Mobile robot and autonomous charging method and system thereof

Abstract

The present application discloses a mobile robot and its autonomous charging method and system, relating to the field of mobile robots. The mobile robot includes a camera, and the autonomous charging method of the mobile robot includes: obtaining an image captured by the camera and identifying information in the image; when the information includes a QR code, obtaining the first posture of the mobile robot based on the QR code; when the information includes environmental features, obtaining the second posture of the mobile robot based on the environmental features; determining the current posture of the mobile robot using the first posture and / or the second posture; and controlling the mobile robot to move to dock with a charging station based on the current posture to perform a charging operation. The present application does not require the additional provision of other acquisition devices, has low hardware costs, and when the mobile robot implements the autonomous charging function, it is not limited by the distance between the mobile robot and the charging station.

Description

Technical Field

[0001] The present application relates to the field of mobile robots, and in particular to a mobile robot and an autonomous charging method and system thereof. Background Art

[0002] With the continuous development and advancement of technology, the degree of automation in industrial production and social life continues to increase, and mobile robots have emerged as a result. When a mobile robot runs low on power, the ability to automatically return to a charging station for recharging is a practical function of mobile robots. Therefore, autonomous charging technology is the key to solving the problem of mobile robot autonomy.

[0003] At present, infrared detection technology is generally used to achieve autonomous charging of mobile robots. When using infrared detection technology, infrared sensor equipment needs to be installed on the charging pile and the mobile robot respectively. The hardware cost is relatively high, and the position of the mobile robot relative to the charging pile can only be identified within the detection range of the infrared sensor equipment, which has great limitations.

[0004] Therefore, how to provide a solution to the above technical problems is a problem that those skilled in the art need to solve at present. Summary of the Invention

[0005] The purpose of this application is to provide a mobile robot and its autonomous charging method and system, which do not require the additional setting of other collection devices, have low hardware costs, and ensure that when the mobile robot realizes the autonomous charging function, it will not be limited by the distance between the mobile robot and the charging pile.

[0006] To solve the above technical problems, the present application provides an autonomous charging method for a mobile robot, wherein the mobile robot includes a camera. The autonomous charging method for the mobile robot includes:

[0007] Acquire an image captured by the camera and identify information in the image;

[0008] When the information includes a QR code, obtaining a first pose of the mobile robot based on the QR code; when the information includes an environmental feature, obtaining a second pose of the mobile robot based on the environmental feature;

[0009] Determining a current posture of the mobile robot using the first posture and / or the second posture;

[0010] Based on the current posture, the mobile robot is controlled to move to dock with the charging pile to perform a charging operation.

[0011] Optionally, the process of obtaining the first pose of the mobile robot based on the QR code includes:

[0012] Obtaining the relative position of the QR code and the camera;

[0013] The first pose of the mobile robot is calculated using the robot parameters of the mobile robot and the relative pose.

[0014] Optionally, the process of obtaining the relative position of the QR code and the camera includes:

[0015] Determine the ROI region of the QR code in the image;

[0016] Identify the QR code image in the ROI area;

[0017] Performing a projection transformation on the two-dimensional code image, and obtaining a two-dimensional code coordinate system based on basic features of the two-dimensional code;

[0018] The relative position of the two-dimensional code and the camera is determined using the two-dimensional code coordinate system.

[0019] Optionally, the process of obtaining the second posture of the mobile robot based on the environmental feature includes:

[0020] Get the location corresponding to each environmental feature;

[0021] A second posture of the mobile robot is calculated based on positions corresponding to all the environmental features.

[0022] Optionally, before obtaining the position corresponding to each environmental feature, the autonomous charging method of the mobile robot further includes:

[0023] Pre-controlling the mobile robot to move around the charging pile, and acquiring images captured by the camera during the movement of the mobile robot;

[0024] extracting environmental features from each of the images, and recording the identification and location of each of the environmental features;

[0025] constructing a feature dictionary based on the identification and location of all said environmental features;

[0026] Accordingly, the process of obtaining the location corresponding to each environmental feature includes:

[0027] The identification of each identified environmental feature is used to perform a match in the feature dictionary to determine the location corresponding to the environmental feature.

[0028] Optionally, the process of determining the current posture of the mobile robot using the first posture and / or the second posture includes:

[0029] A first relationship is established based on the first posture, the second posture, the QR code feature variance, the environmental feature variance, the QR code factor, and the environmental feature factor, and the current posture of the mobile robot is determined using the first relationship.

[0030] Optionally, the mobile robot further includes a ranging sensor, and the process of controlling the mobile robot to move to dock with the charging pile based on the current posture includes:

[0031] Calculate the control parameters of the mobile robot using the current pose and the target pose;

[0032] Controlling the mobile robot to move to a pre-charging position according to the control parameters;

[0033] Acquiring detection data of the ranging sensor;

[0034] The mobile robot is controlled to move from the pre-charging position to docking with the charging pile based on the detection data.

[0035] Optionally, the process of calculating the control parameters of the mobile robot using the current posture and the target posture includes:

[0036] Get the position deviation and angle deviation based on the current pose and the target pose;

[0037] Inputting the position deviation into a first PID controller to obtain a position control variable;

[0038] Inputting the angle deviation into a second PID controller to obtain an angle control variable;

[0039] A second relational expression is established based on the position control amount, the angle control amount, the position control factor, and the angle control factor, and the control parameters of the mobile robot are calculated using the second relational expression.

[0040] To solve the above technical problems, the present application further provides an autonomous charging system for a mobile robot, wherein the mobile robot includes a camera, and the autonomous charging system for the mobile robot includes:

[0041] An acquisition module, configured to acquire an image captured by the camera and identify information in the image;

[0042] a calculation module, configured to obtain a first pose of the mobile robot based on a QR code when the information includes a QR code, and to obtain a second pose of the mobile robot based on the environmental features when the information includes environmental features;

[0043] a determination module, configured to determine a current posture of the mobile robot using the first posture and / or the second posture;

[0044] The control module is used to control the mobile robot to move to dock with the charging pile based on the current posture and perform a charging operation.

[0045] To solve the above technical problems, the present application also provides a mobile robot, comprising:

[0046] memory for storing computer programs;

[0047] A processor is configured to implement the steps of the autonomous charging method for a mobile robot as described above when executing the computer program.

[0048] As can be seen, the present application uses images captured by the existing camera on the mobile robot to determine the position of the mobile robot and control the mobile robot to dock with the charging pile for charging. No additional collection devices are required, and the hardware cost is low. When determining the current position of the mobile robot, a combination of environmental characteristics and QR codes is used. When the QR code cannot be collected, the current position of the mobile robot can be determined by environmental characteristics, thereby ensuring that the mobile robot is not limited by the distance between the mobile robot and the charging pile when implementing the autonomous charging function.

[0049] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0051] Figure 1 A flowchart of the steps of an autonomous charging method for a mobile robot provided in this application;

[0052] Figure 2 A schematic diagram of the layout of a QR code provided in this application;

[0053] Figure 3 A schematic diagram of the posture fusion process provided by this application;

[0054] Figure 4 A schematic diagram of a hybrid PID calculation model provided in this application;

[0055] Figure 5 This is a schematic diagram of the structure of an autonomous charging system for a mobile robot provided in this application. DETAILED DESCRIPTION

[0056] The core of this application is to provide a mobile robot and its autonomous charging method and system, which does not require the additional setting of other collection devices, has low hardware cost, and when the mobile robot realizes the autonomous charging function, it is not limited by the distance between the mobile robot and the charging pile.

[0057] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0058] First, please refer to Figure 1 , Figure 1 This is a flowchart of the steps of an autonomous charging method for a mobile robot provided in this application, and the autonomous charging method includes:

[0059] S101: Acquire an image captured by a camera and identify information in the image;

[0060] The camera is an existing acquisition device on the mobile robot, located at the rear end of the mobile robot. Specifically, it can be a camera attached to a monocular camera located at the rear end of the mobile robot. The camera begins capturing images after being activated. The process of controlling the camera activation includes, but is not limited to, two methods: controlling the camera activation immediately after the mobile robot begins operation; and controlling the camera activation after the mobile robot reaches a preset position. It is understood that when the power level of the mobile robot's internal energy storage device falls below a preset power level, a preset position that facilitates the mobile robot's autonomous recharging function is set as the navigation endpoint. After the mobile robot reaches the preset position according to navigation, the camera is controlled to activate. This prevents the captured images from including excessive features unrelated to the autonomous recharging function and reduces data processing. The preset position is not the location where the mobile robot docks with the charging station. The camera can capture images upon receiving a capture command or after a preset time interval. As a preferred embodiment, the camera can be controlled to capture images in real time. This embodiment does not specifically limit the triggering conditions for the camera to capture images.

[0061] It is understandable that the image captured by the camera may include information that can indicate the relative position between the mobile robot and the charging pile, including but not limited to QR codes and / or environmental features, so that the mobile robot can be subsequently controlled to move to dock with the charging pile based on the relative position of the mobile robot and the charging pile reflected by the information in the image.

[0062] Specifically, the QR code is pre-set around the charging pile, please refer to Figure 2 As shown, of course, the number and layout of the QR codes can be selected according to actual project needs, as long as the mobile robot can collect the QR codes during the process of returning to the charging pile, this embodiment does not make any specific limitations here.

[0063] S102: When the information includes a QR code, obtaining a first pose of the mobile robot based on the QR code; when the information includes an environmental feature, obtaining a second pose of the mobile robot based on the environmental feature;

[0064] S103: Determine the current posture of the mobile robot using the first posture and / or the second posture;

[0065] Specifically, the image captured by the camera may include only a QR code, only environmental features, or both a QR code and environmental features. If a QR code is recognized in the image, the first pose of the mobile robot is obtained based on the QR code; if environmental features are recognized in the image, the second pose of the mobile robot is obtained based on the environmental features. Assuming that an image captured by the camera only includes a QR code, the first pose of the mobile robot is obtained based on the QR code, and the current pose of the mobile robot can be determined based on the first pose; assuming that an image captured by the camera only includes environmental features, the second pose of the mobile robot can be obtained based on the environmental features, and the current pose of the mobile robot can be determined based on the second pose; assuming that an image captured by the camera includes both a QR code and environmental features, the first pose can be obtained based on the QR code, the second pose can be obtained based on the environmental features, and the current pose of the mobile robot can be determined based on the first pose and the second pose.

[0066] Taking into account the limitations brought about by the fixed position of the camera on the mobile robot and the fixed field of view angle of the camera in actual applications, this embodiment does not only use the QR code captured by the camera as the basis for identifying the current posture of the mobile robot. When the QR code cannot be detected, the current posture of the mobile robot can be determined by the environmental features in the image, thereby avoiding positioning loss. When the QR code can be detected, the current posture of the mobile robot is assisted by the environmental features to improve the accuracy of the current posture.

[0067] Among them, the first pose and the second pose are the relative poses of the mobile robot and the charging pile.

[0068] S104: Based on the current posture, the mobile robot is controlled to move to dock with the charging pile and perform charging operations.

[0069] Specifically, the current posture of the mobile robot is determined based on the information in each image captured by the camera, and then the control parameters of the mobile robot are determined according to the current posture obtained in each cycle. The mobile robot is controlled to move toward the charging pile according to the control parameters until the mobile robot docks with the charging pile and performs the charging operation.

[0070] As can be seen, this embodiment uses images captured by the mobile robot's existing camera to determine the mobile robot's position and control the mobile robot's docking with the charging station for charging. This eliminates the need for additional data collection devices and reduces hardware costs. A combination of environmental characteristics and QR codes is used to determine the mobile robot's current position. If the QR code cannot be captured, the environmental characteristics can be used to determine the mobile robot's current position. This ensures that the mobile robot's autonomous charging function is not limited by the distance between the mobile robot and the charging station.

[0071] Based on the above embodiment:

[0072] As an optional embodiment, the process of obtaining the first pose of the mobile robot based on the QR code includes:

[0073] Get the relative position of the QR code and the camera;

[0074] The first pose of the mobile robot is calculated using the robot parameters and relative pose of the mobile robot.

[0075] Specifically, before executing this embodiment, an operation of identifying whether the image includes a QR code may be included. The process of identifying whether the image includes a QR code includes:

[0076] Grayscale the image to obtain a grayscale image;

[0077] Perform Gaussian blur denoising on the grayscale image to obtain a denoised image;

[0078] Canny edge detection is performed on the denoised image to extract various element features and element contours in the denoised image, and based on the element contours, it is determined whether a QR code exists in the image.

[0079] Specifically, because the four corner elements of a QR code have characteristic attributes that clearly distinguish it from the environment, and the QR code used in this embodiment, which is placed near a charging station, includes a circular pattern element at its center to better distinguish the QR code, the four corners and the central circle can be used as the basic element features of the QR code. The layout of these element features constitutes the element outline of the QR code. The element features of the QR code are searched in the image captured by the camera and the element outline is calculated to determine whether the QR code exists in the image.

[0080] Furthermore, when it is determined based on the above scheme that the image includes a QR code, the relative position between the QR code and the camera is obtained, and the first position of the mobile robot is calculated in combination with the robot parameters of the mobile robot, wherein the robot parameters of the mobile robot are the inherent properties of the mobile robot, such as degrees of freedom, joints, working range, speed, workload, etc.

[0081] As an optional embodiment, the process of obtaining the relative position of the QR code and the camera includes:

[0082] Determine the ROI area of the QR code in the image;

[0083] Identify the QR code image in the ROI area;

[0084] Perform projection transformation on the QR code image and obtain the QR code coordinate system based on the basic features of the QR code;

[0085] The QR code coordinate system is used to determine the relative position of the QR code and the camera.

[0086] Specifically, when it is determined that there is a QR code on the image, the QR code is located in a rough ROI (Region Of Interest) area in the image, and the basic features of the QR code, such as corner points, ID, etc., are extracted in the ROI area. Based on the basic features of the QR code, the position of the QR code on the image can be determined, that is, the position of the QR code image on the image is identified, and the pixel coordinates of the QR code image are specifically determined. The QR code image is projected based on the pixel coordinates, and the QR code coordinate system is obtained in combination with the basic features of the QR code. The relative position of the QR code and the camera can be determined using the QR code coordinate system.

[0087] Considering that there are multiple QR codes deployed near the charging pile, the basic features of the multiple QR codes can be obtained in advance, and a QR code template is obtained based on the basic features of each QR code. The QR code template includes the ID of the QR code. During the movement of the mobile robot, there may be a situation where a certain image captured by the camera includes multiple QR codes. In order to facilitate distinction, the ID of the QR code in the image can be determined by template matching, so as to subsequently determine the relative position of each QR code included in the image and the camera.

[0088] As an optional embodiment, the process of obtaining the second posture of the mobile robot based on the environmental characteristics includes:

[0089] Get the location corresponding to each environmental feature;

[0090] The second pose of the mobile robot is calculated based on the positions corresponding to all environmental features.

[0091] Specifically,

[0092] As an optional embodiment, before obtaining the position corresponding to each environmental feature, the autonomous charging method of the mobile robot further includes:

[0093] Pre-control the mobile robot to move around the charging pile and obtain images captured by the camera during the movement of the mobile robot;

[0094] Extract environmental features from each image and record the identity and location of each environmental feature;

[0095] Construct a feature dictionary based on the identification and location of all environmental features;

[0096] Accordingly, the process of obtaining the location corresponding to each environmental feature includes:

[0097] The identification of each environmental feature is used to match it in the feature dictionary to determine the location corresponding to the environmental feature.

[0098] It is understandable that the more environmental features that can be identified in each image, the more accurate the calculated second posture of the mobile robot. The present application pre-controls the mobile robot to move around the charging pile, and specifically controls the mobile robot to move significantly in front of the charging pile, so that the camera behind the mobile robot can widely capture the scene near the charging pile, thereby being able to fully extract environmental features. It is understandable that environmental features can specifically refer to some special points in the image, such as the corners of an object such as a building or on-site equipment, and record the identification and position of each environmental feature in each image captured by the camera when the mobile robot moves significantly in front of the charging pile, and construct a feature dictionary based on the identification and position of all environmental features, wherein the identification of the environmental feature is used to indicate which type of object the environmental feature belongs to, and the position of the environmental feature is the relative position of the environmental feature and the charging pile.

[0099] In practical applications, when the mobile robot returns to the charging station to charge, it extracts environmental features from the image captured by the camera. Based on the identification of these environmental features, the system searches and matches them against a feature dictionary to determine the relative position of each environmental feature in the image and the charging station. If only one environmental feature is identified in the image, the mobile robot's second pose is determined based on the position of that one feature. If multiple environmental features are identified in the image, the second pose is determined based on the positions of multiple features.

[0100] As an optional embodiment, the process of determining the current posture of the mobile robot using the first posture and / or the second posture includes:

[0101] A first relationship is established based on the first posture, the second posture, the QR code feature variance, the environmental feature variance, the QR code factor, and the environmental feature factor, and the current posture of the mobile robot is determined using the first relationship.

[0102] It is understandable that the posture of the mobile robot determined based on the QR code is related to the imaging quality of the QR code in the image. When the distance between the mobile robot and the charging pile is far, the imaging quality of the QR code in the image is poor, which makes the solved posture of the mobile robot have large noise, resulting in inaccurate positioning. In order to improve the accuracy of positioning, this embodiment takes into account that the noise of the first posture P1 obtained by the QR code and the second posture P2 obtained by the environmental features satisfy the Gaussian distribution, which are N(P1,σ1) and N(P2,σ2) respectively. A simple Kalman filter is used to fuse the first posture and the second posture obtained, so as to obtain a more accurate current posture of the mobile robot. For the posture fusion flow chart, refer to Figure 3 As shown, based on the first posture, the second posture, the QR code feature variance, the environmental feature variance, the QR code factor, and the environmental feature factor, a first relationship is established as follows:

[0103] Among them, P out is the current pose, σ1 is the QR code feature variance, σ2 is the environment feature variance, a is the QR code factor, b is the environment feature factor, P1 is the first pose, and P2 is the second pose.

[0104] It can be understood that a is the QR code factor. When a QR code is recognized in the image, a=1, otherwise a=0. a=0 means that when the camera cannot rely on the QR code to obtain the first pose, it can use the environmental features to locate the mobile robot. Similarly, b is the environmental feature factor. When the environmental features are recognized in the image, that is, the second pose of the mobile robot can be obtained by using the environmental features, b=1, otherwise b=0. out The current posture of the mobile robot after visual fusion, the posture fusion solution provided in this embodiment can not only effectively eliminate the posture noise problem caused by low image quality during the QR code solution process, but also solve the problem of positioning loss caused by the camera not being able to recognize the QR code when the lateral angle of the robot is too large.

[0105] As an optional embodiment, the mobile robot further includes a ranging sensor. The process of controlling the mobile robot to move to dock with the charging pile based on the current posture includes:

[0106] Calculate the control parameters of the mobile robot using the current pose and the target pose;

[0107] Control the mobile robot to move to the pre-charging position according to the control parameters;

[0108] Obtain detection data from the ranging sensor;

[0109] Based on the detection data, the mobile robot is controlled to move from the pre-charging position to docking with the charging pile.

[0110] Specifically, this embodiment can first use PID control based on the current position of the mobile robot to calculate the control parameters of the mobile robot, and move the mobile robot to the pre-charging position according to the control parameters. The pre-charging position is located directly in front of the charging pile. When it is determined that the mobile robot has moved to the pre-charging position, the mobile robot uses the existing ranging sensor located at the rear end of the mobile robot to detect the precise distance between the mobile robot and the charging pile, and then slowly retreats at a fixed speed until the mobile robot moves to dock with the charging pile, thereby charging. Among them, the fixed speed can be set to 0.01m / s. Specifically, the ranging sensor can be a TOF ranging sensor, which has high speed and accuracy. Within a range of 1m, it meets the positioning accuracy of less than 0.5cm at a frequency of 100hz. This embodiment controls the mobile robot to dock with the charging pile based on the camera and the ranging sensor, which makes the positioning of the mobile robot more accurate and improves the autonomous charging efficiency of the mobile robot.

[0111] As an optional embodiment, the process of calculating the control parameters of the mobile robot using the current posture and the target posture includes:

[0112] Get the position deviation and angle deviation based on the current pose and the target pose;

[0113] The position deviation is input into the first PID controller to obtain the position control variable;

[0114] The angle deviation is input into the second PID controller to obtain the angle control variable;

[0115] A second relational expression is established based on the position control amount, the angle control amount, the position control factor, and the angle control factor, and the control parameters of the mobile robot are calculated using the second relational expression.

[0116] Specifically, considering that most solutions currently use single-channel PID control in the lateral motion control of robots, although there are fewer adjustment parameters, the state posture of the mobile robot is a six-dimensional vector, which makes the PID parameter adjustment more complicated, resulting in the control of the mobile robot prone to oscillation.

[0117] To solve the above problems, this embodiment provides a hybrid PID control scheme. Specifically, the posture difference between the mobile robot and the charging pile consists of two parts: position deviation P and position deviation P. e and angular deviation R e , where the position deviation P e =Pc -P t , angular deviation R e =R c -R t .

[0118] Among them, P c is the current position of the mobile robot, P t is the target position corresponding to the charging pile, R c is the current heading of the mobile robot, R t is the target heading corresponding to the charging pile. e and angular deviation R e As the input of the two sub-PID controllers, the two control quantities are calculated as position control quantity Δu P and angle control value Δu R , calculated as follows:

[0119] Δu P =PID P (P e (i),P e (i-1),P e (i-2));

[0120] Δu R =PID R (R e (i),R e (i-1),R e (i-2));

[0121] The position control value Δu P and position control factor K P Multiply the angle control amount Δu R and angle control factor K R Multiply and then add to obtain the final lateral control amount Δu. The second relationship established based on the position control amount, the angle control amount, the position control factor and the angle control factor is as follows:

[0122] Δu=K P ·Δu P +K R ·Δu R ;

[0123] Among them, Δu is the control parameter, K p is the position control factor, Δu p is the position control quantity, K R is the angle control factor, Δu R is the angle control amount.

[0124] Specifically, PID Pis the first PID controller corresponding to the position deviation, PID R is the second PID controller corresponding to the angle deviation, where:

[0125] PID P =K PP [P e (i)-P e (i-1)]+K PI P e (i)+K PD [P e (i)-2P e (i-1)+P e (i-2)];

[0126] PID R =K RP [R e (i)-R e (i-1)]+K RI R e (i)+K RD [R e (i)-2R e (i-1)+R e (i-2)];

[0127] K PP , K PI and K PD is the adjustment parameter of the first PID controller, K PD , K RI and K RD P is the adjustment parameter of the second PID device. e (i) and R e (i) are the position deviation and angle deviation calculated for the i-th time, respectively. The hybrid PID calculation model is as follows: Figure 4 shown.

[0128] According to the final hybrid PID output Δu, the heading angle of the mobile robot is adjusted and controlled, and it runs at a constant speed of -0.1m / s in the longitudinal direction to a fixed position directly in front of the charging pile, that is, the pre-charging position, and the posture deviation is less than the set value.

[0129] Furthermore, considering that after the QR code calibration is completed, the position deviation between the mobile robot and the charging pile is concentrated on the X coordinate axis, and the angle deviation is concentrated on the Yawl angle, when calculating the position deviation and angle deviation, only P can be calculated. xc -P xt and Y c -Y t , in order to optimize the calculation process and reduce the amount of calculation. xc is the horizontal coordinate value of the current position of the mobile robot, Pxt is the horizontal coordinate value of the target position corresponding to the charging pile, Y c is the current yaw angle of the mobile robot, Y t is the target yaw angle corresponding to the charging pile.

[0130] According to the experimental results, the end point position of the hybrid PID control (i.e., the pre-charging position) is located 0.5m in front of the charging pile (the error is less than 0.02m), and the angle is 0rad directly in front of the charging pile (the error is less than 0.1rad). In this posture, the mobile robot can complete the charging docking with the charging pile by retreating at a uniform speed.

[0131] Second, please refer to Figure 5 , Figure 5 This is a schematic diagram of the structure of an autonomous charging system for a mobile robot provided in this application. The mobile robot includes a camera, and the autonomous charging system for the mobile robot includes:

[0132] Acquisition module 1, used to acquire images captured by the camera and identify information in the images;

[0133] Calculation module 2, configured to obtain a first pose of the mobile robot based on the QR code when the information includes the QR code, and to obtain a second pose of the mobile robot based on the environmental features when the information includes the environmental features;

[0134] a determination module 3, configured to determine a current posture of the mobile robot using the first posture and / or the second posture;

[0135] The control module 4 is used to control the mobile robot to move to dock with the charging pile based on the current posture and perform the charging operation.

[0136] As can be seen, this embodiment uses images captured by the mobile robot's existing camera to determine the mobile robot's position and control the mobile robot's docking with the charging station for charging. This eliminates the need for additional data collection devices and reduces hardware costs. A combination of environmental characteristics and QR codes is used to determine the mobile robot's current position. If the QR code cannot be captured, the environmental characteristics can be used to determine the mobile robot's current position. This ensures that the mobile robot's autonomous charging function is not limited by the distance between the mobile robot and the charging station.

[0137] As an optional embodiment, the process of obtaining the first pose of the mobile robot based on the QR code includes:

[0138] Get the relative position of the QR code and the camera;

[0139] The first pose of the mobile robot is calculated using the robot parameters and relative pose of the mobile robot.

[0140] As an optional embodiment, the process of obtaining the relative position of the QR code and the camera includes:

[0141] Determine the ROI area of the QR code in the image;

[0142] Identify the QR code image in the ROI area;

[0143] Perform projection transformation on the QR code image and obtain the QR code coordinate system based on the basic features of the QR code;

[0144] The QR code coordinate system is used to determine the relative position of the QR code and the camera.

[0145] As an optional embodiment, the process of obtaining the second posture of the mobile robot based on the environmental characteristics includes:

[0146] Get the location corresponding to each environmental feature;

[0147] The second pose of the mobile robot is calculated based on the positions corresponding to all environmental features.

[0148] As an optional embodiment, the autonomous charging system of the mobile robot further includes:

[0149] A pre-processing module is used to pre-control the movement of the mobile robot around the charging pile and obtain images captured by the camera during the movement of the mobile robot;

[0150] a recording module for extracting environmental features from each image and recording the identification and location of each environmental feature;

[0151] A construction module for constructing a feature dictionary based on the identification and location of all environmental features;

[0152] Accordingly, the process of obtaining the location corresponding to each environmental feature includes:

[0153] The identification of each environmental feature is used to match it in the feature dictionary to determine the location corresponding to the environmental feature.

[0154] As an optional embodiment, the process of determining the current posture of the mobile robot using the first posture and / or the second posture includes:

[0155] A first relationship is established based on the first posture, the second posture, the QR code feature variance, the environmental feature variance, the QR code factor, and the environmental feature factor, and the current posture of the mobile robot is determined using the first relationship.

[0156] As an optional embodiment, the mobile robot further includes a ranging sensor. The process of controlling the mobile robot to move to dock with the charging pile based on the current posture includes:

[0157] Calculate the control parameters of the mobile robot using the current pose and the target pose;

[0158] Control the mobile robot to move to the pre-charging position according to the control parameters;

[0159] Obtain detection data from the ranging sensor;

[0160] Based on the detection data, the mobile robot is controlled to move from the pre-charging position to docking with the charging pile.

[0161] As an optional embodiment, the process of calculating the control parameters of the mobile robot using the current posture and the target posture includes:

[0162] Get the position deviation and angle deviation based on the current pose and the target pose;

[0163] The position deviation is input into the first PID controller to obtain the position control variable;

[0164] The angle deviation is input into the second PID controller to obtain the angle control variable;

[0165] A second relational expression is established based on the position control amount, the angle control amount, the position control factor, and the angle control factor, and the control parameters of the mobile robot are calculated using the second relational expression.

[0166] In a third aspect, the present application further provides a mobile robot, comprising:

[0167] memory for storing computer programs;

[0168] A processor is configured to implement the steps of the autonomous charging method for a mobile robot as described in any one of the above embodiments when executing a computer program.

[0169] For an introduction to the mobile robot provided in this application, please refer to the above embodiments, and this application will not go into details here.

[0170] The mobile robot provided in this application has the same beneficial effects as the above-mentioned autonomous charging method for the mobile robot.

[0171] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0172] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for autonomously charging a mobile robot, wherein the mobile robot includes a camera, characterized in that: The autonomous charging method of the mobile robot includes: Acquire an image captured by the camera and identify information in the image; When the information includes a QR code, obtaining a first pose of the mobile robot based on the QR code; when the information includes an environmental feature, obtaining a second pose of the mobile robot based on the environmental feature; When only the first posture is obtained, determining the current posture of the mobile robot according to the first posture; when only the second posture is obtained, determining the current posture of the mobile robot according to the second posture; when the first posture and the second posture are obtained, fusing the obtained first posture and the second posture to obtain the current posture of the mobile robot; Based on the current posture, the mobile robot is controlled to move to dock with the charging pile to perform a charging operation.

2. The autonomous charging method for a mobile robot according to claim 1, characterized in that: The process of obtaining the first posture of the mobile robot based on the QR code includes: Obtaining the relative position of the QR code and the camera; The first pose of the mobile robot is calculated using the robot parameters of the mobile robot and the relative pose.

3. The autonomous charging method for a mobile robot according to claim 2, characterized in that: The process of obtaining the relative position of the QR code and the camera includes: Determine the ROI region of the QR code in the image; Identify the QR code image in the ROI area; Performing a projection transformation on the two-dimensional code image, and obtaining a two-dimensional code coordinate system based on basic features of the two-dimensional code; The relative position of the two-dimensional code and the camera is determined using the two-dimensional code coordinate system.

4. The autonomous charging method for a mobile robot according to claim 1, characterized in that: The process of obtaining the second posture of the mobile robot based on the environmental characteristics includes: Get the location corresponding to each environmental feature; A second posture of the mobile robot is calculated based on positions corresponding to all the environmental features.

5. The autonomous charging method for a mobile robot according to claim 4, characterized in that: Before obtaining the position corresponding to each environmental feature, the autonomous charging method of the mobile robot further includes: Pre-controlling the mobile robot to move around the charging pile, and acquiring images captured by the camera during the movement of the mobile robot; extracting environmental features from each of the images, and recording the identification and location of each of the environmental features; constructing a feature dictionary based on the identification and location of all said environmental features; Accordingly, the process of obtaining the location corresponding to each environmental feature includes: The identification of each identified environmental feature is used to perform a match in the feature dictionary to determine the location corresponding to the environmental feature.

6. The autonomous charging method for a mobile robot according to claim 1, characterized in that: The process of fusing the first and second postures to obtain the current posture of the mobile robot includes: A first relationship is established based on the first posture, the second posture, the QR code feature variance, the environmental feature variance, the QR code factor, and the environmental feature factor, and the current posture of the mobile robot is determined using the first relationship.

7. The autonomous charging method for a mobile robot according to any one of claims 1 to 6, characterized in that: The mobile robot further includes a ranging sensor, and the process of controlling the mobile robot to move to dock with the charging pile based on the current posture includes: Calculate the control parameters of the mobile robot using the current pose and the target pose; Controlling the mobile robot to move to a pre-charging position according to the control parameters; Acquiring detection data of the ranging sensor; The mobile robot is controlled to move from the pre-charging position to docking with the charging pile based on the detection data.

8. The autonomous charging method for a mobile robot according to claim 7, characterized in that: The process of calculating the control parameters of the mobile robot using the current posture and the target posture includes: Get the position deviation and angle deviation based on the current pose and the target pose; Inputting the position deviation into a first PID controller to obtain a position control variable; Inputting the angle deviation into a second PID controller to obtain an angle control variable; A second relational expression is established based on the position control amount, the angle control amount, the position control factor, and the angle control factor, and the control parameters of the mobile robot are calculated using the second relational expression.

9. An autonomous charging system for a mobile robot, the mobile robot including a camera, characterized in that: The mobile robot's autonomous charging system includes: An acquisition module, configured to acquire an image captured by the camera and identify information in the image; a calculation module, configured to obtain a first pose of the mobile robot based on a QR code when the information includes a QR code, and to obtain a second pose of the mobile robot based on the environmental features when the information includes environmental features; a determination module, configured to, when only the first posture is obtained, determine the current posture of the mobile robot according to the first posture; when only the second posture is obtained, determine the current posture of the mobile robot according to the second posture; and when both the first posture and the second posture are obtained, fuse the obtained first posture and the obtained second posture to obtain the current posture of the mobile robot; The control module is used to control the mobile robot to move to dock with the charging pile based on the current posture and perform a charging operation.

10. A mobile robot, characterized in that: include: memory for storing computer programs; A processor, configured to implement the steps of the autonomous charging method for a mobile robot as described in any one of claims 1 to 8 when executing the computer program.

Images