Retreating method of self-moving robot and self-moving robot

Abstract

This application discloses a method for retracting a staking device from a self-moving robot, as well as the self-moving robot itself. The method includes: controlling the self-moving robot to move to a retraction point and acquiring first local coordinate information of the self-moving robot in a local coordinate system; if the self-moving robot does not acquire first global coordinate information in a global coordinate system at the retraction point, controlling the self-moving robot to perform a retraction operation to acquire second global coordinate information of the self-moving robot in the global coordinate system; and determining the global coordinates of the retraction point based on the second global coordinate information and the first local coordinate information. When the self-moving robot cannot obtain its own global coordinate information at the retraction point, it acquires the second global coordinate information by performing a retraction operation, indirectly calculating the coordinate information of the retraction point in the global coordinate system to determine the global coordinates of the retraction point. This can improve the success rate of global coordinate positioning of the retraction point.

Description

Technical Field

[0001] This application belongs to the field of automatic control, and in particular relates to a method for removing piles from a self-moving robot and the self-moving robot itself. Background Technology

[0002] Autonomous mobile robots, such as smart lawnmowers, robotic vacuum cleaners, pool cleaning robots, and warehouse transportation robots, have been widely used in home, commercial, and industrial settings to perform specific tasks such as cleaning, maintenance, and transportation in an autonomous or semi-autonomous manner.

[0003] When a self-moving robot is retracting a staking point, occlusion by objects may reduce the positioning accuracy of the retraction point, making it impossible to determine the global coordinates of the retraction point. Therefore, it is necessary to provide a retraction method that can accurately locate the global coordinates of the retraction point. Summary of the Invention

[0004] The embodiments of this application provide a method for removing a self-moving robot from a pile, as well as the self-moving robot itself. Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part by practice of this application.

[0005] According to a first aspect of the embodiments of this application, a method for retracting a self-moving robot from a staking pile is provided, comprising: Control the self-moving robot to move to the retraction point, and obtain the first local coordinate information of the self-moving robot in the local coordinate system; If the self-moving robot fails to obtain the first global coordinate information in the global coordinate system at the retraction point, then the self-moving robot is controlled to perform a retraction operation in order to obtain the second global coordinate information of the self-moving robot in the global coordinate system. Based on the second global coordinate information and the first local coordinate information, the global coordinates of the retraction point are determined.

[0006] In some possible embodiments of this application, the method further includes: In response to the self-moving robot being at the retraction point, the second local coordinate information of the charging pile in the local coordinate system is obtained; wherein, the location of the charging pile is the starting point of the self-moving robot's retraction process; The global coordinates of the charging pile are determined based on the second global coordinate information and the second local coordinate information.

[0007] In some possible embodiments of this application, the retraction operation includes controlling the self-moving robot to move. During the movement, if the global coordinate information of the self-moving robot is obtained, the time when the global coordinate information is obtained is the first time, and the second global coordinate information includes the global coordinate information at the first time. Determining the global coordinates of the retraction point based on the second global coordinate information and the first local coordinate information includes: Obtain the third local coordinate information of the self-moving robot at the first moment; Based on the third local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

[0008] In some possible implementations of this application, determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the third local coordinate information and the second global coordinate information, a first transformation relationship between the global coordinate system and the local coordinate system is determined. Based on the first transformation relationship, the first local coordinate information is converted into third global coordinate information to determine the global coordinates of the retraction point.

[0009] In some possible embodiments of this application, after obtaining the global coordinate information of the self-moving robot at the first moment during the movement, the retraction operation further includes: Control the self-moving robot to stop moving; The method further includes: Obtain the global coordinate information of the self-moving robot at a second time point; wherein, the second time point is the moment when the self-moving robot changes from a moving state to a stationary state; The second global coordinate information is determined based on the global coordinate information at the second time point.

[0010] In some possible embodiments of this application, determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the third local coordinate information and the second global coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined; Based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

[0011] In some possible implementations of this application, determining the fourth local coordinate information of the self-moving robot at the second time moment based on the third local coordinate information and the second global coordinate information includes: Based on the global coordinate information at the first time point and the global coordinate information at the second time point, the distance traveled by the self-moving robot from the first time point to the second time point is determined; Based on the travel distance and the third local coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined.

[0012] In some possible implementations of this application, determining the global coordinates of the retraction point based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the fourth local coordinate information and the global coordinate information at the second time, a second transformation relationship between the global coordinate system and the local coordinate system is determined; Based on the second transformation relationship, the first local coordinate information is converted into third global coordinate information to determine the global coordinates of the retraction point.

[0013] In some possible embodiments of this application, controlling the self-moving robot to move to the retraction point includes: Control the self-moving robot to maintain its direction toward the charging pile and move to the charging pile removal point; The pile retraction operation includes: After controlling the self-moving robot to rotate a preset angle at the retraction point, it plans a movement path and moves based on the movement path.

[0014] In some possible embodiments of this application, the charging pile is provided with a return guidance sign; when the self-moving robot is at the exit point and facing the charging pile, the return guidance sign is within the field of view of the self-moving robot's vision sensor; The step of obtaining the second local coordinate information of the charging pile in the local coordinate system includes: The second local coordinate information is obtained by scanning the regression guidance mark on the charging pile using the visual sensor.

[0015] In some possible embodiments of this application, the method further includes: If the self-moving robot obtains the first global coordinate information in the global coordinate system at the retraction point, it determines the global coordinates of the retraction point based on the first global coordinate information.

[0016] In some possible embodiments of this application, the method further includes: The global coordinates of the charging pile are determined based on the first global coordinate information and the second local coordinate information.

[0017] In some possible embodiments of this application, before controlling the self-moving robot to perform the retraction operation if it fails to obtain the first global coordinate information in the global coordinate system at the retraction point, the method further includes: The self-moving robot is controlled to wait at the retraction point for a first duration.

[0018] According to a second aspect of the embodiments of this application, a self-moving robot is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the embodiments above.

[0019] According to a third aspect of the embodiments of this application, a self-moving robot, the self-moving robot comprising: The first acquisition module is used to control the self-moving robot to move to the retraction point and acquire the first local coordinate information of the self-moving robot in the local coordinate system. The second acquisition module is used to control the self-moving robot to perform a retraction operation if the self-moving robot fails to acquire the first global coordinate information in the global coordinate system at the retraction point, so as to acquire the second global coordinate information of the self-moving robot in the global coordinate system. The conversion module is used to determine the global coordinates of the retraction point based on the second global coordinate information and the first local coordinate information.

[0020] In some possible embodiments of this application, the mobile robot further includes a determining module for: In response to the self-moving robot being at the retraction point, the second local coordinate information of the charging pile in the local coordinate system is obtained; wherein, the location of the charging pile is the starting point of the self-moving robot's retraction process; The global coordinates of the charging pile are determined based on the second global coordinate information and the second local coordinate information.

[0021] In some possible embodiments of this application, the retraction operation includes controlling the self-moving robot to move. During the movement, if the global coordinate information of the self-moving robot is obtained, the time when the global coordinate information is obtained is the first time, and the second global coordinate information includes the global coordinate information at the first time. Determining the global coordinates of the retraction point based on the second global coordinate information and the first local coordinate information includes: Obtain the third local coordinate information of the self-moving robot at the first moment; Based on the third local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

[0022] In some possible implementations of this application, determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the third local coordinate information and the second global coordinate information, a first transformation relationship between the global coordinate system and the local coordinate system is determined. Based on the first transformation relationship, the first local coordinate information is converted into third global coordinate information to determine the global coordinates of the retraction point.

[0023] In some possible embodiments of this application, after obtaining the global coordinate information of the self-moving robot at the first moment during the movement, the retraction operation further includes: Control the self-moving robot to stop moving; The determining module is also used for: Obtain the global coordinate information of the self-moving robot at a second time point; wherein, the second time point is the moment when the self-moving robot changes from a moving state to a stationary state; The second global coordinate information is determined based on the global coordinate information at the second time point.

[0024] In some possible embodiments of this application, determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the third local coordinate information and the second global coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined; Based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

[0025] In some possible implementations of this application, determining the fourth local coordinate information of the self-moving robot at the second moment based on the third local coordinate information and the second global coordinate information includes: Based on the global coordinate information at the first time point and the global coordinate information at the second time point, the distance traveled by the self-moving robot from the first time point to the second time point is determined; Based on the travel distance and the third local coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined.

[0026] In some possible implementations of this application, determining the global coordinates of the retraction point based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the fourth local coordinate information and the global coordinate information at the second time, a second transformation relationship between the global coordinate system and the local coordinate system is determined; Based on the second transformation relationship, the first local coordinate information is converted into third global coordinate information to determine the global coordinates of the retraction point.

[0027] In some possible embodiments of this application, controlling the self-moving robot to move to the retraction point includes: Control the self-moving robot to maintain its direction toward the charging pile and move to the charging pile removal point; The pile retraction operation includes: After controlling the self-moving robot to rotate a preset angle at the retraction point, it plans a movement path and moves based on the movement path.

[0028] In some possible embodiments of this application, the charging pile is provided with a return guidance sign; when the self-moving robot is at the exit point and facing the charging pile, the return guidance sign is within the field of view of the self-moving robot's vision sensor; The step of obtaining the second local coordinate information of the charging pile in the local coordinate system includes: The second local coordinate information is obtained by scanning the regression guidance mark on the charging pile using the visual sensor.

[0029] In some possible implementations of this application, the determining module is further configured to: If the self-moving robot obtains the first global coordinate information in the global coordinate system at the retraction point, it determines the global coordinates of the retraction point based on the first global coordinate information.

[0030] In some possible implementations of this application, the determining module is further configured to: The global coordinates of the charging pile are determined based on the first global coordinate information and the second local coordinate information.

[0031] In some possible embodiments of this application, before controlling the self-moving robot to perform the retraction operation if it fails to obtain the first global coordinate information in the global coordinate system at the retraction point, the self-moving robot is further configured to: The self-moving robot is controlled to wait at the retraction point for a first duration.

[0032] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the methods described in the embodiments above.

[0033] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the methods described in the embodiments above.

[0034] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application.

[0035] The beneficial effects of the technical solutions provided in this application are: When a self-moving robot cannot obtain its own global coordinate information at the retraction point, it performs a retraction operation to acquire secondary global coordinate information. Using this secondary global coordinate information, it indirectly calculates the coordinates of the retraction point in the global coordinate system, thus determining the global coordinates of the retraction point. This improves the success rate of global coordinate localization of the retraction point.

[0036] Based on the global coordinates of the exit point, the robot's local perception information of the charging pile at the exit point was used to further calculate the global coordinates of the charging pile. This is of great significance for the robot to subsequently build or update the environmental map and optimize the return path, enabling the robot to return to the charging pile more accurately.

[0037] By utilizing the global coordinates successfully acquired at any given moment during the movement, and combining them with the local coordinates recorded by the robot's own odometry at that moment, the global coordinates of the retraction point can be easily and efficiently deduced. This method has low requirements for the timing of global coordinate acquisition; it only needs to be successful once during the movement, greatly improving the algorithm's flexibility and adaptability.

[0038] A precise and universal coordinate system transformation method is provided. By calculating the transformation relationship between two coordinate systems, the staking points in the local coordinate system can be accurately mapped to the global coordinate system, ensuring the mathematical rigor and accuracy of coordinate calculation.

[0039] By successfully acquiring the global coordinate information at the first moment, controlling the robot to stop moving and acquiring the high-precision global coordinates in the stationary state (i.e., the global coordinate information at the second moment), measurement errors and positioning jitter during robot movement are effectively avoided, providing a more reliable data foundation for subsequent calculation of the retraction point coordinates, thereby improving the accuracy of the final positioning result.

[0040] By shifting the positioning reference point from the first moment of motion to the second moment of stillness, more reliable global coordinates and their precise corresponding local coordinates can be determined. This method avoids the potential instability of global coordinates during motion, making the reference points used for subsequent calculations more accurate, thereby improving the overall accuracy of the coordinate calculation process.

[0041] After the self-mobile robot acquires global coordinate information at the first moment and stops performing VIO positioning, the straight-line distance and direction change of the robot in the global coordinate system can be directly calculated using the global coordinate information at the first moment and the global coordinate information at the second moment. This allows for the calculation of the fourth local coordinate information of the self-mobile robot at the second moment, providing reliable data support for subsequent coordinate transformation.

[0042] By utilizing high-precision stationary coordinate pairs to solve the second transformation relationship between the global and local coordinate systems, the accuracy of coordinate transformation is significantly improved. Applying this second transformation relationship to the transformation of the retraction point coordinates yields more accurate global coordinates of the retraction point, thereby enhancing the final accuracy of the entire retraction positioning system.

[0043] The specific kinematic behavior of the self-moving robot moving to the charging pile removal point and performing the charging pile removal operation was clarified. It can keep moving towards the charging pile and, when the distance is appropriate, ensure that the charging pile is within the field of view of the self-moving robot's vision sensor, so as to ensure more accurate docking and return to the charging pile.

[0044] After rotating to a preset angle, a movement path is planned, and movement is based on the movement path. This allows for more effective obstacle avoidance and movement to more open areas, so that subsequent operations can be performed after the retraction point is located.

[0045] This paper presents a low-cost, high-precision, and easy-to-implement method for obtaining the relative position of charging piles. By setting regression guidance markers on the charging piles and utilizing the robot's vision sensors, the second local coordinate information of the charging piles can be quickly and accurately obtained at the point of exit, providing a reliable data source for subsequently determining the global coordinates of the charging piles.

[0046] When the robot can directly obtain the first global coordinate information at the retraction point, unnecessary movement and calculation can be avoided, saving time and energy and improving the positioning efficiency of the global coordinates at the retraction point.

[0047] By introducing a brief waiting mechanism, positioning failures caused by temporary or accidental factors are effectively filtered out, avoiding unnecessary retraction operations. This saves the self-moving robot's energy and time, reduces unnecessary movements, and makes the entire retraction decision-making process more rational and intelligent. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 A flowchart illustrating a method for retracting a self-moving robot from a pile, provided for an embodiment of this application; Figure 2 This is a schematic diagram illustrating a scheme for locating a self-moving robot during its movement from a charging station to a decommissioning point, as shown in one example of this application. Figure 3 This is a schematic diagram of a self-moving robot moving from a charging station to a decharging point, as shown in one example of this application. Figure 4 This is a schematic diagram of a self-moving robot rotating at a preset angle at a retraction point, as shown in one example of this application. Figure 5 This is a schematic diagram of a self-moving robot's retraction scheme in one example of this application; Figure 6 This is a schematic diagram of a self-moving robot's retraction scheme in one example of this application; Figure 7 A schematic diagram of the structure of a self-moving robot provided for an embodiment of this application; Figure 8 This is a structural schematic diagram of a self-moving robot provided for an embodiment of this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0050] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0051] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0052] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0053] It should also be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of these terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in sequences other than those illustrated or described.

[0054] The following description of several exemplary embodiments illustrates the technical solutions of this application and the technical effects produced by these solutions. It should be noted that the following embodiments can be referenced, borrowed from, or combined with each other. Identical terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0055] When a mobile device leaves its charging station (during the removal process), it may experience RTK (Real-Time Kinematic) shadowing due to obstructions near the removal point. This means that the satellite signals, differential data, or solution conditions received by the RTK device are blocked or interfered with, preventing the achievement of a "fixed solution" (i.e., centimeter-level accuracy) in certain areas or situations. For example, users often place the lawnmower's charging station in a storage room or under an eave. In such cases, the satellite signal is obstructed by buildings, trees, mountains, etc., leading to decreased positioning accuracy or the inability to achieve a fixed solution. Consequently, the lawnmower cannot accurately locate the global coordinates of the removal point during removal, affecting normal functionality.

[0056] In situations where objects near the retraction point may obstruct the accurate global positioning of the retraction point, this application indirectly calculates the coordinates of the retraction point in the global coordinate system by performing a retraction operation, thereby determining the global coordinates of the retraction point. This can improve the success rate of global coordinate positioning of the retraction point.

[0057] In some possible embodiments of this application, a method for unloading a self-moving robot is provided, wherein the executing entity can be the self-moving robot, and more specifically, it can be the controller of the self-moving robot.

[0058] Among them, self-moving robots are robots or devices that can move autonomously or semi-autonomously, such as lawn mowing robots, sweeping robots, and warehouse inspection AGVs (Automated Guided Vehicles).

[0059] In some possible embodiments of this application, the execution subject of the self-moving robot control method of this application may also be a terminal that communicates with the self-moving robot. The terminal (also referred to as a user terminal or user device) may be a smartphone, tablet computer, laptop computer, desktop computer, intelligent voice interaction device (e.g., smart speaker), wearable electronic device (e.g., smartwatch), vehicle terminal, smart home appliance (e.g., smart TV), AR / VR device, aircraft, etc., but is not limited to these.

[0060] In some possible implementations, the execution entity of the self-moving robot control method of this application may also be a server communicating with the self-moving robot. The server may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server or server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0061] In some possible implementations of this application, such as Figure 1 As shown, a method for retracting a self-moving robot from a charging pile or docking station is provided, wherein retracting refers to the process of the self-moving robot leaving the charging pile or docking station.

[0062] Methods for retracting stubs from self-moving robots include: Step S101: Control the self-moving robot to move to the retraction point and obtain the first local coordinate information of the self-moving robot in the local coordinate system.

[0063] The retraction point is a pre-set key location for the autonomous mobile robot to determine its own position or perform the retraction action during the retraction process. Typically, the retraction point is located within a certain range of the charging pile, ensuring that when the autonomous mobile robot moves to the retraction point during the retraction process, the charging pile is within the field of view of the autonomous mobile robot's vision sensor, thus enabling accurate retraction.

[0064] The local coordinate system is a coordinate system established with the self-moving robot itself as the origin, used to describe the position and orientation of objects around the robot relative to itself. The global coordinate system is a coordinate system fixed relative to the self-moving robot's working environment (such as the entire room, lawn, or yard), used to describe the robot's absolute position in that environment.

[0065] In practice, the self-moving robot can move to a charging station removal point along a fixed direction and at a fixed distance. It can also generate a charging station removal path along a random direction and at a random distance, and determine whether the charging station removal point corresponding to this path is within a certain range of the charging station. If it is within a certain range of the charging station, it moves to the corresponding charging station removal point based on this path.

[0066] Once the self-propelled robot reaches the exit point, its built-in sensors (such as odometry and inertial measurement units (IMUs)) record its position in its local coordinate system, i.e., its first local coordinate information. In this local coordinate system, the robot's center or the center of a specific sensor (such as a vision sensor) is typically used as the origin, with the front direction being the positive X-axis or Y-axis. For example, when the robot reaches the exit point, its local coordinates can be represented as (0, 0, 0), indicating that the robot considers itself to be at the origin of its coordinate system.

[0067] Step S102: If the self-moving robot does not obtain the first global coordinate information in the global coordinate system at the retraction point, then control the self-moving robot to perform the retraction operation in order to obtain the second global coordinate information of the self-moving robot in the global coordinate system.

[0068] At the point of exit from the obstacle, the self-moving robot attempts to acquire its current global coordinate information. When SLAM (Simultaneous Localization and Mapping) is started, the precise position and orientation (orientation) of the self-moving robot cannot be determined, and there is no map. Initialization involves using some sensor data to allow the SLAM algorithm to quickly determine a reliable initial state (position, orientation, scale), after which normal tracking and mapping can begin.

[0069] The mobile robot acquires a flag indicating whether SLAM initialization is complete. If the flag indicating SLAM initialization is complete is acquired, it means that the charging station is less affected by RTK shadows, and the robot can then obtain the first global coordinate information in the global coordinate system.

[0070] If the flag indicating SLAM initialization is not obtained, meaning the first global coordinate information in the global coordinate system is not obtained at the stub removal point, the self-moving robot is controlled to perform a stub removal operation. During the stub removal operation, the flag indicating SLAM initialization is continuously obtained to acquire the second global coordinate information of the self-moving robot in the global coordinate system.

[0071] The pile removal operation may include controlling the movement of the self-moving robot, or it may include controlling the self-moving robot to decelerate until it stops after movement. The specific process of the pile removal operation will be further described in detail below.

[0072] Step S103: Determine the global coordinates of the retraction point based on the second global coordinate information and the first local coordinate information.

[0073] The second global coordinate information corresponds to the coordinate information in the global coordinate system at a certain moment during the robot's retraction operation, while the first local coordinate information corresponds to the coordinate information of the robot in the local coordinate system at the retraction point. By establishing the geometric relationship between these two positions, the conversion relationship between the local coordinate system and the global coordinate system can be deduced. Furthermore, based on the first local coordinate information, the coordinate information of the retraction point in the global coordinate system can be calculated, thereby determining the global coordinates of the retraction point.

[0074] The process of determining the global coordinates of the retraction point will be explained in more detail below.

[0075] In the above embodiments, when the self-moving robot cannot obtain its own global coordinate information at the retraction point, it obtains second global coordinate information by performing a retraction operation. Using the robot's second global coordinate information, it indirectly calculates the coordinates of the retraction point in the global coordinate system to determine the global coordinates of the retraction point. This can improve the success rate of global coordinate positioning of the retraction point.

[0076] like Figure 2 As shown, Figure 2 The diagram below illustrates a scheme for locating a self-moving robot during its movement from a charging station to a decommissioning point, as shown in one example of this application.

[0077] In practical implementation, VIO (Visual-Inertial Odometry) fusion positioning can be used. Visual information is used to calibrate the accumulated error of the IMU, and the IMU is used to predict motion. For details, please refer to [link / reference needed]. Figure 2 As shown: The input can be data from the self-moving robot's vision sensors and IMU, as shown in the figure. The visual sensor acquires image data, such as a sequence of environmental images captured at a certain frame rate (e.g., 30Hz); then the IMU sensor acquires triaxial acceleration and triaxial angular velocity data at a higher frequency (e.g., 200Hz); that is, the image data and IMU data shown in the figure. The input image data is used to extract significant feature points (such as SIFT (Scale-Invariant Feature Transform) or FAST (Features from Accelerated Segment Test) corner points), and feature matching algorithms are used to track these feature points between adjacent frames, i.e., feature extraction and tracking as shown in the figure; Pre-integration is performed on the acceleration and angular velocity measured by the IMU. Since the raw IMU measurements include gravitational components and zero bias, the pre-integration process integrates the IMU measurements over the time interval between two frames to obtain the relative rotation, velocity, and position changes between the two frames, i.e., the IMU integration shown in the figure. During the system startup phase, the joint initialization of vision and IMU needs to be completed, as shown in the figure. Aligning the IMU integral results with the pose changes estimated by vision allows us to calculate the scale factor, gravity vector, initial velocity, and initial values ​​of the zero bias of the IMU's accelerometer and gyroscope, as shown in the figure, which is the alignment between vision and IMU. Continuous state estimation can be achieved using either filtering-based or optimization-based methods. Filtering-based methods (such as MSCKF (Multi-State Constraint Kalman Filter)): The filter treats the robot's state (position, velocity, orientation, IMU bias, etc.) as the variables to be estimated. Each frame of IMU data is used for state prediction, and the feature observations of each frame are used to update the state. Optimization-based methods (such as sliding window graph optimization): The system maintains a sliding window containing the most recent frames (e.g., 10-20 frames), with the robot state and all feature points within the window serving as optimization variables. The visual reprojection error and IMU pre-integration error of each frame constitute a nonlinear least squares problem, which is iteratively optimized. Regardless of the method used, the final output is the optimal state estimate of the robot at each time step, including position, orientation, velocity, and IMU bias. That is, the figure shows filtering-based and optimization-based methods for achieving state estimation and optimization. As runtime increases, drift accumulates. To eliminate drift, the system performs loop closure detection: using methods such as the bag-of-words model, it compares the current frame image with historical keyframes for similarity. If the current frame is found to have spatial overlap with a keyframe from a past moment (i.e., returning to the same location), a loop closure is detected. Once a loop closure is detected, the system triggers global optimization. Global optimization incorporates all keyframes and loop closure constraints along the entire historical trajectory into a large graph optimization problem. By solving this global optimization problem, the entire trajectory can be readjusted, eliminating long-term accumulated drift and obtaining a globally consistent pose estimate. In other words, the system detects loop closures as shown in the diagram; if a loop closure is detected, global optimization is performed. The trajectory output after global optimization provides a positioning result with global accuracy. In applications involving retraction, high-precision local coordinates can be obtained.

[0078] In a typical scenario where a self-moving robot moves from a charging station to a docking station, this VIO fusion localization process can provide the self-moving robot with a continuous, reliable, and smooth pose sequence, thereby providing a key motion information basis for the subsequent coordinate calculation of the docking station and the determination of the global coordinates of the charging station.

[0079] In some possible implementations of this application, the method further includes: (1) In response to the self-moving robot being at the retraction point, the second local coordinate information of the charging pile in the local coordinate system is obtained.

[0080] The location of the charging pile is the starting point for the self-moving robot's retraction process.

[0081] In this embodiment, the charging station is a device that provides power to the autonomous mobile robot, and also serves as a reference point for the robot to perform return and retraction operations. The location of the charging station is defined as the starting point of the robot's retraction process. That is, the autonomous mobile robot starts from the charging station location, moves to the retraction point, and then continues to perform subsequent actions.

[0082] Once the self-moving robot successfully reaches the charging station's exit point, it can use sensors (such as vision sensors, LiDAR, and infrared receivers) to perceive the charging station. Since the exit point is usually a pre-set location close to the charging station (e.g., 1 meter directly in front), the charging station is within the robot's sensor field of view. Using sensor data, the self-moving robot can calculate the charging station's position and orientation relative to itself (i.e., the origin of its local coordinate system). This information is the second local coordinate information. For example, by recognizing a specific pattern on the charging station using a vision sensor and combining it with depth information, the robot can calculate the charging station's coordinates in its local coordinate system as (1m, 0m, 180°), indicating that the charging station is 1 meter in front of the robot and its orientation is opposite to the robot's orientation.

[0083] (2) Determine the global coordinates of the charging pile based on the second global coordinate information and the second local coordinate information.

[0084] The second global coordinate information corresponds to the coordinate information in the global coordinate system at a certain moment during the robot's retraction operation. It is similar to the process of determining the global coordinates of the retraction point. Therefore, the conversion relationship between the local coordinate system and the global coordinate system is calculated first, and then the coordinate information of the charging pile in the global coordinate system is calculated based on the second local coordinate information, thereby determining the global coordinates of the charging pile.

[0085] In the above embodiments, based on determining the global coordinates of the charging pile exit point, the robot's local perception information of the charging pile at the exit point is used to further calculate the global coordinates of the charging pile. This is of great significance for the robot to subsequently build or update the environmental map and optimize the return path, enabling the robot to return to the charging pile more accurately.

[0086] In some possible embodiments of this application, the retraction operation includes controlling the self-moving robot to move. During the movement, if the global coordinate information of the self-moving robot is obtained, the time when the global coordinate information is obtained is the first time, and the second global coordinate information includes the global coordinate information at the first time.

[0087] Self-moving robots can move along straight lines or curves, with the goal of reaching a position where they can successfully acquire global coordinates.

[0088] Step S103, based on the second global coordinate information and the first local coordinate information, determines the global coordinates of the retraction point, which may include: (1) Obtain the third local coordinate information of the mobile robot at the first moment.

[0089] During the movement of a self-moving robot, its internal sensors (such as an odometer) continuously update its local coordinates. When the self-moving robot successfully acquires its global coordinates (second global coordinate information) at the first moment, it simultaneously records its own local coordinates at that moment, which is denoted as third local coordinate information. For example, at the first moment of movement, the odometer shows the robot's position in the local coordinate system as (0.2m, 0m, 0°).

[0090] (2) Determine the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information.

[0091] The third local coordinate information is the local coordinate information obtained by the self-moving robot at the first moment, and the second global coordinate information is the global coordinate information obtained by the self-moving robot at the first moment. The conversion relationship between the local coordinate system and the global coordinate system can be determined through the third local coordinate information and the second global coordinate information. Then, based on the first local coordinate information, the coordinate information of the retraction point in the global coordinate system can be calculated, thereby determining the global coordinates of the retraction point.

[0092] In the above embodiments, by utilizing the global coordinates successfully acquired at any moment during the movement, and combining them with the local coordinates recorded by the robot's own odometer at that moment, the global coordinates of the retreat point can be deduced simply and efficiently. This method has low requirements for the timing of global coordinate acquisition; it only needs to be successful once during the movement, greatly improving the algorithm's flexibility and adaptability.

[0093] In some possible implementations of this application, determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information may include: ① Based on the third local coordinate information and the second global coordinate information, determine the first transformation relationship between the global coordinate system and the local coordinate system.

[0094] The first transformation relationship is a mathematical mapping, typically consisting of a rotation matrix R and a translation vector T. Since the third local coordinate information and the second global coordinate information describe the coordinates of the same physical point (i.e., the robot's position at the first moment) in different coordinate systems, the transformation parameters from the local coordinate system to the global coordinate system can be calculated. For example, suppose the coordinates (x_local, y_local) in the local coordinate system and the coordinates (x_global, y_global) in the global coordinate system satisfy the relationship: [x_global; y_global] = R × [x_local; y_local] + T. Substituting the known third local coordinates and second global coordinates, R and T can be solved.

[0095] ② Based on the first transformation relationship, the first local coordinate information is converted into the third global coordinate information to determine the global coordinates of the retraction point.

[0096] Having obtained the first transformation relation, it can be applied to the local coordinates of the retraction point (first local coordinate information). Substituting the first local coordinate information into the above transformation formula, the calculated result is the coordinates of the retraction point in the global coordinate system, i.e., the third global coordinate information. This coordinate is the global coordinate of the retraction point. For example, after obtaining the transformation matrix R and vector T, substituting the local coordinates (0,0,0) of the retraction point, the global coordinates of the retraction point are the vector T itself.

[0097] The above embodiments provide a precise and universal coordinate system transformation method. By calculating the transformation relationship between two coordinate systems, the staking point in the local coordinate system can be accurately mapped to the global coordinate system, ensuring the mathematical rigor and accuracy of the coordinate calculation.

[0098] Understandably, the second local coordinate information of the charging pile can also be transformed based on the first transformation relationship to determine the global coordinates of the charging pile.

[0099] In some possible implementations of this application, after obtaining the global coordinate information of the self-moving robot at the first moment during the movement, the retraction operation further includes: Control the self-moving robot to stop moving.

[0100] In other words, the movement of the self-moving robot is not continuous, but can be stopped immediately after successfully acquiring the second global coordinate information at the first moment.

[0101] The method also includes: (1) Obtain the global coordinate information of the mobile robot at the second moment.

[0102] The second moment is the moment when the self-moving robot changes from a moving state to a stationary state.

[0103] Understandably, after controlling the self-moving robot to stop—that is, sending a stop command to the moving components—the robot typically does not immediately become stationary; its speed does not instantly drop to zero. After the robot stops moving, its speed drops to zero, and its position no longer changes. At this point, the robot attempts to acquire its global coordinates again. These coordinates in this stable state are recorded as the global coordinate information at the second moment. Because the robot is stationary at this time, the global coordinate information acquired at the second moment is usually more stable and accurate than that acquired during movement (i.e., the global coordinate information at the first moment). For example, the global coordinates acquired by the robot during movement at the first moment might be (3m, 5m), which may contain motion noise; after stopping, acquiring them again at the second moment yields more accurate global coordinates (3.02m, 4.98m).

[0104] (2) Determine the second global coordinate information based on the global coordinate information at the second time.

[0105] The second global coordinate information used for subsequent calculations is the more accurate global coordinate information acquired by the robot at a second moment when it is stationary. This can be understood as a correction and optimization of the coordinates at the first moment.

[0106] In the above embodiments, by controlling the robot to stop moving after successfully acquiring the global coordinate information at the first moment, and acquiring the high-precision global coordinates in the stationary state (i.e., the global coordinate information at the second moment), measurement errors and positioning jitter during robot movement are effectively avoided, providing a more reliable data foundation for subsequent calculation of the retraction point coordinates, thereby improving the accuracy of the final positioning result.

[0107] This embodiment provides another specific implementation method for "determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information". Unlike the previous embodiment which directly established the first transformation relationship, this embodiment further introduces the concept of fourth local coordinate information to calculate the global coordinates of the retraction point.

[0108] In some possible embodiments of this application, determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information may include: ① Based on the third local coordinate information and the second global coordinate information, determine the fourth local coordinate information of the self-moving robot at the second moment.

[0109] Since the mobile robot has moved from the first moment (moving state) to the second moment (stationary state), its position in the local coordinate system has also changed. Because the local coordinates (third local coordinate information) of the first moment are known, and the relative motion of the robot from the first moment to the second moment can be calculated from the global coordinate information of the first moment and the global coordinate information of the second moment, the local coordinates of the second moment, i.e. the fourth local coordinate information, can be further calculated.

[0110] ② Based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information, determine the global coordinates of the retraction point.

[0111] In this application, once the self-mobile robot obtains the global coordinate information at the first moment, it will stop performing VIO positioning, meaning it will no longer directly obtain the local coordinate information. At this point, it is necessary to calculate the fourth local coordinate information at the second moment through other methods.

[0112] Based on the global coordinates (second global coordinate information) at the second moment and their corresponding local coordinates (fourth local coordinate information), the transformation relationship between the global coordinate system and the local coordinate system is determined when the self-moving robot is stationary and in a high-precision state. Then, the global coordinates of the retraction point are further determined based on the first local coordinate information of the retraction point.

[0113] In the above embodiments, by shifting the positioning reference point from the first moment of motion to the second moment of stillness, more reliable global coordinates and their precise corresponding local coordinates can be determined. This method avoids the problem of potential instability of global coordinates during motion, making the reference points used for subsequent calculations more accurate, thereby improving the accuracy of the entire coordinate calculation process.

[0114] In some possible implementations of this application, determining the fourth local coordinate information of the self-moving robot at a second time moment based on the third local coordinate information and the second global coordinate information may include: Based on the global coordinate information at the first moment and the global coordinate information at the second moment, the distance traveled by the self-moving robot from the first moment to the second moment is determined; Based on the travel distance and the third local coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined.

[0115] The distance traveled is calculated in the global coordinate system.

[0116] In this application, once the self-propelled robot acquires global coordinate information at the first moment, it stops performing VIO localization. At this point, by comparing the two global coordinate information at the first and second moments, the straight-line distance and direction change of the robot in the global coordinate system can be directly calculated. For example, if the global coordinates at the first moment are (3m, 5m) and the global coordinates at the second moment are (3.1m, 5m), then the movement distance can be calculated to be 0.1 meters, with the direction being the positive X-axis.

[0117] By combining the local coordinates at the first moment (third local coordinate information, such as (0.2m, 0m)) and this relative motion (including distance and direction), the local coordinates at the second moment (fourth local coordinate information) can be calculated as (0.2m + 0.1m, 0m) = (0.3m, 0m).

[0118] In the above embodiments, after the self-moving robot obtains global coordinate information at the first moment and stops performing VIO positioning, the straight-line distance and direction change of the robot in the global coordinate system can be directly calculated using the global coordinate information at the first moment and the global coordinate information at the second moment. This allows the calculation of the fourth local coordinate information of the self-moving robot at the second moment, providing reliable data support for subsequent coordinate transformation.

[0119] In some possible implementations of this application, determining the global coordinates of the retraction point based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information may include: Based on the fourth local coordinate information and the global coordinate information at the second moment, the second transformation relationship between the global coordinate system and the local coordinate system is determined; Based on the second transformation relationship, the first local coordinate information is converted into the third global coordinate information to determine the global coordinates of the retraction point.

[0120] Similar to the previous embodiments, this embodiment also employs a coordinate system transformation method, but uses a different reference point. Both this and the previous embodiments use a known coordinate pair to solve for the transformation matrix (rotation matrix R and translation vector T) between the two coordinate systems. The difference lies in that this embodiment uses the robot's coordinate pair at the second moment (stationary state), i.e., the fourth local coordinate information (local) and the second moment's global coordinate information (global). Because the global coordinates at the second moment have higher accuracy, the calculated second transformation relationship is also more precise.

[0121] After obtaining a more accurate second transformation relationship, it is applied to the local coordinates of the retraction point (first local coordinate information). The resulting third global coordinate information is the more accurate global coordinates of the retraction point.

[0122] In the above embodiments, by utilizing high-precision stationary state coordinate pairs to calculate the second transformation relationship between the global and local coordinate systems, the accuracy of coordinate transformation is significantly improved. Applying this second transformation relationship to the transformation of the retraction point coordinates yields more accurate global coordinates of the retraction point, thereby improving the final accuracy of the entire retraction positioning system.

[0123] Understandably, the second local coordinate information of the charging pile can also be transformed into a coordinate system based on the second transformation relationship to determine the global coordinates of the charging pile.

[0124] In some possible implementations of this application, controlling the self-moving robot to move to the retraction point includes: Control the self-moving robot to keep moving towards the charging pile until it reaches the exit point.

[0125] The self-returning robot moves towards the charging station while maintaining a direction facing it. This means that when the robot starts from the charging station or prepares to return to the station, its direction of movement is directly facing the charging station, for example, moving backward along a straight line directly in front of the charging station. This ensures that the return point is located on the front axis of the charging station. Furthermore, if the distance is appropriate, it also ensures that the charging station is within the field of view of the self-returning robot's vision sensors, allowing for more precise docking and return.

[0126] like Figure 3 As shown, Figure 3This is a schematic diagram of a self-moving robot moving from a charging pile to a withdrawal point in one example of this application; in the figure, 300 is the charging pile, 301 is the self-moving robot, 301a is the vision sensor of the self-moving robot, 302 is the withdrawal point, the arrow in the figure shows the forward direction of the self-moving device, and 303 is the withdrawal path of the self-moving device from the charging pile 300 to the withdrawal point 302.

[0127] The piling removal operation includes: After controlling the self-moving robot to rotate at a preset angle at the retraction point, it plans a movement path and moves based on the movement path.

[0128] At the retraction point, after the self-moving robot rotates by a preset angle, its orientation can be changed. The vision sensor can detect obstacles within the robot's forward field of view. For example, the preset angle can be 180°, meaning it performs a 180-degree spin, causing the robot to face away from the obstacle. If no obstacle is detected directly ahead, it plans to move in a straight line. If an obstacle is detected, it plans a non-linear trajectory to avoid it.

[0129] like Figure 4 As shown, Figure 4 This is a schematic diagram of a self-moving robot rotating at a preset angle at a charging pile retraction point in one example of this application; after the self-moving robot 400 moves to the charging pile retraction point 401, it is originally facing the charging pile 402, but it can rotate 180° to face the charging pile 402 and then move.

[0130] The self-propelled robot controls itself to move along a planned path and continuously attempts to obtain global coordinates during the movement.

[0131] The above embodiments clarify the specific kinematic behavior of the self-moving robot moving to the charging pile removal point and performing the charging pile removal operation. It keeps moving towards the charging pile, and when the distance is appropriate, it can also ensure that the charging pile is within the field of view of the self-moving robot's vision sensor, so as to ensure more accurate docking and return to the charging pile.

[0132] After rotating to a preset angle, a movement path is planned, and movement is based on the movement path. This allows for more effective obstacle avoidance and movement to more open areas, so that subsequent operations can be performed after the retraction point is located.

[0133] In some possible embodiments of this application, a return guidance sign is provided on the charging pile; when the self-moving robot is at the exit point and facing the charging pile, the return guidance sign is within the field of view of the self-moving robot's vision sensor.

[0134] Among them, return guidance markers are special marks that can be recognized by the sensors of self-moving robots and provide relative position and orientation information. They can be a QR code, an infrared reflective strip, a color block of a specific shape, or a pattern, etc.

[0135] When the autonomous mobile robot is at the exit point and facing the charging station, the return guidance marker is within the field of view of the robot's vision sensor. This ensures that the autonomous mobile robot can clearly observe the marker at the exit point, meaning that during the return process, as the robot moves to the exit point, it can return to the charging station more accurately based on the return guidance marker.

[0136] Obtain the second local coordinate information of the charging pile in the local coordinate system, including: The second local coordinate information is obtained by scanning the regression guidance signs on the charging pile with a visual sensor.

[0137] The vision sensor can be a monocular camera, a binocular camera, or an RGB-D (Red Green Blue-Depth) camera.

[0138] After the robot captures an image of the guidance sign using its vision sensor, it can calculate the sign's 3D position and orientation relative to the camera (i.e., the robot) in real time using image processing algorithms (such as QR code decoding and PnP (Perspective-n-Point) pose calculation algorithms). This calculation result directly represents the charging station's coordinates in the robot's local coordinate system, i.e., the second local coordinate information. For example, after recognizing the QR code, the algorithm outputs the center point of the sign in the camera coordinate system as (0.5m, 0m, 0.2m), and the rotation vector as (0°, -90°, 0°). These data constitute the second local coordinate information.

[0139] The above embodiments provide a low-cost, high-precision, and easy-to-implement method for obtaining the relative position of a charging pile. By setting regression guidance markers on the charging pile and utilizing the robot's vision sensors, the second local coordinate information of the charging pile can be quickly and accurately obtained at the point of exit, providing a reliable data source for subsequently determining the global coordinates of the charging pile.

[0140] In some possible implementations of this application, the method further includes: If the mobile robot obtains the first global coordinate information in the global coordinate system at the retraction point, it determines the global coordinates of the retraction point based on the first global coordinate information.

[0141] Once the autonomous mobile robot reaches the stub removal point, if SLAM initialization is complete, it can successfully acquire its own initial global coordinate information. At this point, there is no need to perform any complex stub removal operations or acquire and calculate more local or global coordinate information. The autonomous mobile robot directly determines the global coordinates of the stub removal point based on this acquired initial global coordinate information for recording and subsequent use.

[0142] In the above embodiments, when the robot can directly obtain the first global coordinate information at the retraction point, unnecessary movement and calculation can be avoided, saving time and energy and improving the positioning efficiency of the global coordinates at the retraction point.

[0143] In some possible implementations of this application, the method further includes: The global coordinates of the charging pile are determined based on the first global coordinate information and the second local coordinate information.

[0144] The mobile robot has already obtained its first global coordinate information at the charging station exit point, and has also obtained its second local coordinate information relative to the charging station through sensors (such as visual sensors scanning and regressing guidance signs). It can then directly perform coordinate transformation. Based on the first global and first local coordinate information, the transformation relationship between the global and local coordinate systems can be determined. This allows the second local coordinate information (the charging station's coordinates in the local coordinate system) to be transformed to the global coordinate system.

[0145] In the above embodiments, when the first global coordinate information of the charging pile withdrawal point can be directly obtained, a method is provided to quickly, directly, and without moving the charging pile to calculate its global coordinates. This allows for more efficient confirmation of the charging pile's global coordinates.

[0146] In some possible implementations of this application, if the self-moving robot does not obtain the first global coordinate information in the global coordinate system at the retraction point, the method further includes the following before controlling the self-moving robot to perform the retraction operation: Control the self-moving robot to wait at the retraction point for the first time.

[0147] This embodiment adds a waiting mechanism before determining whether to perform the piling operation.

[0148] The first duration is a preset time period, such as 3 seconds, 5 seconds, or 10 seconds. In the event of a positioning failure due to temporary issues such as a momentary signal interruption or brief sensor obstruction, the self-moving robot will not immediately determine that the positioning has failed and perform a retraction operation after reaching the retraction point. Instead, it will remain stationary and wait for the first duration. During the waiting period, the self-moving robot will continuously attempt to acquire the first global coordinate information. For example, the self-moving robot may attempt to locate at the retraction point and fail on the first attempt, but after waiting for 2 seconds, SLAM initialization will be successful, and the first global coordinate information will be acquired.

[0149] If the self-moving robot successfully acquires the first global coordinate information after the first waiting period, it can directly determine the global coordinates of the charging pile removal point and further determine the global coordinates of the charging pile itself. Only if the self-moving robot still cannot acquire the first global coordinate information after the first waiting period ends will subsequent charging pile removal operations (such as relocation) be triggered.

[0150] In the above embodiments, by introducing a brief waiting mechanism, positioning failures caused by temporary and occasional factors are effectively filtered out, avoiding unnecessary retraction operations. This saves the energy and time of the self-moving robot, reduces unnecessary movement, and makes the entire retraction decision-making process more rational and intelligent.

[0151] To more clearly illustrate the process of determining the decommissioning point and the global coordinates of the charging pile, the following will provide further explanation with two examples.

[0152] like Figure 5 As shown, Figure 5 This is a schematic diagram of a self-moving robot's retraction scheme in one example of this application; in one example, the retraction method of this application may include the following process: When it is necessary to remove the pile and build a map (but the map has not yet been completed), control the self-moving robot to move to the removal point; Obtain the first local coordinate information of the charging pile withdrawal point and the second local coordinate information of the charging pile; Determine if SLAM initialization is complete; If SLAM initialization is complete at this time, the SLAM coordinates (first global coordinate information) of the mobile robot are obtained. Based on the relationship between the first local coordinate information and the first global coordinate information of the charging pile, the SLAM coordinates of the charging pile (i.e., the global coordinates of the charging pile) are determined, and the mapping is completed. If SLAM initialization is not completed at this time, then control the self-moving robot to wait for a first duration (e.g., 2 seconds). After the first duration, determine whether SLAM initialization is complete; If SLAM initialization is not complete at this time, control the self-moving robot to perform a stub removal operation, i.e., move; During the movement of the self-moving robot, the SLAM initialization is periodically checked. If the SLAM initialization is detected to be complete at the first time (t0), the third local coordinate information (xv, yv, thetav) and the SLAM coordinates (x3, y3, theta3) (which is the second local coordinate information) at time t0 are obtained. Based on the third local coordinate information (xv, yv, thetav) and SLAM coordinates (x3, y3, theta3) at time t0, the first transformation relationship between the global coordinate system and the local coordinate system is determined, thereby determining the global coordinates (SLAM coordinates) of the charging pile and the global coordinates (SLAM coordinates) of the charging pile, and completing the mapping.

[0153] like Figure 6 As shown, Figure 6 This is a schematic diagram of a self-moving robot's retraction scheme in one example of this application. In one example, the retraction method of this application may include the following process: When it is necessary to remove the pile and build a map (but the map has not yet been completed), control the self-moving robot to move to the removal point; Obtain the first local coordinate information of the charging pile withdrawal point and the second local coordinate information of the charging pile; Determine if SLAM initialization is complete; If SLAM initialization is complete at this time, the SLAM coordinates (first global coordinate information) of the mobile robot are obtained. Based on the relationship between the first local coordinate information and the first global coordinate information of the charging pile, the SLAM coordinates of the charging pile (i.e., the global coordinates of the charging pile) are obtained, and the mapping is completed. If SLAM initialization is not complete at this time, then control the self-moving robot to perform a stub removal operation, i.e., move; During the movement of the self-moving robot, the SLAM initialization is periodically checked. If the SLAM initialization is detected to be complete at the first moment (t0), a stop movement command is sent to the moving component of the self-moving robot, and the third local coordinate information (xv, yv, thetav) and SLAM coordinates (x3, y3, theta3) at t0 (that is, the global coordinate information at t0) are obtained. At this time, the self-moving robot stops VIO positioning, that is, it stops obtaining local coordinate information. At time t0, the self-moving robot is still moving, and its positioning may not be accurate. When the self-moving robot comes to a complete stop at the second time (t1), the global coordinate information (x4, y4, theta4) at time t1 is obtained. Based on the relative positional relationship between (x4, y4, theta4) and (x3, y3, theta3), the distance traveled by the self-moving robot between time t0 and time t1 is calculated, thereby determining the fourth local coordinate information (xvr, yvr, thetaavr) at time t1. Then, based on (xvr, yvr, thetaavr) and (x4, y4, theta4), the second transformation relationship between the global coordinate system and the local coordinate system is determined, thereby determining the global coordinates (SLAM coordinates) of the retraction point and the global coordinates (SLAM coordinates) of the charging pile, and completing the mapping.

[0154] The aforementioned method for retracting a bobbin from a moving robot, when the robot cannot obtain its own global coordinate information at the bobbin retraction point, acquires second global coordinate information by performing a bobbin retraction operation. Using this second global coordinate information, the robot indirectly calculates the coordinates of the bobbin retraction point in the global coordinate system, thereby determining the global coordinates of the bobbin retraction point. This improves the success rate of global coordinate localization of the bobbin retraction point.

[0155] Based on the global coordinates of the exit point, the robot's local perception information of the charging pile at the exit point was used to further calculate the global coordinates of the charging pile. This is of great significance for the robot to subsequently build or update the environmental map and optimize the return path, enabling the robot to return to the charging pile more accurately.

[0156] By utilizing the global coordinates successfully acquired at any given moment during the movement, and combining them with the local coordinates recorded by the robot's own odometry at that moment, the global coordinates of the retraction point can be easily and efficiently deduced. This method has low requirements for the timing of global coordinate acquisition; it only needs to be successful once during the movement, greatly improving the algorithm's flexibility and adaptability.

[0157] A precise and universal coordinate system transformation method is provided. By calculating the transformation relationship between two coordinate systems, the staking points in the local coordinate system can be accurately mapped to the global coordinate system, ensuring the mathematical rigor and accuracy of coordinate calculation.

[0158] By successfully acquiring the global coordinate information at the first moment, controlling the robot to stop moving and acquiring the high-precision global coordinates in the stationary state (i.e., the global coordinate information at the second moment), measurement errors and positioning jitter during robot movement are effectively avoided, providing a more reliable data foundation for subsequent calculation of the retraction point coordinates, thereby improving the accuracy of the final positioning result.

[0159] By shifting the positioning reference point from the first moment of motion to the second moment of stillness, more reliable global coordinates and their precise corresponding local coordinates can be determined. This method avoids the potential instability of global coordinates during motion, making the reference points used for subsequent calculations more accurate, thereby improving the overall accuracy of the coordinate calculation process.

[0160] After the self-mobilizing robot acquires global coordinate information at the first moment and stops performing VIO positioning, the straight-line distance and direction change of the robot in the global coordinate system can be directly calculated using the global coordinate information at the first moment and the global coordinate information at the second moment. This allows for the calculation of the fourth local coordinate information of the self-mobilizing robot at the second moment, providing reliable data support for subsequent coordinate transformation.

[0161] By utilizing high-precision stationary coordinate pairs to solve the second transformation relationship between the global and local coordinate systems, the accuracy of coordinate transformation is significantly improved. Applying this second transformation relationship to the transformation of the retraction point coordinates yields more accurate global coordinates of the retraction point, thereby enhancing the final accuracy of the entire retraction positioning system.

[0162] The specific kinematic behavior of the self-moving robot moving to the charging pile removal point and performing the charging pile removal operation was clarified. It can keep moving towards the charging pile and, when the distance is appropriate, ensure that the charging pile is within the field of view of the self-moving robot's vision sensor, so as to ensure more accurate docking and return to the charging pile.

[0163] After rotating to a preset angle, a movement path is planned, and movement is based on the movement path. This allows for more effective obstacle avoidance and movement to more open areas, so that subsequent operations can be performed after the retraction point is located.

[0164] This paper presents a low-cost, high-precision, and easy-to-implement method for obtaining the relative position of charging piles. By setting regression guidance markers on the charging piles and utilizing the robot's vision sensors, the second local coordinate information of the charging piles can be quickly and accurately obtained at the point of exit, providing a reliable data source for subsequently determining the global coordinates of the charging piles.

[0165] When the robot can directly obtain the first global coordinate information at the retraction point, unnecessary movement and calculation can be avoided, saving time and energy and improving the positioning efficiency of the global coordinates at the retraction point.

[0166] By introducing a brief waiting mechanism, positioning failures caused by temporary or accidental factors are effectively filtered out, avoiding unnecessary retraction operations. This saves the self-moving robot's energy and time, reduces unnecessary movements, and makes the entire retraction decision-making process more rational and intelligent.

[0167] In some possible implementations of this application, such as Figure 7 As shown, a self-moving robot 70 is provided, the self-moving robot 70 includes: The first acquisition module 701 is used to control the self-moving robot to move to the retraction point and acquire the first local coordinate information of the self-moving robot in the local coordinate system. The second acquisition module 702 is used to control the self-moving robot to perform a retraction operation if the self-moving robot fails to acquire the first global coordinate information in the global coordinate system at the retraction point, so as to acquire the second global coordinate information of the self-moving robot in the global coordinate system. The conversion module 703 is used to determine the global coordinates of the retraction point based on the second global coordinate information and the first local coordinate information.

[0168] In some possible embodiments of this application, the mobile robot further includes a determining module for: In response to the self-moving robot being at the charging pile retraction point, the second local coordinate information of the charging pile in the local coordinate system is obtained; wherein, the location of the charging pile is the starting point of the self-moving robot's retraction process; The global coordinates of the charging pile are determined based on the second global coordinate information and the second local coordinate information.

[0169] In some possible embodiments of this application, the retraction operation includes controlling the movement of the self-moving robot. During the movement, if the global coordinate information of the self-moving robot is obtained, the moment when the global coordinate information is obtained is the first moment, and the second global coordinate information includes the global coordinate information at the first moment. Based on the second global coordinate information and the first local coordinate information, the global coordinates of the retraction point are determined, including: The third local coordinate information obtained from the mobile robot at the first moment; Based on the third local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

[0170] In some possible implementations of this application, the global coordinates of the retraction point are determined based on the third local coordinate information, the second global coordinate information, and the first local coordinate information, including: Based on the third local coordinate information and the second global coordinate information, the first transformation relationship between the global coordinate system and the local coordinate system is determined; Based on the first transformation relationship, the first local coordinate information is converted into the third global coordinate information to determine the global coordinates of the retraction point.

[0171] In some possible implementations of this application, after obtaining the global coordinate information of the self-moving robot at the first moment during the movement, the staking removal operation further includes: Control the self-moving robot to stop moving; The determination module is also used for: Obtain the global coordinate information of the self-moving robot at the second moment; where the second moment is the moment when the self-moving robot changes from a moving state to a stationary state; The second global coordinate information is determined based on the global coordinate information at the second time step.

[0172] In some possible embodiments of this application, determining the global coordinates of the retraction point based on third local coordinate information, second global coordinate information, and first local coordinate information includes: Based on the third local coordinate information and the second global coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined; Based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

[0173] In some possible implementations of this application, the fourth local coordinate information of the self-moving robot at a second time moment is determined based on the third local coordinate information and the second global coordinate information, including: Based on the global coordinate information at the first moment and the global coordinate information at the second moment, the distance traveled by the self-moving robot from the first moment to the second moment is determined; Based on the travel distance and the third local coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined.

[0174] In some possible implementations of this application, the global coordinates of the retraction point are determined based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information, including: Based on the fourth local coordinate information and the global coordinate information at the second moment, the second transformation relationship between the global coordinate system and the local coordinate system is determined; Based on the second transformation relationship, the first local coordinate information is converted into the third global coordinate information to determine the global coordinates of the retraction point.

[0175] In some possible implementations of this application, controlling the self-moving robot to move to the retraction point includes: Control the self-moving robot to keep moving towards the charging pile until it reaches the exit point; The piling removal operation includes: After controlling the self-moving robot to rotate at a preset angle at the retraction point, it plans a movement path and moves based on the movement path.

[0176] In some possible embodiments of this application, a return guidance sign is provided on the charging pile; when the self-moving robot is at the exit point and facing the charging pile, the return guidance sign is within the field of view of the self-moving robot's vision sensor. Obtain the second local coordinate information of the charging pile in the local coordinate system, including: The second local coordinate information is obtained by scanning the regression guidance signs on the charging pile with a visual sensor.

[0177] In some possible implementations of this application, the determining module is further configured to: If the mobile robot obtains the first global coordinate information in the global coordinate system at the retraction point, it determines the global coordinates of the retraction point based on the first global coordinate information.

[0178] In some possible implementations of this application, the determining module is further configured to: The global coordinates of the charging pile are determined based on the first global coordinate information and the second local coordinate information.

[0179] In some possible embodiments of this application, if the self-moving robot fails to obtain the first global coordinate information in the global coordinate system at the retraction point, before controlling the self-moving robot to perform the retraction operation, the self-moving robot 70 is further configured to: Control the self-moving robot to wait at the retraction point for the first time.

[0180] The aforementioned self-moving robot, when unable to obtain its own global coordinate information at the retraction point, acquires second global coordinate information by performing a retraction operation. Using this second global coordinate information, it indirectly calculates the coordinates of the retraction point in the global coordinate system, thereby determining the global coordinates of the retraction point. This improves the success rate of global coordinate localization of the retraction point.

[0181] Based on the global coordinates of the exit point, the robot's local perception information of the charging pile at the exit point was used to further calculate the global coordinates of the charging pile. This is of great significance for the robot to subsequently build or update the environmental map and optimize the return path, enabling the robot to return to the charging pile more accurately.

[0182] By utilizing the global coordinates successfully acquired at any given moment during the movement, and combining them with the local coordinates recorded by the robot's own odometry at that moment, the global coordinates of the retraction point can be easily and efficiently deduced. This method has low requirements for the timing of global coordinate acquisition; it only needs to be successful once during the movement, greatly improving the algorithm's flexibility and adaptability.

[0183] A precise and universal coordinate system transformation method is provided. By calculating the transformation relationship between two coordinate systems, the staking points in the local coordinate system can be accurately mapped to the global coordinate system, ensuring the mathematical rigor and accuracy of coordinate calculation.

[0184] By successfully acquiring the global coordinate information at the first moment, controlling the robot to stop moving and acquiring the high-precision global coordinates in the stationary state (i.e., the global coordinate information at the second moment), measurement errors and positioning jitter during robot movement are effectively avoided, providing a more reliable data foundation for subsequent calculation of the retraction point coordinates, thereby improving the accuracy of the final positioning result.

[0185] By shifting the positioning reference point from the first moment of motion to the second moment of stillness, more reliable global coordinates and their precise corresponding local coordinates can be determined. This method avoids the potential instability of global coordinates during motion, making the reference points used for subsequent calculations more accurate, thereby improving the overall accuracy of the coordinate calculation process.

[0186] After the self-mobilizing robot acquires global coordinate information at the first moment and stops performing VIO positioning, the straight-line distance and direction change of the robot in the global coordinate system can be directly calculated using the global coordinate information at the first moment and the global coordinate information at the second moment. This allows for the calculation of the fourth local coordinate information of the self-mobilizing robot at the second moment, providing reliable data support for subsequent coordinate transformation.

[0187] By utilizing high-precision stationary coordinate pairs to solve the second transformation relationship between the global and local coordinate systems, the accuracy of coordinate transformation is significantly improved. Applying this second transformation relationship to the transformation of the retraction point coordinates yields more accurate global coordinates of the retraction point, thereby enhancing the final accuracy of the entire retraction positioning system.

[0188] The specific kinematic behavior of the self-moving robot moving to the charging pile removal point and performing the charging pile removal operation was clarified. It can keep moving towards the charging pile and, when the distance is appropriate, ensure that the charging pile is within the field of view of the self-moving robot's vision sensor, so as to ensure more accurate docking and return to the charging pile.

[0189] After rotating to a preset angle, a movement path is planned, and movement is based on the movement path. This allows for more effective obstacle avoidance and movement to more open areas, so that subsequent operations can be performed after the retraction point is located.

[0190] This paper presents a low-cost, high-precision, and easy-to-implement method for obtaining the relative position of charging piles. By setting regression guidance markers on the charging piles and utilizing the robot's vision sensors, the second local coordinate information of the charging piles can be quickly and accurately obtained at the point of exit, providing a reliable data source for subsequently determining the global coordinates of the charging piles.

[0191] When the robot can directly obtain the first global coordinate information at the retraction point, unnecessary movement and calculation can be avoided, saving time and energy and improving the positioning efficiency of the global coordinates at the retraction point.

[0192] By introducing a brief waiting mechanism, positioning failures caused by temporary or accidental factors are effectively filtered out, avoiding unnecessary retraction operations. This saves the self-moving robot's energy and time, reduces unnecessary movements, and makes the entire retraction decision-making process more rational and intelligent.

[0193] In one alternative embodiment, a self-moving robot is provided, such as Figure 8 As shown, Figure 8 The self-moving robot 4000 shown includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this application.

[0194] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0195] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0196] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing computer programs and capable of being read by a computer, without limitation herein.

[0197] The memory 4003 stores computer programs that execute embodiments of this application, and its execution is controlled by the processor 4001. The processor 4001 executes the computer programs stored in the memory 4003 to implement the steps shown in the foregoing method embodiments.

[0198] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the steps and corresponding content of the aforementioned method embodiments.

[0199] This application also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.

[0200] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0201] The above are only optional implementation methods for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application, without departing from the technical concept of this application, also fall within the protection scope of the embodiments of this application.

Claims

1. A method for retracting a stake using a self-moving robot, characterized in that, include: Control the self-moving robot to move to the retraction point, and obtain the first local coordinate information of the self-moving robot in the local coordinate system; If the self-moving robot fails to obtain the first global coordinate information in the global coordinate system at the retraction point, then the self-moving robot is controlled to perform a retraction operation in order to obtain the second global coordinate information of the self-moving robot in the global coordinate system. Based on the second global coordinate information and the first local coordinate information, the global coordinates of the retraction point are determined.

2. The method for retracting a stake using a self-moving robot according to claim 1, characterized in that, The method further includes: In response to the self-moving robot being at the retraction point, the second local coordinate information of the charging pile in the local coordinate system is obtained; wherein, the location of the charging pile is the starting point of the self-moving robot's retraction process; The global coordinates of the charging pile are determined based on the second global coordinate information and the second local coordinate information.

3. The method for retracting a stake using a self-moving robot according to claim 1 or 2, characterized in that, The retraction operation includes controlling the self-moving robot to move. During the movement, if the global coordinate information of the self-moving robot is obtained, the moment when the global coordinate information is obtained is the first moment, and the second global coordinate information includes the global coordinate information at the first moment. Determining the global coordinates of the retraction point based on the second global coordinate information and the first local coordinate information includes: Obtain the third local coordinate information of the self-moving robot at the first moment; Based on the third local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

4. The method for retracting a stake using a self-moving robot according to claim 3, characterized in that, Determining the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the third local coordinate information and the second global coordinate information, a first transformation relationship between the global coordinate system and the local coordinate system is determined. Based on the first transformation relationship, the first local coordinate information is converted into third global coordinate information to determine the global coordinates of the retraction point.

5. The method for retracting a stake using a self-moving robot according to claim 3, characterized in that, After obtaining the global coordinate information of the self-moving robot at the first moment during the movement, the retraction operation further includes: Control the self-moving robot to stop moving; The method further includes: Obtain the global coordinate information of the self-moving robot at a second time point; wherein, the second time point is the moment when the self-moving robot changes from a moving state to a stationary state; The second global coordinate information is determined based on the global coordinate information at the second time point.

6. The method for retracting a stake using a self-moving robot according to claim 5, characterized in that, The determination of the global coordinates of the retraction point based on the third local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the third local coordinate information and the second global coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined; Based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information, the global coordinates of the retraction point are determined.

7. The method for retracting a stake using a self-moving robot according to claim 6, characterized in that, The step of determining the fourth local coordinate information of the self-moving robot at the second moment based on the third local coordinate information and the second global coordinate information includes: Based on the global coordinate information at the first time point and the global coordinate information at the second time point, the distance traveled by the self-moving robot from the first time point to the second time point is determined; Based on the travel distance and the third local coordinate information, the fourth local coordinate information of the self-moving robot at the second moment is determined.

8. The method for retracting a stake using a self-moving robot according to claim 6, characterized in that, Determining the global coordinates of the retraction point based on the fourth local coordinate information, the second global coordinate information, and the first local coordinate information includes: Based on the fourth local coordinate information and the global coordinate information at the second time, a second transformation relationship between the global coordinate system and the local coordinate system is determined; Based on the second transformation relationship, the first local coordinate information is converted into third global coordinate information to determine the global coordinates of the retraction point.

9. The method for retracting a stake from a self-moving robot according to any one of claims 1-8, characterized in that, The control of the self-moving robot to move to the retraction point includes: Control the self-moving robot to maintain its direction toward the charging pile and move to the charging pile removal point; The pile retraction operation includes: After controlling the self-moving robot to rotate a preset angle at the retraction point, it plans a movement path and moves based on the movement path.

10. A self-moving robot, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-9.

Images