Dynamic environment adaptive navigation method, robot and central processing unit

Abstract

The invention discloses a dynamic environment adaptive navigation method, a robot and a central processing unit. The method comprises the following steps: scanning an environment by a laser radar to generate current point cloud data; the electronic price tag unit sends a measurement signal to the base station to obtain an arrival angle positioning position; the nine-axis sensor measures nine-axis data of the robot; the central processing unit compares the current point cloud data with pre-generated supermarket point cloud map data, and marks and evaluates an abnormal area when it is determined that the surrounding environment changes according to a comparison result; when it is determined that the abnormal area needs to be updated immediately, a first current position is obtained according to the arrival angle positioning position and nine-axis data fusion positioning; determining a first path from the current position to the historical safe position; the navigation unit controls the robot to return to a safe position according to the path; the laser radar reconstructs a point cloud map according to the abnormal area; the navigation control unit controls the robot to complete the task according to the reconstructed map. According to the invention, dynamic environment adaptive navigation can be realized.

Description

Technical Field

[0001] The present invention relates to the field of supermarket technology, and in particular to a method, a robot, and a central processing unit for adaptive navigation in a dynamic environment. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] With the development of intelligent technology, smart devices are increasingly being used in large supermarkets and warehouses, taking on tasks such as picking, replenishing, and inventory taking, significantly improving operational efficiency. However, due to environmental factors such as similar shelves, strong reflective surfaces or dim lighting, and potential odometry errors in the positioning system itself, inspection robots often experience positioning failures. This not only affects their normal navigation and operation, but also increases the cost and frequency of manual maintenance.

[0004] In current autonomous mobile robot technology, common positioning methods rely on LiDAR point cloud data for environment mapping and navigation. However, this approach faces significant limitations in dynamic environments, such as warehouses where shelf positions change. Specifically, when the physical layout of the environment changes, the original point cloud map may no longer be accurate, making it easy for the robot to get lost. Furthermore, relying solely on LiDAR point cloud data is difficult to quickly adapt and update in complex or changing environments, thus affecting the robot's navigation efficiency and accuracy. Summary of the Invention

[0005] An embodiment of the present invention provides a method for adaptive navigation in a dynamic environment, for efficient and accurate adaptive navigation in a dynamic environment. The method is applied to a robot and includes:

[0006] The laser radar scans the surrounding environment, generates the current point cloud data of the surrounding environment and sends it to the central processing unit;

[0007] The electronic price tag unit sends a measurement signal to the base station; the base station is used to determine the arrival angle based on the measurement signal and send the arrival angle to the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle and return it to the central processing unit;

[0008] The nine-axis sensor measures the robot's nine-axis data and sends it to the central processing unit;

[0009] The central processing unit compares the current point cloud data with pre-generated supermarket point cloud map data. When the comparison results determine that the surrounding environment has changed, it marks an abnormal area on the map, evaluates the abnormal area, and determines the status of the abnormal area. When the evaluation results determine that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately, it performs fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the robot's first current positioning position; calls the last confirmed safe position in the historical positioning data, and determines the first optimal path from the first current positioning position to the safe position;

[0010] The navigation control unit controls the robot to return to the safe position according to the first optimal path;

[0011] The lidar captures environmental changes that have occurred in abnormal areas since the last scan and reconstructs a point cloud map based on the environmental changes;

[0012] The navigation control unit regenerates the navigation path according to the reconstructed point cloud map; based on the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

[0013] An embodiment of the present invention provides a method for adaptive navigation in a dynamic environment, for efficient and accurate adaptive navigation in a dynamic environment. The method is applied to a central processing unit and includes:

[0014] Compare the current point cloud data with pre-generated supermarket point cloud map data; the current point cloud data is sent by a laser radar, which is used to scan the surrounding environment and generate the current point cloud data of the surrounding environment;

[0015] When the surrounding environment is determined to have changed based on the comparison results, the abnormal area on the map is marked;

[0016] evaluating the abnormal area and determining a status of the abnormal area;

[0017] When it is determined according to the evaluation result that the abnormal area is in a state where navigation cannot be normally realized and needs to be updated immediately, the first current positioning position of the robot is obtained according to the fusion positioning of the arrival angle positioning position and the nine-axis data; the arrival angle positioning position is sent by the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot according to the arrival angle, and the arrival angle is sent by the base station, and the base station is used to determine the arrival angle according to the measurement signal sent by the electronic price tag unit; the nine-axis data is sent by the nine-axis sensor, and the nine-axis sensor is used to measure the nine-axis data of the robot;

[0018] The last position confirmed as safe in the historical positioning data is called, and the first optimal path from the first current positioning position back to the safe position is determined and sent to the navigation control unit; the navigation control unit is used to control the robot to return to the safe position according to the first optimal path; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area, and reconstruct the point cloud map according to the environmental changes; the navigation path is regenerated according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position. The sea is used to: regenerate the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

[0019] An embodiment of the present invention further provides a robot capable of adaptively navigating in a dynamic environment, for efficiently and accurately adaptively navigating in a dynamic environment, the robot comprising:

[0020] LiDAR is used to scan the surrounding environment, generate current point cloud data of the surrounding environment and send it to the central processing unit; capture environmental changes that have occurred since the last scan from abnormal areas, and reconstruct the point cloud map based on the environmental changes;

[0021] The electronic price tag unit is used to send a measurement signal to a base station; the base station is used to determine the arrival angle based on the measurement signal and send the arrival angle to the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle and return it to the central processing unit;

[0022] Nine-axis sensor, used to measure the robot's nine-axis data and send it to the central processing unit;

[0023] The central processing unit is configured to compare the current point cloud data with pre-generated supermarket point cloud map data; when it is determined based on the comparison results that the surrounding environment has changed, mark abnormal areas on the map, evaluate the abnormal areas, and determine the status of the abnormal areas; when it is determined based on the evaluation results that the abnormal areas are in a state where normal navigation cannot be achieved and an immediate update is required, perform fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain a first current positioning position of the robot; call the last position confirmed as safe in the historical positioning data, and determine a first optimal path from the first current positioning position back to the safe position;

[0024] A navigation control unit is used to control the robot to return to the safe position according to the first optimal path; regenerate the navigation path according to the reconstructed point cloud map; and control the robot to continue to execute the task from the safe position according to the regenerated navigation path.

[0025] An embodiment of the present invention provides a central processing unit for adaptive navigation in a dynamic environment, for efficient and accurate adaptive navigation in a dynamic environment, the central processing unit comprising:

[0026] A comparison module is used to compare the current point cloud data with pre-generated supermarket point cloud map data; the current point cloud data is sent by the laser radar, and the laser radar is used to scan the surrounding environment to generate the current point cloud data of the surrounding environment;

[0027] A marking module is used to mark abnormal areas on the map when the surrounding environment is determined to have changed according to the comparison results;

[0028] An evaluation module, configured to evaluate the abnormal area and determine a state of the abnormal area;

[0029] A fusion positioning module is used to perform fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot when it is determined according to the evaluation results that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately; the arrival angle positioning position is sent by the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle, and the arrival angle is sent by the base station, and the base station is used to determine the arrival angle based on the measurement signal sent by the electronic price tag unit; the nine-axis data is sent by the nine-axis sensor, and the nine-axis sensor is used to measure the nine-axis data of the robot;

[0030] An optimal path determination module is used to call the last confirmed safe position in the historical positioning data, determine the first optimal path from the first current positioning position to the safe position, and send it to the navigation control unit; the navigation control unit is used to control the robot to return to the safe position according to the first optimal path; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area, and reconstruct the point cloud map according to the environmental changes; the navigation path is regenerated according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position. The sea is used to: regenerate the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

[0031] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method of dynamic environment adaptive navigation when executing the computer program.

[0032] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for adaptive navigation in a dynamic environment is implemented.

[0033] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for adaptive navigation in a dynamic environment.

[0034] In the embodiment of the present invention, the solution of dynamic environment adaptive navigation is as follows: the laser radar scans the surrounding environment, generates the current point cloud data of the surrounding environment and sends it to the central processing unit; the electronic price tag unit sends the measurement signal to the base station; the base station is used to determine the arrival angle according to the measurement signal, and sends the arrival angle to the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot according to the arrival angle and return it to the central processing unit; the nine-axis sensor measures the nine-axis data of the robot and sends it to the central processing unit; the central processing unit compares the current point cloud data with the pre-generated supermarket point cloud map data, and when it is determined that the surrounding environment has changed according to the comparison result, the abnormal area on the map is marked, the abnormal area is evaluated, and the status of the abnormal area is determined; when the abnormal area is determined to be normal according to the evaluation result, the abnormal area is determined to be normal. When the state that navigation cannot be normally realized and needs to be updated immediately is reached, the robot is positioned by fusion according to the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot; the last position confirmed as safe in the historical positioning data is called to determine the first optimal path from the first current positioning position to the safe position; the navigation control unit controls the robot to return to the safe position according to the first optimal path; the laser radar captures the environmental changes that have occurred since the last scan from the abnormal area, and reconstructs the point cloud map according to the environmental changes; the navigation control unit regenerates the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position, thereby realizing adaptive navigation in a dynamic environment and improving the navigation efficiency and accuracy of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0036] Figure 1 Schematic diagram of the flow of a dynamic environment adaptive navigation method applied to a robot in an embodiment of the present invention;

[0037] Figure 2 Schematic diagram of the principle of dynamic environment adaptive navigation in an embodiment of the present invention;

[0038] Figure 31 is a flow chart of a dynamic environment adaptive navigation method applied to a central processing unit in an embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of the structure of a dynamic environment adaptive navigation robot according to an embodiment of the present invention;

[0040] Figure 5 Schematic diagram of the structure of the central processing unit of the dynamic environment adaptive navigation in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0042] The acquisition, storage, use, and processing of data in the technical solution of this application comply with relevant laws and regulations.

[0043] Before introducing the embodiments of the present invention, the terms involved in the present invention are first introduced.

[0044] ESL: Electronic Shelf Label or Electronic Price Label. Electronic Shelf Label (ESL) is an electronic display device used in retail stores, usually installed on shelves, to display product prices, promotional information, inventory status, etc.

[0045] AOA server: used to manage and control wireless devices, such as ESL, to ensure that tags can receive and send information.

[0046] AOA: Angle of Arrival, the angle of arrival of the wireless signal when it reaches the receiving device.

[0047] AOA positioning: A technology that uses the angle of arrival of the received signal to determine the location of the signal source.

[0048] Nine-axis sensor MEMS: inertial sensing equipment, including accelerometer, gyroscope, and geomagnetic sensor.

[0049] Figure 1 FIG. 1 is a flow chart of a dynamic environment adaptive navigation method for a robot according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0050] Step 101: The laser radar scans the surrounding environment, generates current point cloud data of the surrounding environment, and sends it to the central processing unit;

[0051] Step 102: The electronic price tag unit sends a measurement signal to a base station; the base station is used to determine the arrival angle based on the measurement signal, and send the arrival angle to the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle and return it to the central processing unit;

[0052] Step 103: The nine-axis sensor measures the nine-axis data of the robot and sends it to the central processing unit;

[0053] Step 104: The central processing unit compares the current point cloud data with pre-generated supermarket point cloud map data. When the comparison results determine that the surrounding environment has changed, the central processing unit marks an abnormal area on the map, evaluates the abnormal area, and determines the status of the abnormal area. When the evaluation results determine that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately, the central processing unit performs fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot. The last confirmed safe position in the historical positioning data is called to determine a first optimal path from the first current positioning position to the safe position.

[0054] Step 105: The navigation control unit controls the robot to return to the safe position according to the first optimal path;

[0055] Step 106: The lidar captures environmental changes that have occurred in the abnormal area since the last scan, and reconstructs a point cloud map based on the environmental changes;

[0056] Step 107: The navigation control unit regenerates the navigation path according to the reconstructed point cloud map; and controls the robot to continue to execute the task from the safe position according to the regenerated navigation path.

[0057] The method for dynamic environment adaptive navigation provided by the embodiment of the present invention is as follows: when working: the laser radar scans the surrounding environment, generates current point cloud data of the surrounding environment and sends it to the central processing unit; the electronic price tag unit sends a measurement signal to the base station; the base station is used to determine the arrival angle according to the measurement signal, and sends the arrival angle to the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot according to the arrival angle and return it to the central processing unit; the nine-axis sensor measures the nine-axis data of the robot and sends it to the central processing unit; the central processing unit compares the current point cloud data with the pre-generated supermarket point cloud map data, and when it is determined that the surrounding environment has changed according to the comparison result, the abnormal area on the map is marked, the abnormal area is evaluated, and the status of the abnormal area is determined; when the abnormal area is determined to be When navigation cannot be achieved normally and needs to be updated immediately, the robot's first current position is obtained by fusion positioning based on the arrival angle positioning position and the nine-axis data. The last position confirmed as safe in the historical positioning data is called to determine the first optimal path from the first current position to the safe position. The navigation control unit controls the robot to return to the safe position according to the first optimal path. The lidar captures environmental changes that have occurred in the abnormal area since the last scan and reconstructs the point cloud map based on the environmental changes. The navigation control unit regenerates the navigation path based on the reconstructed point cloud map. Based on the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position, realizing adaptive navigation in a dynamic environment and improving the robot's navigation efficiency and accuracy. The following is a detailed introduction.

[0058] To address the problem of existing robots easily getting lost in dynamic environments due to their use of LiDAR point cloud mapping, the present invention proposes a solution that combines angle-of-arrival (AOA) positioning technology with a nine-axis sensor for robot-assisted navigation and LiDAR mapping. The following is the specific composition and process of this system:

[0059] In order to understand how to implement the present invention, the following first Figure 4 Introduce the composition of the robot system.

[0060] 1. Robots

[0061] a. LiDAR: Used to continuously scan the environment, generate point cloud data of surrounding objects, and achieve preliminary positioning and navigation.

[0062] b. Nine-axis MEMS sensor: measures the robot's acceleration, angular velocity, and magnetic field strength, providing data on the robot's speed and movement direction, assisting in more accurate real-time positioning.

[0063] c. Central Processing Unit: Receives data from the LiDAR, AOA positioning module, and accelerometer, processes and fuses them to achieve precise positioning and path planning.

[0064] d. Figure 4 The “storage unit 09 ” shown: stores the point cloud map of the environment and historical navigation data for reference and update.

[0065] e. Navigation control unit: guides the robot's movement based on the processed data, and controls the robot's behavior and path selection.

[0066] f. Figure 4 The "camera 08" shown is the image acquisition device in the embodiment of the present invention: the camera plays a vital role as a visual sensor in the robot system, which is used to capture visual information of the environment and assist the robot in performing more complex navigation and interaction tasks.

[0067] g.ESL: ESL is used in the robot system to interact with smart tags in the retail environment to provide real-time product information and positioning services. Based on this, in one embodiment, the above-mentioned dynamic environment adaptive navigation method may also include:

[0068] The electronic price tag unit interacts with the smart electronic tags in the supermarket to obtain the location information of the current product bound to the smart electronic tag, and performs robot-assisted positioning based on the location information of the current product bound to the smart electronic tag.

[0069] During specific implementation, the embodiment of the present invention also performs information exchange with smart electronic tags in supermarkets through the ESL unit to perform robot-assisted positioning, thereby improving the accuracy and flexibility of robot positioning.

[0070] 2.AOA positioning module:

[0071] a.AOA server: used to manage and control wireless devices, such as ESL, to ensure that tags can receive and send information.

[0072] b. Base station: Utilizes wireless signal transmission and determines the robot's position relative to the signal source by the angle of arrival of the received signal.

[0073] Figure 2 The schematic diagram of the principle of dynamic environment adaptive navigation in the embodiment of the present invention is as follows. Figure 2 Introduces the process method of adaptive navigation in dynamic environments.

[0074] 1. Base station deployment and configuration

[0075] (1) Location selection and deployment:

[0076] a. Deploy multiple base stations in key areas of dynamic environments, such as shopping malls and supermarkets, to ensure accurate AOA signals are available throughout the area. Select appropriate frequencies and adjust the signal transmission interval and power to optimize base station response time and signal quality.

[0077] b. Consider the layout of base stations to ensure that their coverage fully covers all areas that need to be located. The installation height and location of base stations need to be determined according to the actual environment to maximize coverage efficiency.

[0078] (2) Base station configuration:

[0079] All base stations must be installed horizontally and equipped with high-precision level detection devices to compensate for errors caused by possible installation tilt or uneven ground. Figure 2 "AOA base station deployment" and "AOA positioning" are shown.

[0080] 2. Deploy the robot

[0081] LiDAR Scanning and Navigation Initialization: When the robot starts up, it first uses LiDAR to scan the environment, generating a high-precision initial point cloud map. This serves as the primary basis for basic navigation. This is similar to the LiDAR scanning of the surroundings in step 101, which generates current point cloud data. Simultaneously, the robot's navigation control unit plans the initial navigation path according to a pre-set program, allowing it to begin its mission.

[0082] 3. Environmental scanning and preliminary mapping

[0083] LiDAR system: The robot uses LiDAR to scan the surrounding environment, generate an initial point cloud map and perform basic navigation, such as Figure 2 The "LiDAR scan environment to generate an initial point cloud map" shown.

[0084] 4.AOA plus sensor fusion positioning and navigation system.

[0085] AOA plus sensor fusion positioning: Navigation using lidar (i.e. Figure 2 At the same time as the laser radar navigation positioning in the robot, the robot uses the AOA positioning module, such as Figure 2 The "AOA positioning" shown in the figure and the nine-axis (accelerometer, gyroscope, magnetometer) sensor are based on the known supermarket store map (such as Figure 2 The "store map information" shown in the figure is used for independent positioning, such as Figure 2 The "nine-axis sensor MEMS" and "nine-axis sensor positioning" shown in the figure realize a fusion positioning and navigation system, such as Figure 2The "fused positioning" shown in the figure can be implemented using a Kalman filter algorithm. The AOA provides observations to initially determine the robot's position, while the nine-axis sensor provides state estimates to predict the robot's next position. The filter combines these two data points to output the final position information.

[0086] Specifically, the fusion positioning process, that is, in one embodiment, performing fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot, may include:

[0087] Get the robot's current position and velocity, as well as the covariance matrix of the position and velocity;

[0088] Using the acceleration and angular velocity data from the nine-axis sensor and the robot's motion equation, the robot's position and velocity at the next moment are predicted to obtain the current predicted state; based on the prediction error and noise model, the covariance matrix is ​​updated to obtain the uncertainty of the current predicted state;

[0089] Based on the current predicted state, the predicted observation value of the nine-axis sensor is calculated; the arrival angle positioning position is used as the actual observation value, and the difference between the actual observation value and the predicted observation value is calculated; according to the uncertainty of the current predicted state and the uncertainty of the actual measurement state, the weight of the arrival angle positioning position and the nine-axis positioning position (the nine-axis positioning position is obtained based on the nine-axis data) in the final fusion result is dynamically adjusted;

[0090] According to the difference and the weight, the current position and speed of the robot are corrected to obtain the first current positioning position.

[0091] The above fusion positioning method is introduced in detail below.

[0092] In the embodiment of the present invention, through the two stages of prediction and update, the motion model and observation model of the system are dynamically combined, and the data of multiple sensors (such as nine-axis sensors, AOA positioning, and lidar) can be integrated to achieve precise positioning in dynamic environments.

[0093] The present invention utilizes two phases, prediction and update, to achieve state estimation and error minimization by dynamically adjusting the weights of sensor data. State variables include position and velocity. The prediction phase updates the state based on a motion model, while the update phase corrects the predictions based on measured values.

[0094] (1) Initialization

[0095] Objective: Initialize the robot's position, velocity, and uncertainty (if it is the current moment, you can get the robot's current position and velocity (i.e., current state), as well as the covariance matrix of the position and velocity).

[0096] Define state variables, including position and velocity.

[0097] Set the initial values ​​of state variables, such as the initial position and velocity of the robot.

[0098] A covariance matrix is ​​defined (the data in the covariance matrix represents the accuracy of the state and the correlation between each state) to represent the uncertainty of the initial state. At the same time, the covariance matrix of the nine-axis sensor and process noise is set to ensure the adaptability of the algorithm to different data sources.

[0099] (2) Prediction step

[0100] State prediction: In this stage, the acceleration and angular velocity data provided by the nine-axis sensor are used to predict the position and velocity of the robot at the next moment according to the motion model (such as posture prediction model, velocity prediction model, and position prediction model) to obtain the current predicted state.

[0101] Uncertainty update: Combine the prediction error and the noise model (such as the Gaussian noise model) to update the covariance matrix (the covariance matrix can be regarded as the credibility of the state prediction) to evaluate the credibility of the state prediction and obtain the uncertainty of the current predicted state.

[0102] (3) Update steps

[0103] Use the AOA positioning results as observation data to correct the prediction results.

[0104] ① Measurement prediction: Based on the current predicted state (speed and position), calculate the data that the sensor may observe (predicted observation value) and update the uncertainty of the predicted state.

[0105] ② Measurement residual: Calculate the difference between the actual observation value (AOA result) and the predicted observation value.

[0106] Kalman gain calculation: Based on the uncertainty of the predicted state and the measurement uncertainty (which can be controlled by preset parameters) updated in ① above, the weights of the two (nine-axis positioning position results and AOA positioning results) in the final fusion result are dynamically adjusted.

[0107] ③ State Update: Combine the observed data with the predicted results (the "difference" in ② above) to correct the robot's current position and velocity, obtaining the first current location. Let's use an example to illustrate this step: assuming the current state is X, the AOA result is M, the AOA weight calculated by the Kalman gain is K, and the residual is y, y = MX, and Xnew = X + Ky.

[0108] ④ Covariance update: Update the state uncertainty matrix to reflect the new state credibility.

[0109] (4) Output

[0110] Output result: The fused current position and speed of the robot are used as the final navigation result.

[0111] Subsequent applications: The results will be used for path planning and navigation control, and provide initial values ​​for state prediction at the next moment.

[0112] 5. Dual system positioning

[0113] (1) Robot navigation and positioning:

[0114] a. LiDAR data processing: The LiDAR point cloud data is independently processed by the central processing unit for updating the point cloud map and navigation.

[0115] b. Real-time Navigation and Map Updates: As the robot moves, the LiDAR continuously scans the environment. Newly acquired point cloud data is compared and fused with existing map data to update the map in real time and optimize the navigation path. This comparison and fusion process matches the point cloud information obtained from the current LiDAR scan, such as distance and angle, with the point cloud information in the constructed map to determine the robot's current location.

[0116] c. Position estimation and path planning: Based on the current point cloud map, the robot calculates the optimal path to avoid obstacles and dynamically adjusts its route according to environmental changes.

[0117] (2) AOA and nine-axis sensor data processing: AOA positioning and nine-axis sensor data are synchronously processed and integrated with the store map to provide continuous position updates and corrections, independent of point cloud data. Specifically:

[0118] a. Signal reception and processing: That is, in step 102 above, the electronic shelf label unit sends a measurement signal to the base station; the base station receives the signal from the robot and measures the angle of arrival of the signal. These data are sent to the AOA server, and the position is calculated by the angle of arrival, that is, the AOA positioning result (arrival angle positioning position). In step 102 above, the autonomous mobile device (robot) is equipped with an electronic shelf label (ESL) and an ESL directional antenna. The device sends a request signal of a specific angle to the base station of the electronic shelf label system through the antenna. The base station responds to these request signals (determines the arrival angle based on the measurement signal), and the autonomous mobile device receives these response signals (AOA positioning position).

[0119] b. Position Calculation: The robot's position is calculated using the nine-axis sensor and simultaneously obtains AOA positioning results. The fusion positioning system combines these two positions to determine the robot's final position. Nine-axis sensor positioning results have cumulative errors, which accumulate over time. AOA positioning results, on the other hand, do not have cumulative errors, but they can only be determined when the robot is within base station coverage. Therefore, when the robot is outside base station coverage, the nine-axis sensor is used for positioning. Once the AOA positioning results are available, they are used to correct the current positioning results.

[0120] From the above, it can be seen that in one embodiment, the first current positioning position of the robot is obtained by performing fusion positioning based on the arrival angle positioning position and the nine-axis data, which can include: outside the coverage range of the base station, using the positioning position obtained according to the nine-axis data for positioning; within the coverage range of the base station, using the arrival angle positioning position obtained according to the measurement signal emitted by the electronic price tag unit to correct the nine-axis positioning position.

[0121] In specific implementation, the above-mentioned specific implementation method of fusing the positioning position according to the AOA positioning position and the positioning position obtained according to the nine-axis data improves the positioning accuracy of the robot.

[0122] The nine-axis sensor uses the gyroscope to calculate the current attitude and the accelerometer for integration to estimate velocity and position. Because the nine-axis sensor's position calculations can have cumulative errors, they can be corrected using map information and AOA positioning. For example, if the nine-axis sensor is located in an inaccessible area (such as a shelf), the position needs to be corrected to the nearest accessible area based on the map information. If an AOA positioning result is available and the signal strength is above the threshold, the AOA positioning accuracy is considered high and can be used directly to correct the nine-axis sensor's positioning result.

[0123] From the above, it can be seen that in one embodiment, the current positioning position of the robot is obtained by performing fusion positioning based on the AOA positioning position and the nine-axis positioning position, including: synchronously processing the AOA positioning position and the nine-axis positioning position and integrating the store map to obtain the current positioning position of the robot.

[0124] In specific implementation, the data of AOA positioning and nine-axis sensor are synchronously processed and integrated with the store map, such as Figure 2 The “store map information” shown provides continuous position updates and corrections, independent of point cloud data, further improving the accuracy of robot positioning.

[0125] From the above, it can be seen that in one embodiment, the above-mentioned method of dynamic environment adaptive navigation may also include: when the nine-axis positioning position is located in an inaccessible shelf area, the nine-axis positioning position is corrected according to the map information, and the nine-axis positioning position is corrected to the nearest reachable area.

[0126] In specific implementation, the above specific implementation method of correcting the nine-axis positioning position to the nearest reachable area improves the positioning accuracy of the robot.

[0127] (3) In the embodiments of the present invention, the AOA positioning and the nine-axis sensor can be replaced by a visual positioning system, or the positioning results of the visual positioning system can be further combined to improve the positioning accuracy.

[0128] The visual positioning solution is introduced in detail below.

[0129] a. Location Selection and Deployment: Deploy multiple high-precision cameras in key areas of dynamic environments, such as shopping malls and supermarkets, to ensure accurate visual information throughout the entire area. Select appropriate camera angles and adjust camera resolution to optimize image clarity and recognition performance. Consider the camera layout to ensure that its field of view fully covers all areas requiring positioning. The camera's mounting height and position should be determined based on the actual environment to maximize visual coverage. All cameras must have precise focal length adjustment and undergo regular calibration to ensure image quality and positioning accuracy.

[0130] b. Visual positioning:

[0131] Signal reception and processing: Deployed cameras continuously capture images of the environment and use image recognition technology to identify robots and other landmark objects. This image data is sent to the central processing unit in real time.

[0132] Position calculation: The central processing unit uses image recognition results and machine vision algorithms to determine the robot's precise position. It uses techniques such as feature matching and geometric transformation to synthesize the robot's position information from multiple perspectives.

[0133] c. Positioning exception handling and repositioning:

[0134] Anomaly Identification and Response: While the robot is performing its mission, the system continuously monitors and analyzes data from the LiDAR and vision positioning modules. If the robot's actual position deviates significantly from the expected trajectory, the system automatically triggers an exception handling mechanism.

[0135] Determine current position: The system uses visual localization to accurately estimate the robot's current position.

[0136] Guidance to return to a safe position: If the robot is determined to be lost, the system will recall the last confirmed safe location in its historical positioning data. Using this location data as a reference, the system calculates the optimal path to return to that point.

[0137] Regarding a solution for further combining visual positioning results to improve positioning accuracy, in one embodiment, the above-mentioned dynamic environment adaptive navigation method may further include:

[0138] The image acquisition device acquires current visual image data of the surrounding environment;

[0139] When the central processing unit detects changes in the surrounding environment, it matches the current visual image data with the pre-stored supermarket image data set to obtain the target image information on the shelf; it performs image recognition on the target image information and performs robot-assisted positioning based on the preset location information of the identified goods in the supermarket.

[0140] In specific implementations, this embodiment of the present invention utilizes image-assisted positioning: an image acquisition device collects images of the environment. When a positioning anomaly occurs, the device matches the collected images with a pre-stored image dataset. This image matching process obtains target image information on the shelf, thereby assisting in positioning. This embodiment of the present invention also incorporates current visual image data of the surrounding environment captured by the image acquisition device for robot-assisted positioning, further improving positioning accuracy.

[0141] 6. Navigation and environmental change monitoring

[0142] (1) Dual-system independent monitoring: Each system independently monitors environmental changes and the robot's position status, improving system redundancy and reliability. Specifically:

[0143] a. Continuous monitoring and response: While the robot is performing its tasks, the system continuously monitors environmental changes and the robot's real-time location status.

[0144] b. If significant environmental changes are detected (e.g., shelf movement or new obstacles), the system will automatically mark abnormal areas on the map that need to be updated or reassessed. Figure 2 "Navigation and monitoring, if environmental changes are detected, mark the current area as needing to be updated."

[0145] In specific implementation, the evaluation of the abnormal area includes the following three situations:

[0146] Case 1: Both the map and positioning are abnormal and need to be updated immediately

[0147] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is lower than the first overlap rate threshold, or the deviation between the robot's current positioning position and the expected position exceeds the navigation tolerance threshold, and the navigation path fails, the abnormal area is determined to be in a state where normal navigation cannot be achieved and needs to be updated immediately.

[0148] As can be seen from the above, in one embodiment, evaluating the abnormal area and determining the status of the abnormal area may include:

[0149] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is lower than the first overlap rate threshold (e.g., 70%), or the deviation between the current positioning position of the robot and the expected position exceeds the navigation tolerance threshold (e.g., 15 cm), and the navigation path fails, the abnormal area is determined to be in a state where normal navigation cannot be achieved and needs to be updated immediately.

[0150] In specific implementation, the above specific implementation method of determining that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately further improves the navigation accuracy.

[0151] In the above step 104, the central processing unit compares the current point cloud data with the pre-generated supermarket point cloud map data. When it is determined based on the comparison result that the surrounding environment has changed, the abnormal area on the map is marked, the abnormal area is evaluated, and the status of the abnormal area is determined; when it is determined based on the evaluation result that the abnormal area is in a state where navigation cannot be normally achieved and needs to be updated immediately, the robot is positioned by fusion based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot; the last position confirmed as safe in the historical positioning data is called to determine the first optimal path from the first current positioning position to the safe position.

[0152] In specific implementation, when it is determined according to the evaluation results that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately, fusion positioning is performed based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot, and the last position confirmed as safe in the historical positioning data is called to determine the first optimal path from the first current positioning position to the safe position, which solves the problem of the robot getting lost, and realizes adaptive and precise navigation in a dynamic environment, improving navigation accuracy and efficiency.

[0153] Case 2: Map and positioning are normal and no update is required

[0154] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is higher than the second overlap rate threshold (for example, 90%), and the deviation between the current positioning position of the robot and the expected position is less than the allowable boundary threshold (for example, 5 cm), it is considered that the change in some areas does not exceed the change threshold, and the impact rate on the navigation path is lower than the preset impact rate threshold, and the abnormal area is determined to be in a state where normal navigation can be achieved without updating.

[0155] As can be seen from the above, in one embodiment, evaluating the abnormal area and determining the state of the abnormal area includes:

[0156] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than a second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than an allowable boundary threshold, and the change in some areas does not exceed the change threshold, and the impact rate on the navigation path is lower than a preset impact rate threshold, the abnormal area is determined to be in a state where normal navigation can be achieved and no update is required;

[0157] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0158] In specific implementation, the above specific implementation method of determining that the abnormal area is in a state where normal navigation can be achieved without updating further improves navigation efficiency.

[0159] As can be seen from the above, in one embodiment, the dynamic environment adaptive navigation method may further include:

[0160] When the central processing unit determines, based on the evaluation result, that the abnormal area is in a state where normal navigation can be achieved and no update is required, it sends an instruction to the navigation control unit to continue normal navigation;

[0161] The navigation control unit continues to control the robot to complete the task when receiving the instruction to continue normal navigation.

[0162] In specific implementation, when it is determined according to the evaluation results that the abnormal area is in a state where normal navigation can be achieved and no update is required, an instruction to continue normal navigation is sent to the navigation control unit. When the navigation control unit receives the instruction to continue normal navigation, it continues to control the robot to complete the task, thereby further improving the efficiency of navigation.

[0163] Case 3: There is a certain deviation between the map and the positioning, but no immediate update is required

[0164] One of the following sub-conditions is met:

[0165] Subcase 1: When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is between a first overlap rate threshold (e.g., 70%) and a second overlap rate threshold (e.g., 90%) (including being equal to the first overlap rate threshold and the second overlap rate threshold), and the deviation between the current positioning position of the robot and the expected position is between a navigation tolerance threshold (e.g., 15 cm) and an allowable boundary threshold (e.g., 5 cm) (including being equal to the allowable boundary threshold and the navigation tolerance threshold).

[0166] Sub-case 2: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is lower than the first overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is between the navigation tolerance threshold and the allowable boundary threshold (including being equal to the allowable boundary threshold and the navigation tolerance threshold).

[0167] Sub-case three: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is between the first overlap rate threshold and the second overlap rate threshold (including being equal to the first overlap rate threshold and the second overlap rate threshold), and the deviation between the robot's current positioning position and the expected position is less than the allowable boundary threshold.

[0168] At this time, when it is considered that the change of some areas exceeds the change threshold but the overall navigation effect is not affected, the abnormal area is determined to be in a state where an update is required but not immediately.

[0169] Among them: the first overlap rate threshold is less than the second overlap rate threshold; the allowed boundary threshold is less than the navigation tolerance threshold.

[0170] As can be seen from the above, in one embodiment, evaluating the abnormal area and determining the state of the abnormal area includes:

[0171] When any of the following sub-situations are met, and the changes in some areas exceed the change threshold but do not affect the overall navigation effect, the abnormal area is determined to be in a state where an update is required but not immediately:

[0172] Subcase 1: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0173] Subcase 2: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is less than the first overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0174] Subcase 3: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than the allowable boundary threshold;

[0175] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0176] In specific implementation, the above specific implementation method of determining that the abnormal area is in a state where update is required but not immediately required further improves navigation efficiency.

[0177] In one embodiment, the above dynamic environment adaptive navigation method may further include:

[0178] When the central processing unit determines, based on the evaluation result, that the abnormal area is in a state where an update is required but not immediately, it obtains current point cloud data generated by the laser radar scanning the surrounding environment; determines a second current positioning position of the robot based on the current point cloud data; and generates a second optimal path based on the second current positioning position;

[0179] The navigation control unit controls the robot to continue executing the task from the second current positioning position according to the second optimal path; after completing the task, the navigation control unit controls the robot to return to the abnormal area;

[0180] After completing its mission, the lidar captures environmental changes that have occurred in the abnormal area since the last scan and reconstructs a point cloud map based on the environmental changes.

[0181] In specific implementation, when it is determined according to the evaluation results that the abnormal area is in a state that needs to be updated but does not need to be updated immediately, the second current positioning position of the robot is determined based on the current point cloud data; and a second optimal path avoiding the abnormal area is generated based on the second current positioning position, further improving the efficiency and accuracy of navigation.

[0182] In summary, if the map has two thresholds, the positioning has two thresholds, as shown in Table 1 below:

[0183] Table 1

[0184] M1 The first coincidence rate threshold M2 The second coincidence rate threshold M3 N1 Allowable boundary threshold N2 Navigation tolerance threshold N3

[0185] There are nine combinations in total: M1 N1–Case 1; M1 N2–Case 1; M1 N3–Case 1; M2 N1–Case 3; M2 N2–Case 3; M2 N3–Case 1; M3 N1–Case 2; M3 N2–Case 3; M3 N3–Case 1.

[0186] 7. Positioning exception handling and repositioning

[0187] Coordinated handling of exceptions: If the LiDAR system fails to navigate due to point cloud mismatch, the AOA plus sensor system can independently provide accurate location or guide the robot back to a known location. Assisted positioning: Once the mobile device enters the calibration range of a base station according to the predicted path, or obtains accurate location information through image matching, the location information of the base station is used for assisted positioning. The device corrects its own positioning system based on this information and resumes normal navigation. Specifically:

[0188] Abnormal identification and response

[0189] (1) Identify and locate abnormalities:

[0190] While the robot is performing its mission, the system continuously monitors and analyzes data from the LiDAR, AOA positioning module, and nine-axis sensor. If the robot's actual position deviates significantly from its intended trajectory (for example, if it deviates by more than 10 meters (configurable) from the intended path, or if it is located in an inaccessible area (such as a shelf), the system automatically triggers an exception handling mechanism.

[0191] Abnormal changes in the surrounding environment may be caused by a variety of factors, such as changes in the environment layout (such as shelf movement or new obstacles), which may cause significant deviations in LiDAR positioning.

[0192] Compare the LiDAR positioning results with the map data. If the positioning result is in an unreachable area (such as a shelf area), the current positioning is considered abnormal.

[0193] Judgment by matching degree: By comparing the matching degree between real-time point cloud data and point cloud map data, if the matching degree is less than the threshold, the current positioning is considered abnormal.

[0194] Mark anomalies: Compare the current fusion positioning result with the last valid LiDAR positioning result to calculate the travel distance. Draw a circular area with the last valid LiDAR positioning result as the center and the travel distance as the radius, marking the anomaly area.

[0195] (2) Determine the current position: Since the LiDAR positioning has become abnormal at this time, the system needs to stop using the LiDAR positioning results and switch to using AOA and nine-axis data and combining them with store information for fusion positioning, so as to accurately estimate the current position of the robot.

[0196] (3) Guidance to return to a safe location:

[0197] If the robot is determined to be lost, the system will retrieve the last confirmed safe location from its historical positioning data. This safe location is used as the endpoint, and the current location is fused with the positioning results as the starting point to calculate the optimal path back to the safe location.

[0198] b. The robot will move along the path guided by the system. At the same time, the AOA and nine-axis fusion positioning systems will continuously update their positioning, while the lidar positioning system will continuously perform positioning to ensure that the robot avoids obstacles. Once the lidar locates a reasonable position (the positioning position is a reachable position and the distance from the previous safe position is less than a certain threshold), it can be determined that the robot has returned to the known position, thereby ensuring that the robot can return to the known position safely and effectively. Figure 2 The "Exception handling and repositioning, using AOA and nine-axis fusion positioning to assist the robot to return to a known position" is shown.

[0199] In one embodiment, the navigation control unit controls the robot to return to the safe position according to the first optimal path, including:

[0200] During the process of the navigation control unit controlling the robot to return to the safe position according to the first optimal path, continuously monitoring the distance between the robot and the safe position;

[0201] According to the distance between the robot and the safe position, the robot is controlled to approach the safe position according to a first optimal path and a preset process.

[0202] During specific implementation, the system continuously monitors the distance between the robot and the target safe position to ensure that the robot gradually approaches the target according to the planned path, thereby ensuring the accuracy of navigation.

[0203] In one embodiment, the above dynamic environment adaptive navigation method may further include:

[0204] When the central processing unit detects that the robot has reached a safe position, it uses the arrival angle positioning position and the nine-axis positioning position to correct the safe position to obtain the corrected safe position; it verifies whether the current environment data is consistent with the preset data of the safe position. If it is verified that the current environment data is inconsistent with the preset data of the safe position, it initiates a map reconstruction command to the lidar;

[0205] When the laser radar receives the map reconstruction instruction, it rescans the area within the preset range of the safe position and reconstructs the point cloud map according to the environmental changes.

[0206] In specific implementation, after reaching a safe location, the current position is corrected using AOA and nine-axis sensor data. The current environment is verified to be consistent with the preset data for the safe location. If the current environment data is inconsistent with the preset data for the safe location, a rebuild map command is issued to the LiDAR, starting the subsequent process.

[0207] The above “4. AOA plus sensor fusion positioning and navigation system” to “7. Positioning exception handling and repositioning” are steps 102 to 105.

[0208] 8. Re-build the point cloud map and update it, i.e., step 106 above.

[0209] Navigation based on AOA plus sensor system: When the lidar system needs to be re-matched or calibrated, the position data of the AOA plus sensor system is used to assist in determining the correct position of the robot and guide it to perform necessary reconstruction. That is, the lidar rescans the abnormal area, captures the environmental changes that have occurred since the last scan from the abnormal area, and reconstructs the point cloud map based on the environmental changes, such as Figure 2 The "re-map" shown. Specifically:

[0210] (1) Restart the LiDAR scan:

[0211] a. Once the robot returns to a known safe location or completes a navigation route, and the status of certain areas is marked as needing an update, the robot will begin rescanning the areas that need updating.

[0212] b. Rescanning includes not only a thorough inspection of the immediate return area, but also a reassessment and verification of surrounding areas that may affect navigation.

[0213] c. If the robot successfully completes navigation, it will need to return to the areas marked as needing updating and rescan.

[0214] d. If the robot encounters a situation where the environment changes significantly and it cannot navigate normally, once the robot returns to a known safe location, it will need to rescan and update the point cloud map from this known safe location. After the update is complete, try to restart navigation.

[0215] As can be seen from the above, in one embodiment, the dynamic environment adaptive navigation method may further include:

[0216] The central processing unit re-evaluates and verifies the area around the abnormal area that affects navigation, and reconstructs the point cloud map based on the re-evaluation and verification results.

[0217] During specific implementation, in an embodiment of the present invention, the central processing unit will also re-evaluate and verify the area around the abnormal area that affects navigation, and reconstruct the point cloud map based on the re-evaluation and verification results, thereby further improving the accuracy of robot positioning.

[0218] (2) Update point cloud map:

[0219] a. The updated point cloud data is transmitted back to the central processing unit, and the system compares and integrates this new data with the existing point cloud map.

[0220] b. During this process, the system uses advanced map matching technology to ensure seamless integration of new and old data, while identifying and correcting any inaccuracies in the known data.

[0221] (3) Ensure the accuracy and reliability of maps:

[0222] a. The updated point cloud map is immediately applied to the robot’s navigation system. This ensures that the robot relies on the most accurate and up-to-date map information as it continues to perform its tasks.

[0223] b. Through this method, the system not only corrects navigation errors caused by environmental changes, but also enhances the robot's adaptability and accuracy in the face of future environmental changes.

[0224] 9. Path optimization and continuous navigation, i.e., step 107 above.

[0225] Dual-system path optimization: After the robot returns to its new location and completes the map update, the system continues to optimize the robot's route. Algorithms continuously adjust the path to ensure efficient and safe navigation while reducing sensitivity to environmental changes. The two systems operate independently but assist each other when necessary to ensure continuous and accurate navigation. Specifically, the navigation control unit regenerates the navigation path based on the reconstructed point cloud map. Based on this regenerated navigation path, the robot continues to execute the task from this safe location.

[0226] Recording and Adjustment: During normal positioning, the device records the response signal strength and base station location information in real time. This information is used to update and optimize the predicted path and positioning algorithms to adapt to different environments and conditions. This approach enables autonomous mobile devices (robots) to self-correct and navigate using existing communication infrastructure and image data when the positioning system encounters interference or failure, improving the device's reliability and autonomy in complex environments.

[0227] That is, in one embodiment, the above dynamic environment adaptive navigation method may further include:

[0228] The electronic price tag unit records the strength value of the base station response signal and the base station location information in real time during normal positioning;

[0229] The navigation control unit updates and optimizes the navigation path according to the strength value of the base station response signal and the base station location information to adapt to different environments and conditions.

[0230] During specific implementation, the embodiment of the present invention also updates and optimizes the navigation path based on the strength value of the base station response signal and the base station location information recorded in real time by the ESL unit during normal positioning to adapt to different environments and conditions, thereby improving the accuracy and flexibility of robot positioning.

[0231] In summary, the key points and advantages of the dynamic environment adaptive navigation solution provided by the embodiments of the present invention are:

[0232] 1. Dual positioning system

[0233] This embodiment of the present invention crucially implements two independent but complementary positioning systems: a lidar positioning system and a positioning system that integrates AOA and a nine-axis sensor. These two systems provide multi-level data verification and positioning accuracy, ensuring the most stable and reliable navigation support for the robot in complex or dynamically changing environments.

[0234] (1) LiDAR positioning provides high-precision spatial point cloud data for forming detailed environmental maps and real-time obstacle identification.

[0235] (2) AOA and nine-axis sensor fusion positioning provides accurate position information about the robot in the environment through angle measurement and motion sensing data, especially when the lidar cannot provide accurate data due to line of sight obstruction or external interference.

[0236] In addition, the "AOA and nine-axis sensor fusion positioning" system in the embodiment of the present invention can also be implemented through visual positioning.

[0237] 2. AOA and nine-axis fusion positioning assists lost robots to return to a safe and known location

[0238] When a robot gets lost or encounters navigation anomalies during a mission, a system that integrates AOA positioning and nine-axis sensors can provide critical positioning assistance. This fused positioning technology extracts position information from two independent data sources, optimizes it through an algorithm, and accurately locates the robot's current position, guiding it back to its last known safe location.

[0239] During the assisted return process, the system ensures that the robot's path during the return process is optimal through real-time data monitoring and analysis, and can continuously adjust to cope with new obstacles or environmental changes that may arise.

[0240] 3. Assisted Re-Mapping

[0241] After the robot returns to a known safe location and calibrates its position information, the lidar restarts scanning, updating and re-establishing the point cloud map. This process is critical because it ensures that the robot's navigation map is always up to date, thereby improving navigation accuracy and reliability.

[0242] (1) Map updates include not only rescanning of known areas, but also evaluation and integration of newly changed areas to ensure that any environmental changes can be identified and incorporated into the navigation system.

[0243] (2) The accuracy and reliability of the map directly affect the robot's performance in future mission execution. By continuously optimizing and updating the map, the robot can better adapt to environmental changes and improve mission efficiency.

[0244] By protecting and implementing these three key points, the embodiments of the present invention not only improve the robot's autonomy and flexibility in complex environments, but also significantly enhance the robot system's adaptability to environmental changes and overall operational safety. The integration and optimization of these technologies enables the robot to demonstrate excellent navigation and positioning performance in a variety of environments.

[0245] In summary, the embodiments of the present invention combine Angle of Arrival (AOA) positioning technology and a nine-axis sensor to provide a solution. AOA positioning can determine the position by measuring the angle of arrival of the signal, while the nine-axis sensor can provide real-time data on the robot's motion status. The combination of these two technologies can not only improve the accuracy of the position, but also assist the robot in relocating itself when it gets lost and find its starting point. In this way, the robot can restart the lidar mapping process in a changing environment, effectively solving the problem of re-mapping caused by environmental changes.

[0246] The present invention also provides a method for dynamic environment adaptive navigation applied to a central processing unit, as described in the following embodiments. Because the principles of this method for solving problems are similar to those of the method for dynamic environment adaptive navigation applied to a robot, the implementation of this method can be referenced to the implementation of the method for dynamic environment adaptive navigation applied to a robot, and any repetitions are not repeated here.

[0247] Figure 3 FIG. 1 is a flow chart of a dynamic environment adaptive navigation method applied to a central processing unit in an embodiment of the present invention. Figure 3 Said method comprises the following steps:

[0248] Step 501: Compare the current point cloud data with pre-generated supermarket point cloud map data; the current point cloud data is sent by a laser radar, which is used to scan the surrounding environment and generate the current point cloud data of the surrounding environment;

[0249] Step 502: When it is determined based on the comparison result that the surrounding environment has changed, an abnormal area on the map is marked;

[0250] Step 503: Evaluate the abnormal area and determine the status of the abnormal area;

[0251] Step 504: When it is determined according to the evaluation result that the abnormal area is in a state where navigation cannot be normally achieved and needs to be updated immediately, a fusion positioning is performed based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot; the arrival angle positioning position is sent by the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle, and the arrival angle is sent by the base station, and the base station is used to determine the arrival angle based on the measurement signal sent by the electronic price tag unit; the nine-axis data is sent by the nine-axis sensor, and the nine-axis sensor is used to measure the nine-axis data of the robot;

[0252] Step 505: Call the last position confirmed as safe in the historical positioning data, determine the first optimal path from the first current positioning position to the safe position, and send it to the navigation control unit; the navigation control unit is used to control the robot to return to the safe position according to the first optimal path; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area, and reconstruct the point cloud map according to the environmental changes; the navigation path is regenerated according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position. The sea is used to: regenerate the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

[0253] In one embodiment, performing fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot includes:

[0254] Get the robot's current position and velocity, as well as the covariance matrix of the position and velocity;

[0255] Using the acceleration and angular velocity data from the nine-axis sensor and the robot's motion equation, the robot's position and velocity at the next moment are predicted to obtain the current predicted state; based on the prediction error and noise model, the covariance matrix is ​​updated to obtain the uncertainty of the current predicted state;

[0256] Based on the current predicted state, the predicted observation value of the nine-axis sensor is calculated; the arrival angle positioning position is used as the actual observation value, and the difference between the actual observation value and the predicted observation value is calculated; according to the uncertainty of the current predicted state and the uncertainty of the actual measurement state, the weight of the arrival angle positioning position and the nine-axis positioning position in the final fusion result is dynamically adjusted;

[0257] According to the difference and the weight, the current position and speed of the robot are corrected to obtain the first current positioning position.

[0258] In one embodiment, evaluating the abnormal area and determining the status of the abnormal area includes:

[0259] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is lower than the first overlap rate threshold, or the deviation between the current positioning position of the robot and the expected position exceeds the navigation tolerance threshold, and the navigation path fails, the abnormal area is determined to be in a state where normal navigation cannot be achieved and needs to be updated immediately.

[0260] In one embodiment, the dynamic environment adaptive navigation method applied to the central processing unit may further include:

[0261] When the abnormal area is determined to be in a state that needs to be updated but does not need to be updated immediately based on the evaluation results, the current point cloud data generated by the laser radar scanning the surrounding environment is obtained; based on the current point cloud data, the second current positioning position of the robot is determined; based on the second current positioning position, a second optimal path is generated and sent to the navigation control unit; the navigation control unit is also used to control the robot to continue to execute the task from the second current positioning position according to the second optimal path; after completing the task, the robot is controlled to return to the abnormal area; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area after completing the task, and reconstruct the point cloud map based on the environmental changes.

[0262] In one embodiment, evaluating the abnormal area and determining the status of the abnormal area includes:

[0263] When any of the following sub-situations are met, and the changes in some areas exceed the change threshold but do not affect the overall navigation effect, the abnormal area is determined to be in a state where an update is required but not immediately:

[0264] Subcase 1: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0265] Subcase 2: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is less than the first overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0266] Subcase 3: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than the allowable boundary threshold;

[0267] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0268] In one embodiment, the dynamic environment adaptive navigation method applied to the central processing unit may further include:

[0269] When it is determined according to the evaluation results that the abnormal area is in a state where normal navigation can be achieved and no update is required, an instruction to continue normal navigation is sent to the navigation control unit; the navigation control unit is also used to continue controlling the robot to complete the task when receiving the instruction to continue normal navigation.

[0270] In one embodiment, evaluating the abnormal area and determining the status of the abnormal area includes:

[0271] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than a second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than an allowable boundary threshold, and the change in some areas does not exceed the change threshold, and the impact rate on the navigation path is lower than a preset impact rate threshold, the abnormal area is determined to be in a state where normal navigation can be achieved and no update is required;

[0272] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0273] In one embodiment, the dynamic environment adaptive navigation method applied to the central processing unit may further include:

[0274] When it is detected that the robot has reached a safe position, the safe position is corrected using the arrival angle positioning position and the nine-axis positioning position to obtain a corrected safe position; it is verified whether the current environmental data is consistent with the preset data of the safe position. When it is verified that the current environmental data is inconsistent with the preset data of the safe position, a map reconstruction instruction is initiated to the laser radar; the laser radar is also used to rescan the area within the preset range of the safe position when receiving the map reconstruction instruction, and reconstruct the point cloud map according to the environmental changes.

[0275] In one embodiment, the navigation control unit controls the robot to return to the safe position according to the first optimal path, including:

[0276] During the process of the navigation control unit controlling the robot to return to the safe position according to the first optimal path, continuously monitoring the distance between the robot and the safe position;

[0277] According to the distance between the robot and the safe position, the robot is controlled to approach the safe position according to a first optimal path and a preset process.

[0278] In one embodiment, the dynamic environment adaptive navigation method applied to the central processing unit may further include:

[0279] When a change in the surrounding environment is detected, the current visual image data is matched with a pre-stored supermarket image dataset to obtain target image information on the shelf; image recognition is performed on the target image information, and robot-assisted positioning is performed based on the preset position information of the identified goods in the supermarket; the current visual image data is obtained by capturing the surrounding environment through an image acquisition device.

[0280] In one embodiment, a fusion positioning is performed based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot, including: outside the coverage range of the base station, positioning is performed using the positioning position obtained according to the nine-axis data; within the coverage range of the base station, the arrival angle positioning position obtained according to the measurement signal emitted by the electronic price tag unit is used to correct the nine-axis positioning position.

[0281] In one embodiment, the above-mentioned dynamic environment adaptive navigation method applied to the central processing unit may also include: when the nine-axis positioning position is located in an inaccessible shelf area, the nine-axis positioning position is corrected according to pre-established map information, and the nine-axis positioning position is corrected to the nearest reachable area.

[0282] In one embodiment, the dynamic environment adaptive navigation method applied to the central processing unit may further include:

[0283] Re-evaluate and verify the areas around the abnormal area that affect navigation, and reconstruct the point cloud map based on the re-evaluation and verification results.

[0284] The present invention also provides a dynamic environment adaptive navigation robot, as described in the following embodiments. Because the principles of this robot for solving problems are similar to those of the dynamic environment adaptive navigation method applied to robots, the implementation of this robot can refer to the implementation of the dynamic environment adaptive navigation method applied to robots, and any repetitions will not be repeated.

[0285] Figure 4FIG. 1 is a schematic diagram of the structure of a dynamic environment adaptive navigation robot according to an embodiment of the present invention. Figure 4 As shown, the robot includes:

[0286] LiDAR 01 is used to scan the surrounding environment, generate current point cloud data of the surrounding environment and send it to the central processing unit; capture environmental changes that have occurred since the last scan from abnormal areas, and reconstruct the point cloud map based on the environmental changes;

[0287] The electronic price tag unit 03 is used to send a measurement signal to the base station 06; the base station is used to determine the arrival angle based on the measurement signal and send the arrival angle to the arrival angle server 07, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle and return it to the central processing unit;

[0288] Nine-axis sensor 04 is used to measure the robot's nine-axis data and send it to the central processing unit;

[0289] The central processing unit 05 is configured to compare the current point cloud data with pre-generated supermarket point cloud map data. When the comparison results determine that the surrounding environment has changed, it marks an abnormal area on the map, evaluates the abnormal area, and determines the status of the abnormal area. When the evaluation results determine that the abnormal area is in a state where normal navigation cannot be achieved and requires immediate update, it performs fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain a first current positioning position of the robot; calls the last confirmed safe position in the historical positioning data, and determines a first optimal path from the first current positioning position back to the safe position;

[0290] The navigation control unit 02 is used to control the robot to return to the safe position according to the first optimal path; regenerate the navigation path according to the reconstructed point cloud map; and control the robot to continue to execute the task from the safe position according to the regenerated navigation path.

[0291] In one embodiment, performing fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot may include:

[0292] Get the robot's current position and velocity, as well as the covariance matrix of the position and velocity;

[0293] Using the acceleration and angular velocity data from the nine-axis sensor and the robot's motion equation, the robot's position and velocity at the next moment are predicted to obtain the current predicted state; based on the prediction error and noise model, the covariance matrix is ​​updated to obtain the uncertainty of the current predicted state;

[0294] Based on the current predicted state, the predicted observation value of the nine-axis sensor is calculated; the arrival angle positioning position is used as the actual observation value, and the difference between the actual observation value and the predicted observation value is calculated; according to the uncertainty of the current predicted state and the uncertainty of the actual measurement state, the weight of the arrival angle positioning position and the nine-axis positioning position in the final fusion result is dynamically adjusted;

[0295] According to the difference and the weight, the current position and speed of the robot are corrected to obtain the first current positioning position.

[0296] In one embodiment, evaluating the abnormal area and determining the status of the abnormal area may include:

[0297] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is lower than the first overlap rate threshold, or the deviation between the current positioning position of the robot and the expected position exceeds the navigation tolerance threshold, and the navigation path fails, the abnormal area is determined to be in a state where normal navigation cannot be achieved and needs to be updated immediately.

[0298] In one embodiment, the central processing unit is further configured to, when the abnormal area is determined to be in a state where an update is required but not immediately required based on the evaluation result, obtain current point cloud data generated by a laser radar scanning the surrounding environment; determine a second current positioning position of the robot based on the current point cloud data; and generate a second optimal path based on the second current positioning position;

[0299] The navigation control unit is further configured to control the robot to continue executing the task from the second current positioning position according to the second optimal path; after completing the task, control the robot to return to the abnormal area;

[0300] The above-mentioned lidar is also used to capture environmental changes that have occurred since the last scan from the abnormal area after completing the mission, and reconstruct the point cloud map based on the environmental changes.

[0301] In one embodiment, evaluating the abnormal area and determining the status of the abnormal area may include:

[0302] When any of the following sub-situations are met, and the changes in some areas exceed the change threshold but do not affect the overall navigation effect, the abnormal area is determined to be in a state where an update is required but not immediately:

[0303] Subcase 1: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0304] Subcase 2: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is less than the first overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0305] Subcase 3: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than the allowable boundary threshold;

[0306] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0307] In one embodiment, the central processing unit is further configured to send an instruction to the navigation control unit to continue normal navigation when it is determined based on the evaluation result that the abnormal area is in a state where normal navigation can be achieved and no update is required;

[0308] The navigation control unit is also used to continue controlling the robot to complete the task when receiving an instruction to continue normal navigation.

[0309] In one embodiment, evaluating the abnormal area and determining the status of the abnormal area may include:

[0310] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than a second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than an allowable boundary threshold, and the change in some areas does not exceed the change threshold, and the impact rate on the navigation path is lower than a preset impact rate threshold, the abnormal area is determined to be in a state where normal navigation can be achieved and no update is required;

[0311] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0312] In one embodiment, the central processing unit is further configured to, upon detecting that the robot has reached a safe position, use the arrival angle positioning position and the nine-axis positioning position to correct the safe position to obtain a corrected safe position; verify whether the current environment data is consistent with the preset data of the safe position, and when it is verified that the current environment data is inconsistent with the preset data of the safe position, initiate a map reconstruction instruction to the lidar;

[0313] In one embodiment, the laser radar is further used to rescan the area within the preset range of the safe position when receiving a map reconstruction instruction, and reconstruct the point cloud map according to environmental changes.

[0314] In one embodiment, the navigation control unit controls the robot to return to the safe location according to the first optimal path, which may include:

[0315] During the process of the navigation control unit controlling the robot to return to the safe position according to the first optimal path, continuously monitoring the distance between the robot and the safe position;

[0316] According to the distance between the robot and the safe position, the robot is controlled to approach the safe position according to a first optimal path and a preset process.

[0317] In one embodiment, the image acquisition device is further configured to acquire current visual image data of the surrounding environment;

[0318] The central processing unit is also used to match the current visual image data with a pre-stored supermarket image data set when a change in the surrounding environment is detected, to obtain target image information on the shelf; perform image recognition on the target image information, and perform robot-assisted positioning based on the preset position information of the identified goods in the supermarket.

[0319] In one embodiment, the electronic price label unit is further used to record the strength value of the base station response signal and the base station location information in real time during normal positioning;

[0320] The navigation control unit is also used to update and optimize the navigation path according to the strength value of the base station response signal and the base station location information to adapt to different environments and conditions.

[0321] In one embodiment, the electronic price tag unit is also used to interact with the smart electronic tags in the supermarket to obtain the location information of the current product bound to the smart electronic tag, and perform robot-assisted positioning based on the location information of the current product bound to the smart electronic tag.

[0322] In one embodiment, the first current positioning position of the robot is obtained by performing fusion positioning based on the arrival angle positioning position and the nine-axis data, which can include: positioning outside the coverage range of the base station using the positioning position obtained according to the nine-axis data; within the coverage range of the base station, using the arrival angle positioning position obtained according to the measurement signal emitted by the electronic price tag unit to correct the nine-axis positioning position.

[0323] In one embodiment, the central processing unit is further configured to correct the nine-axis positioning position according to pre-established map information when the nine-axis positioning position is located in an inaccessible shelf area, and correct the nine-axis positioning position to the nearest accessible area.

[0324] In one embodiment, the central processing unit is further configured to re-evaluate and verify the area around the abnormal area that affects navigation, and reconstruct the point cloud map based on the re-evaluation and verification results.

[0325] The present invention also provides a central processing unit for dynamic environment adaptive navigation, as described in the following embodiments. Because the principles underlying the problem solved by this central processing unit are similar to those of the dynamic environment adaptive navigation method applied to a robot, the implementation of this device can be referenced to the implementation of the dynamic environment adaptive navigation method applied to a robot, and any repetitions will not be repeated.

[0326] Figure 5 FIG. 1 is a schematic diagram of the structure of the central processing unit of the dynamic environment adaptive navigation according to an embodiment of the present invention. Figure 5 As shown, the central processing unit includes:

[0327] Comparison module 051 is used to compare the current point cloud data with pre-generated supermarket point cloud map data; the current point cloud data is sent by the laser radar, and the laser radar is used to scan the surrounding environment to generate the current point cloud data of the surrounding environment;

[0328] The marking module 052 is used to mark abnormal areas on the map when it is determined that the surrounding environment has changed according to the comparison results;

[0329] An evaluation module 053 is used to evaluate the abnormal area and determine the status of the abnormal area;

[0330] The fusion positioning module 054 is used to perform fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot when it is determined according to the evaluation result that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately; the arrival angle positioning position is sent by the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle, and the arrival angle is sent by the base station, and the base station is used to determine the arrival angle based on the measurement signal sent by the electronic price tag unit; the nine-axis data is sent by the nine-axis sensor, and the nine-axis sensor is used to measure the nine-axis data of the robot;

[0331] The optimal path determination module 055 is used to call the last confirmed safe position in the historical positioning data, determine the first optimal path from the first current positioning position to the safe position, and send it to the navigation control unit; the navigation control unit is used to control the robot to return to the safe position according to the first optimal path; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area, and reconstruct the point cloud map according to the environmental changes; the navigation path is regenerated according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position. The sea is used to: regenerate the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

[0332] In one embodiment, the fusion positioning module is specifically used to:

[0333] Get the robot's current position, speed and its uncertainty;

[0334] Using the nine-axis data and the robot motion equation, predict the robot's position, speed, and uncertainty at the next moment;

[0335] Use the arrival angle positioning position to correct the position, speed and uncertainty of the robot at the next moment;

[0336] The corrected position of the robot at the next moment is used as the first current positioning position.

[0337] In one embodiment, the above-mentioned evaluation module is also used to: when the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is lower than the first overlap rate threshold, or the deviation between the current positioning position of the robot and the expected position exceeds the navigation tolerance threshold, and the navigation path fails, determine that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately.

[0338] In one embodiment, the above-mentioned optimal path determination module is also used to: when it is determined according to the evaluation results that the abnormal area is in a state that needs to be updated but does not need to be updated immediately, obtain the current point cloud data generated by the laser radar scanning the surrounding environment; determine the second current positioning position of the robot based on the current point cloud data; generate a second optimal path based on the second current positioning position and send it to the navigation control unit; the navigation control unit is also used to control the robot to continue to execute the task from the second current positioning position according to the second optimal path; after completing the task, control the robot to return to the abnormal area; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area after completing the task, and reconstruct the point cloud map based on the environmental changes.

[0339] In one embodiment, the evaluation module is further configured to: determine that the abnormal area is in a state where an update is required but not immediately when any of the following sub-conditions are met and the change of a portion of the area exceeds a change threshold but does not affect the overall navigation effect:

[0340] Subcase 1: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0341] Subcase 2: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is less than the first overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold;

[0342] Subcase 3: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than the allowable boundary threshold;

[0343] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0344] In one embodiment, the central processing unit further includes:

[0345] The continue normal navigation instruction unit is used to send an instruction to continue normal navigation to the navigation control unit when it is determined according to the evaluation result that the abnormal area is in a state where normal navigation can be achieved and no update is required; the navigation control unit is also used to continue controlling the robot to complete the task when receiving the instruction to continue normal navigation.

[0346] In one embodiment, the evaluation module is further configured to:

[0347] When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than a second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than an allowable boundary threshold, and the change in some areas does not exceed the change threshold, and the impact rate on the navigation path is lower than a preset impact rate threshold, the abnormal area is determined to be in a state where normal navigation can be achieved and no update is required;

[0348] The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

[0349] In one embodiment, the central processing unit may further include: a correction unit for correcting the safe position using the arrival angle positioning position and the nine-axis positioning position when detecting that the robot has reached a safe position, to obtain a corrected safe position; a verification unit for verifying whether the current environmental data is consistent with the preset data of the safe position, and when verifying that the current environmental data is inconsistent with the preset data of the safe position, initiating a map reconstruction instruction to the laser radar; the laser radar is also used to rescan the area within the preset range of the safe position upon receiving the map reconstruction instruction, and reconstruct the point cloud map according to environmental changes.

[0350] In one embodiment, the navigation control unit is specifically configured to:

[0351] During the process of the navigation control unit controlling the robot to return to the safe position according to the first optimal path, continuously monitoring the distance between the robot and the safe position;

[0352] According to the distance between the robot and the safe position, the robot is controlled to approach the safe position according to a first optimal path and a preset process.

[0353] In one embodiment, the above-mentioned central processing unit also includes a visually assisted positioning unit, which is used to match the current visual image data with a pre-stored supermarket image data set when a change in the surrounding environment is detected, to obtain target image information on the shelf; perform image recognition on the target image information, and perform robot-assisted positioning based on the preset position information of the identified goods in the supermarket: wherein, the current visual image data is obtained by an image acquisition device capturing the surrounding environment.

[0354] In one embodiment, the electronic price tag unit is also used to record the strength value of the base station response signal and the base station location information in real time during normal positioning; the navigation control unit is also used to update and optimize the navigation path according to the strength value of the base station response signal and the base station location information to adapt to different environments and conditions.

[0355] In one embodiment, the electronic price tag unit is also used to interact with the smart electronic tags in the supermarket to obtain the location information of the current product bound to the smart electronic tag, and perform robot-assisted positioning based on the location information of the current product bound to the smart electronic tag.

[0356] In one embodiment, the fusion positioning module is specifically used to: outside the coverage range of the base station, use the positioning position obtained according to the nine-axis data for positioning; within the coverage range of the base station, use the arrival angle positioning position obtained according to the measurement signal emitted by the electronic price tag unit to correct the nine-axis positioning position.

[0357] In one embodiment, the above-mentioned central processing unit also includes: a correction unit, which is used to correct the nine-axis positioning position according to pre-established map information when the nine-axis positioning position is located in an inaccessible shelf area, and correct the nine-axis positioning position to the nearest accessible area.

[0358] In one embodiment, the central processing unit further includes: a reassessment and verification unit, configured to reassess and verify the area around the abnormal area that affects navigation, and reconstruct the point cloud map based on the reassessment and verification results.

[0359] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method of dynamic environment adaptive navigation when executing the computer program.

[0360] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for adaptive navigation in a dynamic environment is implemented.

[0361] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for adaptive navigation in a dynamic environment.

[0362] In an embodiment of the present invention, a solution for dynamic environment adaptive navigation is provided, through: a laser radar scans the surrounding environment to generate current point cloud data of the surrounding environment; a navigation control unit generates a navigation path according to the current point cloud data, and controls the robot to perform tasks according to the navigation path; an ESL unit sends a measurement signal to a base station; the base station is used to determine an arrival angle according to the measurement signal, and sends the arrival angle to an AOA server, and the AOA server is used to determine the AOA positioning position of the robot according to the arrival angle and return it to the central processing unit; a nine-axis sensor measures the nine-axis data of the robot and sends it to the central processing unit; when the central processing unit detects changes in the surrounding environment, it marks an abnormal area on the map; compares the current point cloud data with pre-generated supermarket point cloud map data; evaluates the abnormal area according to the comparison result, and determines the state of the abnormal area; after determining that the abnormal area is When navigation cannot be achieved normally and needs to be updated immediately, the nine-axis positioning position of the robot is determined according to the nine-axis data; the AOA positioning position and the nine-axis positioning position are fused and positioned to obtain the first current positioning position of the robot; the last position confirmed as safe in the historical positioning data is called to determine the first optimal path from the first current positioning position to the safe position; the navigation control unit controls the robot to return to the safe position according to the first optimal path; the laser radar rescans the abnormal area, captures the environmental changes that have occurred since the last scan from the abnormal area, and reconstructs the point cloud map according to the environmental changes; the navigation control unit regenerates the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position, thereby realizing adaptive navigation in a dynamic environment and improving the navigation efficiency and accuracy of the robot.

[0363] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0364] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0365] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0366] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0367] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for adaptive navigation in a dynamic environment, characterized in that: The method is applied to a robot, and the method comprises: The laser radar scans the surrounding environment, generates the current point cloud data of the surrounding environment and sends it to the central processing unit; The electronic price tag unit sends a measurement signal to the base station; the base station is used to determine the arrival angle based on the measurement signal and send the arrival angle to the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle and return it to the central processing unit; The nine-axis sensor measures the robot's nine-axis data and sends it to the central processing unit; The central processing unit compares the current point cloud data with pre-generated supermarket point cloud map data. When the comparison results determine that the surrounding environment has changed, it marks an abnormal area on the map, evaluates the abnormal area, and determines the status of the abnormal area. When the evaluation results determine that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately, it performs fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the robot's first current positioning position; calls the last confirmed safe position in the historical positioning data, and determines the first optimal path from the first current positioning position to the safe position; The navigation control unit controls the robot to return to the safe position according to the first optimal path; The lidar captures environmental changes that have occurred in abnormal areas since the last scan and reconstructs a point cloud map based on the environmental changes; The navigation control unit regenerates the navigation path according to the reconstructed point cloud map; based on the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

2. The method according to claim 1, wherein Performing fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot includes: Get the robot's current position and velocity, as well as the covariance matrix of the position and velocity; Using the acceleration and angular velocity data from the nine-axis sensor and the robot's motion equation, the robot's position and velocity at the next moment are predicted to obtain the current predicted state; based on the prediction error and noise model, the covariance matrix is ​​updated to obtain the uncertainty of the current predicted state; Based on the current predicted state, the predicted observation value of the nine-axis sensor is calculated; the arrival angle positioning position is used as the actual observation value, and the difference between the actual observation value and the predicted observation value is calculated; according to the uncertainty of the current predicted state and the uncertainty of the actual measurement state, the weight of the arrival angle positioning position and the nine-axis positioning position in the final fusion result is dynamically adjusted; According to the difference and the weight, the current position and speed of the robot are corrected to obtain the first current positioning position.

3. The method according to claim 1, wherein Evaluating the abnormal area and determining the status of the abnormal area includes: When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is lower than the first overlap rate threshold, or the deviation between the current positioning position of the robot and the expected position exceeds the navigation tolerance threshold, and the navigation path fails, the abnormal area is determined to be in a state where normal navigation cannot be achieved and needs to be updated immediately.

4. The method according to claim 3, wherein Also includes: When the central processing unit determines, based on the evaluation result, that the abnormal area is in a state where an update is required but not immediately, it obtains current point cloud data generated by the laser radar scanning the surrounding environment; determines a second current positioning position of the robot based on the current point cloud data; and generates a second optimal path based on the second current positioning position; The navigation control unit controls the robot to continue executing the task from the second current positioning position according to the second optimal path; after completing the task, the navigation control unit controls the robot to return to the abnormal area; After completing its mission, the lidar captures environmental changes that have occurred in the abnormal area since the last scan and reconstructs a point cloud map based on the environmental changes.

5. The method according to claim 4, wherein Evaluating the abnormal area and determining the status of the abnormal area includes: When any of the following sub-situations are met, and the changes in some areas exceed the change threshold but do not affect the overall navigation effect, the abnormal area is determined to be in a state where an update is required but not immediately: Subcase 1: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold; Subcase 2: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is less than the first overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than or equal to the navigation tolerance threshold and greater than or equal to the allowable boundary threshold; Subcase 3: The overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than or equal to the first overlap rate threshold and less than or equal to the second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than the allowable boundary threshold; The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

6. The method according to claim 3, wherein Also includes: When the central processing unit determines, based on the evaluation result, that the abnormal area is in a state where normal navigation can be achieved and no update is required, it sends an instruction to the navigation control unit to continue normal navigation; The navigation control unit continues to control the robot to complete the task when receiving the instruction to continue normal navigation.

7. The method according to claim 6, wherein Evaluating the abnormal area and determining the status of the abnormal area includes: When the overlap rate between the current point cloud data and the pre-established supermarket point cloud map data is greater than a second overlap rate threshold, and the deviation between the robot's current positioning position and the expected position is less than an allowable boundary threshold, and the change in some areas does not exceed the change threshold, and the impact rate on the navigation path is lower than a preset impact rate threshold, the abnormal area is determined to be in a state where normal navigation can be achieved and no update is required; The first overlap rate threshold is smaller than the second overlap rate threshold, and the allowable boundary threshold is smaller than the navigation tolerance threshold.

8. The method according to claim 1, wherein Also includes: When the central processing unit detects that the robot has reached a safe position, it uses the arrival angle positioning position and the nine-axis positioning position to correct the safe position to obtain the corrected safe position; it verifies whether the current environment data is consistent with the preset data of the safe position. If it is verified that the current environment data is inconsistent with the preset data of the safe position, it initiates a map reconstruction command to the lidar; When the laser radar receives the map reconstruction instruction, it rescans the area within the preset range of the safe position and reconstructs the point cloud map according to the environmental changes.

9. The method according to claim 1, wherein The navigation control unit controls the robot to return to the safe position according to the first optimal path, including: During the process of the navigation control unit controlling the robot to return to the safe position according to the first optimal path, continuously monitoring the distance between the robot and the safe position; According to the distance between the robot and the safe position, the robot is controlled to approach the safe position according to a first optimal path and a preset process.

10. The method according to claim 1, wherein Also includes: The image acquisition device acquires current visual image data of the surrounding environment; When the central processing unit detects changes in the surrounding environment, it matches the current visual image data with the pre-stored supermarket image data set to obtain the target image information on the shelf; it performs image recognition on the target image information and performs robot-assisted positioning based on the preset location information of the identified goods in the supermarket.

11. The method according to claim 1, wherein Also includes: The electronic price tag unit records the strength value of the base station response signal and the base station location information in real time during normal positioning; The navigation control unit updates and optimizes the navigation path according to the strength value of the base station response signal and the base station location information to adapt to different environments and conditions.

12. The method according to claim 1, wherein Also includes: The electronic price tag unit interacts with the smart electronic tags in the supermarket to obtain the location information of the current product bound to the smart electronic tag, and performs robot-assisted positioning based on the location information of the current product bound to the smart electronic tag.

13. The method according to claim 1, wherein The robot's first current positioning position is obtained by fusing the arrival angle positioning position and the nine-axis data, including: positioning outside the coverage range of the base station using the positioning position obtained according to the nine-axis data; within the coverage range of the base station, the nine-axis positioning position is corrected using the arrival angle positioning position obtained according to the measurement signal emitted by the electronic price tag unit.

14. The method according to claim 1, wherein Also includes: When the nine-axis positioning position is located in an inaccessible shelf area, the nine-axis positioning position is corrected according to the pre-established map information and the nine-axis positioning position is corrected to the nearest accessible area.

15. The method according to claim 1, wherein Also includes: The central processing unit re-evaluates and verifies the area around the abnormal area that affects navigation, and reconstructs the point cloud map based on the re-evaluation and verification results.

16. A method for adaptive navigation in a dynamic environment, characterized in that: The method is applied to a central processing unit and comprises: Compare the current point cloud data with pre-generated supermarket point cloud map data; the current point cloud data is sent by a laser radar, which is used to scan the surrounding environment and generate the current point cloud data of the surrounding environment; When the surrounding environment is determined to have changed based on the comparison results, the abnormal area on the map is marked; evaluating the abnormal area and determining a status of the abnormal area; When it is determined according to the evaluation results that the abnormal area is in a state where navigation cannot be normally achieved and needs to be updated immediately, the first current positioning position of the robot is obtained by fusion positioning based on the arrival angle positioning position and the nine-axis data; the arrival angle positioning position is sent by the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle, and the arrival angle is sent by the base station, and the base station is used to determine the arrival angle based on the measurement signal sent by the electronic price tag unit; the nine-axis data is sent by the nine-axis sensor, and the nine-axis sensor is used to measure the nine-axis data of the robot; The last position confirmed as safe in the historical positioning data is called, and the first optimal path from the first current positioning position back to the safe position is determined and sent to the navigation control unit; the navigation control unit is used to control the robot to return to the safe position according to the first optimal path; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area, and reconstruct the point cloud map according to the environmental changes; the navigation path is regenerated according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position. The sea is used to: regenerate the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

17. A robot capable of adaptive navigation in a dynamic environment, characterized in that: include: LiDAR is used to scan the surrounding environment, generate current point cloud data of the surrounding environment and send it to the central processing unit; capture environmental changes that have occurred since the last scan from abnormal areas, and reconstruct the point cloud map based on the environmental changes; The electronic price tag unit is used to send a measurement signal to a base station; the base station is used to determine the arrival angle based on the measurement signal and send the arrival angle to the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle and return it to the central processing unit; Nine-axis sensor, used to measure the robot's nine-axis data and send it to the central processing unit; The central processing unit is configured to compare the current point cloud data with pre-generated supermarket point cloud map data; when it is determined based on the comparison results that the surrounding environment has changed, mark abnormal areas on the map, evaluate the abnormal areas, and determine the status of the abnormal areas; when it is determined based on the evaluation results that the abnormal areas are in a state where normal navigation cannot be achieved and an immediate update is required, perform fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain a first current positioning position of the robot; call the last position confirmed as safe in the historical positioning data, and determine a first optimal path from the first current positioning position back to the safe position; A navigation control unit is used to control the robot to return to the safe position according to the first optimal path; regenerate the navigation path according to the reconstructed point cloud map; and control the robot to continue to execute the task from the safe position according to the regenerated navigation path.

18. A central processing unit for adaptive navigation in a dynamic environment, characterized in that: include: A comparison module is used to compare the current point cloud data with pre-generated supermarket point cloud map data; the current point cloud data is sent by the laser radar, and the laser radar is used to scan the surrounding environment to generate the current point cloud data of the surrounding environment; A marking module is used to mark abnormal areas on the map when the surrounding environment is determined to have changed according to the comparison results; An evaluation module, configured to evaluate the abnormal area and determine a state of the abnormal area; The fusion positioning module is used to perform fusion positioning based on the arrival angle positioning position and the nine-axis data to obtain the first current positioning position of the robot when it is determined according to the evaluation results that the abnormal area is in a state where normal navigation cannot be achieved and needs to be updated immediately; the arrival angle positioning position is sent by the arrival angle server, and the arrival angle server is used to determine the arrival angle positioning position of the robot based on the arrival angle, and the arrival angle is sent by the base station, and the base station is used to determine the arrival angle based on the measurement signal sent by the electronic price tag unit; the nine-axis data is sent by the nine-axis sensor, and the nine-axis sensor is used to measure the nine-axis data of the robot; An optimal path determination module is used to call the last confirmed safe position in the historical positioning data, determine the first optimal path from the first current positioning position to the safe position, and send it to the navigation control unit; the navigation control unit is used to control the robot to return to the safe position according to the first optimal path; the laser radar is also used to capture environmental changes that have occurred since the last scan from the abnormal area, and reconstruct the point cloud map according to the environmental changes; the navigation path is regenerated according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position. The sea is used to: regenerate the navigation path according to the reconstructed point cloud map; according to the regenerated navigation path, the robot is controlled to continue to execute the task from the safe position.

19. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 16 is implemented.

20. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 16 is implemented.

21. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 16 is implemented.

Images