WO2023045644A1

WO2023045644A1 - Positioning method and device for mobile robot, storage medium and electronic device

Info

Publication number: WO2023045644A1
Application number: PCT/CN2022/113375
Authority: WO
Inventors: 王朕; 郁顺昌; 齐焱
Original assignee: 追觅创新科技(苏州)有限公司
Priority date: 2021-09-23
Filing date: 2022-08-18
Publication date: 2023-03-30
Also published as: CN113907645A

Abstract

A positioning method and device for a mobile robot, a storage medium and an electronic device. The method comprises: when detected that a mobile robot is in a first state, acquiring the position coordinates of at least two target objects detected by the mobile robot in a second state, the first state being a state in which a pose failure occurs in the mobile robot, and the second state being a state in which a pose failure does not occur in the mobile robot (S202); determining first relative positions between the mobile robot and the at least two target objects (S204); and calculating the position coordinates of the mobile robot according to the position coordinates of the at least two target objects and the first relative positions (S206). The method solves the problem in the related technology that when a pose failure occurs in a mobile robot, the position of the mobile robot cannot be determined.

Description

Mobile robot positioning method and device, storage medium and electronic device

This disclosure claims the priority of the following patent application: a Chinese patent application submitted to the China Patent Office on September 23, 2021, with the application number 202111117669.5, and the title of the invention is "Positioning method and device, storage medium and electronic device for a mobile robot"; The entire contents of the aforementioned patent applications are incorporated by reference in this disclosure.

technical field

The present disclosure relates to the communication field, and in particular, to a positioning method and device for a mobile robot, a storage medium, and an electronic device.

Background technique

With the rapid development of robot technology, robots have now been applied to various fields. Robots need to interact with the environment and users, and environmental perception is the most basic and critical link in the interaction process of robots. In order to ensure the positioning and mapping accuracy of the robot, it is necessary to use the past information to obtain the accurate machine pose. Existing machine relocalization techniques are divided into methods based on traditional feature points, methods based on machine learning and methods based on deep learning. Among them, the relocation based on traditional feature points uses feature points for matching, and then obtains the machine pose. When the machine is lifted and the wheels are slipping, the pose of the machine itself is lost or the calculation is wrong, and the position of the mobile robot cannot be determined, which in turn leads to Vision Simultaneous Location And Mapping (VSLAM) mapping The case of overlays.

Aiming at the problem in the related art that the position of the mobile robot cannot be determined when the pose of the mobile robot fails, no effective solution has been proposed yet.

Therefore, it is necessary to improve the prior art to overcome the defects in the prior art.

Contents of the invention

The purpose of the present disclosure is to provide a positioning method and device, a storage medium and an electronic device for a mobile robot, so as to at least solve the problem in the related art that the position of the mobile robot cannot be determined when the pose of the mobile robot fails.

The purpose of this disclosure is to be achieved through the following technical solutions:

According to an aspect of an embodiment of the present disclosure, there is provided a positioning method for a mobile robot, including: when it is detected that the mobile robot is in the first state, acquiring at least two data detected by the mobile robot in the second state The position coordinates of a target object; the first state is a state where the mobile robot has a pose failure, and the second state is a state where the mobile robot has no pose failure; determine the relationship between the mobile robot and the First relative positions of at least two target objects; calculating the position coordinates of the mobile robot according to the position coordinates of the at least two target objects and the first relative positions.

Further, the acquiring the position coordinates of at least two target objects detected by the mobile robot in the second state includes: identifying at least two target objects based on the image data collected by the image acquisition component; according to the The identifications of at least two target objects are matched from a preset relationship library to obtain the position coordinates of the at least two target objects; wherein, the preset relationship library stores the correspondence between the identification of the target object and the position coordinates of the target object relation.

Further, the determining the first relative position between the mobile robot and the at least two target objects includes: determining the distance between the mobile robot and the at least two target objects according to the target ranging method, and obtaining at least two First distance; determine the first directional relationship between the mobile robot and the at least two objects based on the image data collected by the image acquisition component; determine the first directional relationship according to the first directional relationship and the at least two first distances First relative positions of the mobile robot and the at least two target objects.

Further, the method further includes: when the mobile robot is in the second state, identifying the target object based on the image data collected by the image acquisition component; determining the position coordinates of the target object; The identifier of and the position coordinates of the target object are correspondingly stored in a preset relationship library.

Further, the determining the position coordinates of the target object includes: determining a second relative position between the target object and the mobile robot; determining the target according to the second relative position and the position coordinates of the mobile robot The object's location coordinates.

Further, determining the second relative position between the target object and the mobile robot includes: determining the distance between the mobile robot and the target object according to a target ranging method to obtain a second distance; Determining a second directional relationship between the mobile robot and the target object based on the image data; determining a second relative position between the mobile robot and the target object according to the second directional relationship and the second distance.

Further, it is detected that the mobile robot is in the first state through at least one of the following methods, including: detecting that the moving wheels of the mobile robot are idling; detecting that the moving wheels of the mobile robot are not in contact with the target plane.

According to another aspect of the embodiments of the present disclosure, there is provided a positioning device for a mobile robot, including: an acquisition module, configured to acquire the location of the mobile robot in the second state when it is detected that the mobile robot is in the first state The detected position coordinates of at least two target objects; the first state is a state where the mobile robot has a pose failure, and the second state is a state where the mobile robot has no pose failure; a determination module , for determining a first relative position between the mobile robot and the at least two target objects; a calculation module, for calculating the mobile robot according to the position coordinates of the at least two target objects and the first relative position location coordinates.

According to yet another aspect of the embodiments of the present disclosure, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute any of the above-mentioned steps when running. The positioning method of the mobile robot described above.

According to yet another aspect of the embodiments of the present disclosure, there is also provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to perform any of the above The localization method of the mobile robot described in the item.

Through the present disclosure, in the case of a pose failure of the mobile robot, the position coordinates of at least two target objects are obtained when the mobile robot does not have a pose failure, and at the same time, the first relative positions between the mobile robot and the at least two target objects are determined , and then the position coordinates of the mobile robot can be calculated according to the first relative position and the position coordinates of the target object. By adopting the above technical solution, the problem that the position of the mobile robot cannot be determined in the case of a pose failure of the mobile robot is solved. Furthermore, in the case of a pose failure of the mobile robot, the position of the mobile robot can also be determined.

Description of drawings

The drawings described here are used to provide a further understanding of the present disclosure, and constitute a part of the present disclosure. The schematic embodiments of the present disclosure and their descriptions are used to explain the present disclosure, and do not constitute improper limitations to the present disclosure. In the attached picture:

FIG. 1 is a block diagram of the hardware structure of a computer terminal of a method for determining a target object according to an embodiment of the present disclosure;

FIG. 2 is a flow chart of a method for determining a target object according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram (1) of detecting obstacles according to a method for determining a target object according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram (2) of detecting obstacles according to a method for determining a target object according to an embodiment of the present disclosure;

[Corrected 01.09.2022 under Rule 91]

Detailed ways

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

It should be noted that the terms "first" and "second" in the specification and claims of the present disclosure and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence.

The method embodiments provided by the embodiments of the present disclosure may be executed in a mobile robot or a similar computing device. Taking running on a mobile robot as an example, FIG. 1 is a block diagram of a hardware structure of a robot according to a positioning method for a mobile robot according to an embodiment of the present disclosure. As shown in Figure 1, the mobile robot can include one or more (only one is shown in Figure 1) processor 102 (processor 102 can include but not limited to microprocessor (Microprocessor Unit, MPU for short) or programmable logic device (Programmable logic device, referred to as PLD) and other processing devices and memory 104 for storing data, optionally, the above-mentioned mobile robot can also include transmission equipment 106 and input and output equipment 108 for communication functions. Common in the art Those skilled in the art can understand that the structure shown in Figure 1 is only illustrative, and it does not limit the structure of the above-mentioned mobile robot.For example, the mobile robot can also include more or less components than shown in Figure 1, or have the same Functionally equivalent to that shown in Figure 1 or a different configuration with more functionality than shown in Figure 1.

The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the mobile robot positioning method in the embodiment of the present disclosure, and the processor 102 runs the computer program stored in the memory 104, Thereby executing various functional applications and data processing, that is, realizing the above-mentioned method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, and these remote memories may be connected to the mobile robot through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via the network. A specific example of the above-mentioned network may include a wireless network provided by a mobile robot's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC for short), which can be connected to other network devices through a base station so as to communicate with the Internet. In an example, the transmission device 106 may be a radio frequency (Radio Frequency, RF for short) module, which is used to communicate with the Internet in a wireless manner.

In this embodiment, a positioning method that operates on the mobile robot described above is provided. FIG. 2 is a flowchart (1) of a positioning method for a mobile robot according to an embodiment of the disclosure. As shown in FIG. 2 , the process includes the following steps :

Step S202: When it is detected that the mobile robot is in the first state, obtain the position coordinates of at least two target objects detected by the mobile robot in the second state; the first state is the mobile robot A state where a pose failure occurs, and the second state is a state where the mobile robot does not have a pose failure;

It should be noted that whether the mobile robot is in the first state is detected by at least one of the following methods: detecting whether the moving wheels of the mobile robot are idling; detecting whether the moving wheels of the mobile robot are in contact with the target plane.

In the prior art, when the mobile robot lifts up and the wheels slip, the pose of the machine itself is lost or the calculation is wrong, which causes VSLAM to be unable to determine the position of the mobile robot. If the moving wheels of the robot are in contact with the target plane, the VSLAM cannot determine the position of the mobile robot, and then determine that the mobile robot is in the first state, that is, determine that the mobile robot is in a state where the pose is invalid.

Step S204: determining a first relative position between the mobile robot and the at least two target objects;

Step S206: Calculate the position coordinates of the mobile robot according to the position coordinates of the at least two target objects and the first relative position.

It should be noted that the technical solutions of the embodiments of the present application can be applied to mobile robots, including but not limited to sweeping robots.

Through the above steps, in the case of a pose failure of the mobile robot, the position coordinates of at least two target objects are obtained when the mobile robot does not have a pose failure, and at the same time, the first relative positions of the mobile robot and the at least two target objects are determined , and then the position coordinates of the mobile robot can be calculated according to the first relative position and the position coordinates of the target object. By adopting the above technical solution, the problem that the position of the mobile robot cannot be determined in the case of a pose failure of the mobile robot is solved. Furthermore, in the case of a pose failure of the mobile robot, the position of the mobile robot can also be determined.

In order to better understand the technical solution of the present application, the technical solution of the embodiment of the present application can be divided into two parts from the time level, the first part: the mobile robot fails in the pose; the second part: the mobile robot occurs Pose fails.

Specifically, the first part is described in detail as follows:

In an optional embodiment, when the mobile robot is in the second state, the target object is identified based on the image data collected by the image acquisition component; the position coordinates of the target object are determined; the target object is The identifier of and the position coordinates of the target object are correspondingly stored in a preset relationship library.

That is to say, when the mobile robot is in a non-failure state, the mobile robot can collect the image data during the traveling process through its own image acquisition component, and then use the object recognition model to identify the image data to determine the presence of The target object and the identification of the target object, then the mobile robot will further determine the position coordinates of the target object, and then store the identification of the target object and the position coordinates of the target object in the preset relationship library.

It should be noted that the above image data includes: pictures, videos and so on. The above-mentioned target objects include: obstacles, furniture, etc.

Specifically, the above-mentioned mobile robot can determine the position coordinates of the target object in the following manner: determine the second relative position between the target object and the mobile robot; determine according to the second relative position and the position coordinates of the mobile robot The location coordinates of the target object.

That is to say, in the case of no pose failure of the mobile robot, the mobile robot can determine its own coordinates through VSLAM, and then the mobile robot only needs to determine the relative position corresponding to the target object to determine the position coordinates of the target object. For example: the coordinates of the mobile robot are (2, 2), the target object is one meter (relative position) due west of the mobile robot, and the coordinates of the target object are (1, 2). It should be noted that the positive direction of the X-axis of the coordinate system is due east, the positive direction of the Y-axis is due north, and the length of a unit in the coordinate system is one meter.

It should be noted that, in an optional embodiment, the determination of the second relative position between the target object and the mobile robot may be achieved in the following manner: determine the distance between the mobile robot and the target object according to the target ranging method , to obtain the second distance; determine the second direction relationship between the mobile robot and the target object based on the image data collected by the image acquisition component; determine the relationship between the mobile robot and the target object according to the second direction relationship and the second distance The second relative position of the target object.

That is to say, the mobile robot can first determine the distance between the target object and itself through the target ranging method, and then determine which direction the target object is in itself according to the image data collected by the image acquisition component. After determining the direction and distance, it can Determine the relative position. For example, the target object is determined to be one meter away from the mobile robot through the target ranging method, and the target object is determined to be in the due west of the mobile robot through image data, and then the relative position is one meter due to the west. It should be noted that there are many methods of target ranging, including: monocular ranging, binocular ranging, depth sensor ranging, laser ranging, and so on.

Furthermore, by adopting the technical solution of the first part, the mobile robot can determine the position coordinates of all target objects in the area where the mobile robot is located without pose failure, and then map the target object identification to the position coordinates of the target object Stored in a preset relational library.

Further, the following is a specific description of the second part:

In the case of a pose failure of the mobile robot, the position coordinates of at least two target objects detected by the mobile robot in the second state can be obtained first, and the first relative positions between the mobile robot and the at least two target objects can be determined , and then the mobile robot can calculate the position coordinates of the mobile robot according to the position coordinates of at least two target objects and the first relative position.

For a better understanding, obtaining the position coordinates of at least two target objects detected by the mobile robot in the second state may be achieved in the following manner: identifying at least two target objects based on the image data collected by the image acquisition component ; According to the identification of the at least two target objects, the position coordinates of the at least two target objects are obtained by matching from the preset relationship library; wherein, the preset relationship library stores the identification of the target object and the target object Correspondence of position coordinates.

That is to say, the mobile robot needs to collect images of the target area through the image collection component, and then determine at least two target objects from the collected pictures, and determine the position coordinates of the at least two target objects from the preset relationship library . If the mobile robot determines the target object A and the target object B according to the image acquisition component, then it can determine the coordinates of the target object A as (1, 2) and the target object B (5, 2) from the preset relationship library.

Further, determining the first relative positions of the mobile robot and at least two target objects may be achieved in the following manner: determine the distance between the mobile robot and the at least two target objects according to the target ranging method, and obtain at least two first relative positions A distance; determine the first directional relationship between the mobile robot and the at least two objects based on the image data collected by the image acquisition component; determine the movement according to the first directional relationship and the at least two first distances A first relative position between the robot and the at least two target objects.

That is to say, the mobile robot can first determine the distance between the target object and itself through the target ranging method, and then determine which direction the target object is in itself according to the image data collected by the image acquisition component. After determining the direction and distance, it can Determine the relative position. For example, the target object A is determined to be two meters away from the mobile robot through the target distance measurement method, and the target object is determined to be in the due west direction of the mobile robot through the image data, and then the relative position is two meters due to the west direction. The target object B is determined to be two meters away from the mobile robot through the target ranging method, and the target object B is determined to be in the due east direction of the mobile robot through the image data, and then the relative position is two meters due east.

After determining the position coordinates and the first relative position of at least two target objects, the position coordinates of the mobile robot can be calculated, for example, the coordinates of the target object A are (1, 2), and the target object B (5, 2), The target object A is two meters to the west of the mobile robot, and the target object B is two meters to the east of the mobile robot, and the coordinates of the mobile robot are (3, 2).

Further, in an optional embodiment, the mobile robot includes two states during the traveling process. The first state is an abnormal state in which a pose failure occurs, and the second state is a normal state in which a pose failure does not occur. In the In the second state, the mobile robot detects the surrounding object information (label information, detection frame information) through the AI camera (equivalent to the above-mentioned image acquisition component) during the travel process, and determines the distance from the object to the robot through the principle of monocular ranging, so as to determine The relative position between the object and the robot, and then determine the global coordinates of the object according to the relative position of the two (in the second state, the global coordinates of the robot can be determined based on VSLAM), for example, when the robot travels to position A, it detects For refrigerators, the AI camera can mark the refrigerator, and determine the distance from the refrigerator to the robot through the principle of monocular distance measurement, thereby determining the relative position between the refrigerator and the robot, and then determine the global coordinates of the refrigerator according to the relative positions of the two. In the second state, the robot can determine the global coordinates of multiple objects, and mark each object (for example, mark a refrigerator, a table, etc.).

In the first state, VSLAM cannot locate the global coordinates of the mobile robot due to pose failure. At this time, at least two objects within the robot’s field of vision can be obtained at the position where the pose failure occurs, determined by the AI camera. The tags of the two objects, so that the global coordinates corresponding to the two objects can be obtained according to the tags of the two objects (the global coordinates are determined in the second state and are accurate), and then through the principle of monocular distance measurement Determine the distance from the object to the mobile robot, thereby determining the relative position between the object and the mobile robot, and then calculate the global coordinates of the mobile robot based on the relative positions of the two objects and the mobile robot and the global coordinates of the two objects.

Apparently, the embodiments described above are only some of the embodiments of the present disclosure, not all of them. In order to better understand the positioning method of the mobile robot, the above process is described below in conjunction with the embodiments, but it is not used to limit the technical solutions of the embodiments of the present disclosure, specifically:

In an optional embodiment, FIG. 3 is a flow chart (2) of a positioning method for a mobile robot according to an embodiment of the present disclosure. Based on the flow chart shown in FIG. 3 , the optional embodiment of the present disclosure provides The technical solution can be summarized as the following steps:

Step 1: When the sweeping robot (equivalent to the mobile robot in the above embodiment) T2 time (equivalent to the above-mentioned The second state in the embodiment) object detection information at the current location;

Specifically, the AI camera (equivalent to the image acquisition component in the above embodiment) is arranged in front of the cleaning robot, and the AI camera's collection field of view is the forward direction of the cleaning robot. During the cleaning process, the sweeping robot turns on the AI camera in real time, and the sweeping robot inputs the collected images into the detection model to obtain the detection information of the target object on the ground in front. The detection information includes: label information and detection frame information.

Step 2: Obtain the global map coordinate information of the target object at T2 (equivalent to the global coordinates in the above-mentioned embodiment);

Specifically, for the detection information of the target object obtained in step 1, the target object pose in the machine coordinate system can be obtained by using the principle of monocular distance measurement (relationship between projection transformation and rigid body transformation). Then, combined with the pose information at the current position of the sweeping robot, the coordinate information of the target object under the global map is obtained. For example, the sweeping robot detects the dining table A in front of it, combines the detection frame information and the current pose information of the machine to obtain the coordinate information of the dining table A in the global map coordinate system, and stores it in the sweeping robot.

Step 3: Based on the global coordinate information of two or more target objects at the current position, determine the pose information of the sweeping robot;

Specifically, if the sweeping robot lifts up or the wheels slip during the cleaning process, the lifting of the sweeping robot will cause the machine's pose to be lost, and the slipping of the sweeping robot's wheels will cause VSLAM positioning errors, resulting in inaccurate VSLAM mapping. At the same moment, the AI camera captures the detection information of more than two target objects. The target object is an object that has been detected by AI many times during the normal driving of the sweeping robot (the machine pose exists and is accurate) before the pose failure of the sweeping robot, and the coordinate information under the global map is given. In the implementation of the present disclosure, based on the image coordinates of the target object at the moment, according to the above-mentioned principle of monocular distance measurement, the coordinate information of the target object in the machine coordinate system (equivalent to the position coordinates in the above embodiments) is restored, according to the machine coordinate system , the coordinate transformation relationship between the global coordinate system and the machine pose of the sweeping robot, and finally obtain the pose information of the machine at this time.

Step 4: Based on the pose information in step 3, update the pose when the VSLAM positioning fails and correct the wrong relocation, so as to avoid the map being inaccurate.

Specifically, the VSLAM pose failure occurs when the machine is lifted and relocated, and the relocation error mostly occurs during the wheel slipping process. Based on the two or more target objects detected by the above-mentioned AI, the reverse calculated machine pose information is used to fill and correct the machine pose at this time. In this way, the occurrence of inaccurate VSLAM mapping is avoided.

In addition, the above-mentioned embodiments of the present disclosure use AI real-time detection to establish the semantic information and global map coordinate information of ground target objects. In the case of traditional VSLAM positioning failures, use AI to identify and match more than two target objects to obtain a priori global map Coordinates, and then fill and correct the current machine pose, solve the problem of traditional VSLAM positioning failure and positioning error, improve the accuracy of positioning and mapping, and avoid inaccurate mapping.

At the same time, the embodiments of the present disclosure can also directly use the deep neural network to realize end-to-end machine pose prediction. Or use CNN to encode images, construct a database containing image features and real-world poses, and then achieve relative pose prediction by matching the most similar images in the database.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as a read-only memory (Read-Only Memory) Memory, abbreviated as ROM), random access memory (Random Access Memory, abbreviated as RAM), magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, computer, server, or network device) etc.) to perform the methods of the various embodiments of the present disclosure.

In this embodiment, a positioning device for a mobile robot is also provided, and the positioning device for a mobile robot is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have already been described will not be repeated. As used below, the term "module" may be a combination of software and/or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.

Fig. 4 is a structural block diagram of a positioning device for a mobile robot according to an embodiment of the present disclosure. As shown in Fig. 4, the device includes:

The obtaining module 42 is used to obtain the position coordinates of at least two target objects detected by the mobile robot in the second state when it is detected that the mobile robot is in the first state; the first state is the A state where the mobile robot has a pose failure, and the second state is a state where the mobile robot has no pose failure;

A determining module 44, configured to determine a first relative position between the mobile robot and the at least two target objects;

A calculation module 46, configured to calculate the position coordinates of the mobile robot according to the position coordinates of the at least two target objects and the first relative position.

Through the above modules, in the case of a pose failure of the mobile robot, obtain the position coordinates of at least two target objects when the mobile robot does not have a pose failure, and at the same time, determine the first relative position between the mobile robot and the at least two target objects , and then the position coordinates of the mobile robot can be calculated according to the first relative position and the position coordinates of the target object. By adopting the above technical solution, the problem that the position of the mobile robot cannot be determined in the case of a pose failure of the mobile robot is solved. Furthermore, in the case of a pose failure of the mobile robot, the position of the mobile robot can also be determined.

Optionally, the acquisition module 42 is also configured to identify at least two target objects based on the image data collected by the image acquisition component; and obtain the at least two target objects from a preset relationship library according to the identification of the at least two target objects The position coordinates of each target object; wherein, the preset relationship library stores the corresponding relationship between the identification of the target object and the position coordinates of the target object.

Optionally, the determination module 44 is further configured to determine the distance between the mobile robot and the at least two target objects according to the target distance measurement method to obtain at least two first distances; A first directional relationship between the mobile robot and the at least two objects; determining a first relative position between the mobile robot and the at least two target objects according to the first directional relationship and the at least two first distances .

Optionally, the calculation module 46 is also used to identify the target object based on the image data collected by the image acquisition component when the mobile robot is in the second state; determine the position coordinates of the target object; The object identifier and the position coordinates of the target object are correspondingly stored in a preset relationship library.

Optionally, the calculation module 46 is further configured to determine a second relative position between the target object and the mobile robot; determine the position coordinates of the target object according to the second relative position and the position coordinates of the mobile robot.

Optionally, the calculation module 46 is also used to determine the distance between the mobile robot and the target object according to the target ranging method to obtain a second distance; determine the distance between the mobile robot and the target object based on the image data collected by the image acquisition component. A second directional relationship of the target object; determining a second relative position between the mobile robot and the target object according to the second directional relationship and the second distance.

Optionally, the acquisition module 42 is also used to detect that the mobile robot is in the first state through at least one of the following methods, including: detecting that the mobile wheels of the mobile robot are idling; detecting that the mobile wheels of the mobile robot are not in contact with Target plane contact.

It should be noted that the above-mentioned modules can be realized by software or hardware. For the latter, it can be realized by the following methods, but not limited to this: the above-mentioned modules are all located in the same processor; or, the above-mentioned modules can be combined in any combination The forms of are located in different processors.

Embodiments of the present disclosure also provide a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps in any one of the above method embodiments when running.

Optionally, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

S1. When it is detected that the mobile robot is in the first state, acquire the position coordinates of at least two target objects detected by the mobile robot in the second state; the first state is when the mobile robot occurs A state of pose failure, the second state is a state where the mobile robot has no pose failure;

S2. Determine a first relative position between the mobile robot and the at least two target objects;

S3. Calculate the position coordinates of the mobile robot according to the position coordinates of the at least two target objects and the first relative position.

Optionally, in this embodiment, the above-mentioned storage medium may include but not limited to: various media capable of storing computer programs such as USB flash drive, read-only memory ROM, random access memory RAM, mobile hard disk, magnetic disk or optical disk.

Embodiments of the present disclosure also provide an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

Optionally, the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.

Optionally, in this embodiment, the above-mentioned processor may be configured to execute the following steps through a computer program:

Optionally, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementation manners, and details are not repeated in this embodiment.

Obviously, those skilled in the art should understand that each module or each step of the above-mentioned disclosure can be realized by a general-purpose computing device, and they can be concentrated on a single computing device, or distributed in a network composed of multiple computing devices Alternatively, they may be implemented in program code executable by a computing device so that they may be stored in a storage device to be executed by a computing device, and in some cases in an order different from that shown here The steps shown or described are carried out, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps among them are fabricated into a single integrated circuit module for implementation. As such, the present disclosure is not limited to any specific combination of hardware and software.

The above descriptions are only preferred embodiments of the present disclosure, and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

A positioning method for a mobile robot, characterized in that the method comprises:

When it is detected that the mobile robot is in the first state, the position coordinates of at least two target objects detected by the mobile robot in the second state are obtained; the first state is the pose of the mobile robot In an invalid state, the second state is a state in which the mobile robot has not experienced a pose failure;

determining a first relative position of the mobile robot to the at least two target objects;

The position coordinates of the mobile robot are calculated according to the position coordinates of the at least two target objects and the first relative position.
The positioning method of a mobile robot according to claim 1, wherein said obtaining the position coordinates of at least two target objects detected by said mobile robot in a second state comprises:

Identifying at least two target objects based on the image data collected by the image collection component;

According to the identifiers of the at least two target objects, the position coordinates of the at least two target objects are obtained by matching from a preset relationship library; wherein, the preset relationship library stores the identifiers of the target objects and the positions of the target objects Coordinate correspondence.
The positioning method for a mobile robot according to claim 1, wherein said determining the first relative position between said mobile robot and said at least two target objects comprises:

Determining the distance between the mobile robot and the at least two target objects according to the target ranging method to obtain at least two first distances;

determining a first directional relationship between the mobile robot and the at least two objects based on the image data collected by the image collection component;

A first relative position between the mobile robot and the at least two target objects is determined according to the first directional relationship and the at least two first distances.
The positioning method of a mobile robot according to claim 1, wherein said method further comprises:

When the mobile robot is in the second state, identifying the target object based on the image data collected by the image collection component;

determining the location coordinates of the target object;

The identifier of the target object and the position coordinates of the target object are correspondingly stored in a preset relationship library.
The positioning method of a mobile robot according to claim 4, wherein said determining the position coordinates of said target object comprises:

determining a second relative position of the target object to the mobile robot;

The position coordinates of the target object are determined according to the second relative position and the position coordinates of the mobile robot.
The positioning method of mobile robot according to claim 5, wherein, determining the second relative position of the target object and the mobile robot comprises:

Determining the distance between the mobile robot and the target object according to the target ranging method to obtain a second distance;

determining a second directional relationship between the mobile robot and the target object based on the image data collected by the image collection component;

A second relative position between the mobile robot and the target object is determined according to the second directional relationship and the second distance.
The positioning method for a mobile robot according to claim 1, wherein it is detected that the mobile robot is in the first state by at least one of the following methods, including:

Detecting that the mobile wheels of the mobile robot are idling;

It is detected that the mobile wheels of the mobile robot are not in contact with the target plane.
A device for determining global coordinates, including:

An acquisition module, configured to acquire the position coordinates of at least two target objects detected by the mobile robot in a second state when it is detected that the mobile robot is in the first state; the first state is the A state where the mobile robot has a pose failure, and the second state is a state where the mobile robot does not have a pose failure;

a determining module, configured to determine a first relative position between the mobile robot and the at least two target objects;

A calculation module, configured to calculate the position coordinates of the mobile robot according to the position coordinates of the at least two target objects and the first relative position.
A computer-readable storage medium, wherein a computer program is stored in the storage medium, wherein the computer program is configured to perform the method described in any one of claims 1 to 7 when running.
An electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to perform the method described in any one of claims 1 to 7 method.