Wearable device-based assisted carrying control method, apparatus, device, and medium

Abstract

The application provides an auxiliary carrying control method and device based on a wearable device, equipment and a medium. The method comprises the following steps: obtaining an object carrying strategy of a target object to be carried, so as to determine a first control data set of the wearable device; obtaining a target stability analysis result corresponding to the first control data set; determining a target control data set of the wearable device based on the target stability analysis result, so as to control the wearable device through the target control data set, and carry the target object based on the object carrying strategy. The flexibility of the wearable device in assisting the carrying of the object is improved, the stability of the control of the auxiliary carrying operation of the wearable device is improved, the control precision of the control of the auxiliary carrying operation of the wearable device is improved, the auxiliary degree and the load of the wearable device in the target object carrying process are improved, the load of the target object carrying on the worker is reduced, and the damage degree of the worker is reduced.

Description

Technical Field

[0001] This application relates to the field of exoskeleton robot technology, and in particular to an assisted handling control method, device, equipment and medium based on wearable devices. Background Technology

[0002] With the development of technology, people can rely on external handling equipment to assist in the handling of goods. However, handling equipment may lack flexibility in complex working environments.

[0003] Therefore, improving the operational flexibility of material handling equipment is of great importance. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the first aspect of this application proposes an assisted handling control method based on wearable devices.

[0006] The second aspect of this application proposes an auxiliary handling control device based on wearable devices.

[0007] The third aspect of this application proposes a robot.

[0008] The fourth aspect of this application discloses an electronic device.

[0009] The fifth aspect of this application proposes a computer-readable storage medium.

[0010] The first aspect of this application proposes an assisted handling control method based on a wearable device, comprising: acquiring an object handling strategy for a target object to be handled, thereby determining a first control dataset for the wearable device; acquiring a target stability analysis result corresponding to the first control dataset; and determining a target control dataset for the wearable device based on the target stability analysis result, so as to control the wearable device through the target control dataset to handle the target object based on the object handling strategy.

[0011] A second aspect of this application proposes an assisted handling control device based on a wearable device, comprising: a first acquisition module for acquiring an object handling strategy for a target object to be handled, thereby determining a first control dataset for the wearable device; a second acquisition module for acquiring a target stability analysis result corresponding to the first control dataset; and a control module for determining a target control dataset for the wearable device based on the target stability analysis result, thereby controlling the wearable device through the target control dataset to handle the target object based on the object handling strategy.

[0012] The third aspect of this application provides a robot capable of performing the wearable device-based assisted handling control method as described in the first aspect above.

[0013] The fourth aspect of this application provides an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute instructions to implement the wearable device-based assisted handling control method as described in the first aspect above.

[0014] The fifth aspect of this application provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by the processor of an electronic device, enables the electronic device to perform the wearable device-based assisted handling control method as described in the first aspect above.

[0015] The wearable device-based assisted handling control method and apparatus proposed in this application improves the flexibility of external devices in assisting the handling of target objects by using wearable devices to assist in the handling of target objects. Based on the target stability analysis results of the first control dataset, a target control dataset is determined, and the wearable device is controlled to assist in the handling of the target object based on the target control dataset. This improves the stability and accuracy of the wearable device's assisted handling operation control, enhances the degree of assistance and load of the wearable device during the target object handling process, reduces the load on workers during the handling of the target object, thereby reducing the degree of injury to workers and improving the safety and stability of workers during object handling. This optimizes the wearable device-based assisted handling control method.

[0016] It should be understood that the description herein is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0018] Figure 1 This is a schematic flowchart of an embodiment of the assisted handling control method based on wearable devices according to this application;

[0019] Figure 2 This is a flowchart illustrating another embodiment of the assisted handling control method based on wearable devices in this application;

[0020] Figure 3 This is a schematic diagram of the structure of an auxiliary handling control device based on a wearable device according to an embodiment of this application;

[0021] Figure 4 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0022] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0023] The following description, with reference to the accompanying drawings, describes an assisted handling control method, apparatus, device, and medium based on wearable devices, according to embodiments of this application.

[0024] Figure 1 This is a flowchart illustrating an embodiment of the assisted handling control method based on wearable devices according to this application. Figure 1 As shown, the method includes:

[0025] S101, Obtain the object handling strategy of the target object to be moved in order to determine the first control dataset of the wearable device.

[0026] During the process of moving objects, people can use external devices to assist in the movement. The external devices worn by people can be defined as wearable devices, and the people equipped with wearable devices can be defined as the wearable devices themselves.

[0027] Optionally, the object that needs to be moved can be obtained, which is the target object to be moved. Further, the moving strategy of the target object is determined based on the preset moving strategy acquisition method, and the strategy is determined as the object moving strategy of the target object.

[0028] In this scenario, the load of the wearable device during assisted handling can be determined based on the object handling strategy of the target object. Then, the various handling operations that the wearable device needs to perform during handling can be determined. The control data required to control the wearable device to perform these various handling operations is determined as the first control data of the wearable device, and thus a first control dataset composed of the first control data is obtained.

[0029] It should be noted that the first control dataset can be composed of control data of each component of the wearable device. Based on the control data of each component, each component can perform its own operation, thereby achieving the overall handling assistance operation of the wearable device.

[0030] S102, Obtain the target stability analysis results corresponding to the first control dataset.

[0031] In this embodiment of the disclosure, when the wearable device is controlled based on each of the first control data in the first control dataset, the assisted handling operation performed by the wearable device may be unstable.

[0032] In this scenario, a stability analysis can be performed on the first control dataset, and based on the results of the stability analysis of the first control dataset, it can be determined whether the operation of the wearable device will become unstable when controlled based on the first control dataset.

[0033] Among them, the analysis results obtained by performing stability analysis on the first control dataset can be determined as the target stability analysis results corresponding to the first control dataset.

[0034] S103, Based on the target stability analysis results, determine the target control dataset of the wearable device, so as to control the wearable device through the target control dataset and move the target object based on the object handling strategy.

[0035] In this embodiment of the application, the target stability analysis results can be used to determine whether the wearable device can normally assist in the transport of the target object during the assisted transport operation.

[0036] Specifically, when it is determined from the target stability analysis results that the wearable device can normally perform the corresponding auxiliary handling operation when the control of the wearable device is performed through the first control dataset, it can be determined that the auxiliary handling operation of the wearable device can be realized based on the first control dataset. In this scenario, the first control dataset can be identified as the control dataset used when performing auxiliary handling operation control on the wearable device, i.e., the target control dataset.

[0037] Furthermore, when the target stability analysis results indicate that the wearable device may not be able to perform the corresponding assisted handling operation when the first control dataset is used to control the assisted handling operation, it can be determined that the assisted handling operation of the wearable device cannot be achieved based on the first control dataset. In this scenario, a new control dataset can be generated, and the target control dataset used for the assisted handling operation control of the wearable device can be determined based on the new control dataset.

[0038] The wearable device-based assisted handling control method proposed in this application improves the flexibility of the wearable device in assisting the handling of target objects. It determines the target control dataset based on the target stability analysis results of the first control dataset, and controls the wearable device to assist in the handling of the target object based on the target control dataset. This improves the stability and accuracy of the wearable device's assisted handling operation control, enhances the degree of assistance and load of the wearable device during the target object handling process, reduces the load on workers during target object handling, thereby reducing the degree of injury to workers and improving the safety and stability of workers during object handling. This method optimizes the wearable device-based assisted handling control method.

[0039] In the above embodiments, the handling of the target object can also be combined with... Figure 2 To understand further, Figure 2 This is a flowchart illustrating another embodiment of the assisted handling control method based on wearable devices, as shown below. Figure 2 As shown, the method includes:

[0040] S201, Based on the pre-acquired handling strategy output model and the acquired image of the target object, determine the object handling strategy for the target object.

[0041] In this embodiment of the application, the strategy used when transporting the target object can be obtained through a trained model for acquiring the transport strategy, and this strategy can be used as the object transport strategy of the target object.

[0042] The trained model can be designated as the transport strategy output model. Optionally, before transporting the target object, the target object can be imaged using the image acquisition component configured on the wearable device to obtain the acquired image of the target object. Further, the acquired image of the target object is input into the trained transport strategy output model, which extracts the relevant features of the target object based on the acquired image of the target object input into the model.

[0043] Optionally, the handling strategy output model can identify and estimate the object type, appearance, and weight of the target object based on the feature information extracted from the acquired image of the target object, and then determine the handling strategy suitable for the target object based on the estimated information, which is the object handling strategy output by the model.

[0044] The target object handling strategy can include standing posture strategy, handling posture strategy, and handling method strategy. The standing posture strategy can include the standing position and the standing orientation. The handling posture strategy can include changes in posture during handling, such as upright posture, bending posture, twisting posture, and lateral bending posture. The handling method strategy can include changes in the way the target object is handled, such as grasping method, lifting method, and carrying method.

[0045] S202, based on the object handling strategy, determine the first waist control data and the first joint control data of the wearable device to determine the first control dataset.

[0046] Optionally, based on the object handling strategy, the object attribute data of the target object can be obtained.

[0047] In this embodiment of the disclosure, relevant data such as the object type, object weight, object shape, and object size of the target object can be obtained from the object handling strategy. This data can be determined as the object attribute data of the target object.

[0048] Optionally, based on the pre-acquired wearable object attribute data and object attribute data, the first waist control data of the wearable device is determined through the pre-acquired target waist control model.

[0049] In this embodiment of the disclosure, during the transportation of the target object, the wearable device needs to control the waist, and the wearable device needs to assist the wearable device in controlling the waist. In this scenario, the device control data obtained when the wearable device assists the wearable device in controlling the waist can be determined as the first waist control data of the wearable device, and the model obtained from the first waist control data can be determined as the pre-acquired target waist control model.

[0050] The target waist control model can be constructed based on waist dynamics and waist kinematics models in related technologies, or it can be constructed based on other methods; no specific limitations are made here.

[0051] Optionally, the object configuring the wearable device can be defined as the device wearable object of the wearable device. In this scenario, the relevant attribute data of the wearable object can be obtained based on a preset information acquisition method, and the obtained attribute data can be defined as the wearable object attribute data of the device wearable object of the wearable device.

[0052] It should be noted that the wearable object attribute data may include the wearable object's height, weight, upper limb length, waist joint length, and other attribute data, without specific limitations here.

[0053] In this scenario, the pre-acquired wearable object attribute data and the target object's object attribute data can be input into the target waist control model. Based on the input object attribute data and wearable object attribute data, the target waist control model obtains the control data when the wearable device assists in the waist control of the wearable object, and outputs it as the first waist control data.

[0054] Optionally, based on wearable object attribute data and object attribute data, the first joint control data of the wearable device is determined through a pre-acquired target joint control model.

[0055] In this embodiment of the disclosure, during the transportation of the target object, the wearable object needs to control the upper limb joints, and the wearable device needs to assist in controlling the upper limb joints of the wearable object. In this scenario, the device control data obtained when the wearable device assists in controlling the upper limb joints of the wearable object can be determined as the first joint control data of the wearable device, and the model obtained from the first joint control data can be determined as the pre-acquired target joint control model.

[0056] The target joint control model can be constructed based on the upper limb dynamics model and upper limb kinematics model in related technologies, or it can be constructed based on other methods, without specific limitations here.

[0057] In this scenario, the pre-acquired wearable object attribute data and the target object's object attribute data can be input into the target joint control model. Based on the input object attribute data and wearable object attribute data, the target joint control model obtains the control data when the wearable device assists in controlling the upper limb joints of the wearable object, and outputs it as the first joint control data.

[0058] Optionally, a first control dataset for the wearable device is determined based on the first waist control data and the first joint control data.

[0059] Among them, a dataset consisting of first waist control data and first joint control data can be obtained, which is the first control dataset of the wearable device.

[0060] S203, Obtain the target stability analysis results corresponding to the first control dataset.

[0061] Optionally, the first waist control data in the first control dataset is compared with preset stability conditions to obtain the first candidate stability analysis result of the first waist control data.

[0062] In this embodiment of the application, the judgment condition used when performing stability analysis on the first waist control data can be determined as the stability condition corresponding to the first waist control data. The first waist control data can be compared with the stability condition, and the stability analysis result of the first waist control data can be obtained based on the comparison result. This result is the first candidate stability analysis result of the first waist control data.

[0063] In other words, when the comparison result indicates that the first waist control data matches the stability condition, it can be determined that the stability of the first waist control data meets the relevant stability requirements, and thus stability can be used as the first candidate stability analysis result of the first waist control data.

[0064] Furthermore, when the comparison results indicate that the first waist control data does not match the stability condition, it can be determined that the stability of the first waist control data does not meet the relevant stability requirements, and thus instability can be used as the first candidate stability analysis result of the first waist control data.

[0065] Optionally, the first joint control data in the first control dataset is compared with the stability conditions to obtain a second candidate stability analysis result for the first joint control data.

[0066] In this embodiment of the application, the judgment condition used when performing stability analysis on the first joint control data can be determined as the stability analysis condition of the first joint control data. Then, based on the comparison result of the first joint control data and its corresponding stability condition, the stability analysis result of the first joint control data can be obtained as the second candidate stability analysis result.

[0067] The specific process of obtaining the stability analysis results of the second candidate can be understood in conjunction with the process of obtaining the stability analysis results of the first candidate described above, and will not be repeated here.

[0068] It should be noted that the stability conditions corresponding to the first waist control data and the first joint control data mentioned above can be determined based on the Lyapunov stability conditions in related technologies, or based on other stability conditions, without specific limitations here.

[0069] Optionally, the target stability analysis result is obtained based on the first candidate stability analysis result and the second candidate stability analysis result.

[0070] In this embodiment of the application, the first candidate stability analysis result and the second candidate stability analysis result can be integrated, and the integrated stability analysis result can be determined as the target stability analysis result corresponding to the first control dataset.

[0071] S204. Based on the first control dataset and the object handling strategy, obtain the second control dataset output by the pre-acquired upper limb and waist joint control model, so as to obtain the target control data residual of the second control dataset based on the first control dataset.

[0072] Optionally, based on the first waist control data in the first control dataset and the object handling strategy, the second joint control data output by the upper limb waist joint control model is obtained.

[0073] In this embodiment, the control model corresponding to the upper limb joint and the control model corresponding to the waist can be integrated based on the model integration method in the related technology, thereby realizing the combination of the control model of the upper limb joint and the control model of the waist, and the combined model is determined as the upper limb and waist combined control model.

[0074] Optionally, the first waist control data and the object handling strategy in the first control dataset can be input into the upper limb waist joint control model. The upper limb waist joint control model can then predict the control data of the upper limb joints based on the input data, and output the predicted data as the second joint control data of the wearable device.

[0075] Optionally, based on the first joint control data and the object handling strategy in the first control dataset, the second waist control data output by the upper limb and waist joint control model is obtained.

[0076] In this embodiment, the first joint control data and the object handling strategy in the first control dataset can be input into the upper limb and waist joint control model. The upper limb and waist joint control model can then predict the waist control data based on the input data and output the predicted data as the second waist control data of the wearable device.

[0077] Optionally, a second control dataset for the wearable device is obtained based on the second joint control data and the second waist control data.

[0078] In this embodiment of the application, the dataset composed of the second joint control data and the second waist control data can be determined as the second control dataset of the wearable device.

[0079] Optionally, the residual of the second control dataset based on the first control dataset is obtained as the target control data residual.

[0080] In this embodiment of the application, the first control dataset and the second control dataset can be processed by an algorithm for obtaining the residual value between datasets in the related technology, and then the residual value between the two can be obtained according to the result of the algorithm processing. The residual value can be determined as the target control data residual.

[0081] S205. Based on the target stability analysis results and the target control data residuals, determine the target control dataset.

[0082] Optionally, in response to the target stability analysis result indicating that the stability of the first control dataset is normal and the residual of the target control data is less than or equal to a preset residual threshold, the first control dataset is determined to be the target control dataset.

[0083] In this embodiment of the application, based on the target stability analysis results and the target control data residuals, it can be identified whether the operation state of the auxiliary handling operation meets the preset auxiliary handling operation state requirements when the wearable device is controlled based on the first control dataset.

[0084] Specifically, when the target stability analysis result indicates that the stability of the first control dataset is normal, and the residual of the target control data is less than or equal to the preset residual threshold, it can be determined that when the wearable device is controlled based on the first control dataset, the operation state of the wearable device performing auxiliary handling operation on the wearable object meets the preset auxiliary handling operation state requirements.

[0085] In this scenario, it can be determined that when the wearable device is controlled based on the first control dataset, the wearable device can normally complete the auxiliary handling operation of the target object being transported by the device wearable object. Furthermore, the first control dataset can be identified as the target control dataset.

[0086] Optionally, in response to the target stability analysis results indicating an abnormal stability of the first control dataset, and / or the residual of the target control data being greater than the residual threshold, model optimization is performed on the control model for each first control data in the first control dataset.

[0087] In this embodiment of the application, when the target stability analysis result indicates that the stability of the first control dataset is abnormal, it can be determined that when the wearable device is controlled based on the first control dataset, the operation state of the wearable device performing auxiliary handling operation on the wearable object may not meet the preset auxiliary handling operation state requirements.

[0088] Furthermore, when the residual of the target control data is greater than the residual threshold, it can be determined that when the wearable device is controlled based on the first control dataset, the operation state of the wearable device performing auxiliary handling operations on the wearable object may not meet the preset auxiliary handling operation state requirements.

[0089] Optionally, when at least one of the above situations occurs, it can be determined that the target waist control model that obtains the first waist control data in the first control dataset cannot achieve accurate prediction of waist control data, and the target joint control model that obtains the first joint control data in the first control dataset cannot achieve accurate prediction of joint control data. In this scenario, it is necessary to return to adjust and optimize the target waist control model and the target joint control model.

[0090] Among them, the model adjustment and optimization algorithm based on the relevant technology can be used to adjust the model parameters of the target waist control model and the target joint control model based on the first control dataset and the target control data residual obtained at present, until the adjusted target waist control model and the adjusted target joint control model meet their respective model adjustment and optimization termination conditions, and thus obtain the optimized target waist control model and the optimized target joint control model.

[0091] Optionally, based on the new first control data output by each optimized control model, a new first control dataset is obtained, and the new target stability analysis results and new target control data residuals corresponding to the new first control dataset are obtained until the new target stability analysis results indicate that the stability is normal and the new target control data residuals are less than or equal to the residual threshold, and the new first control dataset is determined as the target control dataset.

[0092] In this embodiment of the application, after obtaining the optimized target waist control model and the optimized target joint control model, new first waist control data can be obtained based on the first waist control data acquisition method proposed above and the optimized target waist control model. Similarly, new first joint control data can be obtained based on the first joint control data acquisition method proposed above and the optimized target joint control model. Furthermore, a new first control dataset can be obtained based on the new first waist control data and the new first joint control data.

[0093] Furthermore, a stability analysis is performed on the new first control dataset. Based on the new target stability analysis results and the new target control data residuals of the new first control dataset, it is determined whether the operation state of the wearable device performing auxiliary handling operations on the wearable object can meet the preset auxiliary handling operation state requirements when the wearable device is controlled based on the new first control dataset.

[0094] Specifically, when the operation state is identified as meeting the preset requirements for the auxiliary handling operation state, it can be determined that when the wearable device is controlled based on the new first control dataset, the wearable device can normally complete the auxiliary handling operation of the target object being handled by the device wearable object. Furthermore, the new first control dataset can be identified as the target control dataset.

[0095] Accordingly, when it is identified that the operation state cannot meet the preset requirements of the auxiliary handling operation state, the model can be returned to continue to be adjusted and optimized until the first control dataset obtained based on the optimized model meets the above-mentioned conditions. Then, the first control dataset that meets the corresponding conditions can be determined as the target control dataset of the wearable device.

[0096] S206, Motion control of wearable devices is performed based on the target control dataset to assist the wearable device in moving the target object based on the object handling strategy.

[0097] In this embodiment, based on the control strategy of wearable devices in related technologies, when the wearable device is moving a target object, motion control is performed on the wearable device based on the target control data, so that it can perform corresponding auxiliary moving operations based on the target control data.

[0098] Furthermore, based on the execution of auxiliary handling operations, auxiliary handling is achieved when the device-wearing object is moving the target object.

[0099] The wearable device-based assisted handling control method proposed in this application improves the flexibility of the wearable device in assisting the handling of target objects. It determines the target control dataset based on the target stability analysis results of the first control dataset, and controls the wearable device to assist in the handling of the target object based on the target control dataset. This improves the stability and accuracy of the wearable device's assisted handling operation control, enhances the degree of assistance and load of the wearable device during the target object handling process, reduces the load on workers during target object handling, thereby reducing the degree of injury to workers and improving the safety and stability of workers during object handling. This method optimizes the wearable device-based assisted handling control method.

[0100] Corresponding to the wearable device-based auxiliary handling control methods proposed in the above embodiments, one embodiment of this application also proposes a wearable device-based auxiliary handling control device. Since the wearable device-based auxiliary handling control device proposed in this application corresponds to the wearable device-based auxiliary handling control methods proposed in the above embodiments, the implementation methods of the wearable device-based auxiliary handling control methods are also applicable to the wearable device-based auxiliary handling control device proposed in this application, and will not be described in detail in the following embodiments.

[0101] Figure 3 This is a schematic diagram of the structure of an assisted handling control device based on a wearable device according to an embodiment of this application, as shown below. Figure 3 As shown, the wearable device-based assisted handling control device 300 includes a first acquisition module 31, a second acquisition module 32, and a control module 33, wherein:

[0102] The first acquisition module 31 is used to acquire the object handling strategy of the target object to be moved, so as to determine the first control dataset of the wearable device;

[0103] The second acquisition module 32 is used to acquire the target stability analysis results corresponding to the first control dataset;

[0104] The control module 33 is used to determine the target control dataset of the wearable device based on the target stability analysis results, so as to control the wearable device through the target control dataset to move the target object based on the object handling strategy.

[0105] In this embodiment of the application, the control module 33 is further configured to: obtain a second control dataset output by the pre-acquired upper limb and waist joint control model based on the first control dataset and the object handling strategy, so as to obtain the corresponding target control data residual; determine the target control dataset based on the target stability analysis results and the target control data residual; and perform motion control on the wearable device based on the target control dataset to assist the wearable device in carrying the target object based on the object handling strategy.

[0106] In this embodiment of the application, the control module 33 is further configured to: determine the first control dataset as the target control dataset in response to the target stability analysis result indicating that the stability of the first control dataset is normal and the residual of the target control data is less than or equal to a preset residual threshold.

[0107] In this embodiment of the application, the control module 33 is further configured to: respond to the target stability analysis result indicating that the stability of the first control dataset is abnormal, and / or that the target control data residual is greater than the residual threshold, return to perform model optimization on the control model of each first control data in the first control dataset; based on the new first control data output by each optimized control model, obtain a new first control dataset, and continue to obtain the new target stability analysis result and the new target control data residual corresponding to the new first control dataset, until the new target stability analysis result indicates that the stability is normal and the new target control data residual is less than or equal to the residual threshold, and determine the new first control dataset as the target control dataset.

[0108] In this embodiment of the application, the control module 33 is further configured to: obtain second joint control data output by the upper limb and waist joint control model based on the first waist control data and the object handling strategy in the first control dataset; obtain second waist control data output by the upper limb and waist joint control model based on the first joint control data and the object handling strategy in the first control dataset; obtain a second control dataset of the wearable device based on the second joint control data and the second waist control data; and obtain the residual of the second control dataset based on the first control dataset as the target control data residual.

[0109] In this embodiment of the application, the first acquisition module 31 is further configured to: determine the object handling strategy of the target object based on the pre-acquired handling strategy output model and the acquired image of the target object; and determine the first waist control data and the first joint control data of the wearable device based on the object handling strategy to determine the first control dataset.

[0110] In this embodiment of the application, the first acquisition module 31 is further configured to: obtain object attribute data of the target object based on the object handling strategy; determine the first waist control data of the wearable device based on the pre-acquired wearable object attribute data and object attribute data, through the pre-acquired target waist control model; determine the first joint control data of the wearable device based on the wearable object attribute data and object attribute data, through the pre-acquired target joint control model; and determine the first control dataset of the wearable device based on the first waist control data and the first joint control data.

[0111] In this embodiment of the application, the second acquisition module 32 is further configured to: compare the first waist control data in the first control dataset with preset stability conditions to obtain a first candidate stability analysis result of the first waist control data; compare the first joint control data in the first control dataset with stability conditions to obtain a second candidate stability analysis result of the first joint control data; and obtain a target stability analysis result based on the first candidate stability analysis result and the second candidate stability analysis result.

[0112] The wearable device-based assisted handling control device proposed in this application improves the flexibility of the wearable device in assisting the handling of target objects. It determines the target control dataset based on the target stability analysis results of the first control dataset and controls the wearable device to assist in the handling of the target object based on the target control dataset. This improves the stability and accuracy of the wearable device's assisted handling operation control, enhances the degree of assistance and load of the wearable device during the target object handling process, reduces the load on workers during the handling of the target object, thereby reducing the degree of injury to workers and improving the safety and stability of workers during object handling. It also optimizes the assisted handling control method based on wearable devices.

[0113] To achieve the above embodiments, this application also proposes a robot capable of executing the wearable device-based assisted handling control method provided in the above embodiments.

[0114] To achieve the above embodiments, this application also provides an electronic device, a computer-readable storage medium, and a computer program product.

[0115] Figure 4 This is a block diagram of an electronic device 400 according to an embodiment of this application, as shown below. Figure 4 As shown, the electronic device 400 includes a memory 401, a processor 402, and a computer program stored in the memory 401 and executable on the processor 402. When the processor 402 executes program instructions, it implements the assisted handling control method based on wearable devices provided in the above embodiments.

[0116] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the wearable device-based assisted handling control method provided in the above embodiments.

[0117] To implement the above embodiments, this application also proposes a computer program product on which a computer program is stored. When the computer program is executed by a processor, it implements the wearable device-based assisted handling control method provided in the above embodiments.

[0118] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0119] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0120] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0121] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0122] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0123] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0124] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0125] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for assisted handling control based on wearable devices, characterized in that, The method includes: Obtain the object handling strategy for the target object to be moved in order to determine the first control dataset for the wearable device; Obtain the target stability analysis results corresponding to the first control dataset; Based on the target stability analysis results, a target control dataset for the wearable device is determined, and the wearable device is controlled through the target control dataset to move the target object based on the object handling strategy. The step of determining the target control dataset for the wearable device based on the target stability analysis results, and controlling the wearable device through the target control dataset to move the target object based on the object handling strategy, includes: Based on the first control dataset and the object handling strategy, a second control dataset is obtained from the output of the pre-acquired upper limb and waist joint control model, so as to obtain the corresponding target control data residual; The target control dataset is determined based on the target stability analysis results and the target control data residuals. Motion control is performed on the wearable device based on the target control dataset to assist the wearable device's wearable object in moving the target object based on the object handling strategy; The step of obtaining a second control dataset output by the pre-acquired upper limb and waist joint control model based on the first control dataset and the object handling strategy to obtain the corresponding target control data residual includes: Based on the first waist control data in the first control dataset and the object handling strategy, the second joint control data output by the upper limb waist joint control model is obtained. Based on the first joint control data in the first control dataset and the object handling strategy, the second waist control data output by the upper limb and waist joint control model is obtained; Based on the second joint control data and the second waist control data, the second control dataset of the wearable device is obtained; The residual of the second control dataset based on the first control dataset is obtained as the target control data residual.

2. The method according to claim 1, characterized in that, The step of determining the target control dataset based on the target stability analysis results and the target control data residuals includes: In response to the target stability analysis result indicating that the first control dataset is stable and the target control data residual is less than or equal to a preset residual threshold, the first control dataset is determined to be the target control dataset.

3. The method according to claim 1, characterized in that, The step of determining the target control dataset based on the target stability analysis results and the target control data residuals includes: In response to the target stability analysis result indicating that the first control dataset is abnormally stable, and / or the residual of the target control data is greater than the residual threshold, the control model of each first control data in the first control dataset is optimized respectively. Based on the new first control data output by each optimized control model, a new first control dataset is obtained. The new target stability analysis results and new target control data residuals corresponding to the new first control dataset are then obtained until the new target stability analysis results indicate that the stability is normal and the new target control data residuals are less than or equal to the residual threshold. The new first control dataset is then determined as the target control dataset.

4. The method according to claim 1, characterized in that, The method for obtaining the object handling strategy of the target object to be handled, in order to determine the first control dataset of the wearable device, includes: Based on the pre-acquired transport strategy output model and the acquired image of the target object, the object transport strategy of the target object is determined. Based on the object handling strategy, the first waist control data and the first joint control data of the wearable device are determined to determine the first control dataset.

5. The method according to claim 4, characterized in that, Based on the object handling strategy, the first waist control data and the first joint control data of the wearable device are determined to determine the first control dataset, including: Based on the object handling strategy, the object attribute data of the target object are obtained; Based on the pre-acquired wearable object attribute data and the object attribute data, the first waist control data of the wearable device is determined through the pre-acquired target waist control model. Based on the wearable object attribute data and the object attribute data, the first joint control data of the wearable device is determined through the pre-acquired target joint control model; Based on the first waist control data and the first joint control data, the first control dataset of the wearable device is determined.

6. The method according to claim 5, characterized in that, The step of obtaining the target stability analysis results corresponding to the first control dataset includes: The first waist control data in the first control dataset is compared with the preset stability conditions to obtain the first candidate stability analysis result of the first waist control data. The first joint control data in the first control dataset is compared with the stability condition to obtain the second candidate stability analysis result of the first joint control data; Based on the first candidate stability analysis results and the second candidate stability analysis results, the target stability analysis results are obtained.

7. An auxiliary handling control device based on wearable devices, characterized in that, The device includes: The first acquisition module is used to acquire the object handling strategy of the target object to be moved, so as to determine the first control dataset of the wearable device; The second acquisition module is used to acquire the target stability analysis results corresponding to the first control dataset; The control module is used to determine the target control dataset of the wearable device based on the target stability analysis results, so as to control the wearable device through the target control dataset to move the target object based on the object handling strategy; Furthermore, the control module is also used for: Based on the first control dataset and the object handling strategy, a second control dataset is obtained from the output of the pre-acquired upper limb and waist joint control model, so as to obtain the corresponding target control data residual; The target control dataset is determined based on the target stability analysis results and the target control data residuals. Motion control is performed on the wearable device based on the target control dataset to assist the wearable device's wearable object in moving the target object based on the object handling strategy; as well as, Based on the first waist control data in the first control dataset and the object handling strategy, the second joint control data output by the upper limb waist joint control model is obtained. Based on the first joint control data in the first control dataset and the object handling strategy, the second waist control data output by the upper limb and waist joint control model is obtained; Based on the second joint control data and the second waist control data, the second control dataset of the wearable device is obtained; The residual of the second control dataset based on the first control dataset is obtained as the target control data residual.

8. A robot, characterized in that, The robot is capable of performing the method as described in any one of claims 1-6.

Images