A method and system for controlling the driving of objects and machines of unmanned engineering equipment

Abstract

The present invention discloses a method and system for controlling the physical machine driving of unmanned engineering equipment, which belongs to the field of equipment control technology, and includes: determining a physical sensing object that matches the engineering equipment to be driven, and collecting first-level data according to the sensor of the physical sensing object; determining the driving problem characteristics based on the data characteristics of the first-level data and the physical sensing object, and matching the driving solution characteristics corresponding to the driving problem characteristics; determining the second-level data according to the driving solution characteristics and the first-level data, and determining the equipment object that drives the engineering equipment based on the second-level data; determining at least one control parameter that matches the equipment object, and after the control parameter completes the driving verification, driving the engineering equipment based on the control parameter. The present invention solves the problem of poor control effectiveness of existing unmanned equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and in particular to a method and system for controlling a vehicle drive of unmanned engineering equipment. Background Art

[0002] With the rapid development of automation technology in heavy industry, unmanned engineering equipment has always been the focus of heavy industry enterprises. Among them, unmanned engineering equipment is equipment that uses advanced or classical control methods to control engineering equipment equipped with control systems according to specified rules to replace manual operation.

[0003] At present, the control of existing unmanned engineering equipment is usually directly operated and controlled according to a pre-set control algorithm. However, since the control algorithm is pre-set and the industrial environment is easily affected by various external factors, the unmanned engineering equipment will be more disturbing and less robust, thereby reducing the effectiveness of the control of the unmanned equipment. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for controlling the physical and mechanical driving of unmanned engineering equipment, the main purpose of which is to solve the problem of poor control effectiveness of existing unmanned equipment.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for controlling the driving of an object machine of an unmanned engineering equipment, comprising:

[0007] Determine a physical sensing object that matches the engineering equipment to be driven, and collect first-level data according to the sensor of the physical sensing object;

[0008] Determine a driving problem feature based on the data features of the first-level data and the object sensing object, and match a driving solution feature corresponding to the driving problem feature;

[0009] Determine the second level data according to the driving solution feature and the first level data, and determine the device object for driving the engineering device based on the second level data;

[0010] At least one control parameter matching the device object is determined, and after the control parameter has completed drive verification, the engineering device is driven based on the control parameter.

[0011] A further improvement of the technical solution of the present invention is that: the object sensing object includes a visual sensing object, an auditory sensing object and a tactile sensing object;

[0012] The determining of the object sensing object matching the engineering equipment to be driven and collecting the first-level data according to the sensor of the object sensing object specifically includes: when receiving a control instruction carrying a target control object triggered by the engineering equipment to be driven, querying the object sensing object corresponding to the target control object based on a preset object mapping relationship, querying at least one sensor bound to the target object sensing object, and instructing the sensor to collect the first-level data matching the object sensing object;

[0013] The preset object mapping relationship is configured with at least one of a visual sensing object, an auditory sensing object, and a tactile sensing object corresponding to different control objects.

[0014] A further improvement of the technical solution of the present invention is that: the determining of the driving problem feature based on the data feature of the first-level data and the object sensing object specifically includes: determining the data feature of the first-level data according to the acquisition type of the sensor; retrieving the problem set of the object sensing object, and querying the driving problem feature with problem relevance in the problem set based on the data feature;

[0015] The matching of the driving solution feature corresponding to the driving problem feature specifically includes: if the driving problem feature is a processing feature, then calling the processing strategy that matches the processing feature based on the data feature; if the driving problem feature is a monitoring feature, then calling the monitoring strategy that matches the monitoring feature based on the data feature; if the driving problem feature is a compensation feature, then calling the compensation strategy that matches the compensation feature based on the data feature.

[0016] Further improvements to the technical solution of the present invention are: the data features include image features, text features, audio features and numerical features; the problem set includes problem features corresponding to different data features; the processing strategy includes processing algorithms and processing scripts; the monitoring strategy includes time monitoring, threshold monitoring and execution monitoring; the compensation strategy includes feedback compensation, specified compensation and compound compensation.

[0017] A further improvement of the technical solution of the present invention is that: determining the second-level data according to the driving solution characteristics and the first-level data, and determining the device object for driving the engineering equipment based on the second-level data specifically includes:

[0018] Processing the first-level data based on the processing strategy, the monitoring strategy or the compensation strategy to obtain second-level data;

[0019] The first-level candidate objects matching the data feature are searched based on the preset object search list, and the device objects matching the second-level data are searched based on the object sequence of the first-level candidate objects.

[0020] A further improvement of the technical solution of the present invention is that the method further comprises:

[0021] Verifying and classifying the control parameters and the device objects based on the trained classification model to obtain classification scores for the control parameters;

[0022] If the classification score is greater than the preset driving score, completing the driving verification of the control parameters;

[0023] If the classification score is less than or equal to the preset driving score, the control parameter is adjusted according to the compensation range of the device object to re-perform the driving verification.

[0024] A further improvement of the technical solution of the present invention is that after driving the engineering equipment based on the control parameters, the method further includes:

[0025] Collecting the third-level data in the process of driving the engineering equipment based on the associated object sensing object of the object sensing object, and determining the driving monitoring conditions of the associated object sensing object;

[0026] If the third level data does not match the drive monitoring condition, a machine drive abnormality alarm message is generated.

[0027] A vehicle-driven control system for unmanned engineering equipment, comprising:

[0028] A first determination module is used to determine a physical sensing object that matches the engineering equipment to be driven, and collect first-level data according to the sensor of the physical sensing object;

[0029] A matching module, configured to determine a driving problem feature based on the data features of the first-level data and the object sensing object, and match a driving solution feature corresponding to the driving problem feature;

[0030] A second determination module, configured to determine second-level data according to the driving solution feature and the first-level data, and determine a device object for driving the engineering equipment based on the second-level data;

[0031] The driving module is used to determine at least one control parameter matching the device object, and drive the engineering device based on the control parameter after the control parameter completes the driving verification.

[0032] A storage medium stores at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the object-machine drive control method of unmanned engineering equipment.

[0033] A terminal comprises: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus;

[0034] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the object-machine drive control method of unmanned engineering equipment.

[0035] Due to the adoption of the above technical solution, the technical progress achieved by the present invention is:

[0036] The present invention provides a method and system for controlling a physical-machine drive of unmanned engineering equipment. Compared with the prior art, an embodiment of the present invention determines a physical-machine drive control object that matches the engineering equipment to be driven, and collects first-level data according to the sensor of the physical-machine drive object; determines a driving problem feature based on the data features of the first-level data and the physical-machine drive object, and matches a driving solution feature corresponding to the driving problem feature; determines second-level data according to the driving solution feature and the first-level data, and determines a device object for driving the engineering equipment based on the second-level data; determines at least one control parameter that matches the device object, and drives the engineering equipment based on the control parameter after the control parameter completes the driving verification, so as to realize that the engineering equipment can use the external physical world data for precise driving at any time, meet the flexible control requirements of the engineering equipment, and improve the robustness of the engineering equipment in executing operations, thereby improving the control efficiency and accuracy of the unmanned equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 It is a flow chart of a method for controlling a vehicle driving of an unmanned engineering equipment provided in an embodiment of the present invention;

[0039] Figure 2 is a queue schematic diagram provided in an embodiment of the present invention;

[0040] Figure 3 It is a block diagram of a physical-machine drive control system for unmanned engineering equipment provided in an embodiment of the present invention;

[0041] Figure 4 is a schematic diagram of the structure of a terminal provided in an embodiment of the present invention;

[0042] Among them, 21, a first determination module; 22, a matching module; 23, a second determination module; 24, a driving module; 302, a processor; 304, a communication interface; 306, a memory; 308, a bus; 310, a program. DETAILED DESCRIPTION

[0043] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatus.

[0044] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "several" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0045] The present invention is further described in detail below with reference to the accompanying drawings and embodiments:

[0046] The embodiment of the present invention provides a method for controlling the driving of an object machine of an unmanned engineering equipment. Figure 1 As shown, the method includes:

[0047] 101. Determine a physical sensing object that matches the engineering equipment to be driven, and collect first-level data according to the sensor of the physical sensing object.

[0048] In the embodiment of the present invention, the current execution subject may be a server for unmanned automatic control of unmanned engineering equipment, or a terminal device embedded with a control processor. In this case, the unmanned engineering equipment includes but is not limited to drones, unmanned loaders, unmanned rollers and other equipment, which are not specifically limited in the embodiment of the present invention. Among them, the engineering equipment to be driven is machinery and equipment with automatic control functions in different industrial engineering projects, such as intelligent robots. Object sensing objects include visual sensing objects, auditory sensing objects and tactile sensing objects; visual sensing objects are objects that are sensed by mechanical vision for automatic control, such as image objects; auditory sensing objects are objects that are sensed by mechanical hearing for automatic control, such as sound objects; tactile sensing objects are objects that are sensed by mechanical touch for automatic control, such as distance objects, temperature objects, etc., which are not specifically limited in the embodiment of the present invention.

[0049] It should be noted that the first-level data is collected by sensors corresponding to different physical sensing objects. For example, the auditory sensing object is sound data collected by a sound collector, which is not specifically limited in the embodiment of the present invention. Correspondingly, the first-level data includes image data, sound data, and touch data (for example, temperature data, pressure data, distance data, etc.), which is not specifically limited in the embodiment of the present invention.

[0050] In another embodiment of the present invention, for further definition and explanation, the step of determining a physical sensing object matching the engineering equipment to be driven, and collecting the first level data according to the sensor of the physical sensing object includes:

[0051] When receiving a control instruction to be triggered by the engineering equipment to be driven;

[0052] Query the physical sensing object corresponding to the target control object based on the preset object mapping relationship;

[0053] At least one sensor bound to the target object is queried, and the sensor is instructed to collect first-level data matching the object.

[0054] In order to realize the accurate collection of physical world information to cooperate with the accurate driving of unmanned engineering equipment, when the current execution end collects the first-level data, it first receives the control instruction triggered by the expected driving of the engineering equipment. At this time, the control instruction can be triggered based on the user in the engineering equipment, or based on the specified conditions (such as time conditions, etc.) in the engineering equipment. The control instruction carries the target control object. At this time, the target control object is used to characterize the object of the expected driving of the engineering equipment after the operation is performed, such as temperature, displacement, pressure, etc., which is not specifically limited in the embodiment of the present invention. Further, the current execution end queries the physical sensing object matching the target control object based on the preset object mapping relationship, wherein the preset object mapping relationship is configured with at least one of the visual sensing object, the auditory sensing object, and the touch sensing object corresponding to different control objects. For example, if the target control object is temperature, it can be matched as the target touch sensing object based on the preset object mapping relationship. For example, if the target control object is distance, it can be matched as the touch sensing object (distance infrared sensing) and the visual sensing object (image sensing) based on the preset object mapping relationship. The preset mapping relationship is configured according to the accuracy requirements of the engineering equipment data collection, which is not specifically limited in the embodiment of the present invention. Furthermore, after the object sensing object is determined, at least one sensor bound to the target object sensing object is queried. At this time, the sensor is different according to different object sensing objects. For example, the sensor bound to the visual sensing object is a camera, the sensor bound to the auditory sensing object is an audio collector (recorder), and the sensor bound to the touch sensing object is an infrared displacement detector or a temperature detector, etc., which is not specifically limited in the embodiments of the present invention.

[0055] It should be noted that the current execution end can pre-bind different physical sensing objects with multiple sensors, that is, data can be collected through multiple sensors. Then, after the bound sensors are determined, collection instructions are sent to each sensor to collect the first-level data.

[0056] 102. Determine driving problem features based on data features of the first-level data and the object sensing object, and match driving solution features corresponding to the driving problem features.

[0057] In an embodiment of the present invention, after the current execution end collects and obtains the first-level data, it extracts data features of the first-level data. Since the first-level data includes image data, sound data, and tactile data, when extracting features, an image feature recognition model can be used to extract features for image data, and a speech conversion model can be used to convert the sound data and then perform keyword extraction. For tactile data, tactile extreme values, tactile ranges, data structures, and numerical units can be used to extract features. Furthermore, the driving problem features are determined based on the data features and the object sensing objects, which are not specifically limited in the embodiment of the present invention.

[0058] In another embodiment of the present invention, for further definition and explanation, the step of determining the driving problem characteristics based on the data characteristics of the first-level data and the object sensing object includes:

[0059] Determine the data characteristics of the first-level data according to the collection type of the sensor;

[0060] The problem set of the object being sensed is retrieved, and the driving problem features in the problem set that are relevant to the problem are queried based on the data features.

[0061] In order to realize automatic driving of unmanned mechanical equipment, and for different driving requirements, when determining the driving problem characteristics based on the data characteristics of the first-level data and the object sensing object, specifically, first determine the data characteristics of the first-level data based on the collection type of the first-level data collected by the sensor, at this time, the collection type includes text type, image type, numerical type, sound type, etc., which is not specifically limited in the embodiment of the present invention. The data characteristics include image characteristics, text characteristics, audio characteristics and numerical characteristics. When determining the data characteristics of the first-level data based on the collection type, a feature extraction method can be used, that is, for the first-level data collected by the image type, an image feature recognition model can be used to extract characteristics to obtain image characteristics; for the first-level data collected by the sound type, a voice conversion model can be used to convert the sound data and then extract keywords to obtain audio characteristics; for the first-level data collected by the text type, a key name and verb extraction method can be used to obtain text characteristics; for the first-level data collected by the numerical type, the numerical data in the first-level data collected by the touch sensor can be extracted according to the tactile extreme value, tactile range, data structure, and numerical unit to obtain numerical characteristics, which is not specifically limited in the embodiment of the present invention.

[0062] It should be noted that, since the object sensing objects include visual sensing objects, auditory sensing objects and tactile sensing objects, when the unmanned equipment is driven, in order to solve the accuracy of the equipment behavior during the driving process, the driving behavior of the unmanned equipment is cyclically controlled in the form of generating problems and solving problems, thereby improving the control effectiveness of the unmanned equipment. The current execution end retrieves the problem set of the object sensing object to query the driving problem features with problem relevance in the problem set based on the data features. Among them, the problem set contains problem features corresponding to different data features, and the driving solution features include processing strategies, monitoring strategies and compensation strategies. Specifically, different object sensing objects are pre-bound with matching problem sets, and the problem features in the problem set are determined by polling, that is, a problem pool and a pointer queue associated with the problem pool are pre-created in the current execution end. According to the configured time conditions (for example, once every 1 minute), storage conditions (for example, once when the storage space is greater than 1G), and system operation conditions (for example, once when the system operation ratio is a or the system runs a specified thread), matching problem features are selected from the problem pool and stored in the pointer queue. At this time, the pointer queue can store the problem features corresponding to the three conditions in parallel, such as Figure 2As shown, the pointer jumps according to the predetermined timestamp, and selects the problem features that meet the three conditions in turn and puts them into the problem set to increase the matching flexibility of problem solving. Then, based on the data features, the driving problem features with problem relevance in the problem set are queried. At this time, having problem relevance refers to the relationship that can exist between the problem feature and the data feature. For example, the data feature is time, and the problem feature is the time threshold and time format. There is a problem relevance between the problem feature and the data feature. It can be configured based on a preset mapping relationship, or it can be based on a classification model pre-trained based on data-problem feature samples to classify and mark the data features to determine the problem features. The embodiment of the present invention does not make specific limitations.

[0063] Specifically, the driver solution features that match the driver problem features include:

[0064] If the driving problem feature is a processing feature, a processing strategy matching the processing feature is retrieved based on the data feature. The processing strategy includes a processing algorithm and a processing script.

[0065] If the driving problem feature is a monitoring feature, the monitoring strategy matching the monitoring feature is retrieved based on the data feature. The monitoring strategy includes time monitoring, threshold monitoring, and execution monitoring.

[0066] If the driving problem feature is a compensation feature, a compensation strategy matching the compensation feature is retrieved based on the data feature. The compensation strategies include feedback compensation, specified compensation, and compound compensation.

[0067] In order to use the determined driving problem characteristics to automatically and unmannedly solve the problems generated during the operation of the equipment, when the driving problem characteristics are determined and the driving solution characteristics are matched, specifically, the problem driving characteristics are first determined. At this time, the driving problem characteristics include processing characteristics, monitoring characteristics and compensation characteristics. Correspondingly, the driving solution characteristics are used to characterize the strategies adopted to solve the driving problems, including processing strategies, monitoring strategies and compensation strategies. Among them, the processing characteristics are used to characterize the data processing method used for data characteristics in order to solve the driving problems; the monitoring characteristics are used to characterize the data monitoring method used for data characteristics in order to solve the driving problems; the compensation characteristics are used to characterize the data compensation method used for data characteristics in order to solve the driving problems. The embodiments of the present invention do not make specific limitations. In a specific implementation scenario, when determining the driving problem characteristics, it can be determined according to the labels that are pre-marked on the problem characteristics. Each driving problem characteristic can be manually marked with at least one corresponding label to determine whether it is a processing characteristic, a monitoring characteristic, and a compensation characteristic. Furthermore, when it is determined to be a processing characteristic, a processing strategy that matches the processing characteristic is retrieved based on the data characteristic. At this time, the processing strategy includes a processing algorithm and a processing script. The processing algorithm may include a formula algorithm designed or configured by a developer for the data to calculate the result of the data processing. The processing script may include a program code compiled by a developer for the data to obtain the result of the data processing based on the program execution. The embodiment of the present invention does not specifically limit the specific content of the formula algorithm and the script. When the driving problem feature is a monitoring feature, a monitoring strategy matching the monitoring feature is retrieved based on the data feature. At this time, the monitoring strategy includes time monitoring, threshold monitoring, and execution monitoring. Time monitoring is a monitoring strategy that starts the data feature according to a specified time condition, threshold monitoring is a monitoring strategy that starts the data feature according to a specified threshold condition, and execution monitoring is a monitoring strategy that starts the data feature according to a specified execution action. The specific content of time, threshold, and execution action can be configured by the developer based on the unmanned execution requirements of the device, and the embodiment of the present invention does not make specific restrictions. When the driving problem feature is a compensation feature, a compensation strategy matching the compensation feature is retrieved based on the data feature. At this time, the compensation strategy includes feedback compensation, specified compensation, and composite compensation. Feedback compensation is a compensation strategy for re-entering operating parameters for the device based on the comparison result between the data feature and the expected result. Specified compensation is a compensation strategy for adjusting the upper and lower values ​​of the data feature according to the specified parameters. Composite compensation is a strategy for compensating feedback compensation and specified compensation at the same time. The specific values, parameter values, etc. of the compensation are not specifically limited. The developer can configure them based on the unmanned execution requirements of the device, and the embodiment of the present invention does not make specific restrictions.

[0068] 103. Determine the second level data according to the driving solution characteristics and the first level data, and determine the equipment object for driving the engineering equipment based on the second level data.

[0069] In the embodiment of the present invention, after the current execution end obtains the driving solution feature, the second-level data is processed according to the driving solution feature and the first-level data. At this time, the second-level data is the data obtained after one processing. Furthermore, the equipment object of the engineering equipment to be controlled is determined based on the second-level data. Among them, the equipment object is the specific object of controlling the engineering equipment according to the automatic control algorithm, including but not limited to the valve opening, heater, robot arm, etc., which is not specifically limited in the embodiment of the present invention.

[0070] In another embodiment of the present invention, for further definition and explanation, the step of determining the second level data according to the driving solution characteristics and the first level data, and determining the device object for driving the engineering equipment based on the second level data specifically includes:

[0071] Processing the first-level data based on a processing strategy, a monitoring strategy, or a compensation strategy to obtain second-level data;

[0072] Based on the preset object query list, the first-level candidate objects matching the data features are queried, and based on the object sequence of the first-level candidate objects, the device objects matching the second-level data are queried.

[0073] In order to realize the collection of secondary data, thereby improving the accuracy of data processing of unmanned equipment during automatic execution, when the current execution end determines the second-level data and equipment objects, specifically, firstly processes the first-level data based on the aforementioned processing strategy, monitoring strategy or compensation strategy to obtain the second-level data. Then, according to the content recorded in the preset object query list, the first-level candidate objects matching the data features are queried. At this time, the preset object query list records the first-level candidate objects corresponding to different data features. The first-level candidate objects are used to characterize multiple equipment objects executed based on the data features (equipment objects include but are not limited to parameters, hardware devices and software content during the operation of the equipment), which can be pre-configured based on different unmanned equipment, and the embodiment of the present invention does not make specific restrictions. Then, the equipment object matching the second-level data is queried from the object sequence of the first-level candidate objects. Among them, the object sequence stores multiple equipment objects executed by data features and is sorted according to priority. When querying the second-level data, the corresponding equipment object can be queried from this object sequence based on the pre-selected number of queries, and the embodiment of the present invention does not make specific restrictions.

[0074] 104. Determine at least one control parameter that matches the device object, and after the control parameter completes the drive verification, drive the engineering device based on the control parameter.

[0075] In the embodiment of the present invention, after the device object is determined, in order to ensure that the device object can safely and effectively perform control operations, the current execution end matches the control parameters of the device object to drive the engineering equipment according to the control parameters. In addition, since the engineering equipment is a fully automated device, in order to enable the engineering equipment to be driven accurately, the current execution end performs a drive check on the control parameters after obtaining the control parameters, and can evaluate or score the control parameters to determine whether the engineering equipment can be driven, which is not specifically limited in the embodiment of the present invention.

[0076] It should be noted that the control parameter is a specific parameter for unmanned control of the device object. For example, if the device object is a robotic arm, the control parameter may be a distance moved by the robotic arm. The embodiment of the present invention does not make any specific limitation.

[0077] In another embodiment of the present invention, for further definition and description, the steps further include:

[0078] Based on the trained classification model, the control parameters and equipment objects are verified and classified to obtain the classification scores of the control parameters;

[0079] If the classification score is greater than the preset drive score, the drive verification of the control parameters is completed;

[0080] If the classification score is less than or equal to the preset drive score, the control parameters are adjusted according to the compensation range of the device object to re-perform the drive calibration.

[0081] In order to achieve accurate and effective control of unmanned equipment based on control parameters, the current execution end also uses a classification model to verify and classify the control parameters and equipment objects. At this time, the classification model can be a decision tree model and a convolutional neural network. The classification model is trained using training samples with pre-marked classification score labels, so as to verify the classification through the trained classification model to obtain the classification score of the control parameter. Furthermore, the current execution end judges the obtained classification score by setting a preset drive score. If the classification score is greater than the preset drive score, the drive verification of the control parameter is completed. If the classification score is less than or equal to the preset drive score, the control parameter is adjusted according to the compensation range of the equipment object, indicating that the control parameter exceeds the controllable range of the equipment object. Therefore, the compensation range is used as the maximum and minimum values ​​of the control parameter for compensation, that is, when the equipment object adjusts the control parameter, the control parameter is adjusted according to the maximum or minimum value of the compensation. The embodiment of the present invention does not make specific limitations.

[0082] In another embodiment of the present invention, for further definition and explanation, after the step of driving the engineering equipment based on the control parameter, the method further includes:

[0083] The associated object sensing object collects the third-level data in the process of driving the engineering equipment based on the associated object sensing object, and determines the driving monitoring conditions of the associated object sensing object;

[0084] If the third-level data does not match the drive monitoring conditions, an abnormality alarm message of the generated machine drive will be generated.

[0085] In order to ensure that the unmanned equipment can be driven safely and effectively, the current execution end, after driving the engineering equipment using the control parameters, collects the third-level data of the engineering equipment during the control process based on the associated object sensing object of the object sensing object. Among them, the associated object sensing object and other object sensing objects with which the object sensing object has a pre-established association relationship, for example, the visual sensing object pre-configures the associated object sensing object as a touch sensing object, so that after the visual sensing object is used to collect the first-level data to drive the engineering equipment to perform the unmanned control operation, the touch sensing object is used to collect the third-level data, which is not specifically limited in the embodiment of the present invention. At the same time, after determining the associated object sensing object, it is also necessary to match the drive monitoring conditions of this associated object sensing object to determine whether the control state of the engineering equipment represented by the third-level data is normal according to this drive monitoring condition. At this time, the drive monitoring condition is a condition for configuring the object sensing object as a monitoring target of the associated object sensing object, which can be configured according to different engineering equipment requirements. For example, when the object sensing object is a visual sensing object, the corresponding associated object sensing object is a touch sensing object. At this time, the collected third-level data is distance data, and the corresponding drive monitoring condition can be whether the distance threshold is exceeded. If exceeded, it means that the drive monitoring condition is not matched, and then the object machine drive abnormal alarm information is generated. The embodiment of the present invention does not specifically limit the form of the object machine drive abnormal alarm information.

[0086] The present invention provides a method for controlling object-machine drive of unmanned engineering equipment. Compared with the prior art, the embodiment of the present invention determines an object sensing object matching the engineering equipment to be driven, and collects first-level data according to the sensor of the object sensing object; determines driving problem characteristics based on data characteristics of the first-level data and the object sensing object, and matches driving solution characteristics corresponding to the driving problem characteristics; determines second-level data according to the driving solution characteristics and the first-level data, and determines a device object for driving the engineering equipment based on the second-level data; determines at least one control parameter matching the device object, and drives the engineering equipment based on the control parameter after the control parameter completes the driving verification, so as to realize that the engineering equipment can use the external physical world data for precise driving at any time, meet the flexible control requirements of the engineering equipment, and improve the robustness of the engineering equipment in executing operations, thereby improving the control efficiency and accuracy of the unmanned equipment.

[0087] Furthermore, as a response to the above Figure 1 The embodiment of the present invention provides a vehicle driving control system for unmanned engineering equipment, such as Figure 3 As shown, the system includes:

[0088] A first determination module 21 is used to determine a physical sensing object that matches the engineering equipment to be driven, and collect first-level data according to the sensor of the physical sensing object;

[0089] A matching module 22, for determining a driving problem feature based on data features of the first-level data and the object sensing object, and matching a driving solution feature corresponding to the driving problem feature;

[0090] A second determination module 23, configured to determine the second level data according to the driving solution characteristics and the first level data, and determine the equipment object driving the engineering equipment based on the second level data;

[0091] The driving module 24 is used to determine at least one control parameter that matches the equipment object, and drive the engineering equipment based on the control parameter after the control parameter has completed the driving verification.

[0092] Furthermore, the object sensing object includes a visual sensing object, an auditory sensing object and a tactile sensing object.

[0093] The first determination module 21 is specifically used for, when receiving a control instruction triggered by the driven engineering equipment, the control instruction carries a target control object; based on a preset object mapping relationship, querying the physical sensing object corresponding to the target control object, wherein the preset object mapping relationship is configured with at least one of the visual sensing object, the auditory sensing object, and the tactile sensing object corresponding to different control objects; querying at least one sensor bound to the target physical sensing object, and instructing the sensor to collect the first-level data matching the physical sensing object.

[0094] Furthermore, the matching module 22 is specifically used to determine the data features of the first-level data according to the acquisition type of the sensor, the data features including image features, text features, audio features and numerical features; retrieve the problem set of the object being sensed, and query the driving problem features with problem relevance in the problem set based on the data features, wherein the problem set contains problem features corresponding to different data features;

[0095] Furthermore, the driver solution features include processing strategies, monitoring strategies, and compensation strategies.

[0096] The matching module 22 is also specifically used for, if the driving problem feature is a processing feature, then based on the data feature, calling the processing strategy that matches the processing feature, the processing strategy includes a processing algorithm and a processing script; if the driving problem feature is a monitoring feature, then based on the data feature, calling the monitoring strategy that matches the monitoring feature, the monitoring strategy includes time monitoring, threshold monitoring, and execution monitoring; if the driving problem feature is a compensation feature, then based on the data feature, calling the compensation strategy that matches the compensation feature, the compensation strategy includes feedback compensation, specified compensation, and compound compensation.

[0097] Furthermore, the second determination module 23 is specifically used to process the first-level data based on a processing strategy, a monitoring strategy or a compensation strategy to obtain second-level data; query the first-level candidate objects that match the data characteristics based on a preset object query list, and query the device objects that match the second-level data based on the object sequence of the first-level candidate objects.

[0098] Furthermore, the system also includes:

[0099] The verification module is used to verify and classify the control parameters and equipment objects based on the trained classification model to obtain the classification score of the control parameters; if the classification score is greater than the preset drive score, the drive verification of the control parameters is completed; if the classification score is less than or equal to the preset drive score, the control parameters are adjusted according to the compensation range of the equipment object to re-perform the drive verification.

[0100] Furthermore, the system also includes:

[0101] A third determination module is used to collect the third-level data in the process of driving the engineering equipment based on the associated object sensing object of the object sensing object, and determine the driving monitoring conditions of the associated object sensing object;

[0102] The generation module is used to generate machine drive abnormal alarm information if the third-level data does not match the drive monitoring conditions.

[0103] The present invention provides a physical-machine drive control system for unmanned engineering equipment. Compared with the prior art, the embodiments of the present invention determine a physical-machine drive control system that matches the engineering equipment to be driven, and collect first-level data according to the sensor of the physical-machine drive control system; determine drive problem characteristics based on data characteristics of the first-level data and the physical-machine drive control system, and match drive solution characteristics corresponding to the drive problem characteristics; determine second-level data according to the drive solution characteristics and the first-level data, and determine a device object for driving the engineering equipment based on the second-level data; determine at least one control parameter that matches the device object, and after the control parameter completes the drive verification, drive the engineering equipment based on the control parameter, so as to realize that the engineering equipment can use the external physical world data for precise driving at any time, meet the flexible control requirements of the engineering equipment, and improve the robustness of the engineering equipment in executing operations, thereby improving the control efficiency and accuracy of the unmanned equipment.

[0104] According to one embodiment of the present invention, a storage medium is provided, wherein the storage medium stores at least one executable instruction, and the computer executable instruction can execute the object-machine drive control method of unmanned engineering equipment in any of the above method embodiments.

[0105] Figure 4 A schematic diagram of the structure of a terminal provided according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the terminal.

[0106] like Figure 4 As shown, the terminal may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0107] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .

[0108] The communication interface 304 is used to communicate with other devices such as clients or other servers.

[0109] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the embodiment of the object-machine drive control method of the unmanned engineering equipment.

[0110] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0111] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. The one or more processors included in the terminal may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0112] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0113] The program 310 may be specifically configured to enable the processor 302 to perform the following operations:

[0114] Determine the physical sensing object that matches the engineering equipment to be driven, and collect the first-level data according to the sensor of the physical sensing object;

[0115] Determine the driving problem features based on the data features of the first-level data and the object sensing object, and match the driving solution features corresponding to the driving problem features;

[0116] Determine the second level data according to the driving solution characteristics and the first level data, and determine the equipment object for driving the engineering equipment based on the second level data;

[0117] At least one control parameter matching the device object is determined, and after the control parameter has completed the drive verification, the engineering device is driven based on the control parameter.

[0118] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0119] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for controlling the driving of a vehicle by an unmanned engineering device, characterized in that: include: Determine a physical sensing object that matches the engineering equipment to be driven, and collect first-level data according to the sensor of the physical sensing object; Determine a driving problem feature based on the data features of the first-level data and the object sensing object, and match a driving solution feature corresponding to the driving problem feature; Determine the second level data according to the driving solution feature and the first level data, and determine the device object for driving the engineering device based on the second level data; Determine at least one control parameter matching the device object, and after the control parameter completes the drive verification, drive the engineering device based on the control parameter; The object sensing objects include visual sensing objects, auditory sensing objects and tactile sensing objects; The determining of the object sensing object matching the engineering equipment to be driven and collecting the first-level data according to the sensor of the object sensing object specifically includes: when receiving a control instruction carrying a target control object triggered by the engineering equipment to be driven, querying the object sensing object corresponding to the target control object based on a preset object mapping relationship, querying at least one sensor bound to the target object sensing object, and instructing the sensor to collect the first-level data matching the object sensing object; The preset object mapping relationship is configured with at least one of a visual sensing object, an auditory sensing object, and a tactile sensing object corresponding to different control objects; The determining of the driving problem feature based on the data feature of the first-level data and the object sensing object specifically includes: determining the data feature of the first-level data according to the acquisition type of the sensor; retrieving the problem set of the object sensing object, and querying the driving problem feature with problem relevance in the problem set based on the data feature; The matching of the driving solution feature corresponding to the driving problem feature specifically includes: if the driving problem feature is a processing feature, then calling the processing strategy that matches the processing feature based on the data feature; if the driving problem feature is a monitoring feature, then calling the monitoring strategy that matches the monitoring feature based on the data feature; if the driving problem feature is a compensation feature, then calling the compensation strategy that matches the compensation feature based on the data feature.

2. The method according to claim 1, characterized in that The data features include image features, text features, audio features and numerical features; the problem set includes problem features corresponding to different data features; the processing strategy includes processing algorithms and processing scripts; the monitoring strategy includes time monitoring, threshold monitoring and execution monitoring; the compensation strategy includes feedback compensation, specified compensation and compound compensation.

3. The method according to claim 2, characterized in that The determining of the second level data according to the driving solution feature and the first level data, and determining the device object for driving the engineering equipment based on the second level data specifically includes: Processing the first-level data based on the processing strategy, the monitoring strategy or the compensation strategy to obtain second-level data; The first-level candidate objects matching the data feature are searched based on the preset object search list, and the device objects matching the second-level data are searched based on the object sequence of the first-level candidate objects.

4. The method according to claim 3, characterized in that The method further comprises: Verifying and classifying the control parameters and the device objects based on the trained classification model to obtain classification scores for the control parameters; If the classification score is greater than the preset driving score, completing the driving verification of the control parameters; If the classification score is less than or equal to the preset driving score, the control parameter is adjusted according to the compensation range of the device object to re-perform the driving verification.

5. The method according to claim 1, characterized in that After driving the engineering equipment based on the control parameters, the method further includes: Collecting the third-level data in the process of driving the engineering equipment based on the associated object sensing object of the object sensing object, and determining the driving monitoring conditions of the associated object sensing object; If the third level data does not match the drive monitoring condition, a machine drive abnormality alarm message is generated.

6. A vehicle drive control system for unmanned engineering equipment, characterized in that: include: A first determination module is used to determine a physical sensing object that matches the engineering equipment to be driven, and collect first-level data according to the sensor of the physical sensing object; A matching module, configured to determine a driving problem feature based on the data features of the first-level data and the object sensing object, and match a driving solution feature corresponding to the driving problem feature; A second determination module, configured to determine second-level data according to the driving solution feature and the first-level data, and determine a device object for driving the engineering equipment based on the second-level data; A driving module, used for determining at least one control parameter matching the device object, and driving the engineering device based on the control parameter after the control parameter completes the driving verification; Object sensing objects include visual sensing objects, auditory sensing objects, and tactile sensing objects. The first determination module is specifically used for, when receiving a control instruction triggered by the engineering equipment to be driven, the control instruction carries a target control object; based on a preset object mapping relationship, querying a physical sensing object corresponding to the target control object, wherein the preset object mapping relationship is configured with at least one of a visual sensing object, an auditory sensing object, and a tactile sensing object corresponding to different control objects; querying at least one sensor bound to the target physical sensing object, and instructing the sensor to collect first-level data matching the physical sensing object; A matching module, specifically used to determine data features of the first-level data according to the acquisition type of the sensor, the data features including image features, text features, audio features and numerical features; Retrieve the problem set of the object of object sensing, and query the driving problem features with problem relevance in the problem set based on the data features. The problem set contains problem features corresponding to different data features; Driver solution features include processing strategies, monitoring strategies, and compensation strategies. The matching module is specifically used to, if the driving problem feature is a processing feature, retrieve a processing strategy based on the data feature to match the processing feature; if the driving problem feature is a monitoring feature, retrieve a monitoring strategy based on the data feature to match the monitoring feature; and if the driving problem feature is a monitoring feature, retrieve a compensation strategy based on the data feature to match the compensation feature.

7. A storage medium storing at least one executable instruction, wherein the executable instruction enables a processor to execute an operation corresponding to the object-machine drive control method of unmanned engineering equipment according to any one of claims 1 to 5.

8. A terminal, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the object-machine drive control method of unmanned engineering equipment according to any one of claims 1-5.

Images