determine a moving path of the mobile robot to the non-extreme environment based on the second pose; and control the mobile robot to move according to the moving path.

19. The mobile robotic system of any of claims 12-18, wherein, The processor is further configured to construct the correspondence between the description information and the pose in the following manner: for each position to which the mobile robot moves in a mapping stage, acquire description information of the specified sound wave received by the mobile robot at the position, determine a current attitude of the mobile robot, and combine the position and the determined attitude as a pose corresponding to the acquired description information.

20. The mobile robotic system of claim 19, wherein, The description information includes a time difference of arrival of the specified sound wave; wherein the time difference of arrival is a time difference between different sound wave receiving devices in the mobile robot receiving the specified sound wave. The processor is specifically configured to determine an attitude angle of the mobile robot relative to a sound line of the specified sound wave based on the time difference of arrival in the acquired description information and a relative distance between different sound wave receiving devices in the mobile robot; and determine the attitude of the mobile robot based on the attitude angle and an attitude of a specified sound emitting device.

21. The mobile robotic system of claim 20, wherein, The mobile robot includes two sound wave receiving devices; The processor is specifically configured to determine the attitude angle of the mobile robot relative to the sound line of the specified sound wave by using the following formula: Wherein φ is the attitude angle of the mobile robot relative to the sound line of the specified sound wave, Δt is the time difference of arrival in the acquired description information, and L is the relative distance between the two sound wave receiving devices in the mobile robot.

22. The mobile robotic system of any of claims 12-18, wherein, The processor is specifically configured to determine the pose of the mobile robot as a third pose by taking the first pose as an initial pose of a first repositioning algorithm; and determine the pose of the mobile robot as a current pose of the mobile robot by taking the third pose as an initial pose of a second repositioning algorithm; wherein the first repositioning algorithm is at least one of an image repositioning algorithm and a laser radar repositioning algorithm; and the second repositioning algorithm is a repositioning algorithm different from the first repositioning algorithm among the image repositioning algorithm and the laser radar repositioning algorithm.

23. An electronic device, comprising: The processor, the communication interface, the memory and the communication bus complete mutual communication through the communication bus; The memory is used to store a computer program. A processor for implementing the method steps of any one of claims 1-11 when executing instructions stored on a memory.

Images