Autonomous positioning and navigation method and device for mobile robot based on target recognition

Abstract

The invention relates to a mobile robot autonomous positioning navigation method and device based on target recognition, and the method comprises the steps: obtaining a real-time image of an environment right ahead a mobile robot, carrying out the preprocessing of the real-time image, and carrying out the detection of calibration plate feature points, and obtaining a plurality of feature points; constructing a target function for minimizing a re-projection error based on the plurality of feature points; on the basis of the optimal solution of the objective function, calculating pose parameters of the mobile robot under a world coordinate system; planning an optimal path of the robot from the starting point to the target point, and outputting a path sequence; constructing a state model and a cost function based on the path sequence and a kinematic model of the mobile robot; optimizing and determining a control parameter sequence applied to the mobile robot; and updating the pose parameters in real time, and continuously iterating the control parameter sequence until the mobile robot reaches the target point. Through the industrial camera, the visual algorithm and the prediction model, high-precision state updating and path tracking of the robot and stability of the system are achieved.

Description

Technical Field

[0001] The present invention belongs to the field of mobile robot automatic control, and in particular relates to a mobile robot autonomous positioning and navigation method and device based on target recognition. Background Art

[0002] Mobile robot navigation technology uses sensors to perceive and locate the environment, uses path planning algorithms to plan the current optimal global path, and combines motion control algorithms to achieve precise control. This technology is of great significance to the autonomous action and task execution of mobile robots.

[0003] Existing mobile robot navigation technology usually uses sensor data to obtain the robot's position and posture, thereby achieving autonomous positioning and status updates of the robot, and performing feedback control based on the robot's current state. The main problems and defects in the existing technology include: the robot control method usually performs feedback control based on the current state, lacks the ability to predict control, resulting in poor speed control performance when making sharp turns or near the end point, thereby affecting tracking accuracy. At the same time, in the event of external disturbances or large system errors, excessive correction or delayed response of feedback control can easily cause the system to overshoot or oscillate, thereby affecting the stability of control. Summary of the invention

[0004] To solve the problems raised by the background technology, in the first aspect of the present invention, a method for autonomous positioning and navigation of a mobile robot based on target recognition is provided, comprising: obtaining a real-time image of the environment directly in front of the mobile robot, and preprocessing the real-time image and detecting feature points of a calibration plate to obtain a plurality of feature points; constructing an objective function that minimizes the reprojection error based on the plurality of feature points; calculating the posture parameters of the mobile robot in the world coordinate system based on the optimal solution of the objective function; determining the starting point, target position and orientation of the mobile robot, planning the optimal path of the mobile robot from the starting point to the target point, and outputting a path sequence; constructing a state model and a cost function based on the path sequence and the kinematic model of the mobile robot; optimizing and determining a control parameter sequence applied to the mobile robot based on the state model and the cost function; updating the posture parameters in real time based on visual positioning, and continuously iterating the control parameter sequence according to the posture parameters until the mobile robot reaches the target point.

[0005] In some embodiments of the present invention, constructing an objective function for minimizing the reprojection error based on the multiple feature points includes: obtaining the intrinsic parameter matrix of the camera; determining the projection relationship equation based on the intrinsic parameter matrix and the multiple feature points; and constructing an optimization objective function by minimizing the reprojection error of three-dimensional points on the image plane.

[0006] Furthermore, the calculation of the posture parameters of the mobile robot in the world coordinate system based on the optimal solution of the objective function includes: calculating the rotation matrix and the translation vector based on the optimal solution of the objective function; establishing a world coordinate system with the center of the calibration plate as the origin; and calculating the posture parameters of the mobile robot in the world coordinate system based on the rotation matrix, the translation vector, the world coordinate system and the installation position of the camera on the mobile robot.

[0007] In some embodiments of the present invention, the construction of the state model and cost function based on the path sequence and the kinematic model of the mobile robot includes: defining a discrete desired state sequence based on the path sequence; constructing a discrete robot state model based on the kinematic control model of the mobile robot; and constructing a cost function based on the state prediction sequence and the desired state sequence.

[0008] According to the state model and the control parameter vector, a cost function is constructed to minimize the control parameter vector.

[0009] Furthermore, the cost function is expressed as: ,in Indicated in The state vector of the step, represents the target state vector; Indicated in The system state vector of the step; Indicated in The control input vector of the step, represents the tracking error matrix.

[0010] In the above embodiment, the preprocessing of the real-time image includes: performing image denoising and gray-scaling on the real-time image.

[0011] According to a second aspect of the present invention, a mobile robot autonomous positioning and navigation device based on target recognition is provided, comprising: an acquisition module for acquiring a real-time image of the environment directly in front of the mobile robot, and performing preprocessing and calibration plate feature point detection on the real-time image to obtain a plurality of feature points; a calculation module for constructing an objective function for minimizing the reprojection error based on the plurality of feature points; calculating the posture parameters of the mobile robot in the world coordinate system based on the optimal solution of the objective function; a planning module for determining the starting point, target position and orientation of the mobile robot, planning the optimal path of the mobile robot from the starting point to the target point, and outputting a path sequence; an optimization module for constructing a state model and a cost function based on the path sequence and the kinematic model of the mobile robot; optimizing and determining a control parameter sequence applied to the mobile robot based on the state model and the cost function; an iteration module for updating the posture parameters in real time based on visual positioning, and continuously iterating the control parameter sequence according to the posture parameters until the mobile robot reaches the target point.

[0012] The third aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the mobile robot autonomous positioning and navigation method provided in the first aspect of the present invention.

[0013] A fourth aspect of the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the mobile robot autonomous positioning and navigation method provided in the first aspect of the present invention.

[0014] The beneficial effects of the present invention are: (1) The present invention uses industrial cameras and visual algorithms to achieve sub-pixel feature point position matching accuracy, thereby obtaining high-precision posture information. Compared with the multi-sensor fusion positioning method, visual recognition has higher accuracy and real-time performance. Visual recognition can calculate the relative accurate position between the robot and the target by identifying the calibration target, thereby achieving high-precision status update of the robot.

[0015] (2) By optimizing the model predictive controller, introducing the terminal state cost and adjusting the control input weight, the controller can output more accurate and smooth control instructions. By establishing a discretized robot state space model and high-precision real-time state updates, the robot's future behavior is predicted, and the optimal control input is obtained based on the objective function optimization solution, thereby maintaining accurate path tracking and improving the stability of the system.

[0016] (3) The present invention is quick and easy to transplant. The positioning technology based on target recognition only requires the configuration of a standard industrial camera and a general computing platform to achieve rapid deployment and functional expansion, thereby improving the flexibility and scalability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a basic flow chart of a method for autonomous positioning and navigation of a mobile robot in some embodiments of the present invention; Figure 2 A schematic diagram of a specific process of a mobile robot autonomous positioning and navigation method in some embodiments of the present invention; Figure 3 A schematic diagram of a simulation environment in some embodiments of the present invention; Figure 4 Schematic diagram of visual target and feature point extraction results in some embodiments of the present invention; Figure 5 Coordinate system establishment and system schematic diagram in some embodiments of the present invention; Figure 6 Graphs showing robot path tracking simulation results in some embodiments of the present invention; Figure 7 Graphs showing simulation results of robot speed and angular velocity in some embodiments of the present invention; Figure 8 It is a schematic diagram of the structure of the autonomous positioning and navigation device of a mobile robot in some embodiments of the present invention; Fig. 9 It is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. DETAILED DESCRIPTION

[0018] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0019] refer to Figure 1 and Figure 2In the first aspect of the present invention, a method for autonomous positioning and navigation of a mobile robot based on target recognition is provided, comprising: S100. Acquiring a real-time image of the environment directly in front of the mobile robot, and preprocessing the real-time image and detecting feature points of a calibration plate to obtain a plurality of feature points; S200. Constructing an objective function for minimizing the reprojection error based on the plurality of feature points; calculating the posture parameters of the mobile robot in the world coordinate system based on the optimal solution of the objective function; S300. Determining the starting point, target position and orientation of the mobile robot, planning the optimal path of the mobile robot from the starting point to the target point, and outputting a path sequence; S400. Constructing a state model and a cost function based on the path sequence and the kinematic model of the mobile robot; optimizing and determining a control parameter sequence applied to the mobile robot based on the state model and the cost function; S500. Real-time updating of the posture parameters based on visual positioning, and continuously iterating the control parameter sequence according to the posture parameters until the mobile robot reaches the target point.

[0020] refer to Figure 3 and Figure 4 In S100 of some embodiments of the present invention, a real-time image of the environment in front of the mobile robot is acquired, and the real-time image is preprocessed and the feature points of the calibration plate are detected to obtain a plurality of feature points; Specifically, the image sensor is used to obtain real-time image data of the environment in front of the robot, and the obtained image data is preprocessed, including image denoising and grayscale conversion, and then the visual target feature point detection is performed. Figure 3 As shown in the figure, the image sensor is used to obtain real-time image data of the environment in front of the robot, and the obtained image data is preprocessed, including image denoising and grayscale conversion, and then the visual target plate feature point detection is performed. This example uses an asymmetric dot calibration plate as the target. The visual target (calibration plate) and feature point extraction results are shown in the figure below. Figure 4 shown.

[0021] In S200 of some embodiments of the present invention, constructing an objective function that minimizes the reprojection error based on the multiple feature points includes: S201. Obtain the camera's intrinsic parameter matrix; Specifically, the positioning of the mobile robot requires the establishment of a coordinate system and a coordinate system conversion. The coordinate system establishment and system schematic diagram of the present invention are shown in FIG. Figure 4 The pose estimation requires the intrinsic parameters of the camera, which is set by setting the horizontal resolution of the camera in the simulation. and vertical resolution for , Field of view for , calculate the camera's intrinsic parameter matrix for: ; S202. Determine a projection relationship equation according to the internal parameter matrix and the plurality of feature points; 3D Point To 2D image point The projection relationship can be expressed by the following equation: , In the formula, is the camera internal parameter matrix, including focal length and principal point coordinates, is the scale factor.

[0022] S203. Construct an optimization objective function by minimizing the reprojection error of the three-dimensional point on the image plane. Specifically, in order to solve the rotation matrix with translation vector , the optimization objective function is constructed by minimizing the reprojection error of the three-dimensional point on the image plane, specifically: , In the formula, is the actual observed image point, is the image point projected from the current pose estimate.

[0023] Further, in step S204, the calculating of the posture parameters of the mobile robot in the world coordinate system based on the optimal solution of the objective function includes: S2041. Based on the optimal solution of the objective function, calculate the rotation matrix and the translation vector; Specifically, define the error vector , is the observed value, It is estimated by the current and Compute the expected value of . Construct the Jacobian matrix , whose elements are the error functions with respect to parameters and The partial derivative of : , In each iteration, according to the formula Calculate the update amount of the parameters, and get After that, update the current and : , Repeat the above iterative steps until the error meets the preset convergence criteria , is the set error threshold. Through iterative optimization, the camera position is accurately estimated and the optimized rotation matrix is ​​obtained. with translation vector .

[0024] S2042. Establish a world coordinate system with the center of the calibration plate as the origin; Specifically, the world coordinate system is established with the center of the target plate as the origin, then the transformation matrix from the camera coordinate system to the world coordinate system can be expressed as a 4×4 matrix, as shown below: ; S2043. Based on the rotation matrix, the translation vector, the world coordinate system and the installation position of the camera on the mobile robot, calculate the posture parameters of the mobile robot in the world coordinate system.

[0025] Specifically, the transformation matrix from the robot coordinate system to the camera coordinate system is obtained according to the installation position and direction of the camera on the mobile robot: , then the transformation matrix from the robot coordinate system to the world coordinate system is , and invert this transformation matrix to obtain the posture parameters of the mobile robot in the world coordinate system.

[0026] In S300 of some embodiments of the present invention, a starting point, a target position and an orientation of the mobile robot are determined, an optimal path of the mobile robot from the starting point to the target point is planned, and a path sequence is output; Specifically, exemplarily, the initial point position is defined as , the target point position is , the units are The initial and final heading angles are , plan the global optimal path of the robot from the starting point to the target point, and output the path sequence .

[0027] In S400 of some embodiments of the present invention, defining a discrete desired state sequence based on a path sequence includes: S401. Define the state vector of the mobile robot based on the path sequence; define the control parameter vector; Specifically, a two-wheel differential wheeled robot is used to define the robot state vector ,in and is the position of the robot on the two-dimensional plane, is the angle the robot is facing. The control input of the robot is defined as ,in is the linear velocity of the robot in the current direction, is the angular velocity of the robot in its current orientation.

[0028] S402. Constructing a discrete robot state model based on the kinematic control model of the mobile robot; Specifically, under pure rolling conditions, the robot's kinematic equations can be used to update the position and orientation through control input: , In the formula , and Respectively indicate the location ,Location and orientation The time derivative of .

[0029] S403. Constructing a state model by discretizing the kinematic equations; Specifically, the forward Euler method is used to discretize the continuous-time system, and we get: , Combining the above equations into a state-space model ,in is the state vector, For control input.

[0030] S404. Construct a cost function based on the state prediction sequence and the expected state sequence.

[0031] Specifically, a model predictive controller is designed to optimize the control input by minimizing the cost of the objective function. as follows: The objective function consists of two parts: the stage cost and the terminal cost. The stage cost part is used to evaluate the deviation between the state and the target state at each time step, as well as the cost of the control input. The terminal cost part is used to evaluate the final step of the prediction cycle (the step), the deviation between the system state and the expected target state. Indicated in The state vector of the step, is the target state vector, representing the desired state, It is in The system state vector of the step. It is in The control input vector of the step. is the tracking error matrix, which reflects the importance of each state variable. is the weight matrix of the control input, which is used to adjust the cost of the control input.

[0032] , , , , , Represents the state variables And control input The weight coefficient of . To ensure that the control input is within the feasible range, the system constraints are constructed , .in , the final optimization problem is to minimize the objective function by solving the control input sequence at the current moment. The optimization goal is to find the control input and state sequence , so that the objective function Minimum.

[0033] Extract the first control input from the optimization result and apply the robot .

[0034] refer to Figure 5 and Figure 6 In S500 of some embodiments of the present invention, the posture parameters are updated in real time based on visual positioning, and the control parameter sequence is continuously iterated according to the posture parameters until the mobile robot reaches the target point.

[0035] Specifically, the current state of the robot is updated through visual positioning, and iteration and optimization are performed to achieve continuous control and path tracking until the target point is reached. In each iteration, the control input is calculated based on the current state and the result of the optimization problem. The optimal control input sequence given by the optimization solver is the future step control input sequence, at each time step , apply the first control input , then update the status and re-optimize. The system status is updated as follows , is the dynamic model function of the system. At the next moment, the new state will be used as the starting point for the next optimization, and the future will be optimized again. The system behavior is predicted and controlled dynamically based on the step-by-step control input, ensuring that the control strategy can be continuously optimized and adapt to environmental changes.

[0036] In this example, the robot updates its state based on the visual positioning results and applies the latest optimal control input at each step, and finally obtains the following Figure 5 The path tracking simulation results are shown in Figure 1. The blue path in the figure is the global planning path, and the red path is the actual driving path of the robot. The results show that the robot can achieve continuous control and high-precision path tracking through this method. Its lateral position at the end point is The deviation from the target value is , and its heading angle at the end point is The deviation from the target value is ; At the same time, in the process of going to the target point, if Figure 6 As shown in the figure, when approaching a turn and approaching the target position, the robot predicts the control in advance and slows down, achieving smooth transition and precise tracking.

[0037] In a specific embodiment of the present invention, the following steps are included: Step 1: Use the image sensor to obtain real-time image data of the environment in front of the robot, and pre-process the acquired image data, including image denoising and grayscale conversion, and then perform feature point detection on the visual target board; Step 2: Definition 3D feature points The corresponding image plane projection point The relationship equation is constructed by minimizing the reprojection error of the three-dimensional points on the image plane to construct the optimization objective function. The iterative optimization solution is performed based on the least squares method to obtain the relative posture relationship between the world coordinate system and the camera coordinate system. The posture parameters of the mobile robot in the world coordinate system are obtained after transformation.

[0038] Step 3: Define the position and orientation of the starting point and the target point, and plan the optimal path for the robot from the starting point to the target point; Step 4: Establish the kinematic control model of the mobile robot and the discretized robot state model, design the model predictive controller, construct the target cost function to minimize the tracking error, smooth the control input, use the optimization solver to obtain the optimal control input and state sequence, extract the first control input in the optimization result and apply it to the robot.

[0039] Step 5: Update the current state of the robot in real time, perform the next iteration, and re-optimize according to the new state to achieve continuous control and path tracking until reaching the target point.

[0040] Example 2 refer to Figure 8In a second aspect of the present invention, a mobile robot autonomous positioning and navigation device 1 based on target recognition is provided, comprising: an acquisition module 11, used to acquire a real-time image of the environment directly in front of the mobile robot, and pre-process the real-time image and detect the feature points of a calibration plate to obtain a plurality of feature points; a calculation module 12, used to construct an objective function that minimizes the reprojection error based on the plurality of feature points; based on the optimal solution of the objective function, calculate the posture parameters of the mobile robot in the world coordinate system; a planning module 13, used to determine the starting point, target position and orientation of the mobile robot, plan the optimal path of the mobile robot from the starting point to the target point, and output a path sequence; an optimization module 14, used to construct a state model and a cost function based on the path sequence and the kinematic model of the mobile robot; based on the state model and the cost function, optimize and determine the control parameter sequence applied to the mobile robot; an iteration module 15, used to update the posture parameters in real time based on visual positioning, and continuously iterate the control parameter sequence according to the posture parameters until the mobile robot reaches the target point.

[0041] Furthermore, the calculation module 12 includes: an acquisition unit for acquiring the intrinsic parameter matrix of the camera; a determination unit for determining the projection relationship equation based on the intrinsic parameter matrix and the multiple feature points; and a construction unit for constructing an optimization objective function by minimizing the reprojection error of the three-dimensional points on the image plane.

[0042] Example 3 refer to Fig. 9 According to a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method of the first aspect of the present invention.

[0043] The electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0044] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Fig. 9 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Fig. 9 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0045] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above functions defined in the method of the embodiment of the present disclosure are executed. It should be noted that the computer-readable medium described in the embodiment of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus, or a device. In an embodiment of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus, or a device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0046] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device. The computer-readable medium carries one or more computer programs. When the one or more programs are executed by the electronic device, the electronic device: Computer program code for performing the operations of embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, Python, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0047] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A mobile robot autonomous positioning and navigation method based on target recognition, characterized in that: include: Acquire a real-time image of the environment in front of the mobile robot, and perform preprocessing and calibration plate feature point detection on the real-time image to obtain multiple feature points; Based on the multiple feature points, construct an objective function that minimizes the reprojection error; Based on the optimal solution of the objective function, calculating the posture parameters of the mobile robot in the world coordinate system; Determine the starting point, target position and orientation of the mobile robot, plan the optimal path from the starting point to the target point, and output the path sequence; Based on the path sequence and the kinematic model of the mobile robot, a state model and a cost function are constructed; based on the state model and the cost function, the control parameter sequence applied to the mobile robot is optimized and determined; The posture parameters are updated in real time based on visual positioning, and the control parameter sequence is continuously iterated according to the posture parameters until the mobile robot reaches the target point.

2. The mobile robot autonomous positioning and navigation method based on target recognition according to claim 1 is characterized in that: The constructing of an objective function that minimizes the reprojection error based on the multiple feature points comprises: Get the camera's intrinsic parameter matrix; Determining a projection relationship equation according to the intrinsic parameter matrix and the plurality of feature points; The optimization objective function is constructed by minimizing the reprojection error of three-dimensional points on the image plane.

3. The mobile robot autonomous positioning and navigation method based on target recognition according to claim 2 is characterized in that: The step of calculating the posture parameters of the mobile robot in the world coordinate system based on the optimal solution of the objective function includes: Based on the optimal solution of the objective function, calculating the rotation matrix and the translation vector; Establish the world coordinate system with the center of the calibration plate as the origin; Based on the rotation matrix, the translation vector, the world coordinate system and the installation position of the camera on the mobile robot, the position and posture parameters of the mobile robot in the world coordinate system are calculated.

4. The mobile robot autonomous positioning and navigation method based on target recognition according to claim 1 is characterized in that: The construction of the state model and the cost function based on the path sequence and the kinematic model of the mobile robot includes: Define a discrete sequence of desired states based on the path sequence; Based on the kinematic control model of the mobile robot, a discrete robot state model is constructed; The cost function is constructed based on the state prediction sequence and the expected state sequence.

5. The mobile robot autonomous positioning and navigation method based on target recognition according to claim 4 is characterized in that: The cost function is expressed as: ,in Indicated in The state vector of the step, represents the target state vector; Indicated in The system state vector of the step; Indicated in The control input vector of the step, represents the tracking error matrix.

6. The mobile robot autonomous positioning and navigation method based on target recognition according to claim 1 is characterized in that: The preprocessing of the real-time image includes: performing image denoising and gray-scaling on the real-time image.

7. A mobile robot autonomous positioning and navigation device based on target recognition, characterized in that: include: The acquisition module is used to acquire the real-time image of the environment in front of the mobile robot, and perform preprocessing and calibration plate feature point detection on the real-time image to obtain multiple feature points; A calculation module, used for constructing an objective function that minimizes a reprojection error based on the multiple feature points; Based on the optimal solution of the objective function, calculating the posture parameters of the mobile robot in the world coordinate system; The planning module is used to determine the starting point, target position and orientation of the mobile robot, plan the optimal path from the starting point to the target point, and output the path sequence; The optimization module is used to construct a state model and a cost function based on the path sequence and the kinematic model of the mobile robot; based on the state model and the cost function, the control parameter sequence applied to the mobile robot is optimized and determined; The iteration module is used to update the posture parameters in real time based on visual positioning, and continuously iterate the control parameter sequence according to the posture parameters until the mobile robot reaches the target point.

8. The mobile robot autonomous positioning and navigation device based on target recognition according to claim 7, characterized in that: The calculation module comprises: An acquisition unit, used to acquire the intrinsic parameter matrix of the camera; A determination unit, configured to determine a projection relationship equation according to the intrinsic parameter matrix and the plurality of feature points; A construction unit is used to construct an optimization objective function by minimizing the reprojection error of three-dimensional points on the image plane.

9. An electronic device, comprising: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the mobile robot autonomous positioning and navigation method based on target recognition as described in any one of claims 1 to 6.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method for autonomous positioning and navigation of a mobile robot based on target recognition as described in any one of claims 1 to 6 is implemented.

Images