Docking method, device, robot, base station, storage medium and electronic device

Abstract

This invention provides a docking method, apparatus, robot, base station, storage medium, and electronic device, belonging to the field of robotics technology. The docking method, applied to a system consisting of a base station and an autonomously moving robot, includes: responding to a docking command, controlling the robot to travel to a first position and identifying a preset marker to obtain the position information of the preset marker, wherein the preset marker is pre-set on the base station, and the first position is within a preset area near the base station; determining a first base station position and a docking position based on the position information of the preset marker and the current position of the robot; controlling the robot to travel to the docking position and performing a docking operation with the base station based on the first base station position. This improves the accuracy of the docking position, has low complexity, long service life, low maintenance cost, and high docking accuracy, contributing to a higher recharge success rate.

Description

Technical Field

[0001] This invention relates to the field of robotics, specifically to a docking method, a docking device, a robot, a base station, a machine-readable storage medium, and an electronic device. Background Technology

[0002] With the development of science and technology, robots are now widely used in social life, bringing convenience to people's lives. For example, the most common mobile robots are robotic vacuum cleaners used in homes. Robots, in conjunction with base stations, can automate tasks. Base stations are electronic devices that assist robots in performing these tasks automatically. Different types of robots correspond to base stations with different functions to facilitate automated work. For instance, most base stations provide docking and charging services for robots. The robot autonomously docks at the base station and connects to its charging port to recharge.

[0003] Existing common docking solutions are based on infrared signals. Infrared signals are transmitted through a base station by electronic components after structural design, and the robot receives them. However, this method is affected by factors such as transmission frequency, light intensity, and transmission range. While the technology is mature and stable, it also suffers from several problems, including complex processes, numerous influencing factors, limited accuracy, and short lifespan. This can lead to docking failures due to inaccurate docking between the robot and the base station. Summary of the Invention

[0004] The purpose of this invention is to provide a docking method, a docking device, a robot, a base station, a machine-readable storage medium, and an electronic device. This docking method improves the accuracy of the docking position and effectively solves the problems of positioning ambiguity and docking failure caused by infrared signals being easily blocked, reflected, and attenuated by distance.

[0005] To achieve the above objectives, a first aspect of this application provides a docking method applied to a system consisting of a base station and an autonomously walking robot, the method comprising: In response to a docking command, the robot is controlled to travel to a first position and identify a preset marker to obtain the position information of the preset marker. The preset marker is pre-set on the base station, and the first position is within a preset area near the base station. Based on the location information of the preset marker and the current position of the robot, the location of the first base station and the docking location are determined; The robot is controlled to travel to the docking position, and based on the location of the first base station, a docking operation with the base station is performed.

[0006] In this embodiment of the application, the identification of the preset marker includes: The robot is controlled to take pictures of the preset markers to obtain marker images; The location information of the preset marker is obtained by recognizing the marked image.

[0007] In this embodiment of the application, the first position is an area with the base station as the origin, along its front direction, and suitable for recognizing the preset mark.

[0008] In this embodiment of the application, controlling the robot to travel to a first position and identifying a preset marker to obtain the position information of the preset marker includes: Based on preset map information, the robot is controlled to travel to the first position and identify preset markers; If the preset marker is successfully identified, the location information of the preset marker is obtained; If the preset marker is not successfully identified, a second position is determined, and the robot is controlled to travel to the second position to identify the preset marker and obtain the position information of the preset marker.

[0009] In this embodiment of the application, the preset markers are multiple; In the event that none of the preset markers are successfully identified, determining the second position includes: Based on the location information of the identified preset markers and the current position of the robot, the base station's calculated position is determined; The calculated location of the base station is matched with the pre-stored historical base station locations to obtain the matching result; Based on the matching results, the predicted location of the base station is obtained; The closest photo-taking point to the predicted location of the base station is determined to obtain the second location.

[0010] In this embodiment of the application, the base station is provided with an infrared transmitting component, and the robot is provided with an infrared receiving component. The infrared transmitting component is used to transmit infrared signals, and the infrared receiving component is used to receive infrared signals. Determining the second position includes: Acquire the infrared signal emitted by the base station; The second position is determined based on the infrared signal.

[0011] In this embodiment of the application, the infrared signal includes multiple infrared signals; Determining the second position based on the infrared signal includes: Obtain the mission map; In the task map, find areas that match the shape of the base station to obtain multiple estimated initial base station areas; Based on the infrared signal, the estimated location of the base station is determined in the initial region of the plurality of estimated base stations; Based on the base station's estimated location and various infrared signals, the predicted area is obtained; Based on the predicted region, the second position is obtained.

[0012] In this embodiment of the application, obtaining the predicted area based on the base station's estimated location and various infrared signals includes: Based on the estimated location of the base station, the infrared emission coverage area is determined; Based on the receiving location and signal value of each infrared signal, the infrared receiving coverage area corresponding to each infrared signal is determined. The intersection of the infrared receiving coverage area and the infrared emitting coverage area corresponding to each infrared signal is calculated to obtain multiple polygons; Based on the multiple polygons, the predicted region is obtained.

[0013] In this embodiment of the application, obtaining the predicted region based on the plurality of polygons includes: Obtain the confidence score for each polygon; Based on the confidence level of each polygon, a high-confidence polygon is determined from the plurality of polygons; The union of the high-confidence polygons is used to obtain the prediction region.

[0014] In this embodiment of the application, obtaining the second location based on the predicted region includes: The intersection area of ​​the strong signal area and the weak signal area of ​​the infrared signal emitted by the base station is determined in the prediction area to obtain the second position.

[0015] In this embodiment of the application, determining the location of the first base station and the docking location based on the location information of the preset marker and the current location of the robot includes: Based on the location information of the preset marker and the current position of the robot, the location of the first base station is determined; Based on the location of the first base station, the docking position is determined at a preset distance directly in front of the base station.

[0016] In this embodiment of the application, there are multiple preset markers, which are symmetrically arranged around the interface between the base station and the robot; Determining the location of the first base station based on the location information of the preset marker and the current location of the robot includes: Based on the position information of each preset marker and the current position of the robot, the position of each preset marker relative to the robot is determined. Based on the positions of each preset marker relative to the robot, the center position of the interface between the base station and the robot is calculated to obtain the position of the first base station.

[0017] A second aspect of this application provides a docking device for use in a system consisting of a base station and an autonomously walking robot, the device comprising: The first control module is used to respond to the docking command, control the robot to travel to the first position, and identify the preset mark to obtain the position information of the preset mark, wherein the preset mark is preset on the base station, and the first position is in a preset area near the base station; The determination module is used to determine the location of the first base station and the docking location based on the location information of the preset marker and the current location of the robot; The second control module is used to control the robot to travel to the docking position and, based on the position of the first base station, to perform a docking operation with the base station.

[0018] A third aspect of this application provides a robot that docks with a base station using the aforementioned docking method.

[0019] A fourth aspect of this application provides a base station for docking with the aforementioned robot.

[0020] A fifth aspect of this application provides an electronic device, the electronic device comprising: At least one processor; A memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-described docking method by executing the instructions stored in the memory.

[0021] A sixth aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned docking method.

[0022] The above technical solution utilizes a system consisting of a base station and an autonomous robot. Responding to a docking command, the system controls the robot to travel to a first position and identify a preset marker to obtain its location information. The preset marker is pre-set on the base station, and the first position is within a preset area near the base station. Based on the location information of the preset marker and the robot's current position, the first base station position and docking position are determined. The robot is then controlled to travel to the docking position and, based on the first base station position, performs a docking operation with the base station. This solution, by setting markers on the base station and having the robot identify them, can accurately determine the actual base station and docking positions, thereby obtaining the actual coordinates of the base station and docking position, establishing an absolute position reference, and improving docking positioning accuracy. This overcomes the positioning errors caused by infrared signal attenuation due to blockage, reflection, and distance, and the resulting docking failures. The system has a simple structure, high reliability, and low maintenance cost, and can significantly improve docking accuracy and recharge success rate.

[0023] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0024] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 The illustration shows a flowchart of a docking method according to an embodiment of this application; Figure 2 This illustration shows a schematic diagram of the QR code location according to an embodiment of the present application; Figure 3 This illustration schematically shows a diagram of estimating the optimal photographing position based on infrared signals according to an embodiment of this application. Figure 4 This illustration shows a schematic diagram of base station location calculation according to an embodiment of the present application; Figure 5 This schematic diagram illustrates a region range calculated based on infrared signals according to an embodiment of this application. Figure 6 The diagram illustrates a structural block diagram of a docking device according to an embodiment of this application.

[0025] Explanation of reference numerals in the attached figures 410 - First control module; 420 - Determining module; 430 - Second control module. Detailed Implementation

[0026] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0027] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0028] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0029] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0030] Please refer to Figure 1 , Figure 1 The schematic diagram illustrates a flowchart of a docking method according to an embodiment of this application. This embodiment provides a docking method applied to a system consisting of a base station and an autonomously walking robot, the method comprising the following steps: Step 210: In response to the docking command, control the robot to travel to the first position and identify the preset mark to obtain the position information of the preset mark, wherein the preset mark is preset on the base station, and the first position is within a preset area near the base station; In this embodiment, the docking command can be issued by the user or automatically by the robot after completing its work. For example, when a robot vacuum cleaner finishes its work and prepares to return to its charging dock, it automatically issues a docking command. Upon receiving the docking command, the robot can navigate to a first location using a map, or it can locate the first location by positioning itself. This map can be a SLAM map. The first location can be a pre-set location, specifically a location a certain distance in front of a base station, where a preset marker on the base station can be captured. That is, the first location can be an area centered on the base station, extending in a direction directly in front of it, suitable for recognizing the preset marker. The direction directly in front can refer to the direction in which the base station docks with the robot. For example, the first location can be a square area with sides of 0.5 meters centered 2 meters in front of the base station, where the preset marker can be captured. The first location can also be determined within a preset area near the base station location after the base station location is determined in the SLAM map. The preset marker can be a QR code image, a barcode image, etc., and there can be one or more preset markers. These preset markers can be set during the base station design phase. For example, please refer to... Figure 2 , Figure 2 The illustration shows a schematic diagram of the QR code locations according to an embodiment of this application, with QR code 1 and QR code 2 symmetrically arranged on the base station. The location information of the preset marker includes the marker's position, orientation, etc. The position of the preset marker on the base station can be determined according to actual conditions; for example, it can be placed near the interface between the base station and the robot. The identification process can be performed by taking a picture of the base station using a vision device on the robot.

[0031] In some embodiments, the identification of the preset marker includes: First, the robot is controlled to take a picture of the preset mark to obtain a mark image; In this embodiment, the robot can be equipped with a vision device, such as a camera. After the robot reaches the first position, the camera on the robot takes a picture to obtain a marked image. The number and type of the aforementioned vision device are not limited in this embodiment. For the sake of illustrative purposes, this embodiment mainly uses a camera as an example for explanation.

[0032] Then, the marked image is identified to obtain the location information of the preset mark.

[0033] In this embodiment, the aforementioned marked image contains a mark. By recognizing the mark, the position of the preset mark in the visual device coordinate system can be obtained, that is, the position of the preset mark in the image coordinate system, thus obtaining the position information of the preset mark. For example, if the preset mark is a QR code, then the marked image contains a QR code. By recognizing the QR code in the marked image, the position of the QR code in the pixel coordinate system can be obtained. The above-mentioned recognition of the marked image can be implemented using existing image recognition technology, which will not be elaborated further here.

[0034] By controlling the robot to take pictures of the preset markers and then recognizing the marker images, the location information of the preset markers can be obtained quickly and accurately.

[0035] To facilitate explanation of the solution, this embodiment primarily uses a pre-set marker as a QR code. It should be noted that, to prevent wear and tear on the pre-set marker from affecting recognition performance, it can be installed inside the base station using engraving or encapsulation stickers. The position of the pre-set marker on the base station can be defined during the template design stage, and automated application of the pre-set markers is achieved through assembly line production.

[0036] In some embodiments, controlling the robot to travel to a first position and identifying a preset marker to obtain the position information of the preset marker includes: First, the robot is controlled to travel to a first position and identify a preset marker; In this embodiment, the robot can be navigated to the first location based on map information, or it can be positioned to reach the first location. The robot's camera then captures and identifies preset markers on the base station.

[0037] If the preset marker is successfully identified, the location information of the preset marker is obtained; In this embodiment, if the recognition is successful, the location information of the preset marker is obtained based on the recognition result.

[0038] In real-world scenarios, there can be multiple preset markers. During recognition, due to the robot's perspective, only a few markers may be recognized from the side or distance. For example, if the preset markers are multiple QR codes, when the robot passes perpendicularly to the base station, it may only recognize the QR code on the right front because the camera is facing forward. In some scenarios, lighting can also affect the recognition results. For instance, in low light conditions, such as at night, or if the camera lens is dirty, or if the preset markers are located inside the base station, the robot may fail to recognize them when taking a side view of the inside of the base station. It should be noted that the above are just examples of recognition failures. In actual implementation, any failure to fully recognize a preset marker can be considered a recognition failure.

[0039] Accordingly, if the preset mark is not successfully identified, a second position can be determined, and the robot can be controlled to travel to the second position to identify the preset mark and obtain the position information of the preset mark.

[0040] In this embodiment, if recognition fails, a second location can be determined. This second location may refer to the optimal photo-taking location, and the robot can then be controlled to move to this second location for recognition. Determining the second location can be achieved by first determining the base station location and then determining the optimal photo-taking location based on that location. Alternatively, it can be based on the lighting conditions in the actual scene, selecting a well-lit area as the second location.

[0041] It should be noted that, in practice, if the preset marker is not successfully identified at the second location, the second location can be redefined, and the robot can be controlled to move to the second location to identify the preset marker. This process can be repeated multiple times to identify the location information of the preset marker. If the location information of the preset marker is still not identified after a limited number of attempts, docking will not be performed.

[0042] By controlling the robot to travel to the first position and identify the preset mark, and if the preset mark is not successfully identified, a second position can be determined, and the robot can be controlled to travel to the second position to identify the preset mark. This can greatly increase the probability of successfully identifying the preset mark and help improve the docking success rate.

[0043] In some embodiments, if there are multiple preset markers and none of them are successfully identified, the identification is considered to have failed. For example, if there are four preset markers and three are successfully identified, the identification is considered to have failed. In this case, if historical base station locations are stored, the possible location and orientation of the base station can be inferred by combining the location information of the identified preset markers, and the nearest photo-taking point can be calculated for photo identification. That is, determining the second location includes: First, based on the location information of the identified preset markers and the current position of the robot, the base station's calculated position is determined; In this embodiment, the robot observes the marker through a vision device and can obtain the marker's observed pose in the vision device's coordinate system. That is, the aforementioned identified preset marker position information includes the marker's observed pose in the vision device's coordinate system and the marker's identifier. Based on the marker's observed pose in the vision device's coordinate system, combined with pre-calibrated extrinsic parameters between the vision device and the robot, the marker's pose in the robot's coordinate system can be calculated, i.e., the marker's position and orientation relative to the robot. Then, using the robot's current pose in the world coordinate system, the marker is transformed from the robot's coordinate system to the world coordinate system, obtaining the marker's pose in the world coordinate system. Finally, based on the marker's pre-calibrated fixed pose in the base station's coordinate system, i.e., the marker's position relative to the base station, the pose of the base station relative to the world coordinate system can be calculated through coordinate system transformation relationships, i.e., the calculated position of the base station. The mathematical essence is: base station transformation relative to the world coordinate system = marker transformation relative to the world coordinate system × base station transformation relative to the marker's coordinate system (i.e., the inverse of the marker transformation relative to the base station). The above coordinate system transformation relationships can be pre-calibrated and will not be elaborated further here.

[0044] It should be noted that there can be multiple identified preset markers. Multiple base station locations can be calculated using the location information of each identified preset marker, and then the average value can be obtained to get the calculated base station location.

[0045] Then, the calculated location of the base station is matched with the pre-stored historical base station locations to obtain the matching result; In this embodiment, the aforementioned pre-stored historical maintenance base station locations can refer to the base station locations recorded by the robot when performing a task, such as the base station location at the start of the task. The matching process involves comparing the calculated base station location with the historical maintenance base station location to determine if they match. If they match, the matching is successful; otherwise, the matching fails.

[0046] Then, based on the matching results, the predicted location of the base station is obtained; In this embodiment, if the matching result is successful, it means that the base station has not moved, and the historically maintained base station location can be used as the predicted base station location; if the matching result is unsuccessful, it means that the base station has moved, and the calculated base station location can be used as the predicted base station location.

[0047] Finally, the closest photo-taking point to the predicted location of the base station is determined to obtain the second location.

[0048] In this embodiment, after obtaining the predicted location of the base station, the nearest photo-taking point can be determined based on the predicted location of the base station, thereby obtaining the second location.

[0049] By utilizing the location information of the identified preset markers, the possible location and orientation of the base station can be inferred in reverse. By combining this with the reference historical base station locations, the base station location can be accurately predicted, making the predicted location more consistent with the actual situation. This makes the calculation of the nearest photo point, i.e., the second location, more reliable and helps to increase the probability of successful identification.

[0050] In some embodiments, the base station is provided with an infrared transmitting component, and the robot is provided with an infrared receiving component. The infrared transmitting component is used to transmit infrared signals, and the infrared receiving component is used to receive infrared signals. In this embodiment, the infrared emitting component (which may be an infrared LED array of a specific wavelength, in conjunction with modulation circuitry, etc.) mounted on the base station is responsible for encoding control commands or positioning data into infrared signals and transmitting them directionally or omnidirectionally into the surrounding space. The infrared receiving component (including infrared receiver tubes, filters, and demodulation circuitry, etc.) configured on the robot is used to capture the infrared signals from the base station, filter out ambient light interference, demodulate and restore them into digital commands or position information, thereby enabling the base station to control or relatively position the robot in real time. For example, the base station emits encoded and modulated infrared beams in different directions. These beams form specific fan-shaped coverage areas in space. The robot can be equipped with an infrared receiving component, such as an infrared receiver array located at the tail of the robot, which can not only detect the presence of infrared light but also decode which beam it comes from and measure its signal strength.

[0051] Accordingly, determining the second position includes: First, the infrared signal emitted by the base station is acquired; In this embodiment, the robot can receive infrared signals emitted from the base station through an infrared receiving component. The infrared signals can refer to infrared signals received by the robot at different angles at different positions during the execution of the task.

[0052] Then, based on the infrared signal, the second position is determined.

[0053] In this embodiment, based on infrared signals including signal strength and signal angle, the robot can calculate its precise position and orientation relative to the base station, and then deduce the nearest camera point, thus obtaining the second position.

[0054] By estimating the optimal shooting position based on infrared signals, a second position can be obtained, which is applicable to scenarios where the base station location cannot be determined, thus improving applicability. For example, when a robot moves from one task scenario to another new task scenario, the base station location changes, and the robot cannot know the base station location in the current task scenario. In this case, the second position can be estimated using infrared signals.

[0055] In some embodiments, in order to improve the accuracy of the second position, when the infrared signal includes multiple infrared signals, determining the second position based on the infrared signals includes: The first step is to obtain the mission map; In this embodiment, the aforementioned task map refers to the map of the current new task scenario, which can be a SLAM map, obstacle map, etc. The robot can move autonomously or under control within the scenario using various onboard sensors (such as LiDAR, visual cameras, depth cameras, IMU, etc.), explore the environment, and process sensor data in real time, transforming the perceived environmental features (such as walls, furniture, and equipment outlines) into a unified digital map.

[0056] The second step is to find areas in the task map that match the shape of the base station to obtain multiple estimated initial areas of the base station. In this embodiment, the shape of the base station includes information such as its shape and height; for example, the base station may be concave. Areas with the same shape as the base station can be found on the task map; these areas represent potential base station locations, thus yielding multiple estimated initial base station areas. Please refer to... Figure 4 , Figure 4 The illustration shows a schematic diagram of base station location estimation according to an embodiment of this application. The possible location of the base station is estimated based on a SLAM map, which depends on the actual shape of the base station (tall base station, low base station), and then graphic shape matching is performed to determine the possible location of the base station.

[0057] The third step is to determine the estimated location of the base station in the initial area of ​​the plurality of estimated base stations based on the infrared signal. In this embodiment, the initial areas of the multiple estimated base stations may contain debris piles or corners. Therefore, further screening is required. Specifically, the estimated location of the base station can be selected from these initial areas based on various infrared signals. This can be achieved by determining the corresponding infrared transmission coverage area for each initial area, and then determining if any infrared signal receiving location falls within that coverage area. If so, it indicates a possible location for the base station, which is the estimated location. Conversely, if not, the initial area may contain debris piles, corners, etc., and needs to be excluded.

[0058] The fourth step is to obtain the predicted area based on the base station's estimated location and various infrared signals; In this embodiment, the infrared transmission coverage area can be determined based on the estimated location of the base station, and correspondingly, the infrared reception coverage area can be determined based on each infrared signal. Infrared signals can only be transmitted and received if the base station is simultaneously within both the infrared transmission and reception coverage areas; this area is the predicted area.

[0059] Fifth step: Based on the predicted region, obtain the second position.

[0060] In this embodiment, the optimal shooting point can be determined within the prediction area to obtain the second location. For example, a region with a stronger signal within the prediction area can be selected as the second location.

[0061] In some embodiments, to further improve the recognition success rate, obtaining the second position based on the predicted region includes: determining the intersection area of ​​the strong signal area and the weak signal area of ​​the infrared signal emitted by the base station in the predicted region to obtain the second position.

[0062] In this embodiment, the prediction region includes the signal values ​​of infrared signals emitted by base stations at different locations. The determination of the strong and weak signal regions can be achieved by pre-setting a signal threshold and judging whether the signal strength of the infrared signals emitted by base stations at various locations in the prediction region is greater than the threshold. If it is greater, it is considered a strong signal region; otherwise, it is considered a weak signal region. Alternatively, it can be achieved by pre-setting the signal value ranges corresponding to strong and weak signals and then matching them separately. The intersection of the strong and weak signal regions is the second location. Please refer to [link to previous text]. Figure 3 , Figure 3 This illustration schematically shows a diagram of estimating the optimal image capture position based on infrared signals according to this embodiment.

[0063] The aforementioned strong signal areas are usually closer to the base station, while the weak signal areas extend outwards. Their intersection is often a more ideal location for the target. This avoids limiting the shooting angle (such as excessive elevation angle or poor composition) or causing the target to occupy too little space in the frame due to being too close to the base station. This creates more favorable observation geometry in physical space for obtaining high-quality images and helps to successfully identify the preset markers.

[0064] By matching the shape of base stations on the mission map, a large number of irrelevant areas can be quickly eliminated, limiting the search scope to a few possible areas. This effectively avoids the blindness of global search and reduces the risk of mismatches caused by environmental interference. By combining real-time infrared signal observation data with prior map information for cross-validation, the location of base stations within the initial area is further determined, forming a dual constraint of prior structure and real-time signal, which significantly improves the accuracy of the positioning results and helps to obtain an accurate second location.

[0065] In some embodiments, obtaining the predicted area based on the base station's estimated location and various infrared signals includes: First, based on the estimated location of the base station, the infrared emission coverage area is determined; In this embodiment, based on the estimated location of the base station and combined with the known characteristic parameters of the infrared emitting component, such as vertical and horizontal emission angles, maximum effective range, signal strength attenuation curve, and emission mode, the infrared emission coverage area is determined through geometric projection and spatial modeling. Specifically, with the base station location as the origin and its orientation axis as the center, a three-dimensional conical or fan-shaped coverage model is constructed according to the emission angle. Please refer to [link / reference]. Figure 5 , Figure 5 The illustration shows a schematic diagram of the area range calculated based on infrared signals according to an embodiment of this application; then, the radial boundary of the model is defined based on the effective distance to form an initial theoretical coverage area. To further improve accuracy, obstacle information from the mission map can be further integrated, and signal blind spots blocked by obstacles can be eliminated through ray casting or occlusion detection algorithms to finally obtain the actually usable infrared signal coverage area.

[0066] Then, based on the pose of the infrared receiving component on the robot corresponding to each infrared signal, the infrared receiving coverage area corresponding to each infrared signal is determined. In this embodiment, the pose of the infrared receiving component on the robot corresponding to each infrared signal refers to the real-time pose of the infrared receiving component when the robot receives each infrared signal, including its position and orientation. Combined with the known characteristic parameters of the infrared receiving component (such as horizontal and vertical receiving angles, maximum effective receiving distance, sensitivity threshold, and directional response curve), the infrared receiving coverage area is determined through geometric modeling. Specifically, a three-dimensional conical spatial model is constructed based on the position of the infrared receiving component as the vertex and its orientation as the central axis, according to the receiving angle. The radial boundary of this cone is then defined based on the maximum effective distance, forming the theoretical receiving range. Subsequently, considering the propagation attenuation of infrared signals in the actual environment, a signal strength threshold condition can be introduced to further constrain the effective portion of the theoretical region that can reliably resolve the signal. To further improve accuracy, obstacle information from the task map can be integrated, and obstructed lines of sight can be eliminated through occlusion detection, thereby obtaining the precise receiving coverage area of ​​each infrared signal in the actual scene, i.e., the infrared receiving coverage area. This area reflects the spatial range within which the robot can stably capture and process the corresponding infrared signal under a given receiving component pose. For each infrared signal, the corresponding infrared receiving coverage area can be determined in the above manner.

[0067] Then, the intersection of the infrared receiving coverage area and the infrared emitting coverage area corresponding to each infrared signal is calculated to obtain multiple polygons; In this embodiment, there can be multiple infrared emission coverage areas. By finding the intersection of the infrared receiving coverage area corresponding to any one infrared signal and any one infrared emission coverage area, multiple polygons are obtained. The area corresponding to any polygon represents the area where the base station may exist.

[0068] Finally, the predicted region is obtained based on the multiple polygons.

[0069] In this embodiment, the predicted region can be determined based on the confidence level of the polygon.

[0070] In some embodiments, obtaining the predicted region based on the plurality of polygons includes: The first step is to obtain the confidence level of each polygon; The second step is to determine the high-confidence polygons among the multiple polygons based on the confidence level of each polygon. The third step is to find the union of the high-confidence polygons to obtain the prediction region.

[0071] In this embodiment, a confidence score can be calculated for each polygon, which can be based on indicators such as the average signal strength and signal-to-noise ratio within that polygon. For example, the average signal strength within the polygon can be used as the confidence score. Then, a dynamic or fixed confidence threshold can be set, and all polygons with confidence scores higher than the threshold are selected as high-confidence polygons, representing reliable infrared signal quality and sufficient positioning basis in these areas. All selected high-confidence polygons can be projected onto the same coordinate system (such as the world coordinate system), and their spatial union can be calculated to obtain the prediction region. This operation connects all reliable high-confidence regions to form one or more continuous regions with wider coverage, which are the prediction regions. If the prediction region contains multiple discontinuous sub-regions, they can be further sorted or selected based on their area or proximity to the robot's current position.

[0072] Confidence-based filtering actively removes low-quality, high-error signal areas caused by occlusion, interference, or abnormal propagation, preventing these noisy data from contaminating subsequent location estimation and making the underlying data for the prediction area purer and more reliable. The union operation comprehensively utilizes multiple highly reliable observations; even if the coverage of a single signal is limited, merging them can form a broader and more complete possible area, improving the system's sensing range and spatial continuity, and contributing to a more accurate second location.

[0073] It should be noted that low-confidence polygons can also be used as candidate prediction regions to prevent situations where the preset identifier cannot be identified in high-confidence polygons. Specifically, based on the confidence level of each polygon, high-confidence polygons and low-confidence polygons can be determined from the multiple polygons. The process of determining low-confidence polygons is similar to that of determining high-confidence polygons; all polygons with confidence scores not higher than a threshold can be filtered as low-confidence polygons. The union of the high-confidence polygons is calculated to obtain the first region. Then, it is determined whether the low-confidence polygons intersect with the first region. Specifically, the intersection of the low-confidence polygons and the first region can be calculated. If the intersection is empty, it means that the low-confidence polygons and the first region do not intersect; otherwise, it means that the low-confidence polygons and the first region intersect. If the low-confidence polygons intersect with the first region, they can be used as the second region. The preset identifier can be identified first in the first region. If the preset identifier is not identified in the first region, it can then be identified in the second region. Specifically, during identification, the optimal shooting point can be determined in the first region. That is, the intersection of the strong signal area and the weak signal area of ​​the infrared signal emitted by the base station can be identified in the first region. Then, the robot can be controlled to travel to the intersection area to identify the preset mark. If the preset mark is successfully identified, the location information of the preset mark can be obtained. If the preset mark is not successfully identified, the intersection of the strong signal area and the weak signal area of ​​the infrared signal emitted by the base station can be identified in the second region. Then, the robot can be controlled to travel to the intersection area and identify the preset mark to obtain the location information of the preset mark.

[0074] In practical implementation, the optimal identification position can be determined based on the infrared signals emitted by the base station acquired by the robot. Then, in response to a docking command, the robot is controlled to move to the optimal identification position to obtain the location information of the preset marker. Based on the location information of the preset marker and the current position of the robot, the first base station position and the docking position are determined. The robot is then controlled to move to the docking position, and based on the first base station position, a docking operation with the base station is performed. The process of determining the optimal identification position based on the infrared signals emitted by the base station acquired by the robot is the same as the process of determining the second position based on the infrared signals, and will not be repeated here. This method allows for the rapid determination of the optimal identification position using infrared signals, facilitating quick docking.

[0075] Step 220: Based on the location information of the preset marker and the current position of the robot, determine the location of the first base station and the docking location; In some embodiments, determining the location of the first base station and the docking location based on the location information of the preset marker and the current location of the robot includes: First, based on the location information of the preset marker and the current position of the robot, the location of the first base station is determined; In this embodiment, the position information of the preset marker identified above can refer to the observation pose of the marker in the coordinate system of the vision device. For example, if the vision device is a camera, the position information of the preset marker is the position of the preset marker in the pixel coordinate system. Combining the pre-calibrated extrinsic parameters between the vision device and the robot, the position and orientation of the marker relative to the robot can be calculated. Then, based on the positional relationship between the preset marker and the base station and the position and orientation of the marker relative to the robot, the position and orientation of the base station relative to the robot can be obtained. Finally, by transforming to the global coordinate system, the position of the base station in the global coordinate system, i.e., the position of the first base station, can be obtained.

[0076] Then, based on the location of the first base station, the docking position is determined at a preset distance directly in front of the base station.

[0077] In this embodiment, after determining the location of the first base station, its orientation can be determined, and a preset distance directly in front of the base station can be used as the docking position. The robot can then perform docking operations at this position.

[0078] The location of the first base station is determined based on the location information of the preset marker and the current location of the robot. Then, based on the location of the first base station, the docking position can be quickly and accurately determined at a preset distance directly in front of the base station.

[0079] In some embodiments, in order to more accurately determine the docking position, there may be multiple preset markers, and the multiple preset markers are symmetrically arranged around the docking interface between the base station and the robot; Determining the location of the first base station based on the location information of the preset marker and the current location of the robot includes: First, based on the position information of each preset marker and the current position of the robot, the position of each preset marker relative to the robot is determined; In this embodiment, the position and orientation of the marker relative to the robot can be calculated based on the position information of the preset marker and combined with the pre-calibrated extrinsic parameters between the vision device and the robot, thus obtaining the position of each preset marker relative to the robot.

[0080] Then, based on the positions of each preset marker relative to the robot, the center position of the interface between the base station and the robot is calculated to obtain the position of the first base station.

[0081] In this embodiment, since multiple preset markers are symmetrically arranged around the interface between the base station and the robot, after calculating the position of each preset marker relative to the robot, the symmetry center point can be calculated by fusing the positions of each preset marker relative to the robot, that is, the center position of the interface between the base station and the robot. Then, through coordinate transformation, the center position of the interface is transformed to the global coordinate system to obtain the position of the first base station.

[0082] By symmetrically setting multiple preset markers around the interface between the base station and the robot, the position of each preset marker relative to the robot can be determined based on the position information of each preset marker and the current position of the robot. Then, based on the position of each preset marker relative to the robot, the center position of the interface between the base station and the robot can be calculated, thereby quickly and accurately obtaining the position of the first base station. Since the position of the first base station is the center of the interface between the base station and the robot, the docking position determined based on the position of the first base station is more accurate, which helps to ensure precise docking.

[0083] Step 230: Control the robot to travel to the docking position, and perform a docking operation with the base station based on the position of the first base station.

[0084] In this embodiment, after determining the docking position, the robot can be controlled to move to the docking position, and then the central axis of the base station can be identified according to the position of the first base station. The robot adjusts its posture so that the docking interface of the robot faces the base station, and then moves backward until the docking is successful.

[0085] In the above implementation process, a system consisting of a base station and an autonomous robot responds to a docking command, controlling the robot to travel to a first position and identify a preset marker to obtain the position information of the preset marker. The preset marker is pre-set on the base station, and the first position is within a preset area near the base station. Based on the position information of the preset marker and the robot's current position, the first base station position and the docking position are determined. The robot is then controlled to travel to the docking position and, based on the first base station position, performs a docking operation with the base station. This scheme, by setting a marker on the base station and having the robot identify the marker, can accurately determine the actual base station position and docking position, thereby obtaining the actual coordinates of the base station and docking position, establishing an absolute position reference, and improving docking positioning accuracy. This overcomes the positioning errors caused by infrared signal attenuation due to blockage, reflection, and distance, and the resulting docking failures. The system has a simple structure, high reliability, and low maintenance cost, and can significantly improve docking accuracy and recharge success rate.

[0086] The following explanation uses a cleaning robot as an example. QR codes are installed inside the base station using either engraving or sticker application. The location is defined during the template design phase, and automated application is achieved through a production line. After the robot vacuum finishes its work and prepares to return to its charging dock: If a map exists, it navigates to the base station while continuously taking photos for identification. If identification is successful, the robot calculates the relative position to the base station and the docking position based on its current location and the code's location. The robot navigates to the identification centerline and reverses to dock until successful. If a map exists and part of the code has been identified, the optimal photo-taking position is calculated based on the identified code ID and its location. The robot navigates to the optimal position for supplementary lighting and photo-taking until identification is complete. The robot navigates to the identification centerline, turns around, and reverses to dock until successful. If a map exists but no code has been identified, the optimal photo-taking position is estimated based on infrared signals. After a limited number of attempts, the robot adjusts to the base station's centerline, turns around, and reverses to dock until successful.

[0087] This embodiment provides a robot that uses the above-described docking method to dock with a base station.

[0088] In this embodiment, the robot can be a cleaning robot. By recognizing preset markers, it determines an absolute position reference, establishing a precise global coordinate system and search guidance for docking with easily interfered infrared signals. This corrects the positioning ambiguity and docking failure caused by infrared signal susceptibility to obstruction, reflection, and distance attenuation. It features low complexity, long service life, low maintenance costs, and high docking accuracy, contributing to improved robot recharging success rate.

[0089] This embodiment provides a base station for docking with the robot described above.

[0090] In this embodiment, the preset logo can be installed inside the base station by engraving or encapsulating stickers. The position of the logo is defined in the template design stage, and the logo is automatically affixed during assembly line production.

[0091] Please refer to Figure 6 , Figure 6 A schematic structural block diagram of a docking device according to an embodiment of this application is shown. This embodiment provides a docking device applied to a system consisting of a base station and an autonomously walking robot. The device includes a first control module 410, a determining module 420, and a second control module 430, wherein: The first control module 410 is used to respond to a docking command, control the robot to travel to a first position, and identify a preset marker to obtain the position information of the preset marker, wherein the preset marker is preset on the base station, and the first position is within a preset area near the base station; The determining module 420 is used to determine the location of the first base station and the docking location based on the location information of the preset marker and the current location of the robot; The second control module 430 is used to control the robot to travel to the docking position and, based on the position of the first base station, to perform a docking operation with the base station.

[0092] The docking device includes a processor and a memory. The first control module 410, the determination module 420, and the second control module 430 are all stored in the memory as program units. The processor executes the program units stored in the memory to realize the corresponding functions.

[0093] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and interfacing with the base station can be achieved by adjusting kernel parameters.

[0094] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0095] This invention provides a machine-readable storage medium storing a program that, when executed by a processor, implements the docking method.

[0096] This invention provides a processor for running a program, wherein the program executes the docking method during runtime.

[0097] This application provides an electronic device comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the aforementioned docking method by executing the instructions stored in the memory, applicable to a system composed of a base station and an autonomously walking robot, wherein the processor executes the instructions to perform the following steps: In response to a docking command, the robot is controlled to travel to a first position and identify a preset marker to obtain the position information of the preset marker. The preset marker is pre-set on the base station, and the first position is within a preset area near the base station. Based on the location information of the preset marker and the current position of the robot, the location of the first base station and the docking location are determined; The robot is controlled to travel to the docking position, and based on the location of the first base station, a docking operation with the base station is performed.

[0098] In one embodiment, the identification of the preset marker includes: The robot is controlled to take pictures of the preset markers to obtain marker images; The location information of the preset marker is obtained by recognizing the marked image.

[0099] In one embodiment, the first location is an area with the base station as the origin, along its front direction, and suitable for recognizing the preset marker.

[0100] In one embodiment, controlling the robot to travel to a first position and identifying a preset marker to obtain the position information of the preset marker includes: Control the robot to travel to the first position and identify the preset marker; If the preset marker is successfully identified, the location information of the preset marker is obtained; If the preset marker is not successfully identified, a second position is determined, and the robot is controlled to travel to the second position to identify the preset marker and obtain the position information of the preset marker.

[0101] In one embodiment, there are multiple preset markers; In the event that none of the preset markers are successfully identified, determining the second position includes: Based on the location information of the identified preset markers and the current position of the robot, the base station's calculated position is determined; The calculated location of the base station is matched with the pre-stored historical base station locations to obtain the matching result; Based on the matching results, the predicted location of the base station is obtained; The closest photo-taking point to the predicted location of the base station is determined to obtain the second location.

[0102] In one embodiment, the base station is equipped with an infrared transmitting component, and the robot is equipped with an infrared receiving component. The infrared transmitting component is used to transmit infrared signals, and the infrared receiving component is used to receive infrared signals. Determining the second position includes: Acquire the infrared signal emitted by the base station; The second position is determined based on the infrared signal.

[0103] In one embodiment, the infrared signal includes multiple infrared signals; Determining the second position based on the infrared signal includes: Obtain the mission map; In the task map, find areas that match the shape of the base station to obtain multiple estimated initial base station areas; Based on the infrared signal, the estimated location of the base station is determined in the initial region of the plurality of estimated base stations; Based on the base station's estimated location and various infrared signals, the predicted area is obtained; Based on the predicted region, the second position is obtained.

[0104] In one embodiment, obtaining the predicted area based on the base station's estimated location and various infrared signals includes: Based on the estimated location of the base station, the infrared emission coverage area is determined; Based on the receiving location and signal value of each infrared signal, the infrared receiving coverage area corresponding to each infrared signal is determined. The intersection of the infrared receiving coverage area and the infrared emitting coverage area corresponding to each infrared signal is calculated to obtain multiple polygons; Based on the multiple polygons, the predicted region is obtained.

[0105] In one embodiment, obtaining the predicted region based on the plurality of polygons includes: Obtain the confidence score for each polygon; Based on the confidence level of each polygon, a high-confidence polygon is determined from the plurality of polygons; The union of the high-confidence polygons is used to obtain the prediction region.

[0106] In one embodiment, obtaining the second location based on the predicted region includes: The intersection area of ​​the strong signal area and the weak signal area of ​​the infrared signal emitted by the base station is determined in the prediction area to obtain the second position.

[0107] In one embodiment, determining the location of the first base station and the docking location based on the location information of the preset marker and the current location of the robot includes: Based on the location information of the preset marker and the current position of the robot, the location of the first base station is determined; Based on the location of the first base station, the docking position is determined at a preset distance directly in front of the base station.

[0108] In one embodiment, there are multiple preset markers, which are symmetrically arranged around the interface between the base station and the robot; Determining the location of the first base station based on the location information of the preset marker and the current location of the robot includes: Based on the position information of each preset marker and the current position of the robot, the position of each preset marker relative to the robot is determined. Based on the positions of each preset marker relative to the robot, the center position of the interface between the base station and the robot is calculated to obtain the position of the first base station.

[0109] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0110] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0111] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0113] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0114] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0115] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0116] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0117] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A docking method, characterized in that, The method, applied to a system consisting of a base station and an autonomously walking robot, includes: In response to a docking command, the robot is controlled to travel to a first position and identify a preset marker to obtain the position information of the preset marker. The preset marker is pre-set on the base station, and the first position is within a preset area near the base station. Based on the location information of the preset marker and the current position of the robot, the location of the first base station and the docking location are determined; The robot is controlled to travel to the docking position, and based on the location of the first base station, a docking operation with the base station is performed.

2. The docking method according to claim 1, characterized in that, The identification preset marker includes: The robot is controlled to take pictures of the preset markers to obtain marker images; The location information of the preset marker is obtained by recognizing the marked image.

3. The docking method according to claim 1, characterized in that, The first location is an area with the base station as the origin, along its front direction, and suitable for recognizing the preset mark.

4. The docking method according to claim 1, characterized in that, The step of controlling the robot to travel to a first position and identifying a preset marker to obtain the position information of the preset marker includes: Control the robot to travel to the first position and identify the preset marker; If the preset marker is successfully identified, the location information of the preset marker is obtained; If the preset marker is not successfully identified, a second position is determined, and the robot is controlled to travel to the second position to identify the preset marker and obtain the position information of the preset marker.

5. The docking method according to claim 4, characterized in that, The preset markers are multiple; In the event that none of the preset markers are successfully identified, determining the second position includes: Based on the location information of the identified preset markers and the current position of the robot, the base station's calculated position is determined; The calculated location of the base station is matched with the pre-stored historical base station locations to obtain the matching result; Based on the matching results, the predicted location of the base station is obtained; The closest photo-taking point to the predicted location of the base station is determined to obtain the second location.

6. The docking method according to claim 5, characterized in that, The step of obtaining the predicted location of the base station based on the matching result includes: If the matching result is successful, the pre-stored historical base station location will be used as the predicted base station location. If the matching result fails, the calculated location of the base station will be used as the predicted location of the base station.

7. The docking method according to claim 4, characterized in that, The base station is equipped with an infrared transmitting component, and the robot is equipped with an infrared receiving component. The infrared transmitting component is used to transmit infrared signals, and the infrared receiving component is used to receive infrared signals. Determining the second position includes: Acquire the infrared signal emitted by the base station; The second position is determined based on the infrared signal.

8. The docking method according to claim 7, characterized in that, The infrared signal includes multiple infrared signals; Determining the second position based on the infrared signal includes: Obtain the mission map; In the task map, find areas that match the shape of the base station to obtain multiple estimated initial base station areas; Based on the infrared signal, the estimated location of the base station is determined in the initial region of the plurality of estimated base stations; Based on the base station's estimated location and various infrared signals, the predicted area is obtained; Based on the predicted region, the second position is obtained.

9. The docking method according to claim 8, characterized in that, The process of obtaining the predicted area based on the base station's estimated location and various infrared signals includes: Based on the estimated location of the base station, the infrared emission coverage area is determined; Based on the receiving location and signal value of each infrared signal, the infrared receiving coverage area corresponding to each infrared signal is determined. The intersection of the infrared receiving coverage area and the infrared emitting coverage area corresponding to each infrared signal is calculated to obtain multiple polygons; Based on the multiple polygons, the predicted region is obtained.

10. The docking method according to claim 9, characterized in that, The process of obtaining the predicted region based on the plurality of polygons includes: Obtain the confidence score for each polygon; Based on the confidence level of each polygon, a high-confidence polygon is determined from the plurality of polygons; The union of the high-confidence polygons is used to obtain the prediction region.

11. The docking method according to claim 8, characterized in that, The process of obtaining the second location based on the predicted region includes: The intersection area of ​​the strong signal area and the weak signal area of ​​the infrared signal emitted by the base station is determined in the prediction area to obtain the second position.

12. The docking method according to claim 1, characterized in that, The process of determining the location of the first base station and the docking location based on the location information of the preset marker and the current location of the robot includes: Based on the location information of the preset marker and the current position of the robot, the location of the first base station is determined; Based on the location of the first base station, the docking position is determined at a preset distance directly in front of the base station.

13. The docking method according to claim 12, characterized in that, The preset markers are multiple, and the multiple preset markers are symmetrically arranged around the interface between the base station and the robot; Determining the location of the first base station based on the location information of the preset marker and the current location of the robot includes: Based on the position information of each preset marker and the current position of the robot, the position of each preset marker relative to the robot is determined. Based on the positions of each preset marker relative to the robot, the center position of the interface between the base station and the robot is calculated to obtain the position of the first base station.

14. A docking device, characterized in that, The device is applicable to a system consisting of a base station and an autonomously walking robot, and includes: The first control module is used to respond to the docking command, control the robot to travel to the first position, and identify the preset mark to obtain the position information of the preset mark, wherein the preset mark is preset on the base station, and the first position is in a preset area near the base station; The determination module is used to determine the location of the first base station and the docking location based on the location information of the preset marker and the current location of the robot; The second control module is used to control the robot to travel to the docking position and, based on the position of the first base station, to perform a docking operation with the base station.

15. A robot, characterized in that, The robot docks with the base station using the docking method described in any one of claims 1-12.

16. A base station, characterized in that, The base station is used to dock with the robot described in claim 14.

17. An electronic device, characterized in that, The electronic device includes: At least one processor; A memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the docking method according to any one of claims 1 to 13 by executing the instructions stored in the memory.

18. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the docking method according to any one of claims 1 to 13.

Images