An intelligent robot control system, method and device based on artificial intelligence

Abstract

The present invention discloses an intelligent robot control system, method and device based on artificial intelligence, which relate to the field of intelligent robot control technology. The article storage module comprises a storage user identification unit, a storage information input unit, an article storage volume verification unit and an article storage weight verification unit; the central control module comprises a route planning unit, a first delivery time prediction unit, an operation early warning unit, a comprehensive abnormality analysis unit and a processing time prediction unit; the object taking module comprises a taking out user identification unit, an in-cabin weight verification unit and an article taking out photography unit; the distribution progress and potential problems can be understood in time, so as to take appropriate countermeasures and adjust the distribution plan according to the real-time situation.

Description

Technical Field

[0001] The present invention relates to the field of intelligent robot control technology, and in particular to an intelligent robot control system, method and device based on artificial intelligence. Background Art

[0002] Traditional hotel delivery services usually rely on manual delivery, which has problems such as low delivery efficiency, high labor costs, and difficulty in accurately controlling delivery time. At the same time, with the diversification of customer needs, hotels need to provide more personalized and flexible services, which further increases the difficulty of delivery services. With the rapid development of artificial intelligence technology, intelligent robots have been introduced into hotel delivery services as a new service means. Intelligent robots have advanced functions such as autonomous navigation, voice recognition, and face recognition. They can complete delivery tasks independently, greatly improving delivery efficiency and accuracy. At the same time, intelligent robots can also provide personalized services according to customer needs, such as scheduled delivery, voice interaction, etc., meeting customers' needs for diversified and personalized services.

[0003] In the Chinese invention application with application publication number CN113537534A, a robot delivery method and device are disclosed, including: receiving a delivery task; obtaining a delivery path and an estimated delivery time according to the delivery task; obtaining target information according to the delivery path; determining the in-transit time of the robot when performing the delivery task according to the target information; determining the start time of the robot's delivery according to the estimated delivery time and the in-transit time;

[0004] In the above invention application, the scheduled delivery time is obtained from the consignee corresponding to the delivery task, the in-transit time of the robot when performing the delivery task is determined, and the start delivery time of the robot is determined based on the scheduled delivery time and the in-transit time, so as to try to ensure that the robot can appear at the receiving location on time when the scheduled delivery time arrives. However, the in-transit time of the intelligent robot during the delivery process is not fixed. Due to the influence of emergencies, such as the tire being entangled by foreign objects and unable to continue to operate, the robot tilting or even overturning due to failure to avoid obstacles in time, the delivery time will be extended accordingly when encountering emergencies. If only normal situations are considered without considering emergencies, the delivery plan lacks flexibility. Once an unexpected event occurs, the entire delivery system may be seriously affected, resulting in delivery delays or failures, thereby reducing the trust and satisfaction with the delivery service.

[0005] To this end, the present invention provides an intelligent robot control system, method and device based on artificial intelligence. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the shortcomings of the prior art, the present invention provides an intelligent robot control system, method and device based on artificial intelligence. The present invention obtains the tire abnormality index by deeply analyzing the operation data of the intelligent robot. , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormality coefficient Zx of the intelligent robot, which can accurately locate the fault source of the intelligent robot, such as tire abnormality, hardware abnormality or drive motor abnormality, provide a clear direction for subsequent fault repair and maintenance, improve the efficiency and accuracy of fault handling, consider multiple aspects of fault factors, and quantify the degree of fault evaluation.

[0008] And based on the comprehensive abnormality coefficient Zx, the intervention processing time of the intelligent robot is predicted, and the second delivery time of the intelligent robot to each delivery location is calculated. , sending out delivery timeout warnings can timely understand the delivery progress and potential problems, so as to take appropriate countermeasures and adjust the delivery plan according to the real-time situation, thereby solving the technical problems recorded in the background technology.

[0009] (II) Technical solution

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent robot control system based on artificial intelligence, comprising:

[0011] The item storage module includes a storage user identification unit, a storage information input unit, an item storage volume verification unit, and an item storage weight verification unit; the storage user identification unit is used to identify and record the user who needs to perform storage operations; the storage information input unit is used to input the storage space of the item, the location information of the item delivery, and the item storage image; the item storage volume verification unit is used to verify whether the volume of the stored item can be placed in the corresponding space, and issue a corresponding storage volume abnormality warning; the item storage weight verification unit is used to verify whether the intelligent robot space for the stored item can bear the weight, and issue a corresponding storage weight abnormality warning;

[0012] The central control module includes a route planning unit, a first delivery time prediction unit, an operation warning unit, a comprehensive abnormality analysis unit and a processing time prediction unit; the route planning unit is used to plan the delivery path of the intelligent robot; the first delivery time prediction unit analyzes the first delivery time of the intelligent robot to each delivery location based on the path planned by the route planning unit The operation warning unit is used to monitor the intelligent robot during the delivery process, analyze the intelligent robot operation abnormality index Qy, and issue an operation abnormality warning; the comprehensive abnormality analysis unit is used to deeply analyze the intelligent robot operation data after receiving the operation abnormality warning to obtain the tire abnormality index , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormal coefficient Zx of the intelligent robot; the processing time prediction unit predicts the intervention processing time of the intelligent robot based on the comprehensive abnormal coefficient Zx, and calculates the second delivery time of the intelligent robot to each delivery location , send out delivery timeout warning;

[0013] The item retrieval module includes an item retrieval user identification unit, an in-cabin weight verification unit and an item retrieval photography unit; the item retrieval user identification unit is used to identify and record the user who needs to perform the item retrieval operation; the in-cabin weight verification unit is used to verify the in-cabin weight of the intelligent robot cabin after the item retrieval is completed, and remind the user to continue to retrieve the item; the item retrieval photography unit is used to collect and record the image of the item taken out.

[0014] Furthermore, user identity recognition is performed by collecting and storing the user's facial image or video stream through a camera, and importing it into an official facial recognition system to determine and record the stored user's identity information. If the stored user's identity information fails to be recognized, the item storage process is terminated.

[0015] Furthermore, after storing the user identity information record, the available status of the intelligent robot's cabin is identified, and after the available cabin is output to the display screen, the storage cabin and the delivery location are selected through the display screen, and the image of the stored items is captured through the camera. If the available cabin is 0, the item storage function is closed and a delivery request is sent to the central control module.

[0016] Furthermore, after the item storage space and the delivery location are input, the corresponding storage space door is opened, the item is placed in the corresponding storage space and the door is closed. After the door is closed, a pop-up message appears on the display screen asking whether the volume can be accommodated. If yes is selected, the volume verification of the stored item is passed. If no is selected, the volume verification of the stored item fails, and the item storage process ends.

[0017] Furthermore, after the volume of the deposited items has been verified, the gravity sensor installed in the corresponding cabin is used to detect the weight of the items to determine whether the weight of the items exceeds the maximum weight threshold of the corresponding cabin. If it exceeds the maximum weight threshold, the weight verification of the deposited items has failed, an overweight warning is issued, the cabin door is opened, and the item storage process ends. If it does not exceed the maximum weight threshold, the weight verification of the deposited items has passed, the weight of the deposited items is recorded, and the status of the corresponding cabin is changed to in use.

[0018] Among them, the maximum weight threshold is determined by load safety testing.

[0019] Furthermore, after receiving the delivery request, the starting position of the intelligent robot is obtained using GPS, the distance between the starting position of the robot and multiple delivery locations is analyzed, and the Dijkstra algorithm is used to plan the optimal delivery path of the intelligent robot.

[0020] Furthermore, the shortest path from the starting point to all delivery locations is obtained, and the horizontal distance of the path from the starting point to the first delivery location of the intelligent robot is extracted. and floor change number , the horizontal distance from the first delivery position to the second delivery position and floor change number Repeat the above operation until the horizontal distance from the n-1th delivery position to the nth delivery position is obtained. and floor change number .

[0021] Furthermore, the historical delivery records of the intelligent robot are obtained, including the start time of delivery, the time to reach the elevator, the time to take the elevator, the time to get off the elevator, the arrival time, and the time to complete the retrieval. After sorting, the average speed of intelligent robot delivery Pj, the average elevator waiting time Dp, and the average ride time for each floor change are obtained. And the average retrieval time Qw.

[0022] Furthermore, the horizontal distance of the intelligent robot from the starting point to all delivery locations and the number of floors changed are obtained, combined with the average delivery speed Pj of the intelligent robot, the average waiting time Dp of the elevator, and the average riding time for each number of floors changed. and the average pickup time Qw, calculate the first delivery time of the intelligent robot to each delivery location :

[0023]

[0024] Among them, n represents the cabin number of the intelligent robot, and a represents the number of floors changed.

[0025] Furthermore, the target speed of each tire is extracted from the intelligent robot driving instructions. The speed sensor is used to detect the actual speed of each tire of the intelligent robot in real time. The Tilt Sensor detects the angle between the intelligent robot and the ground in real time. , after linear normalization processing, the intelligent robot operation abnormality index Qy is calculated:

[0026]

[0027] Among them, b represents the sequence number of each tire of the intelligent robot, is the critical tipping angle of the intelligent robot;

[0028] When the intelligent robot's operation abnormality index Qy is less than 0, an operation abnormality warning is issued.

[0029] Furthermore, after receiving the abnormal operation warning, the operation data of each drive motor of the intelligent robot is obtained, including the current ,Voltage and temperature , analyze and obtain the hardware abnormality index of each drive motor :

[0030]

[0031] Wherein, c is the sequential number of each drive motor;

[0032] When the hardware abnormality index of the drive motor Greater than 2 When , the drive motor is considered abnormal, and the number of abnormal drive motors Gd is counted; The abnormality index of all drive motor hardware The mean of .

[0033] Further, the target speed of each tire is obtained and actual speed , analyze and obtain the abnormality index of each tire of the intelligent robot :

[0034]

[0035] When the tire abnormality index When it is less than 0, the tire is considered abnormal, and the number of abnormal tires Lg is counted.

[0036] Further, obtain the tire abnormality index , number of abnormal tires Lg, hardware abnormality index And the number of abnormal drive motors Gd, calculate the comprehensive abnormal coefficient Zx of the intelligent robot:

[0037]

[0038] The calculation formula of the corresponding intelligent robot's comprehensive abnormality coefficient Zx is as above.

[0039] Furthermore, the first delivery time of the intelligent robot arriving at each delivery location is obtained. And the predicted intervention processing time Tgc, calculate the second delivery time of the intelligent robot to each delivery location :

[0040]

[0041] when If it exceeds 1 hour, a delivery timeout warning will be sent out.

[0042] An intelligent robot control method based on artificial intelligence comprises the following steps:

[0043] S11, identifying and recording the user who needs to perform storage operations;

[0044] S12, input the storage space of the item, the location information of the item being delivered and the item storage image;

[0045] S13, verify whether the volume of the stored items can be placed in the corresponding compartment, and issue a corresponding warning of abnormal storage volume;

[0046] S14, verify whether the intelligent robot compartment can bear the weight of the stored items, and issue a corresponding warning of abnormal stored weight;

[0047] S21. Plan the delivery path of the intelligent robot;

[0048] S22: Analyze the first delivery time of the intelligent robot to each delivery location based on the path planned by the route planning unit ;

[0049] S23. Monitor the intelligent robot during its delivery process, analyze the intelligent robot's abnormal operation index Qy, and issue an abnormal operation warning;

[0050] S24. After receiving the abnormal operation warning, the intelligent robot operation data is deeply analyzed to obtain the tire abnormality index , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormal coefficient Zx of the intelligent robot;

[0051] S25. Predict the intervention processing time of the intelligent robot based on the comprehensive abnormality coefficient Zx, and calculate the second delivery time of the intelligent robot to each delivery location , send out delivery timeout warning;

[0052] S31, identifying and recording the user who needs to perform the object-taking operation;

[0053] S32, verifying the weight of the intelligent robot cabin after the object is taken, and reminding the user to continue taking objects;

[0054] S33, collecting and recording the image of the taken-out object.

[0055] An intelligent robot control device based on artificial intelligence is characterized by comprising an item storage module, a central control module and an item picking module.

[0056] (III) Beneficial effects

[0057] The present invention provides an intelligent robot control system, method and device based on artificial intelligence, which has the following beneficial effects:

[0058] 1. By judging whether the weight of the items exceeds the maximum weight threshold of the corresponding cabin, if it exceeds the maximum weight threshold, the weight verification of the stored items fails, and an overweight storage warning is issued to ensure that the intelligent robot cabin can withstand the weight of the stored items, avoid structural damage or collapse, extend its service life, and reduce safety risks during transportation.

[0059] 2. In-depth analysis of the intelligent robot's operating data to obtain the tire abnormality index , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormality coefficient Zx of the intelligent robot, which can accurately locate the fault source of the intelligent robot, such as tire abnormality, hardware abnormality or drive motor abnormality, provide a clear direction for subsequent fault repair and maintenance, improve the efficiency and accuracy of fault handling, consider multiple aspects of fault factors, and quantify the degree of fault evaluation.

[0060] 3. Predict the intervention processing time of the intelligent robot based on the comprehensive abnormality coefficient Zx, and calculate the second delivery time of the intelligent robot to each delivery location , sending out delivery timeout warnings, so that you can timely understand the delivery progress and potential problems, so as to take appropriate countermeasures and adjust the delivery plan according to the real-time situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a schematic diagram of the structure of an intelligent robot control system based on artificial intelligence of the present invention;

[0062] Figure 2 A schematic diagram of a flow chart of an intelligent robot control method based on artificial intelligence of the present invention;

[0063] Figure 3 The present invention is a schematic structural diagram of an intelligent robot control device based on artificial intelligence. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] See also Figure 1 The present invention provides an intelligent robot control system based on artificial intelligence, comprising:

[0066] The item storage module includes a storage user identification unit, a storage information input unit, an item storage volume verification unit, and an item storage weight verification unit; the storage user identification unit is used to identify and record the user who needs to perform storage operations; the storage information input unit is used to input the storage space of the item, the location information of the item delivery, and the item storage image; the item storage volume verification unit is used to verify whether the volume of the stored item can be placed in the corresponding space, and issue a corresponding storage volume abnormality warning; the item storage weight verification unit is used to verify whether the intelligent robot space for the stored item can bear the weight, and issue a corresponding storage weight abnormality warning;

[0067] User identity recognition collects and stores the user's facial image or video stream through the camera, imports it into the official facial recognition system to determine and record the stored user's identity information. If the stored user's identity information fails to be recognized, the item storage process ends.

[0068] After storing the user identity information record, the available status of the intelligent robot's cabin is identified, and after the available cabin is output to the display screen, the storage cabin and the delivery location are selected through the display screen, and the image of the stored items is captured through the camera. If the available cabin is 0, the item storage function is closed and a delivery request is sent to the central control module.

[0069] After the item storage space and delivery location are entered, the corresponding storage space door is opened, the item is placed in the corresponding storage space and the door is closed. After the door is closed, a pop-up message will pop up on the display screen asking whether the volume can be accommodated. If yes is selected, the volume verification of the stored item is passed. If no is selected, the volume verification of the stored item fails, and the item storage process ends.

[0070] After the volume of the deposited items is verified, the gravity sensor installed in the corresponding cabin is used to detect the weight of the items to determine whether the weight of the items exceeds the maximum weight threshold of the corresponding cabin. If it exceeds the maximum weight threshold, the weight verification of the deposited items fails, an overweight warning is issued, the cabin door is opened, and the item storage process ends. If it does not exceed the maximum weight threshold, the weight verification of the deposited items passes, the weight of the deposited items is recorded, and the status of the corresponding cabin is changed to in use.

[0071] Among them, the maximum weight threshold is determined by load safety testing.

[0072] By judging whether the weight of the items exceeds the maximum weight threshold of the corresponding cabin, if it exceeds the maximum weight threshold, the weight verification of the stored items will fail, and an overweight storage warning will be issued to ensure that the intelligent robot cabin can withstand the weight of the stored items, avoid structural damage or collapse, extend its service life, and reduce safety risks during transportation.

[0073] The central control module includes a route planning unit, a first delivery time prediction unit, an operation warning unit, a comprehensive abnormality analysis unit and a processing time prediction unit; the route planning unit is used to plan the delivery path of the intelligent robot; the first delivery time prediction unit analyzes the first delivery time of the intelligent robot to each delivery location based on the path planned by the route planning unit The operation warning unit is used to monitor the intelligent robot during the delivery process, analyze the intelligent robot operation abnormality index Qy, and issue an operation abnormality warning; the comprehensive abnormality analysis unit is used to deeply analyze the intelligent robot operation data after receiving the operation abnormality warning to obtain the tire abnormality index , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormal coefficient Zx of the intelligent robot; the processing time prediction unit predicts the intervention processing time of the intelligent robot based on the comprehensive abnormal coefficient Zx, and calculates the second delivery time of the intelligent robot to each delivery location , sending out delivery timeout warnings.

[0074] After receiving the delivery request, use GPS to obtain the starting position of the intelligent robot, analyze the distance between the robot's starting position and multiple delivery locations, and use the Dijkstra algorithm to plan the optimal delivery path for the intelligent robot.

[0075] The Dijkstra algorithm is a single-source shortest path problem. By continuously updating the shortest path from the starting point to each delivery location, the shortest path from the starting point to all delivery locations is finally obtained.

[0076] Get the shortest path from the starting point to all delivery locations, and extract the horizontal distance of the path from the starting point to the first delivery location of the intelligent robot and floor change number , the horizontal distance from the first delivery position to the second delivery position and floor change number Repeat the above operation until the horizontal distance from the n-1th delivery position to the nth delivery position is obtained. and floor change number .

[0077] Get the intelligent robot's historical delivery records, including the start time of delivery, the time to reach the elevator, the time to take the elevator, the time to get off the elevator, the arrival time, and the time to complete the pickup. After sorting, get the average speed of intelligent robot delivery Pj, the average elevator waiting time Dp, and the average ride time for each floor change And the average retrieval time Qw.

[0078] Get the horizontal distance of the intelligent robot's path from the starting point to all delivery locations and the number of floors changed, combined with the average delivery speed Pj of the intelligent robot, the average elevator waiting time Dp, and the average ride time for each number of floors changed and the average pickup time Qw, calculate the first delivery time of the intelligent robot to each delivery location :

[0079]

[0080] Among them, n represents the cabin number of the intelligent robot, and a represents the number of floors changed.

[0081] Extract the target speed of each tire from the intelligent robot drive instructions The speed sensor is used to detect the actual speed of each tire of the intelligent robot in real time. The Tilt Sensor detects the angle between the intelligent robot and the ground in real time. , after linear normalization processing, the intelligent robot operation abnormality index Qy is calculated:

[0082]

[0083] Among them, b represents the sequence number of each tire of the intelligent robot, is the critical angle of the intelligent robot's tipping over. The robot is controlled to walk on a slope experimental platform with an adjustable slope, and the slope gradient is gradually increased until the robot tips over while walking on the slope. The slope angle at this time is the critical angle of the robot's tipping over.

[0084] When the intelligent robot operation abnormality index Qy is less than 0, an operation abnormality warning is issued to the outside, indicating that the current intelligent robot operation is abnormal and manual intervention is required.

[0085] After receiving the abnormal operation warning, obtain the operation data of each drive motor of the intelligent robot, including current ,Voltage and temperature , analyze and obtain the hardware abnormality index of each drive motor :

[0086]

[0087] Among them, c is the serial number of each drive motor, current The voltage is obtained by detecting the current sensor. The temperature is detected by the voltage sensor. Obtained through temperature sensor detection.

[0088] When the hardware abnormality index of the drive motor Greater than 2 When , the drive motor is considered abnormal, and the number of abnormal drive motors Gd is counted. The abnormality index of all drive motor hardware The mean of .

[0089] Get the target speed of each tire and actual speed , analyze and obtain the abnormality index of each tire of the intelligent robot :

[0090]

[0091] When the tire abnormality index When it is less than 0, the tire is considered abnormal, and the number of abnormal tires Lg is counted.

[0092] Get tire abnormality index , number of abnormal tires Lg, hardware abnormality index And the number of abnormal drive motors Gd, calculate the comprehensive abnormal coefficient Zx of the intelligent robot:

[0093]

[0094] In-depth analysis of intelligent robot operation data to obtain tire abnormality index , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormality coefficient Zx of the intelligent robot, which can accurately locate the fault source of the intelligent robot, such as tire abnormality, hardware abnormality or drive motor abnormality, provide a clear direction for subsequent fault repair and maintenance, improve the efficiency and accuracy of fault handling, consider multiple aspects of fault factors, and quantify the degree of fault evaluation.

[0095] Obtain the historical intervention records of the intelligent robot, including the comprehensive abnormality coefficient and intervention processing time of each intervention in the intelligent robot, build an intervention processing time prediction model for the intelligent robot based on the vector regression model, and output the intervention processing time prediction model after sample data training and testing. Use the intervention processing time prediction model to predict the intervention processing time of the intelligent robot, and obtain the predicted intervention processing time Tgc under the current comprehensive abnormality coefficient conditions.

[0096] The sample code of the intelligent robot's intervention processing time prediction model is as follows:

[0097] from sklearn.model_selection import train_test_split

[0098] from sklearn.linear_model import LinearRegression

[0099] from sklearn.metrics import mean_squared_error, r2_score

[0100] import pandas as pd

[0101] # Assume we have a DataFrame named df, which contains two columns: 'anomaly_coefficient' (comprehensive anomaly coefficient) and 'intervention_time' (intervention treatment time)

[0102] # df = pd.read_csv('your_data.csv')# Read data

[0103] # Split features and target variables

[0104] X = df['anomaly_coefficient'].values.reshape(-1, 1) # Features need to be a two-dimensional array

[0105] y = df['intervention_time'].values

[0106] # Divide into training set and test set

[0107] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

[0108] # Create and train the model

[0109] model = LinearRegression()

[0110] model.fit(X_train, y_train)

[0111] # Predict test set

[0112] y_pred = model.predict(X_test)

[0113] # Evaluate the model

[0114] mse = mean_squared_error(y_test, y_pred)

[0115] r2 = r2_score(y_test, y_pred)

[0116] print(f'Mean Squared Error: {mse}')

[0117] print(f'R² Score: {r2}')

[0118] # Use the model to make predictions (input new comprehensive anomaly coefficient)

[0119] new_anomaly_coefficient = [...] # Replace with the comprehensive anomaly coefficient you want to predict

[0120] new_prediction = model.predict(new_anomaly_coefficient.reshape(-1,1))

[0121] print(f'Predicted intervention time: {new_prediction[0]}')

[0122] Get the first delivery time of the intelligent robot arriving at each delivery location And the predicted intervention processing time Tgc, calculate the second delivery time of the intelligent robot to each delivery location :

[0123]

[0124] when If it exceeds 1 hour, a delivery timeout warning will be sent out and the cabin will be opened to switch to manual delivery.

[0125] According to the comprehensive abnormality coefficient Zx, the intervention processing time of the intelligent robot is predicted, and the second delivery time of the intelligent robot to each delivery location is calculated. , sending out delivery timeout warnings, so that you can timely understand the delivery progress and potential problems, so as to take appropriate countermeasures and adjust the delivery plan according to the real-time situation.

[0126] The item retrieval module includes an item retrieval user identification unit, an in-cabin weight verification unit and an item retrieval photography unit; the item retrieval user identification unit is used to identify and record the user who needs to perform the item retrieval operation; the in-cabin weight verification unit is used to verify the in-cabin weight of the intelligent robot cabin after retrieval, and remind the user to continue retrieval; the item retrieval photography unit is used to collect and record the image of the item retrieval.

[0127] The gravity sensor installed in the corresponding cabin is used to detect the weight of the items in the intelligent robot cabin after picking up the items, and determine whether the weight in the cabin has returned to 0 after picking up the items. If it has not returned to 0, the weight verification of the picked-up items has failed, and a reminder to continue picking up the items is sent out. If the weight in the cabin has returned to 0, the weight verification of the picked-up items has passed, the picking process ends, and the corresponding cabin status is changed to idle.

[0128] See also Figure 2 The present invention provides an intelligent robot control method based on artificial intelligence, comprising the following steps:

[0129] S11, identifying and recording the user who needs to perform storage operations;

[0130] S12, input the storage space of the item, the location information of the item being delivered and the item storage image;

[0131] S13, verify whether the volume of the stored items can be placed in the corresponding compartment, and issue a corresponding warning of abnormal storage volume;

[0132] S14, verify whether the intelligent robot compartment can bear the weight of the stored items, and issue a corresponding warning of abnormal stored weight;

[0133] S21. Plan the delivery path of the intelligent robot;

[0134] S22: Analyze the first delivery time of the intelligent robot to each delivery location based on the path planned by the route planning unit ;

[0135] S23. Monitor the intelligent robot during its delivery process, analyze the intelligent robot's abnormal operation index Qy, and issue an abnormal operation warning;

[0136] S24. After receiving the abnormal operation warning, the intelligent robot operation data is deeply analyzed to obtain the tire abnormality index , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormal coefficient Zx of the intelligent robot;

[0137] S25. Predict the intervention processing time of the intelligent robot based on the comprehensive abnormality coefficient Zx, and calculate the second delivery time of the intelligent robot to each delivery location , send out delivery timeout warning;

[0138] S31, identifying and recording the user who needs to perform the object-taking operation;

[0139] S32, verifying the weight of the intelligent robot cabin after the object is taken, and reminding the user to continue taking objects;

[0140] S33, collecting and recording the image of the taken-out object.

[0141] See also Figure 3 The present invention provides an intelligent robot control device based on artificial intelligence, including: an item storage module, a central control module and a picking module.

[0142] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent robot control system based on artificial intelligence, characterized in that: include: The item storage module includes a storage user identification unit, a storage information input unit, an item storage volume verification unit, and an item storage weight verification unit; The storage user identification unit is used to identify and record the user who needs to perform storage operations; the storage information input unit is used to input the storage space of the item, the location information of the item being delivered, and the image of the item being stored; the item storage volume verification unit is used to verify whether the volume of the stored item can be placed in the corresponding space, and issue a corresponding storage volume abnormality warning; the item storage weight verification unit is used to verify whether the intelligent robot space can bear the weight of the stored item, and issue a corresponding storage weight abnormality warning; A central control module, including a route planning unit, a first delivery time prediction unit, an operation warning unit, a comprehensive abnormality analysis unit, and a processing time prediction unit; The route planning unit is used to plan the delivery route of the intelligent robot; the first delivery time prediction unit analyzes the first delivery time of the intelligent robot to each delivery location based on the route planned by the route planning unit. ; The operation warning unit is used to monitor the intelligent robot during the delivery process, analyze the intelligent robot operation abnormality index Qy, and issue an operation abnormality warning; The comprehensive abnormality analysis unit is used to deeply analyze the operation data of the intelligent robot to obtain the tire abnormality index after receiving the abnormal operation warning. , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormal coefficient Zx of the intelligent robot; the processing time prediction unit predicts the intervention processing time of the intelligent robot based on the comprehensive abnormal coefficient Zx, and calculates the second delivery time of the intelligent robot to each delivery location , send out delivery timeout warning; The item retrieval module includes an item retrieval user identification unit, an in-cabin weight verification unit and an item retrieval photography unit; the item retrieval user identification unit is used to identify and record the user who needs to perform the item retrieval operation; the in-cabin weight verification unit is used to verify the in-cabin weight of the intelligent robot cabin after the item retrieval is completed, and remind the user to continue to retrieve the item; the item retrieval photography unit is used to collect and record the image of the item taken out.

2. The intelligent robot control system based on artificial intelligence according to claim 1 is characterized by: Get the shortest path from the starting point to all delivery locations, and extract the horizontal distance of the path from the starting point to the first delivery location of the intelligent robot and floor change number , the horizontal distance from the first delivery position to the second delivery position and floor change number Repeat the above operation until the horizontal distance from the n-1th delivery position to the nth delivery position is obtained. and floor change number .

3. The intelligent robot control system based on artificial intelligence according to claim 2, characterized in that: Get the horizontal distance of the intelligent robot's path from the starting point to all delivery locations and the number of floors changed, combined with the average delivery speed Pj of the intelligent robot, the average elevator waiting time Dp, and the average ride time for each number of floors changed and the average pickup time Qw, calculate the first delivery time of the intelligent robot to each delivery location : Among them, n represents the cabin number of the intelligent robot, and a represents the number of floors changed.

4. The intelligent robot control system based on artificial intelligence according to claim 1, characterized in that: Extract the target speed of each tire from the intelligent robot drive instructions The speed sensor is used to detect the actual speed of each tire of the intelligent robot in real time. The Tilt Sensor detects the angle between the intelligent robot and the ground in real time. , after linear normalization processing, the intelligent robot operation abnormality index Qy is calculated: Among them, b represents the sequence number of each tire of the intelligent robot, is the critical tipping angle of the intelligent robot; When the intelligent robot's operation abnormality index Qy is less than 0, an operation abnormality warning is issued.

5. The intelligent robot control system based on artificial intelligence according to claim 4 is characterized in that: After receiving the abnormal operation warning, obtain the operation data of each drive motor of the intelligent robot, including current ,Voltage and temperature , analyze and obtain the hardware abnormality index of each drive motor : Wherein, c is the sequential number of each drive motor; When the hardware abnormality index of the drive motor Greater than 2 When , the drive motor is considered abnormal, and the number of abnormal drive motors Gd is counted; The hardware abnormality index of all drive motors The mean of .

6. The intelligent robot control system based on artificial intelligence according to claim 5, characterized in that: Get the target speed of each tire and actual speed , analyze and obtain the abnormality index of each tire of the intelligent robot : When the tire abnormality index When it is less than 0, the tire is considered abnormal, and the number of abnormal tires Lg is counted.

7. The intelligent robot control system based on artificial intelligence according to claim 6 is characterized in that: Get tire abnormality index , number of abnormal tires Lg, hardware abnormality index And the number of abnormal drive motors Gd, calculate the comprehensive abnormal coefficient Zx of the intelligent robot: The calculation formula of the corresponding intelligent robot's comprehensive abnormality coefficient Zx is as above.

8. The intelligent robot control system based on artificial intelligence according to claim 7 is characterized in that: Get the first delivery time of the intelligent robot arriving at each delivery location And the predicted intervention processing time Tgc, calculate the second delivery time of the intelligent robot to each delivery location : when If it exceeds 1 hour, a delivery timeout warning will be sent out.

9. An intelligent robot control method based on artificial intelligence, characterized in that: The steps include: S11, identifying and recording the user who needs to perform storage operations; S12, input the storage space of the item, the location information of the item being delivered and the item storage image; S13, verify whether the volume of the stored items can be placed in the corresponding compartment, and issue a corresponding warning of abnormal storage volume; S14, verify whether the intelligent robot compartment can bear the weight of the stored items, and issue a corresponding warning of abnormal stored weight; S21. Plan the delivery path of the intelligent robot; S22: Analyze the first delivery time of the intelligent robot to each delivery location based on the path planned by the route planning unit ; S23. Monitor the intelligent robot during its delivery process, analyze the intelligent robot's abnormal operation index Qy, and issue an abnormal operation warning; S24. After receiving the abnormal operation warning, the intelligent robot operation data is deeply analyzed to obtain the tire abnormality index , number of abnormal tires Lg, hardware abnormality index and the number of abnormal drive motors Gd, and further calculate the comprehensive abnormal coefficient Zx of the intelligent robot; S25. Predict the intervention processing time of the intelligent robot based on the comprehensive abnormality coefficient Zx, and calculate the second delivery time of the intelligent robot to each delivery location , send out delivery timeout warning; S31, identifying and recording the user who needs to perform the object-taking operation; S32, verifying the weight of the intelligent robot cabin after the object is taken, and reminding the user to continue taking objects; S33, collecting and recording the image of the taken-out object.

Images