WO2022252482A1

WO2022252482A1 - Robot, and environment map construction method and apparatus therefor

Info

Publication number: WO2022252482A1
Application number: PCT/CN2021/126706
Authority: WO
Inventors: 汤煜; 熊友军
Original assignee: 深圳市优必选科技股份有限公司
Priority date: 2021-05-31
Filing date: 2021-10-27
Publication date: 2022-12-08
Also published as: CN113297259A

Abstract

A robot, and an environment map construction method and apparatus therefor. The method comprises: acquiring a sensing data frame during a moving process of a robot, and an absolute position, and generating a sensing data frame library; according to an absolute position corresponding to a sensing data frame currently acquired by the robot, and a preset distance threshold value, searching the sensing data frame library for an absolute position that matches the current absolute position, and a sensing data frame corresponding to the matching absolute position; and matching the found sensing data frame with the currently acquired sensing data frame, and performing loop closure optimization and environment map construction according to a matching result. A sensing data frame is screened by means of an absolute position, such that the problem of detecting a wrong loop closure point in a similar scenario can be avoided; and the sensing data frame is screened by means of the absolute position, such that the probability of being unable to complete matching can be reduced, thereby facilitating reducing the matching calculation amount of the sensing data frame, and improving the efficiency of environment map construction.

Description

Method and device for constructing robot and its environment map

This application claims priority to a Chinese patent application with application number 202110598469.X filed at the China Patent Office on May 31, 2021, the entire contents of which are incorporated herein by reference.

technical field

The present application belongs to the field of robots, and in particular relates to a method and device for constructing a robot and its environment map.

Background technique

Before a robot performs a task, it usually needs to build a map of the scene where the robot is located. According to the map constructed by the robot, the positioning accuracy can be improved, so that the path ruled by the robot is more reasonable and the navigation is safer. When the robot is building a map, it usually recursively deduces the pose of the subsequent keyframes based on the motion estimation of the robot and the initial pose of the first keyframe of the robot. Due to the accumulation of errors, the poses of subsequent key frames will become larger and larger, which is not conducive to the robot's accurate mapping.

In order to reduce the cumulative error of the robot, after the robot acquires a new key frame, it performs similarity detection between the acquired key frame and the previous key frame to determine whether the current position of the robot is consistent with the previous position, that is, to detect the loop point through loop detection . The robot can correct the cumulative error according to the loop detection to improve the accuracy of the map.

However, when the robot compares and matches the newly acquired key frame with the previous key frame, if the global matching method is used, the calculation amount is large and the matching time is long. If the local matching is used, the matching may not be successful. probability. If there is repetitive content in the scene where the robot is located, such as similar rooms or warehouses, it is easy to generate wrong loops, which is not conducive to accurate and effective map construction.

technical problem

In view of this, the embodiment of the present application provides a method and device for constructing a robot and its environment map to solve the problem that the matching efficiency of the loop closure detection is not high, the loop closure detection is prone to errors, or the loop closure cannot be detected when the environment map is constructed in the prior art. Point of question.

technical solution

The first aspect of the embodiments of the present application provides a method for constructing a robot environment map, the method comprising:

Obtain the sensing data frame during the movement of the robot, and obtain the absolute position corresponding to the sensing data frame, and generate a sensing data frame library according to the acquired sensing data frame and absolute position;

According to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, search the absolute position matching the current absolute position in the sensing data frame library, and the sensing data corresponding to the matched absolute position frame;

Match the searched sensor data frame with the currently acquired sensor data frame, and perform loopback optimization and environment map construction according to the matching result.

With reference to the first aspect, in a first possible implementation manner of the first aspect, the sensor data frame is a key frame.

In combination with the first possible implementation of the first aspect, in the second possible implementation of the first aspect, acquiring the sensing data frame during the movement of the robot includes one or more of the following methods:

Determine the key frame during the robot's movement according to the preset movement distance threshold;

Or, according to the preset rotation angle threshold, determine the key frame during the movement of the robot;

Alternatively, according to a preset difference degree threshold, key frames during the movement of the robot are determined.

In combination with the first aspect or the first possible implementation of the first aspect, in the third possible implementation of the first aspect, according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, in Find the absolute position matched by the current absolute position in the sensing data frame library, and the sensing data frame corresponding to the matched absolute position, including:

Calculate the distance between the absolute position corresponding to the currently acquired sensing data frame and the absolute position of the sensing data frame library;

If the calculated distance is less than the preset distance threshold, then determine the absolute position in the sensing data frame library corresponding to the distance;

According to the corresponding relationship between the absolute position and the sensing data frame in the sensing data frame database, the sensing data frame corresponding to the determined absolute position is searched.

In combination with the first aspect or the first possible implementation of the first aspect, in the fourth possible implementation of the first aspect, the determined sensing data frame is matched with the currently acquired sensing data frame, and according to the matching The result is loopback optimization and environment map construction, including:

calculating the similarity between the determined sensing data frame and the currently acquired sensing data frame;

Comparing the similarity with a preset similarity threshold, selecting a sensing data frame whose similarity is greater than the predetermined similarity threshold and located in the sensing data frame library;

The trajectory of the robot will be optimized based on the selected sensor data frame and absolute position;

The environment map is constructed according to the optimized trajectory.

With reference to the first aspect, in a fifth possible implementation manner of the first aspect, obtaining the absolute position corresponding to the sensing data frame includes:

According to the preset UWB base station, the absolute position corresponding to the robot when acquiring the sensing data frame is determined.

With reference to the first aspect, in the sixth possible implementation of the first aspect, according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, the current sensing data frame library is searched for When the absolute position matches the absolute position, if the absolute position matching the current absolute position is not found in the sensor data frame library, the currently acquired sensor data frame and the absolute position are added to the Sensory data frame library.

The second aspect of the embodiment of the present application provides a robot environment map construction device, the device comprising:

The data acquisition unit is used to acquire the sensing data frame during the movement of the robot, and acquire the absolute position corresponding to the sensing data frame, and generate the sensing data frame library according to the acquired sensing data frame and absolute position;

The data search unit is used to search the absolute position matched by the current absolute position in the sensing data frame library according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, and the matched absolute position The sensor data frame corresponding to the position;

The sensing data frame matching unit is configured to match the searched sensing data frame with the currently acquired sensing data frame, and perform loopback optimization and environment map construction according to the matching result.

The third aspect of the embodiments of the present application provides a robot, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, it realizes The steps of the method according to any one of the first aspect.

The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and it is characterized in that, when the computer program is executed by a processor, any one of the above aspects of the first aspect can be implemented. steps of the method described in the item.

Beneficial effect

Compared with the prior art, the embodiment of the present application has the beneficial effect that: during the movement of the robot, the sensing data frame currently acquired by the robot and its corresponding absolute position are obtained, and according to the absolute position, the pre-acquired sensing data frame Find the corresponding absolute position in the data frame library, match the sensor data frame corresponding to the searched relative position with the currently acquired sensor data frame, and perform loopback optimization and environment map construction according to the matching result. Since the sensing data frame is filtered by the absolute position, the problem of detecting a wrong loopback point in a similar scene can be avoided, and the sensing data frame is filtered by the absolute position, which can reduce the probability that the matching cannot be completed, which is beneficial to reduce the sensing data frame The amount of matching calculations can improve the construction efficiency of environmental maps.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the accompanying drawings that need to be used in the descriptions of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only for the present application For some embodiments, those of ordinary skill in the art can also obtain other drawings based on these drawings without paying creative efforts.

FIG. 1 is a schematic diagram of a robot loopback detection in the prior art provided by an embodiment of the present application;

Fig. 2 is a schematic diagram of the implementation flow of a robot environment map construction method provided by the embodiment of the present application;

Fig. 3 is a schematic diagram of a position correction provided by the embodiment of the present application;

Fig. 4 is a schematic diagram of the moving trajectory of an adjusted robot provided in the embodiment of the present application;

FIG. 5 is a schematic diagram of an environment map construction device for a robot provided in an embodiment of the present application;

Fig. 6 is a schematic diagram of a robot provided by an embodiment of the present application.

Embodiments of the present invention

In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

In order to illustrate the technical solutions described in this application, specific examples are used below to illustrate.

Before the robot performs the task, it needs to construct the current scene map of the robot, so as to plan the trajectory or route of the task according to the constructed scene map.

When a robot constructs a scene map, the robot usually constructs a continuous and consistent scene map around the environment based on the motion estimation of the robot and combined with the collected scene data. When obtaining the motion estimation of the robot, the robot usually fixes the initial position of the first laser frame, and combines the motion information of the robot to determine the pose of each subsequent laser frame. When an error occurs in one of the pose estimations, the robot will add it to the subsequent pose calculation results, which is not conducive to building a globally consistent trajectory and map.

In order to reduce the pose estimation error generated by motion estimation, the robot can optimize the pose of the robot by means of loop closure detection. For example, the robot compares and matches the currently collected laser frame with the previously collected laser frame, and determines the loopback point of the robot's motion trajectory according to the matched laser frame. The robot adjusts the trajectory of the robot according to the detected loop points, so as to achieve the purpose of reducing the pose estimation error generated by motion estimation.

In loop detection, if the scene where the map is built is large, the robot acquires more laser frames. If global matching is used, that is, the current laser frame is matched with each previously stored laser frame, the amount of calculation is large and time-consuming. longer. If partial matching is used, it is necessary to ensure that the cumulative error is within a small range in order to successfully match. In the schematic diagram of the robot movement trajectory shown in Figure 1, the robot starts from point O, and the solid line trajectory in the figure is obtained according to motion estimation, and the dotted line in the figure is the actual trajectory of the robot. When the robot is at the O' position, the robot searches for laser frames that can be matched within the predetermined range of the estimated position through local matching. Since the matching degree between the searched laser frame and the laser frame at position O' is very low, the robot may not be able to match successfully.

If there are multiple similar scenes in the current scene of the robot, such as similar rooms or warehouses, etc. Camera or laser frames may have mismatches, rendering the resulting map garbled and unusable.

In order to overcome the above problems, the embodiment of the present application proposes a robot environment map construction method, by adding absolute position information during the movement of the robot, to establish the absolute position corresponding to the sensing data frame acquired by the robot. The position that can be matched is screened out through the matching and screening of the absolute position, and then the result of the loop detection is determined through the matching of the sensor data frame, thereby improving the accuracy of the loop detection and the accuracy of the map construction. Due to the screening of the absolute position, the mismatching problem of similar scenes can be avoided, and it is beneficial to improve the matching efficiency.

As shown in Figure 2, it is a schematic diagram of the implementation process of a robot environment map construction method proposed in the embodiment of the present application, including:

In S201, the sensing data frame during the moving process of the robot is acquired, and the absolute position corresponding to the sensing data frame is acquired, and a sensing data frame library is generated according to the acquired sensing data frame and absolute position.

The sensing data frame in the embodiment of the present application may include information such as scene images, distances between obstacles in the scene and the robot, and poses of the robot. Wherein, the scene image may be collected by a camera, or may be a laser image collected by a laser radar. The distance between the obstacle in the scene and the robot can be detected by laser radar, or the distance between the obstacle in the scene where the robot is located and the robot can be collected by a binocular camera. The pose information of the robot can be determined by the odometer and IMU (English full name is Inertial Measurement Unit, Chinese full name is inertial measurement unit) of the robot.

The absolute position can be determined by the robot in combination with an auxiliary positioning device. In a possible implementation manner, a positioning base station may be set in the scene where the robot is located, and a detection signal is sent through the positioning base station. The robot determines the distance between the robot and the positioning base station according to the received positioning signal. The absolute position of the robot is determined according to the determined two or more than three distances and the preset position of the positioning base station.

Wherein, the positioning base station may be a UWB (English full name is Ultra Wideband, Chinese full name is Ultra Wideband) base station. Alternatively, the positioning base station may also be a Bluetooth base station, such as iBeacon positioning based on Bluetooth 4.0, or Wifi positioning based on a Wifi base station.

After the absolute position of the robot and the sensing data frame of the robot are acquired, a corresponding relationship between the absolute position and the sensing data frame is established. It is convenient to quickly determine the sensor data frame of the robot according to the absolute position.

When the robot starts to move, the sensing data frame obtained from the starting position of the robot can be added to the sensing data frame library. During the movement of the robot, if the acquired sensing data frame corresponds to the absolute position, filter out the absolute position in the sensing data frame library that matches the currently acquired absolute position. If the absolute position matching the currently acquired absolute position cannot be filtered out, or the sensory data frame corresponding to the filtered absolute position cannot match the current sensory data frame, the currently acquired sensory data frame and its corresponding The absolute position of is added to the sensory data frame library. That is, during the moving process of the robot, the data in the sensing data frame library is updated through comparison and matching.

In a possible implementation manner, in order to improve the efficiency of scene map construction, the sensing data frame may be a key frame. The key frame is a representative data frame selected from common data frames.

In some implementation manners, the keyframes may be determined according to repetition information between keyframes. For example, the first key frame can be determined according to the starting position. When determining the subsequent key frame, it can be determined by determining the similarity between the current data frame and the adjacent previous key frame. For example, it may be determined to generate a new key frame when the similarity is greater than a predetermined key frame similarity constant.

In some implementations, whether to generate a new keyframe can be determined based on the distance the robot moves. The first keyframe can be determined according to the starting position. To determine the next key frame, it may be determined whether to generate a new key frame according to the moving distance of the robot relative to the position corresponding to the previous key frame. For example, when the moving distance is greater than a predetermined key frame distance constant, a new key frame is generated.

In some implementation manners, whether to generate a new key frame may be determined according to the rotation angle of the robot. The first keyframe can be determined according to the starting position. When determining the next key frame, whether to generate a new key frame can be determined according to whether the rotation angle of the robot is greater than a predetermined key frame angle constant.

It can be understood that one or more of the above methods for determining the key frame may be used. That is, when any trigger condition is met, a new keyframe is generated.

When the sensing data (image data, distance data, and trajectory data) is collected in the way of key frames, it can effectively reduce the amount of sensing data collection and comparison calculation, and improve the construction efficiency of the scene map.

In S202, according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, the absolute position matching the current absolute position is searched in the sensing data frame library, and the matched absolute position corresponds to sensor data frame.

It is assumed that n-1 sensing data frames are stored in the sensing data frame library (the value of n changes with the update of the sensing database). The absolute position corresponding to the nth sensing data frame currently collected is obtained, for example, it may be expressed as pn(xn, yn). When screening the sensing data frames, preliminary screening can be performed according to the matching degree of the absolute position.

In the screening process, the absolute position pn(xn, yn) corresponding to the currently acquired sensing data frame can be calculated to match any absolute position pk(xk, yk) in the data sensing frame library, k<n. The distance T between the absolute position pn and any absolute position pk in the data sensing frame library can be calculated:

T＝∪ _k sqrt((x _s -x _k ) ² +(y _s -y _k ) ² )≤R(k＝1,…,s-1)

When the calculated distance is less than the preset distance threshold, the absolute distance in the sensing data frame corresponding to the distance T can be selected, and according to the correspondence between the absolute position in the data sensing frame library and the sensing data frame Relationship, find the sensor data frame corresponding to the selected absolute position.

In the schematic diagram of position correction shown in Figure 3, when the robot detects that the relative position of the robot is O' through the odometer or the inertial measurement unit, the sensor data frame corresponding to the position is obtained. At this time, according to the absolute positioning device of the robot, it can be determined that the absolute position of the robot is O'(P'), and according to the preset distance threshold R, the search range corresponding to the dotted circle in Figure 3 can be obtained, and it is determined that the The absolute position in the search range that belongs to the sensory data frame library. For example, it may be determined that the absolute position O is within the search range. According to the absolute position O, find the corresponding sensing data frame.

The absolute position in a sensing data frame library is found in the schematic diagram of position correction shown in Fig. 3 . In a possible implementation, multiple absolute positions can be found within the determined range. According to the found multiple absolute positions, multiple corresponding sensing data frames are determined.

In S203, the searched sensing data frame is matched with the currently acquired sensing data frame, and loop-closing optimization and environment map construction are performed according to the matching result.

When one or more sensor data frames are found according to the absolute position, one or more sensor data frames can be matched with the currently acquired sensor data frames, that is, the calculated sensor data frames and the currently acquired sensor data frames The similarity of the sense data frame. If the similarity is greater than a predetermined similarity threshold, the sensing data frame and the absolute position are selected to optimize the moving trajectory of the robot. For example, the loopback point of the robot can be determined according to the absolute position, and the attitude information of the robot at the loopback point can be determined according to the sensor data frame. According to the determined loop point and posture information, the moving track of the robot is adjusted, and the posture change information of the robot during the moving process is adjusted. An environment map is constructed from the adjusted trajectory and adjusted pose change information.

In the schematic diagram of the adjusted moving trajectory of the robot as shown in Figure 4, the absolute position O'(P') of the robot is determined according to the UWB base station set in the scene where the robot is located, and the current absolute position O'(P') of the robot is detected. P') and the absolute position O in the moving track of the robot are the loop-back point, and the attitude of the moving track of the robot is adjusted according to the loop-back point, and the adjusted moving track of the robot shown in FIG. 4 is obtained. According to the adjusted trajectory and posture, the environment map of the scene where the robot is located can be determined more accurately. In addition, since the application uses absolute distance screening, it can reduce the amount of matching calculations for sensing data frames, and at the same time avoid false detection of loopback points in similar scenes, reducing the probability of failure to match successfully in partial matching.

In a possible implementation, when the loopback point is not detected, the application can also correct the robot's movement trajectory according to the absolute position detected by the robot, combined with the robot's movement trajectory, so as to further improve the robot map construction the accuracy.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

FIG. 5 is a schematic diagram of an apparatus for constructing an environment map for a robot provided in an embodiment of the present application, and the apparatus corresponds to the method for constructing an environment map for a robot in FIG. 2 . As shown in Figure 5, the device includes:

The data acquisition unit 501 is configured to acquire the sensing data frame during the movement of the robot, and acquire the absolute position corresponding to the sensing data frame, and generate a sensing data frame library according to the acquired sensing data frame and absolute position;

The data search unit 502 is configured to search the absolute position matched by the current absolute position in the sensing data frame library according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, and the matched absolute position The sensor data frame corresponding to the absolute position;

The sensing data frame matching unit 503 is configured to match the searched sensing data frame with the currently acquired sensing data frame, and perform loopback optimization and environment map construction according to the matching result.

In order to further reduce the calculation amount of map construction, the sensing data frame may be a key frame.

When determining the key, one or more of the following methods may be included:

In a possible implementation, the data acquisition unit may be used for:

In a possible implementation, the sensing data frame matching unit may be used for:

The environment map is constructed according to the optimized trajectory.

In order to improve the accuracy of map construction, the sensor data frame library can be updated in real time, and according to the absolute position corresponding to the sensor data frame currently acquired by the robot and the preset distance threshold, search in the sensor data frame library When the current absolute position matches the absolute position, if the absolute position matching the current absolute position is not found in the sensing data frame library, add the currently acquired sensing data frame and the absolute position to The sensory data frame library.

Wherein, the absolute position in the embodiment of the present application may be determined according to a positioning signal sent by a preset UWB base station.

Fig. 6 is a schematic diagram of a robot provided by an embodiment of the present application. As shown in Figure 6, the robot 6 of this embodiment includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and operable on the processor 60, such as the environment map construction program of the robot . When the processor 60 executes the computer program 62, the steps in the above embodiments of the environment map construction method for each robot are realized. Alternatively, when the processor 60 executes the computer program 62, the functions of the modules/units in the above-mentioned device embodiments are implemented.

Exemplarily, the computer program 62 can be divided into one or more modules/units, and the one or more modules/units are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the robot 6 .

The robot may include, but not limited to, a processor 60 and a memory 61 . Those skilled in the art can understand that Fig. 6 is only an example of the robot 6, and does not constitute a limitation to the robot 6, and may include more or less components than shown in the illustration, or combine certain components, or different components, for example The robot may also include input and output devices, network access devices, buses, and the like.

The so-called processor 60 can be a central processing unit (Central Processing Unit, CPU), and can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

The memory 61 may be an internal storage unit of the robot 6 , such as a hard disk or memory of the robot 6 . Described memory 61 also can be the external storage device of described robot 6, for example the plug-in type hard disk that is equipped on described robot 6, smart memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, Flash card (Flash Card), etc. Further, the memory 61 may also include both an internal storage unit of the robot 6 and an external storage device. The memory 61 is used to store the computer program and other programs and data required by the robot. The memory 61 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the above system, reference may be made to the corresponding process in the foregoing method embodiments, and details will not be repeated here.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the device/terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the integrated module/unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments in this application can also be completed by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium. The computer program When executed by a processor, the steps in the above-mentioned various method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, computer-readable media Excluding electrical carrier signals and telecommunication signals.

The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still implement the foregoing embodiments Modifications to the technical solutions described in the examples, or equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the application, and should be included in the Within the protection scope of this application.

Claims

A method for constructing an environment map of a robot, characterized in that the method comprises:

Obtain the sensing data frame during the movement of the robot, and obtain the absolute position corresponding to the sensing data frame, and generate a sensing data frame library according to the acquired sensing data frame and absolute position;

According to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, search the absolute position matching the current absolute position in the sensing data frame library, and the sensing data corresponding to the matched absolute position frame;

Match the searched sensor data frame with the currently acquired sensor data frame, and perform loopback optimization and environment map construction according to the matching result.
The method according to claim 1, wherein the sensing data frame is a key frame.
The method according to claim 2, wherein obtaining the sensing data frame during the movement of the robot includes one or more of the following methods:

Determine the key frame during the robot's movement according to the preset movement distance threshold;

Or, according to the preset rotation angle threshold, determine the key frame during the movement of the robot;

Alternatively, according to a preset difference degree threshold, key frames during the movement of the robot are determined.
The method according to claim 1 or 2, characterized in that, according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, the current absolute position matching is searched in the sensing data frame library The absolute position of , and the sensor data frame corresponding to the matched absolute position, including:

Calculate the distance between the absolute position corresponding to the currently acquired sensing data frame and the absolute position of the sensing data frame library;

If the calculated distance is less than the preset distance threshold, then determine the absolute position in the sensing data frame library corresponding to the distance;

According to the corresponding relationship between the absolute position and the sensing data frame in the sensing data frame database, the sensing data frame corresponding to the determined absolute position is searched.
The method according to claim 1 or 2, wherein the determined sensing data frame is matched with the currently acquired sensing data frame, and loopback optimization and environment map construction are performed according to the matching result, including:

calculating the similarity between the determined sensing data frame and the currently acquired sensing data frame;

Comparing the similarity with a preset similarity threshold, selecting a sensing data frame whose similarity is greater than the predetermined similarity threshold and located in the sensing data frame library;

The trajectory of the robot will be optimized based on the selected sensor data frame and absolute position;

The environment map is constructed according to the optimized trajectory.
The method according to claim 1, wherein obtaining the absolute position corresponding to the sensing data frame comprises:

According to the preset UWB base station, the absolute position corresponding to the robot when acquiring the sensing data frame is determined.
The method according to claim 1, characterized in that, according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, the absolute position matching the current absolute position is searched in the sensing data frame library. position, if an absolute position matching the current absolute position is not found in the sensing data frame library, add the currently acquired sensing data frame and the absolute position to the sensing data frame library .
A robot environment map construction device, characterized in that the device comprises:

The data acquisition unit is used to acquire the sensing data frame during the movement of the robot, and acquire the absolute position corresponding to the sensing data frame, and generate the sensing data frame library according to the acquired sensing data frame and absolute position;

The data search unit is used to search the absolute position matched by the current absolute position in the sensing data frame library according to the absolute position corresponding to the sensing data frame currently acquired by the robot and the preset distance threshold, and the matched absolute position The sensor data frame corresponding to the position;

The sensing data frame matching unit is configured to match the searched sensing data frame with the currently acquired sensing data frame, and perform loopback optimization and environment map construction according to the matching result.
A robot, comprising a memory, a processor, and a computer program stored in the memory and operable on the processor, characterized in that, when the processor executes the computer program, the computer program according to claims 1 to 7 is realized. The step of any described method.
A computer-readable storage medium storing a computer program, wherein the computer program implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed by a processor.