WO2023078112A1

WO2023078112A1 - Method and apparatus for determining state of robot, and storage medium and electronic apparatus

Info

Publication number: WO2023078112A1
Application number: PCT/CN2022/127006
Authority: WO
Inventors: 孙伟
Original assignee: 追觅创新科技(苏州)有限公司
Priority date: 2021-11-05
Filing date: 2022-10-24
Publication date: 2023-05-11
Also published as: CN116091593A

Abstract

A method and apparatus for determining the state of a robot, and a storage medium and an electronic apparatus. The method comprises: acquiring a first position and a second position, which are determined by means of an odometer when a robot walks; optimizing the first position by using first point cloud data of a surrounding environment that is acquired by the robot at a first time point, so as to obtain a first posture; optimizing the second position by using second point cloud data of the surrounding environment that is acquired by the robot at a second time point, so as to obtain a second posture; determining a first short-time variation of the posture of the robot on the basis of the first posture and the second posture; determining a second short-time variation of the posture of the robot on the basis of the first point cloud data and the second point cloud data; and determining whether the state of the robot is abnormal by means of comparing the first short-time variation with the second short-time variation.

Description

Method and device for determining robot state, storage medium, electronic device

This disclosure claims the priority of the following patent application: a Chinese patent application submitted to the China Patent Office on November 5, 2021, with the application number 202111309025.6, and the title of the invention is "method and device for determining the state of a robot, a storage medium, and an electronic device"; 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 method and device for determining a state of a robot, a storage medium, and an electronic device.

Background technique

With the rapid development of artificial intelligence, more and more intelligent robots have entered people's lives, making people's lives more and more convenient.

With the popularity of robots, people encounter more and more problems in the process of using robots. For example, when the sweeping robot is working, it may encounter situations of getting stuck or slipping. In order to ensure the normal use of the sweeping robot, people need to judge this abnormal situation in time, so as to make corresponding treatment, otherwise it will cause inaccurate positioning, which will affect the cleaning efficiency of the machine and reduce the user experience. However, in the prior art, there is no solution capable of judging the abnormality of the robot in time.

Aiming at the above-mentioned problems existing in related technologies, no effective solution has been proposed yet.

Contents of the invention

Embodiments of the present disclosure provide a method and device for determining a state of a robot, a storage medium, and an electronic device, so as to at least solve the problem in the related art that an abnormality of a robot cannot be judged in time.

According to one aspect of the present disclosure, a method for determining the state of a robot is provided, including: acquiring a first position and a second position determined by an odometer when the robot is walking, wherein the first position is the robot The position at the first time point, the second position is the position of the robot at the second time point, and the time difference between the first time point and the second time point is less than a predetermined threshold; using the The first point cloud data of the surrounding environment acquired by the robot at the first time point is used to optimize the first position to obtain a first pose, and using the first point cloud data obtained by the robot at the second time point The obtained second point cloud data of the surrounding environment optimizes the second position to obtain a second attitude; determine a first short-term change in the attitude of the robot based on the first attitude and the second attitude; Determining a second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data; by comparing the first short-term variation with the second short-term variation , to determine whether the state of the robot is abnormal.

In an exemplary embodiment, using the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first pose includes: based on the The first point cloud data determines the target point cloud data of a predetermined area centered on the first position; matches the target point cloud data with the area map pre-generated by the robot to obtain the first pose .

In an exemplary embodiment, determining the target point cloud data of a predetermined area centered on the first position based on the first point cloud data includes: extracting the predetermined point cloud data from the first point cloud data The point cloud data of the area; the point cloud data of the predetermined area is rotated multiple times according to the predetermined rotation mode, so as to obtain the point cloud data of the predetermined area after each rotation; the predetermined area after each rotation The point cloud data of is determined as the target point cloud data.

In an exemplary embodiment, performing multiple rotations on the point cloud data of the predetermined area according to a predetermined rotation manner includes: performing multiple rotations on the point cloud data of the predetermined area according to a rotation manner of one degree at a time.

In an exemplary embodiment, determining the second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data includes: Match the second point cloud data to obtain a matching result; determine the rotation information of the second point cloud data relative to the first point cloud data based on the matching result; determine the second point cloud data based on the rotation information short-term variation.

In an exemplary embodiment, by comparing the first short-term variation with the second short-term variation, determining whether the state of the robot is abnormal includes: comparing the first short-term variation and the second short-term variation, determine the pose incremental difference between the first short-term variation and the second short-term variation; if it is determined that the pose incremental difference exceeds a predetermined threshold , determining that the state of the robot is an abnormal state; and determining that the state of the robot is a normal state when it is determined that the pose incremental difference does not exceed the predetermined threshold.

According to another aspect of the present disclosure, there is also provided a device for determining the state of a robot, including: an acquisition module, configured to acquire the first position and the second position determined by the odometer when the robot is walking, wherein the The first position is the position of the robot at the first time point, the second position is the position of the robot at the second time point, and the distance between the first time point and the second time point The time difference is less than a predetermined threshold; the optimization module is configured to use the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first posture, and use The second point cloud data of the surrounding environment acquired by the robot at the second time point optimizes the second position to obtain a second posture; a first determination module is configured to obtain a second posture based on the first posture and The second pose determines the first short-term change in the pose of the robot; the second determination module is configured to determine the first change in the pose of the robot based on the first point cloud data and the second point cloud data Two short-term variations; a third determining module, configured to determine whether the state of the robot is abnormal by comparing the first short-term variation with the second short-term variation.

In an exemplary embodiment, the optimization module includes: a determining unit configured to determine target point cloud data of a predetermined area centered on the first position based on the first point cloud data; a matching unit configured to and matching the target point cloud data with the area map pre-generated by the robot to obtain the first pose.

According to another embodiment of the present disclosure, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, wherein, when the program runs, the program described in any one of the above-mentioned embodiments is executed. described method.

According to another embodiment of the present disclosure, there is also provided an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to execute any one of the above implementations through the computer program. method described in the example.

Through this disclosure, it is possible to compare the positioning results of the robot relying on the odometer and the positioning results completely dependent on the laser, and to confirm in time whether the robot is abnormal based on the comparison results. This operation can be performed in real time without the need to introduce additional equipment. It ensures the real-time confirmation of the abnormal state of the robot, and effectively solves the problem that the abnormality of the robot cannot be judged in time in related technologies, thereby achieving timely confirmation of whether the robot state is abnormal, ensuring the working efficiency of the machine, and improving the user experience.

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 application. 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 a hardware structure of a method for determining a robot state according to an embodiment of the present disclosure;

2 is a flowchart of a method for determining a state of a robot according to an embodiment of the present disclosure;

Fig. 3 is a structural block diagram of an apparatus for determining a state of a robot according to an embodiment of the present disclosure.

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 application 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 in the embodiments of the present application 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 method for determining a state of a 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 (the processor 102 can include but not limited to processing devices such as microprocessor MCU or programmable logic device FPGA, etc.) and a memory 104 for storing data. In an exemplary embodiment, the above-mentioned mobile robot may also include a transmission device 106 and an input and output device 108 for communication functions. Those of ordinary skill in the art can understand that the structure shown in Figure 1 is only schematic, and it does not limit the structure of the above-mentioned mobile robot. For example, the mobile robot may also include more or fewer components than those shown in FIG. 1 , or have a different configuration that is functionally equivalent to or more functionally than that shown in FIG. 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 method for determining the state of the robot 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 is to realize 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 a 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 one example, the transmission device 106 may be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet in a wireless manner.

First, the application scenario of the present disclosure is described:

During the normal driving process, the robot relies on the odometer combined with the laser point cloud for joint positioning. When the machine is slipping or stuck, the wheels will spin idly, causing the odometer to be inaccurate, which in turn will cause inaccurate positioning of the machine and the inability to get out of trouble in time.

For example, the robot may need to drive to different areas during its work, and the road types in the path it drives may be diverse. When driving on a road with many debris, some small debris may be (For example, stones, wire balls, cables, plastic bags, etc.) are involved in the wheels, which may cause the robot to get stuck or slip. Since the robot has the ability to drive autonomously, there are few dedicated personnel near the robot. exist. In this case, when the robot fails, it cannot be detected in time, resulting in irreversible damage to the robot. To solve this problem, an embodiment of the present disclosure proposes a method for determining the state of the robot, which can promptly confirm whether the state of the robot is abnormal. The robots involved in the embodiments of the present disclosure may be sweeping robots, robots with transportation functions (for example, express transportation robots), or guide robots in shopping malls, etc., as long as they are robots with automatic driving capabilities, they can be included in this article. within the scope of public protection.

The present disclosure is described below in conjunction with embodiment:

In this embodiment, a method for determining the state of a robot is provided, as shown in Figure 2, the method includes the following steps:

S202. Obtain the first position and the second position determined by the odometer when the robot is walking, wherein the first position is the position of the robot at the first time point, and the second position is the the position of the robot at a second point in time, the time difference between the first point in time and the second point in time being less than a predetermined threshold;

S204. Using the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first pose, and using the robot at the second The second point cloud data of the surrounding environment acquired at the time point optimizes the second position to obtain a second attitude;

S206. Determine a first short-term change in the posture of the robot based on the first posture and the second posture;

S208. Determine a second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data;

S210. Determine whether the state of the robot is abnormal by comparing the first short-term variation with the second short-term variation.

In the above embodiment, the positioning result of the robot relying on the odometer can be compared with the positioning result completely relying on the laser. If the deviation of the result is large, it means that there is a big problem with the result given by the odometer. At this time, the machine may slip or be stuck in an abnormal situation. Therefore, corresponding processing can be performed in real time. The aforementioned predetermined threshold can be flexibly set, for example, set to 1 second, 2 seconds, 5 seconds, 10 seconds and so on.

In the above embodiments, the odometer is the pulse signal of the robot's wheels. The wheels will give pulse signals during walking, and the number of pulses of the left and right wheels (or other types of wheels) can be inferred how many times the left and right wheels have turned. So as to estimate the trajectory of the robot. The odometry is an input data used to calculate the pose of the machine. In the above embodiment, the approximate position of the machine movement can be inferred by the odometer first. Then use the point cloud to optimize (for example, match by brute force search to optimize the position, wherein, brute force search refers to matching point cloud and map near the odometer estimated position to find a match The pose with the highest value is used to optimize the positioning, that is, the data given by the odometer is used as the pose prior of the robot. Use the violent search (Scan Matching) method to optimize the given pose).

Wherein, the execution subject of the above-mentioned operations may be an intelligent robot (for example, a sweeping robot, a delivery robot, a guide robot, etc.), or a processor provided in an intelligent robot, or other devices with similar processing capabilities.

Through the above-mentioned embodiments, it is possible to compare the positioning results of the robot relying on the odometer and the positioning results completely relying on the laser, and timely confirm whether the robot is abnormal based on the comparison results. This operation can be performed in real time without the need to introduce additional equipment , which ensures the real-time confirmation of the abnormal state of the robot, effectively solves the problem that the abnormal state of the robot cannot be judged in time in related technologies, and then achieves timely confirmation of whether the robot state is abnormal, ensures the working efficiency of the machine, and improves the user experience.

In an exemplary embodiment, using the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first pose includes: based on the The first point cloud data determines the target point cloud data of a predetermined area centered on the first position; matches the target point cloud data with the area map pre-generated by the robot to obtain the first pose . In this embodiment, the predetermined area centered on the first position can be a circular area, a square area, a rectangular area, or other types of areas (as for the size of the area, it can be flexibly set according to the actual scene, For example, the circular area with the first position as the center and a radius of 10 centimeters can be determined as the above-mentioned predetermined area; or, the square area obtained by taking the first position as the center and extending 5 centimeters up, down, left, and right can be determined as The above-mentioned predetermined area; alternatively, the rectangular area obtained by taking the first position as the center, extending up and down by an additional 10 cm, and left and right by an additional 15 cm can be determined as the above-mentioned predetermined area). The matching method in this embodiment may be the aforementioned brute force matching method, or other matching methods, for example, selecting a predetermined number of point clouds from the target point cloud data to match with the regional map, and so on.

In an exemplary embodiment, determining the target point cloud data of a predetermined area centered on the first position based on the first point cloud data includes: extracting the predetermined point cloud data from the first point cloud data The point cloud data of the area; the point cloud data of the predetermined area is rotated multiple times according to the predetermined rotation mode, so as to obtain the point cloud data of the predetermined area after each rotation; the predetermined area after each rotation The point cloud data of is determined as the target point cloud data. Optionally, performing multiple rotations on the point cloud data in the predetermined area according to a predetermined rotation method includes: performing multiple rotations on the point cloud data in the predetermined area according to a rotation method of one degree each time, of course, other rotation methods may also be used. The rotation mode can be selected at each rotation angle of 5 degrees, for example, the rotation mode of 5 degrees at a time, and the rotation mode of 10 degrees at a time. It should also be noted that the angle of each rotation can also be different. The following is a description with specific examples:

First, suppose the odometry infers that the robot has walked 30 cm. At this moment, the point cloud of the surrounding environment is acquired by the laser sensor. Then, move the point cloud within a range of 5 cm up, down, left, and right with the estimated walking distance (that is, the end point after walking 30 cm) as the center, and obtain a total of 100 point clouds of 10*10. Rotate these point clouds one degree at a time to obtain 360*100 point clouds. Finally, match these point clouds with the map to match the best point cloud. The attitude corresponding to the point cloud is the most accurate. This attitude can be regarded as the current attitude of the robot to complete the optimization. Assume that the robot moves 30 cm from the odometer and the angle is 0 degrees. Through matching, it is known that the angle is 1 cm around this, and 3 degrees is the best match. After the optimization is completed, the posture of the robot becomes 31 cm. 3 degrees. Compare the real-time attitude with the attitude obtained by the same method before, and obtain the short-term change of the machine attitude.

In an exemplary embodiment, determining the second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data includes: Match the second point cloud data to obtain a matching result; determine the rotation information of the second point cloud data relative to the first point cloud data based on the matching result; determine the second point cloud data based on the rotation information short-term variation. In this embodiment, instead of relying on the odometer, the iterative closest point algorithm (Iterative Closest Point) is used to determine the pose of the robot completely relying on laser data. The ICP method is to infer the change of pose by comparing the two point clouds before and after and matching them in pairs. Assume that the machine obtains a frame of point cloud after moving 30 centimeters. Since the environment does not change much, the point cloud before 30 centimeters is matched with the point cloud after 30 centimeters, so that the degree of overlap of the point cloud is the highest. The point cloud and the point cloud The distance between point clouds is minimal. At this moment, the attitude of the previous frame point cloud rotated to the next frame point cloud is the estimated pose of the robot. This method can isolate the influence of the odometer. It can be seen that the short-term variation of the machine's attitude can be obtained by comparing the attitude obtained by laser matching in real time with the attitude obtained by laser matching.

In an exemplary embodiment, by comparing the first short-term variation with the second short-term variation, determining whether the state of the robot is abnormal includes: comparing the first short-term variation and the second short-term variation, determine the pose incremental difference between the first short-term variation and the second short-term variation; if it is determined that the pose incremental difference exceeds a predetermined threshold , determining that the state of the robot is an abnormal state; and determining that the state of the robot is a normal state when it is determined that the pose incremental difference does not exceed the predetermined threshold. In this embodiment, comparing the difference between the two short-term changes is actually comparing the pose incremental difference between the two short-term changes. It can be seen from the foregoing description that in the embodiment of the present disclosure, ICP tracks a posture change, and brute force search tracks a posture change, which can obtain the posture change amount within a certain period of time, for example, the posture change amount within one second. The attitude change of the two methods within one second should be too large, which indicates that there is a problem with the odometer or point cloud data. If the difference is greater than the preset value. It means that the a priori given by the odometer is inaccurate, and there is a problem of wheel slipping or jamming. At this time, certain means can be used to deal with this abnormal situation. When this situation is detected, if it is triggered in a short time, it may be considered that the wheels of the machine are slipping to increase the scope of violent search. If it is triggered for a long time, the robot can create a local map. When the state is normal, use the local map to perform small-scale relocation on the original map to calibrate the attitude.

Through the above-mentioned embodiment, it can be known in real time when the result of the odometer can be trusted and when an abnormal situation occurs to the robot. In this way, the abnormal situation is dealt with in time, so that the stability of the robot is greatly improved, the probability of getting out of trouble is increased, and the situation of machine positioning inaccuracy and overlapping images is significantly reduced.

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 such an 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 ROM/RAM, disk, CD) contains several instructions to enable a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present disclosure.

In this embodiment, a device for determining the state of a robot is also provided, and the device is used to implement the above embodiments and preferred implementation modes, and those that have been explained will not be repeated here. 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. 3 is a structural block diagram of a device for determining the state of a robot according to an embodiment of the present disclosure. As shown in Fig. 3 , the device includes:

An acquisition module 32, configured to acquire a first position and a second position determined by the odometer when the robot is walking, wherein the first position is the position of the robot at the first time point, and the second position is the position of the robot at the first time point. The position is the position of the robot at a second time point, and the time difference between the first time point and the second time point is less than a predetermined threshold;

An optimization module 34, configured to use the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first pose, and use the robot to The second point cloud data of the surrounding environment acquired at the second time point is optimized for the second position to obtain a second attitude;

A first determination module 36, configured to determine a first short-term change in the posture of the robot based on the first posture and the second posture;

A second determining module 38, configured to determine a second short-term change in the attitude of the robot based on the first point cloud data and the second point cloud data;

The third determining module 310 is configured to determine whether the state of the robot is abnormal by comparing the first short-term variation with the second short-term variation.

In an exemplary embodiment, the optimization module 34 includes: a determination unit, configured to determine target point cloud data of a predetermined area centered on the first position based on the first point cloud data; a matching unit, It is used to match the target point cloud data with the area map pre-generated by the robot to obtain the first pose.

In an exemplary embodiment, the determining unit is configured to determine the target point cloud data of a predetermined area centered on the first position based on the first point cloud data in the following manner: from the first The point cloud data of the predetermined area is extracted from the point cloud data; the point cloud data of the predetermined area is rotated multiple times according to the predetermined rotation mode, so as to obtain the point cloud data of the predetermined area after each rotation; The point cloud data of the predetermined area after each rotation is determined as the target point cloud data.

In an exemplary embodiment, the determining unit is configured to perform multiple rotations on the point cloud data of the predetermined area according to a predetermined rotation method in the following manner: the point cloud data of the predetermined area is rotated by one degree each time Cloud data undergoes multiple rotations.

In an exemplary embodiment, the second determination module 38 is configured to determine the second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data in the following manner : Matching the first point cloud data and the second point cloud data to obtain a matching result; determining the rotation of the second point cloud data relative to the first point cloud data based on the matching result information; determining the second short-term variation based on the rotation information.

In an exemplary embodiment, the third determining module 310 is configured to determine whether the state of the robot is abnormal by comparing the first short-term variation with the second short-term variation in the following manner : By comparing the first short-term variation with the second short-term variation, determine the pose incremental difference between the first short-term variation and the second short-term variation; When the pose incremental difference exceeds a predetermined threshold, it is determined that the state of the robot is an abnormal state; when it is determined that the pose incremental difference does not exceed the predetermined threshold, it is determined that the state of the robot is normal state.

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.

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

S1. Obtain the first position and the second position determined by the odometer when the robot is walking, wherein the first position is the position of the robot at the first time point, and the second position is the the position of the robot at a second point in time, the time difference between the first point in time and the second point in time being less than a predetermined threshold;

S2. Using the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first pose, and using the robot at the second The second point cloud data of the surrounding environment acquired at the time point optimizes the second position to obtain a second attitude;

S3. Determine a first short-term change in the posture of the robot based on the first posture and the second posture;

S4. Determine a second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data;

S5. Determine whether the state of the robot is abnormal by comparing the first short-term variation with the second short-term variation.

In an exemplary embodiment, the above-mentioned computer-readable storage medium may include but not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM) , mobile hard disk, magnetic disk or optical disk and other media that can store computer programs.

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.

In an exemplary embodiment, the electronic device may further include a transmission device and an input and output device, wherein the transmission device is connected to the processor, and the input and output device is connected to the processor.

In an exemplary embodiment, the above-mentioned processor may be configured to execute the following steps through a computer program:

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 In fact, they can be implemented in program code executable by a computing device, and thus, they can be stored in a storage device to be executed by a computing device, and in some cases, can be executed in an order different from that shown here. Or described steps, or they are 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 method for determining the state of a robot, comprising:

Obtaining a first position and a second position determined by the odometer when the robot is walking, wherein the first position is the position of the robot at the first time point, and the second position is the position of the robot at a position at a second point in time, the time difference between the first point in time and the second point in time being less than a predetermined threshold;

Using the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first pose, and using the robot at the second time point Optimizing the second position on the acquired second point cloud data of the surrounding environment to obtain a second attitude;

determining a first short-term change in the posture of the robot based on the first posture and the second posture;

determining a second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data;

By comparing the first short-term variation with the second short-term variation, it is determined whether the state of the robot is abnormal.
The method according to claim 1, wherein the first position is optimized by using the first point cloud data of the surrounding environment acquired by the robot at the first time point to obtain a first pose, comprising:

determining target point cloud data of a predetermined area centered on the first position based on the first point cloud data;

Matching the target point cloud data with the area map pre-generated by the robot to obtain the first pose.
The method according to claim 2, wherein determining the target point cloud data of a predetermined area centered on the first position based on the first point cloud data comprises:

extracting point cloud data of the predetermined area from the first point cloud data;

performing multiple rotations on the point cloud data of the predetermined area according to a predetermined rotation manner, so as to obtain the point cloud data of the predetermined area after each rotation;

The point cloud data of the predetermined area after each rotation is determined as the target point cloud data.
The method according to claim 3, wherein performing multiple rotations on the point cloud data in the predetermined area according to a predetermined rotation method comprises:

The point cloud data in the predetermined area is rotated multiple times in a rotation manner of one degree at a time.
The method according to claim 1, wherein determining the second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data comprises:

matching the first point cloud data and the second point cloud data to obtain a matching result;

determining rotation information of the second point cloud data relative to the first point cloud data based on the matching result;

The second short-term variation is determined based on the rotation information.
The method according to claim 1, wherein, by comparing the first short-term variation with the second short-term variation, determining whether the state of the robot is abnormal comprises:

By comparing the first short-term variation and the second short-term variation, determine the pose incremental difference between the first short-term variation and the second short-term variation;

When it is determined that the pose incremental difference exceeds a predetermined threshold, determining that the state of the robot is an abnormal state;

If it is determined that the pose incremental difference does not exceed the predetermined threshold, it is determined that the state of the robot is a normal state.
A device for determining the state of a robot, including:

An acquisition module, configured to acquire a first position and a second position determined by the odometer when the robot is walking, wherein the first position is the position of the robot at the first time point, and the second position is the position of the robot at a second time point, and the time difference between the first time point and the second time point is less than a predetermined threshold;

An optimization module, configured to use the first point cloud data of the surrounding environment acquired by the robot at the first time point to optimize the first position to obtain a first pose, and use the robot at the first point in time to optimize the first position. Optimizing the second position on the second point cloud data of the surrounding environment acquired at the second time point to obtain a second attitude;

A first determination module, configured to determine a first short-term change in the posture of the robot based on the first posture and the second posture;

A second determining module, configured to determine a second short-term variation of the attitude of the robot based on the first point cloud data and the second point cloud data;

The third determining module is configured to determine whether the state of the robot is abnormal by comparing the first short-term variation with the second short-term variation.
The device according to claim 7, wherein the optimization module comprises:

a determining unit, configured to determine target point cloud data of a predetermined area centered on the first position based on the first point cloud data;

A matching unit, configured to match the target point cloud data with an area map pre-generated by the robot to obtain the first pose.
A computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 6 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 execute the method described in any one of claims 1 to 6 through the computer program .