Map construction method and device, electronic equipment and storage medium

Abstract

The invention relates to a map construction method and device, electronic equipment and a storage medium. The map construction method comprises the following steps: determining a target following object; the following target follows the object to move to a plurality of position points, and a first map is constructed at each position point; and determining a target map according to the first map at each position point. According to the method, the target following object guides the robot to construct the map, so that the map can be constructed in the expected area of the user without additional control operation, and the use experience of the user can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of robotics, and in particular to a map construction method, device, electronic device, and storage medium. Background Art

[0002] With the continuous development and maturity of robotics technology, a wide variety of robots have begun to enter our daily lives. Map building is the most fundamental function of robots, which involves scanning their surroundings and creating a 3D or 2D map to facilitate movement within them. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides a map construction method, device, electronic device and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, a map construction method is provided, the method comprising:

[0005] Determine the target to follow;

[0006] Following the target following object to move to a plurality of location points, and constructing a first map at each of the location points;

[0007] A target map is determined according to the first map at each of the location points.

[0008] In an exemplary embodiment, constructing a first map at each of the location points includes:

[0009] At each of the position points, acquiring a scene image and a depth image of the scene image;

[0010] Determine, based on the depth image, a first position coordinate of each scene pixel point in the scene image in a robot coordinate system, wherein the scene pixel point represents all pixel points in the scene image except for pixel points in an area where the target following object is located;

[0011] Construct the first map according to the first location coordinates.

[0012] In an exemplary embodiment, constructing the first map according to the first location coordinates includes:

[0013] Determine the second position coordinates of the robot in the world coordinate system;

[0014] Determining a third position coordinate of each of the scene pixels in a world coordinate system according to the first position coordinate and the second position coordinate;

[0015] The first map is constructed according to the third position coordinates.

[0016] In an exemplary embodiment, determining the target map based on the first map at each of the location points includes:

[0017] For each of the location points, determining a second map of the location point based on the first map of the location point and the first maps of historical location points;

[0018] The target map is determined according to the second map of the location point.

[0019] In an exemplary embodiment, determining the target map based on the second map of the location point includes:

[0020] When the position point is not the end position point, determining a next position point according to the second map of the position point and the target follow-up object until the position point is the end position point;

[0021] When the location point is a termination location point, the second map of the location point is determined to be the target map.

[0022] In an exemplary embodiment, determining the next location point based on the second map of the location point and the target tracking object includes:

[0023] At the position point, acquiring a depth image of the scene image;

[0024] determining, based on the depth image, a fourth position coordinate of the target following object in the scene image in the robot coordinate system;

[0025] determining a follow path based on the second map of the location point and the fourth location coordinates;

[0026] The next location point is determined according to the following path.

[0027] In an exemplary embodiment, the method further comprises:

[0028] When the distance between the robot and the target following object is less than or equal to a distance threshold, and the target following object does not move within a preset time period, the position point of the robot is determined as the end position point.

[0029] In an exemplary embodiment, the method further comprises:

[0030] At each of the position points, the target following object is marked in the scene image.

[0031] According to a second aspect of an embodiment of the present disclosure, a map construction device is provided, the device comprising:

[0032] A first determining module is configured to determine a target following object;

[0033] A mapping module is configured to follow the target object to a plurality of locations and construct a first map at each location;

[0034] The second determination module is configured to determine a target map according to the first map at each of the location points.

[0035] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0036] processor;

[0037] a memory for storing processor-executable instructions;

[0038] The processor is configured to execute the method as described in the first aspect of the embodiment of the present disclosure.

[0039] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the method described in the first aspect of the embodiment of the present disclosure.

[0040] The above method disclosed in the present invention has the following beneficial effects: the method guides the robot to build a map by the target following object, and can build a map in the user's desired area without additional control operations, which can improve the user experience.

[0041] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0043] Figure 1 is a flowchart of a map construction method according to an exemplary embodiment;

[0044] Figure 2 is a flowchart of a map construction method according to an exemplary embodiment;

[0045] Figure 3 is a flowchart of a map construction method according to an exemplary embodiment;

[0046] Figure 4 is a flowchart of a map construction method according to an exemplary embodiment;

[0047] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment;

[0048] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0049] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0050] In the related art, map construction methods include automatic mapping and manual mapping. The automatic mapping method means that the robot freely explores an area and autonomously constructs a map of the area; the manual mapping method means that the user manually controls the movement of the robot through devices such as tablets and handles, and the robot builds a map of the area it passes through during the movement. However, the automatic mapping method requires the robot to explore autonomously. During the exploration process, it is very likely to enter some dangerous areas or areas that the user does not want the robot to enter. In addition, autonomous exploration may also miss some areas, resulting in an incomplete map. The manual mapping method requires the user to manually operate the robot. In addition to requiring the user to spend extra time to familiarize themselves with the robot operation, the user is also required to operate the robot at all times, which results in a poor user experience.

[0051] In an exemplary embodiment of the present disclosure, a map construction method is provided to overcome the problems of map construction methods in related arts. The method includes: determining a target following object; following the target following object to multiple locations, constructing a first map at each location; and determining a target map based on the first map at each location. This method uses the target following object to guide the robot in map construction, enabling map construction in the user's desired area without requiring additional control operations, thereby improving the user experience.

[0052] In an exemplary embodiment of the present disclosure, a map construction method is provided. Figure 1 is a flowchart of a map construction method according to an exemplary embodiment. Figure 1 As shown, the following steps are included:

[0053] Step S101, determining the target to follow;

[0054] Step S102, the following target follows the object to move to multiple locations, and a first map is constructed at each location;

[0055] Step S103: determining a target map based on the first map at each location point.

[0056] The method in the embodiments of the present disclosure is applied to robots, including life service robots, industrial robots, special robots, and other robots with binocular cameras.

[0057] In step S101, during the initialization phase of the map building function, a target object is determined. The target object can be a human or other user-friendly movable object, such as an animal. The user controls the robot through a robot application on a terminal device. The robot application provides a page for selecting the target object, where the user can set the target object as desired. After receiving the user-set target object, the robot's camera captures an image of the current environment. The target object is detected and marked in the image using an object detection algorithm. The detected target object is then presented to the user through the robot application, who confirms the accuracy of the target object. If multiple target objects are detected, they are marked simultaneously, and the user selects one of the multiple target objects. For example, if the target object is a human, multiple human bodies are detected in the current image, each of which is outlined with a box and uploaded to the robot application. The user clicks on a human body within one of the boxes to determine that the human body is the target object.

[0058] In step S102, after determining the target following object, the target following object is used as the target through a target tracking algorithm or a deep learning algorithm, and the robot moves along with the target following object. During the movement, the robot camera obtains a frame of image of the current environment at a preset time interval. The position point of each frame image is the position point to which the robot moves, and a first map is constructed at each position point based on each frame image obtained. The first map represents a three-dimensional dense point cloud map, which is a collection of a series of three-dimensional coordinate points. The first map at each position point represents the collection of each three-dimensional coordinate point in the surrounding environment of each position point. The method for constructing the first map can adopt any three-dimensional map construction method, and the present disclosure does not limit it.

[0059] In step S103, since the field of view of the robot camera at a single location point is limited, the first map constructed at each location point is part of the surrounding environment. Therefore, the first map at each location point needs to be spliced ​​into the same space to obtain a complete map of the current environment, that is, the target map. The target map is a map that can be used for navigation, such as a grid map, so that the robot can subsequently navigate in the current environment according to the target map. Therefore, while determining the target map based on the first map, it is also necessary to convert the map type of the first map to the map type of the target map. For example, when the first map is a point cloud map and the target map is a grid map, the first map at each location point can be converted into a grid map and then the grid maps at each location point can be spliced ​​into the target map. Alternatively, the first map at each location point can be spliced ​​into a complete point cloud map and then converted into a grid map, that is, the target map.

[0060] In an exemplary embodiment of the present disclosure, after determining a target following object, the robot follows the target following object to multiple locations, constructing a first map at each location. Based on the first map at each location, a target map is determined. Throughout the map-building process, the target following object guides the robot in map construction, preventing the robot from entering dangerous areas or areas the user doesn't want it to enter. Furthermore, the user doesn't need to spend extra time familiarizing themselves with the robot's operation, nor does any additional control operation require any action. Therefore, the robot can construct a map in the desired area without any additional control operations, thereby enhancing the user experience. Furthermore, the following function offers a certain level of entertainment, which can enhance user interest.

[0061] In an exemplary embodiment of the present disclosure, a map construction method is provided. Figure 2 is a flowchart of a map construction method according to an exemplary embodiment. Figure 2 As shown, the following steps are included:

[0062] Step S201, determining the target to follow;

[0063] Step S202 , the following target follows the object to move to a plurality of positions, and at each position, a scene image and a depth image of the scene image are acquired;

[0064] Step S203, determining the first position coordinates of each scene pixel in the scene image in the robot coordinate system based on the depth image, where the scene pixel represents all pixel points in the scene image except the pixel points in the area where the target follower object is located;

[0065] Step S204, constructing a first map according to the first location coordinates;

[0066] Step S205: Determine a target map based on the first map at each location point.

[0067] The specific implementation of step S201 and step S205 refers to step S101 and step S103, which will not be repeated here.

[0068] In step S202, the scene image represents an image of the current environment scene captured by the robot camera. In some embodiments, a target following object is marked in the scene image. The target following object is followed by deep learning or a target tracking algorithm, such as a kernelized correlation filter (KCF) algorithm. During the following process, the target tracking algorithm outputs the two-dimensional pixel coordinate value of the target following object in each frame of the scene image, and the target following object is marked in the scene image according to the two-dimensional pixel coordinate value, for example, a box is used to frame the target following object, so as to determine whether the target following object is correct. If the target following object is wrong, the following fails and the target following object is determined again and followed. The physical distance between each pixel point in the scene image and the robot camera is obtained, thereby obtaining a depth image of the scene image, for example, using a binocular parallax algorithm to calculate the physical distance between each pixel point in the scene image and the robot camera.

[0069] In step S203, map construction mainly locates and maps static objects in the surrounding environment, and mobile objects in the surrounding environment need to be ignored. Each scene pixel in the scene image represents all pixel points in the scene image except the pixel points in the area where the target follower object is located. Since the target follower object is a mobile object, the scene pixel point is the pixel point corresponding to the static object. Using the scene pixel points in the scene image for map construction can avoid the corresponding positioning and mapping effect of movable objects. The first position coordinate represents the three-dimensional coordinate in the robot coordinate system. The robot coordinate system represents the establishment of a three-dimensional coordinate system with the robot camera as the coordinate origin. Based on the depth image, the two-dimensional pixel coordinates and depth value of each scene pixel can be obtained, and then according to the camera intrinsic parameters, the first position coordinate of each scene pixel can be calculated by the camera calibration method.

[0070] In step S204, due to the movement of the robot, the robot coordinate system is changing, and building a map requires positioning each scene pixel in an unchanging coordinate system, such as the world coordinate system. Therefore, it is necessary to convert the first position coordinates of each scene pixel in the robot coordinate system into the position coordinates of each scene pixel in the world coordinate system, and mark the position of each scene pixel in the world coordinate system to construct the first map.

[0071] In some embodiments, constructing a first map based on the first location coordinates includes the following steps:

[0072] S24-1, determining the second position coordinates of the robot in the world coordinate system;

[0073] S24-2, determining a third position coordinate of each scene pixel in the world coordinate system based on the first position coordinate and the second position coordinate;

[0074] S24-3, constructing a first map based on the third position coordinates.

[0075] The robot's second position coordinates in the world coordinate system are calculated using a binocular positioning algorithm, such as the orb_slam2 algorithm. Based on the robot's second position coordinates in the world coordinate system, the first position coordinates of each scene pixel in the robot coordinate system are translated and rotated to calculate the third position coordinates of each scene pixel in the world coordinate system. Each scene pixel is then plotted in the world coordinate system based on the third position coordinates to obtain the first map.

[0076] In this embodiment, a binocular vision algorithm is used to calculate the depth map of the scene image, and then the three-dimensional coordinates of each position point in the current environment are determined based on the depth map, and the first map is constructed based on this, which can quickly and easily complete the mapping of the current environment.

[0077] In an exemplary embodiment of the present disclosure, a map construction method is provided. Figure 3 is a flowchart of a map construction method according to an exemplary embodiment. Figure 3 As shown, the following steps are included:

[0078] Step S301, determining the target to follow;

[0079] Step S302, the following target follows the object to move to multiple locations, and a first map is constructed at each location;

[0080] Step S303: for each location point, determine a second map of the location point based on the first map of the location point and first maps of historical location points of the location point;

[0081] Step S304: Determine the target map based on the second map of the location point.

[0082] The specific implementation of steps S301 and S302 refers to steps S101 and S102 and will not be repeated here.

[0083] In step S303, the robot moves to each location in chronological order. The historical location points represent all locations passed before reaching the current location. If the current location is the initial location, the historical location points are empty. The second map represents a map that can be used for navigation, such as a grid map. For each location, the first map for each location and the first maps of each historical location are concatenated, and the concatenated first map is converted into the second map.

[0084] In step S304, the second map of each location point is a combination of the map of the current location point and the maps of the previous location points. Therefore, the second map of the final location point is the target map. The target map is determined by determining whether each location point is the final location point. If a location point is the final location point, the second map of the location point is the target map. If the location point is not the final location point, the target tracking object continues to move, and the target map is determined based on the second maps of subsequent location points.

[0085] In some embodiments, determining the target map based on the second map of the location point includes the following two situations:

[0086] The first method is to determine the next location point according to the second map of the location point and the target following object when the location point is not the end location point, until the location point becomes the end location point.

[0087] When it is determined that the current position point is not the end position point, the next position point is determined based on the second map of the position point and the target following object. The next position point is now the new current position point. Then it is determined whether the new current position point is the end position point. If it is the end position point, the second case is executed. If it is not the end position point, the next position point is determined based on the second map of the new current position point and the target following object. This cycle is repeated until the current position point is determined to be the end position point.

[0088] In some embodiments, determining the next location point based on the second map of the location point and the target tracking object includes the following steps:

[0089] S34-1, at the location point, obtaining a depth image of the scene image;

[0090] S34-2, determining a fourth position coordinate of the target follower object in the scene image in the robot coordinate system based on the depth image;

[0091] S34-3, determining a follow path based on the second map and the fourth position coordinates of the location point;

[0092] S34-4, determining the next location point based on the following path.

[0093] At the current position, a depth image of the scene image is calculated using a binocular time difference algorithm. The entire target object is represented by key points in the area occupied by the target object in the scene image, such as the center point of the target object. The fourth position coordinates of the entire target object in the robot coordinate system are calculated based on the depth image. The three-dimensional position coordinates of the robot in the world coordinate system are then calculated using a binocular positioning algorithm. Based on the three-dimensional position coordinates of the robot in the world coordinate system, the fourth position coordinates are translated and rotated to calculate the three-dimensional position coordinates of the entire target object in the world coordinate system. The second map of the current position is the currently known map. The three-dimensional position coordinates of the entire target object in the world coordinate system are used as the target point. Local path planning and navigation are performed in the second map to obtain a follow-up path, and the next position point can be obtained from the follow-up path. The path planning method can be any path planning method.

[0094] During the robot's movement, the path to follow is determined through path planning, which can avoid obstacles in a known map and explore and map the surrounding environment as much as possible while following the target object.

[0095] The second method is to determine the second map of the location point as the target map when the location point is a terminal location point.

[0096] When it is determined that the current location point is the end location point, the second map of the current location point is the sum of the maps of all the location points, and the second map of the current location point is determined as the target map.

[0097] In some embodiments, when the distance between the robot and the target following object is less than or equal to a distance threshold, and the target following object does not move within a preset time period, the position point of the robot is determined as the end position point.

[0098] When the distance between the robot and the target object is within a certain range (i.e., the distance between the robot and the target object is less than or equal to the distance threshold), the robot is considered close to the target object and path planning is discontinued. If the target object does not move within the preset time, the robot's current location is determined as the final location. Both the distance threshold and the preset time are empirically determined and can be set as needed.

[0099] In an exemplary embodiment of the present disclosure, a map construction method is provided. Figure 4 is a flowchart of a map construction method according to an exemplary embodiment. Figure 4 As shown, the following steps are included:

[0100] Step S401, determining the target to follow;

[0101] Step S402 , the following target follows the object to move to multiple positions, and at each position, a scene image and a depth image of the scene image are acquired;

[0102] Step S403, determining the first position coordinates of each scene pixel in the scene image in the robot coordinate system based on the depth image, where the scene pixel represents all pixel points in the scene image except the pixel points in the area where the target follower object is located;

[0103] Step S404: constructing a first map according to the first location coordinates;

[0104] Step S405, determining a second map of the location point based on the first map of the location point and the first maps of the location point's historical locations;

[0105] Step S406: Determine the target map based on the second map of the location point.

[0106] The specific implementation of steps S401 to S404 refers to steps S201 and S204 , and the specific implementation of steps S405 to S406 refers to steps S303 and S304 , which will not be described in detail here.

[0107] In an exemplary embodiment of the present disclosure, a map construction device is provided. Figure 5 is a block diagram of a map construction device according to an exemplary embodiment. Figure 5 As shown, the map building device includes:

[0108] A first determining module 501 is configured to determine a target to follow;

[0109] A mapping module 502 is configured to follow the target and the object to move to a plurality of locations and construct a first map at each location;

[0110] The second determining module 503 is configured to determine a target map according to the first map at each location point.

[0111] In an exemplary embodiment, the mapping module 502 is further configured to:

[0112] At each position point, a scene image and a depth image of the scene image are acquired;

[0113] Determine, based on the depth image, the first position coordinates of each scene pixel in the scene image in the robot coordinate system, where the scene pixel represents all pixels in the scene image except for the pixels in the area where the target follower object is located;

[0114] A first map is constructed according to the first location coordinates.

[0115] In an exemplary embodiment, the mapping module 502 is further configured to:

[0116] Determine the second position coordinates of the robot in the world coordinate system;

[0117] Determine a third position coordinate of each scene pixel in the world coordinate system based on the first position coordinate and the second position coordinate;

[0118] Construct a first map based on the third location coordinates.

[0119] In an exemplary embodiment, the second determining module 503 is further configured to:

[0120] For each location point, determining a second map of the location point based on the first map of the location point and the first maps of historical location points;

[0121] The target map is determined based on the second map of the location point.

[0122] In an exemplary embodiment, the second determining module 503 is further configured to:

[0123] When the position point is not the end position point, determining the next position point according to the second map of the position point and the target follow-up object until the position point is the end position point;

[0124] When the location point is a terminal location point, the second map of the location point is determined to be the target map.

[0125] In an exemplary embodiment, the second determining module 503 is further configured to:

[0126] At the location point, a depth image of the scene image is acquired;

[0127] Determining, based on the depth image, a fourth position coordinate of the target follower object in the scene image in the robot coordinate system;

[0128] Determining a follow path based on the second map and the fourth position coordinates of the location point;

[0129] Determine the next location point based on the follow path.

[0130] In an exemplary embodiment, the second determining module 503 is further configured to:

[0131] When the distance between the robot and the target following object is less than or equal to the distance threshold, and the target following object does not move within a preset time period, the position point of the robot is determined as the end position point.

[0132] In an exemplary embodiment, the mapping module 502 is further configured to:

[0133] At each location point, the target following object is marked in the scene image.

[0134] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0135] Figure 6 is a block diagram of an electronic device 600 according to an exemplary embodiment.

[0136] Reference Figure 6 , the electronic device 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output (I / O) interface 612 , a sensor component 614 , and a communication component 616 .

[0137] The processing component 602 generally controls the overall operation of the electronic device 600, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 602 may include one or more modules to facilitate interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

[0138] The memory 604 is configured to store various types of data to support operations on the electronic device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0139] The power supply assembly 606 provides power to the various components of the electronic device 600. The power supply assembly 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 600.

[0140] The multimedia component 608 includes a screen that provides an output interface between the electronic device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the electronic device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0141] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0142] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0143] The sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for the electronic device 600. For example, the sensor assembly 614 can detect the open / closed state of the electronic device 600, the relative positioning of components, such as the display and keypad of the electronic device 600. The sensor assembly 614 can also detect changes in the position of the electronic device 600 or a component of the electronic device 600, the presence or absence of user contact with the electronic device 600, the orientation or acceleration / deceleration of the electronic device 600, and temperature changes of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0144] The communication component 616 is configured to facilitate wired or wireless communication between the electronic device 600 and other devices. The electronic device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0145] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0146] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, and the instructions can be executed by the processor 620 of the electronic device 600 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0147] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform a map construction method, wherein the method includes any of the above methods.

[0148] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0149] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A map construction method, characterized in that: The method comprises: Determine the target to follow; Following the target following object to move to a plurality of location points, and constructing a first map at each of the location points; A target map is determined according to the first map at each of the location points.

2. The map construction method according to claim 1, characterized in that: The constructing of a first map at each of the location points comprises: At each of the position points, acquiring a scene image and a depth image of the scene image; Determine, based on the depth image, a first position coordinate of each scene pixel point in the scene image in a robot coordinate system, wherein the scene pixel point represents all pixel points in the scene image except for pixel points in an area where the target following object is located; Construct the first map according to the first location coordinates.

3. The map construction method according to claim 2, characterized in that: The step of constructing the first map according to the first location coordinates includes: Determine the second position coordinates of the robot in the world coordinate system; Determining a third position coordinate of each of the scene pixels in a world coordinate system according to the first position coordinate and the second position coordinate; The first map is constructed according to the third position coordinates.

4. The map construction method according to claim 1, wherein: The determining of the target map according to the first map at each of the location points includes: For each of the location points, determining a second map of the location point based on the first map of the location point and the first maps of historical location points; The target map is determined according to the second map of the location point.

5. The map construction method according to claim 4, characterized in that: The determining the target map based on the second map of the location point includes: When the position point is not the end position point, determining a next position point according to the second map of the position point and the target follow-up object until the position point is the end position point; When the location point is a termination location point, the second map of the location point is determined to be the target map.

6. The map construction method according to claim 5, characterized in that: The determining the next location point according to the second map of the location point and the target following object includes: At the position point, acquiring a depth image of the scene image; determining, based on the depth image, a fourth position coordinate of the target following object in the scene image in the robot coordinate system; determining a follow path based on the second map of the location point and the fourth location coordinates; The next location point is determined according to the following path.

7. The map construction method according to claim 5, characterized in that: The method further comprises: When the distance between the robot and the target following object is less than or equal to a distance threshold, and the target following object does not move within a preset time period, the position point of the robot is determined as the end position point.

8. The map construction method according to claim 2, characterized in that: The method further comprises: At each of the position points, the target following object is marked in the scene image.

9. A map construction device, characterized in that: The device comprises: A first determining module is configured to determine a target following object; A mapping module is configured to follow the target object to a plurality of locations and construct a first map at each location; The second determination module is configured to determine a target map according to the first map at each of the location points.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the method according to any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 8.

Images