Data denoising method, device, electronic device and storage medium

Abstract

Embodiments of the present invention disclose a data denoising method, apparatus, electronic device, and storage medium. The method includes: obtaining collected data collected at the current time for the motion process of a robot's main hand, and a data denoising model that has been established for the robot's main hand, wherein the data denoising model stores historical estimated data; inputting the collected data into the data denoising model so that the data denoising model determines current estimated data based on the historical estimated data and the collected data; obtaining the current estimated data output by the data denoising model, and using the current estimated data as the denoised data obtained after denoising the collected data. The technical solution of the embodiment of the present invention can improve the denoising effect of the master-end robot hand data.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of data processing technology, and in particular to a data denoising method, device, electronic device, and storage medium. Background Art

[0002] At present, surgical robots are being used more and more widely in the medical field.

[0003] It should be noted that the data generated by the robotic hand on the surgical robot usually includes noise caused by the hand tremors of the medical staff operating the robotic hand. The denoising effect of the currently used data denoising scheme is poor and needs to be solved. Summary of the Invention

[0004] Embodiments of the present invention provide a data denoising method, device, electronic device, and storage medium, which can improve the denoising effect of master-side robotic arm data.

[0005] According to one aspect of the present invention, a data denoising method is provided, which may include:

[0006] Acquire collected data collected from the motion process of the robot's main hand at the current time, and a data denoising model that has been established for the robot's main hand, wherein the data denoising model stores historical estimated data;

[0007] Inputting the collected data into a data denoising model so that the data denoising model determines current estimated data based on the historical estimated data and the collected data;

[0008] Obtaining current estimated data output by the data denoising model, and using the current estimated data as denoised data obtained after denoising the collected data;

[0009] The historical estimation data is determined based on the collected data collected from the motion process of the robot's main hand at the previous time, and the previous time includes the historical time closest to the current time among multiple historical times collected from the motion process of the robot's main hand.

[0010] According to another aspect of the present invention, a data denoising apparatus is provided, which may include:

[0011] a data denoising model acquisition module, configured to acquire the collected data collected from the motion process of the robot's main hand at the current time, and the established data denoising model for the robot's main hand, wherein the data denoising model stores historical estimated data;

[0012] a current estimated data determination module, configured to input the collected data into a data denoising model so that the data denoising model determines the current estimated data based on the historical estimated data and the collected data;

[0013] The denoised data is used as a module to obtain the current estimated data output by the data denoising model, and the current estimated data is used as the denoised data obtained after denoising the collected data;

[0014] The historical estimation data is determined based on the collected data collected from the motion process of the robot's main hand at the previous time, and the previous time includes the historical time closest to the current time among multiple historical times collected from the motion process of the robot's main hand.

[0015] According to another aspect of the present invention, there is provided an electronic device, which may include:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor implements the data denoising method provided by any embodiment of the present invention when executing the computer program.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer instructions are stored. The computer instructions are used to enable a processor to implement the data denoising method provided by any embodiment of the present invention when executed.

[0020] The technical solution of an embodiment of the present invention obtains collected data obtained from the motion process of a robot master hand at the current time, and a data denoising model for the robot master hand that has been established, wherein the data denoising model stores historical estimated data; inputs the collected data into the data denoising model so that the data denoising model determines current estimated data based on the historical estimated data and the collected data; obtains the current estimated data output by the data denoising model, and uses the current estimated data as the denoised data obtained after denoising the collected data; wherein the historical estimated data is determined based on collected data obtained from the motion process of the robot master hand at a previous time, wherein the previous time includes the historical time closest to the current time among multiple historical times collected for the motion process of the robot master hand. The above technical solution, combined with the historical estimated data, uses a model to determine the denoised data, which can improve the denoising effect of the master-end robot hand data.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a data denoising method provided according to an embodiment of the present invention;

[0024] Figure 2 is a flow chart of another data denoising method provided according to an embodiment of the present invention;

[0025] Figure 3 is a flow chart of another data denoising method provided according to an embodiment of the present invention;

[0026] Figure 4 is a flow chart of another data denoising method provided according to an embodiment of the present invention;

[0027] Figure 5 is a flowchart of an optional example of another data denoising method provided according to an embodiment of the present invention;

[0028] Figure 6 is a flowchart of another optional example of a data denoising method provided according to an embodiment of the present invention;

[0029] Figure 7 is a structural block diagram of a data denoising device provided according to an embodiment of the present invention;

[0030] Figure 8 3 is a schematic structural diagram of an electronic device for implementing the data denoising method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The situations of "target", "original", etc. are similar and will not be repeated here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or devices.

[0033] Figure 1 This is a flow chart of a data denoising method provided in an embodiment of the present invention. This embodiment is applicable to data denoising scenarios. The method can be performed by a data denoising device provided in an embodiment of the present invention. This device can be implemented using software and / or hardware and can be integrated into an electronic device, such as various user terminals or servers.

[0034] See also Figure 1 The method of the embodiment of the present invention specifically includes the following steps:

[0035] S110. Acquire the collected data obtained by collecting the motion process of the robot main hand at the current time, and the established data denoising model for the robot main hand, wherein the data denoising model stores historical estimation data, and the historical estimation data is determined based on the collected data obtained by collecting the motion process of the robot main hand at the previous time, and the previous time includes the historical time closest to the current time among multiple historical times collected for the motion process of the robot main hand.

[0036] The robot's main hand may be a medical surgical robot's main hand. The data denoising model is used to denoise the collected data; for example, the data denoising model may be an encoder. In this embodiment of the present invention, there is no specific limitation on the type of data denoising model. The historical estimated data is current estimated data determined based on the collected data obtained from the previous time period regarding the movement of the robot's main hand.

[0037] In an embodiment of the present invention, the collected data collected from the motion process of the robot's main hand at the current time and the established data denoising model for the robot's main hand can be obtained through sensors.

[0038] It should be noted that the collected data is obtained by collecting data on the movement process of the robot's main hand. The collected data may include, for example, data such as the rotation angle, movement direction and / or movement distance of the robot's main hand. In the embodiment of the present invention, there is no specific limitation on the content of the collected data.

[0039] S120: Input the collected data into a data denoising model, so that the data denoising model determines current estimated data based on the historical estimated data and the collected data.

[0040] The current estimated data is the data without noise obtained after the data denoising model denoises the collected data.

[0041] S130: Obtain current estimated data output by the data denoising model, and use the current estimated data as denoised data obtained after denoising the collected data.

[0042] The denoised data is the data obtained by removing noise from the collected data.

[0043] It should be noted that the current estimated data is the data without noise estimated by the data denoising model. Therefore, after obtaining the current estimated data output by the data denoising model, the current estimated data can be used as the denoised data obtained after denoising the collected data.

[0044] In the embodiment of the present invention, for example, the robot's slave hand can be controlled to move based on the denoised data, or the denoised data can be displayed to a user so that the user can monitor the movement of the robot's master hand, etc. In the embodiment of the present invention, the function of the denoised data is not specifically limited.

[0045] The technical solution of an embodiment of the present invention obtains collected data obtained from the motion process of a robot master hand at the current time, and a data denoising model for the robot master hand that has been established, wherein the data denoising model stores historical estimated data; inputs the collected data into the data denoising model so that the data denoising model determines current estimated data based on the historical estimated data and the collected data; obtains the current estimated data output by the data denoising model, and uses the current estimated data as the denoised data obtained after denoising the collected data; wherein the historical estimated data is determined based on collected data obtained from the motion process of the robot master hand at a previous time, wherein the previous time includes the historical time closest to the current time among multiple historical times collected for the motion process of the robot master hand. The above technical solution, combined with the historical estimated data, uses a model to determine the denoised data, which can improve the denoising effect of the master-end robot hand data.

[0046] An optional technical solution, after obtaining the current estimated data output by the data denoising model, further includes: updating the historical estimated data stored in the data denoising model according to the current estimated data.

[0047] In an embodiment of the present invention, after obtaining the current estimated data output by the data denoising model, the historical estimated data stored in the data denoising model can be updated based on the current estimated data. That is, the current estimated data can be updated to the historical estimated data stored in the data denoising model, so that the denoised data can be determined based on the updated historical estimated data at the next time. The above technical solution can update the historical estimated data stored in the data denoising model based on the current estimated data obtained at the current time, so that the process of determining the denoised data at the next time involves the factor of the current time, thereby improving the accuracy of the determined denoised data.

[0048] Figure 2 This is a flowchart of another data denoising method provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, the data denoising model also stores historical jitter noise data and historical other noise data; based on the historical estimated data and the collected data, the current estimated data is determined, including: determining the Kalman gain coefficient based on the historical jitter noise data and the historical other noise data; determining the current estimated data based on the historical estimated data, the collected data and the Kalman gain coefficient; wherein the historical jitter noise data is the jitter noise data estimated at the previous time, and the historical other noise data is the noise data other than the jitter noise data estimated at the previous time. The explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0049] See also Figure 2 The method of this embodiment may specifically include the following steps:

[0050] S210. Acquire collected data collected for the motion process of the robot main hand at the current time, and a data denoising model for the robot main hand that has been established, wherein the data denoising model stores historical estimated data, the historical estimated data is determined based on the collected data collected for the motion process of the robot main hand at a previous time, the previous time includes the historical time closest to the current time among multiple historical times collected for the motion process of the robot main hand, the data denoising model also stores historical jitter noise data and historical other noise data, the historical jitter noise data is the jitter noise data estimated at the previous time, and the historical other noise data is the noise data other than the jitter noise data estimated at the previous time.

[0051] Jitter noise data refers to noise data generated by the jitter of the robot's main hand during its movement. For example, the jitter noise data may include angle offset data, movement direction offset data, and / or movement distance offset data generated by the jitter of the robot's main hand. Noise data other than jitter noise data refers to noise data caused by other objective factors other than the jitter noise data.

[0052] S220 , inputting the collected data into the data denoising model so that the data denoising model executes steps S230 to S240 .

[0053] S230 : Determine a Kalman gain coefficient according to historical jitter noise data and historical other noise data.

[0054] In an embodiment of the present invention, the data denoising model may be a data denoising model established based on a Kalman filter algorithm. The data denoising model may determine a Kalman gain coefficient according to historical jitter noise data and historical other noise data.

[0055] It should be noted that when it is required to control the movement of the robot slave hand according to the denoised data, the data denoising model established based on the Kalman filter algorithm can effectively reduce the delay in the master and slave of the surgical robot.

[0056] In the embodiment of the present invention, there is no specific limitation on the method of determining the Kalman gain coefficient based on the historical jitter noise data and the historical other noise data.

[0057] S240: Determine current estimated data based on historical estimated data, collected data, and Kalman gain coefficients.

[0058] In the embodiment of the present invention, the data denoising model can determine the current estimated data based on the historical estimated data, the collected data, and the Kalman gain coefficient. In the embodiment of the present invention, the method for determining the current estimated data based on the historical estimated data, the collected data, and the Kalman gain coefficient is not specifically limited.

[0059] S250: Obtain current estimated data output by the data denoising model, and use the current estimated data as denoised data obtained after denoising the collected data.

[0060] In the technical solution of an embodiment of the present invention, the data denoising model also stores historical jitter noise data and historical other noise data; a Kalman gain coefficient is determined based on the historical jitter noise data and historical other noise data; and current estimated data is determined based on historical estimated data, collected data, and the Kalman gain coefficient. The historical jitter noise data is the jitter noise data estimated at a previous time, and the historical other noise data is the noise data other than the jitter noise data estimated at a previous time. This technical solution, by determining the Kalman gain coefficient, introduces a Kalman filter algorithm into the data denoising model, and uses the historical jitter noise data and historical other noise data as determining factors for determining the current estimated data, thereby improving the accuracy of the determined current estimated data.

[0061] An optional technical solution, after determining the Kalman gain coefficient based on the historical jitter noise data and the historical other noise data, further includes: updating the historical jitter noise data and the historical other noise data stored in the data denoising model based on the Kalman gain coefficient.

[0062] In an embodiment of the present invention, after determining the Kalman gain coefficient based on the historical jitter noise data and the historical other noise data, the current jitter noise data may be determined as the current other noise data based on the Kalman gain coefficient, where the current jitter noise data is the jitter noise data estimated at the current time, and the current other noise data is noise data other than the jitter noise data estimated at the current time; and the historical jitter noise data and the historical other noise data stored in the data denoising model may be updated based on the current jitter noise data. In this embodiment of the present invention, the method for updating the historical jitter noise data and the historical other noise data stored in the data denoising model based on the Kalman gain coefficient is not specifically limited.

[0063] In an embodiment of the present invention, the current jitter noise data can be determined as the current other noise data based on the Kalman gain coefficient, the historical jitter noise data, and the historical other noise data; and the historical jitter noise data and the historical other noise data stored in the data denoising model can be updated based on the current jitter noise data.

[0064] The above technical solution can update the historical jitter noise data and historical other noise data stored in the data denoising model according to the Kalman gain coefficient, so that the process of determining the denoised data at the next time involves the noise factors at the current time, thereby improving the accuracy of the determined denoised data.

[0065] Figure 3It is a flowchart of another data denoising method provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, a data denoising model is established by the following steps: obtaining at least one first sample data generated by operating the robot's main hand movement without shaking, at least one second sample data generated by manually operating the robot's main hand movement smoothly, and at least one third sample data generated by manually operating the robot's main hand movement with shaking; based on the at least one first sample data, at least one second sample data and at least one third sample data, a data denoising model is established. Among them, the explanations of the terms that are the same as or corresponding to the above-mentioned embodiments are not repeated here.

[0066] See also Figure 3 The method of this embodiment may specifically include the following steps:

[0067] S310. Acquire at least one first sample data generated by operating the robot's main hand movement without shaking, at least one second sample data generated by manually and smoothly operating the robot's main hand movement, and at least one third sample data generated by manually and jitterily operating the robot's main hand movement.

[0068] The first sample data is generated by jitter-free manipulation of the robot's main hand. Jitter-free manipulation is ideal jitter-free manipulation, such as through programmed manipulation or jitter-free robot manipulation. The second sample data is generated by manually and smoothly manipulating the robot's main hand. Manual smooth manipulation is manipulation performed in a static state, without complex operations, or with small amplitudes, with minimal jitter. The third sample data is generated by manually and jitter-free manipulation of the robot's main hand. Manual jitter manipulation is manipulation performed in a complex or large-amplitude state, with the potential for significant jitter.

[0069] It should be noted that at least one second sample data can be obtained by multiple operators and / or operators manually and smoothly operating the robot's main hand movement multiple times; and at least one third sample data can be obtained by multiple operators and / or operators manually and jitteringly operating the robot's main hand movement multiple times.

[0070] S320: Establish a data denoising model based on at least one first sample data, at least one second sample data, and at least one third sample data.

[0071] In the embodiment of the present invention, there is no specific limitation on the manner of establishing the data denoising model based on at least one first sample data, at least one second sample data, and at least one third sample data.

[0072] S330. Acquire the collected data collected for the motion process of the robot main hand at the current time, and the established data denoising model for the robot main hand, wherein the data denoising model stores historical estimation data, and the historical estimation data is determined based on the collected data collected for the motion process of the robot main hand at the previous time, and the previous time includes the historical time closest to the current time among multiple historical times collected for the motion process of the robot main hand.

[0073] S340: Input the collected data into a data denoising model, so that the data denoising model determines current estimated data based on the historical estimated data and the collected data.

[0074] S350: Obtain current estimated data output by the data denoising model, and use the current estimated data as denoised data obtained after denoising the collected data.

[0075] The technical solution of the embodiment of the present invention obtains at least one first sample data generated by operating the robot's main hand without jitter, at least one second sample data generated by manually operating the robot's main hand smoothly, and at least one third sample data generated by manually operating the robot's main hand with jitter; and establishes a data denoising model based on the at least one first sample data, at least one second sample data, and at least one third sample data. The above technical solution can obtain data generated by operating the robot's main hand without jitter, manually operating smoothly, and manually operating with jitter, and establish a data denoising model based on the data obtained in multiple situations, thereby improving the established data denoising model's applicability to a variety of different scenarios, thereby improving the accuracy of the current estimated data determined according to the data denoising model.

[0076] An optional technical solution establishes a data denoising model based on at least one first sample data, at least one second sample data and at least one third sample data, including: determining the accuracy error when operating the robot's main hand without jitter based on the at least one first sample data; establishing a data denoising model based on the accuracy error, at least one first sample data, at least one second sample data and at least one third sample data.

[0077] The precision error is the error between at least one first sample data.

[0078] It should be noted that at least one first sample data may be generated by adopting a variety of different jitter-free operation robot main hand movements, and may also be generated by multiple jitter-free operation robot main hand movements. Therefore, there may be certain errors between at least one first sample data due to different types and / or different times of jitter-free operation. Therefore, in an embodiment of the present invention, the accuracy error in the case of jitter-free operation robot main hand movement can be determined based on at least one first sample data; and a data denoising model is established based on the accuracy error, at least one first sample data, at least one second sample data, and at least one third sample data.

[0079] In an embodiment of the present invention, there is no specific limitation on the method of determining the accuracy error in the case of jitter-free operation of the robot's main hand based on at least one first sample data, and establishing a data denoising model based on the accuracy error, at least one first sample data, at least one second sample data, and at least one third sample data.

[0080] The above technical solution can improve the accuracy of the established data denoising model by taking the precision error as one of the factors for establishing the data denoising model, thereby further improving the accuracy of the current estimated data determined according to the data denoising model.

[0081] Figure 4 This is a flowchart of another data denoising method provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, a data denoising model is established by the following steps: obtaining at least one first sample data generated by operating the robot's main hand movement without shaking, at least one second sample data generated by manually operating the robot's main hand movement smoothly, and at least one third sample data generated by manually operating the robot's main hand movement with shaking; based on the at least one first sample data, at least one second sample data and at least one third sample data, a data denoising model is established. The explanations of the terms that are the same as or corresponding to the above-mentioned embodiments are not repeated here.

[0082] See also Figure 4 The method of this embodiment may specifically include the following steps:

[0083] S410. Acquire at least one first sample data generated by operating the robot's main hand movement without shaking, at least one second sample data generated by manually and smoothly operating the robot's main hand movement, and at least one third sample data generated by manually and jitterily operating the robot's main hand movement.

[0084] S420: Establish a data denoising model based on at least one first sample data, at least one second sample data, and at least one third sample data.

[0085] Exemplarily, a data denoising model can be established based on at least one first sample data, at least one second sample data, and at least one third sample data. The data denoising model can be implemented using the function g(x)=f(x)*h(x)+N1(x)+N2(x). Here, g(x) is the collected data; f(x) is the current estimated data; h(x) is the convolution kernel of the signal processing part in the data denoising model; N1(x) is the jitter noise data; and N2(x) is the noise data other than the jitter noise data.

[0086] S430. Acquire collected data collected for the motion process of the robot's main hand at the current time, and a data denoising model for the robot's main hand that has been established, wherein the data denoising model stores historical estimated data, the historical estimated data is determined based on the collected data collected for the motion process of the robot's main hand at a previous time, the previous time includes the historical time closest to the current time among multiple historical times collected for the motion process of the robot's main hand, the data denoising model also stores historical jitter noise data and historical other noise data, the historical jitter noise data is the jitter noise data estimated at the previous time, and the historical other noise data is the noise data other than the jitter noise data estimated at the previous time.

[0087] S440 , inputting the collected data into the data denoising model so that the data denoising model executes steps S450 to S460 .

[0088] S450: Determine a Kalman gain coefficient according to historical jitter noise data and historical other noise data.

[0089] S460: Determine current estimated data based on historical estimated data, collected data, and Kalman gain coefficients.

[0090] S470: Obtain current estimated data output by the data denoising model, and use the current estimated data as denoised data obtained after denoising the collected data.

[0091] The technical solution of the embodiment of the present invention obtains at least one first sample data generated by operating the robot's main hand without jitter, at least one second sample data generated by manually operating the robot's main hand smoothly, and at least one third sample data generated by manually operating the robot's main hand with jitter; and establishes a data denoising model based on the at least one first sample data, at least one second sample data, and at least one third sample data. The above technical solution can obtain data generated by operating the robot's main hand without jitter, manually operating smoothly, and manually operating with jitter, and establish a data denoising model based on the data obtained in multiple situations, thereby improving the established data denoising model's applicability to a variety of different scenarios, thereby improving the accuracy of the current estimated data determined according to the data denoising model.

[0092] An optional technical solution, when the data denoising model also stores historical jitter noise data and historical other noise data, the method also includes: determining initial estimation data, initial jitter noise data and initial other noise data based on at least one first sample data, at least one second sample data and at least one third sample data; when the current time is the time when the movement process of the robot's main hand is first collected, the initial estimation data is used as the historical estimation data, the initial jitter noise data is used as the historical jitter noise data, and the initial other noise data is used as the historical other noise data.

[0093] The initial estimated data is denoised data obtained by estimating the initial historical estimated data. The initial dither noise data is dither noise data obtained by estimating the initial historical dither noise data. The initial other noise data is noise data other than the dither noise data obtained by estimating the initial historical other noise data.

[0094] It should be noted that when the current time is the first time the motion process of the robot's main hand is collected, the current time does not correspond to a previous time, and accordingly, the data denoising model does not store historical estimated data, historical jitter noise data, and historical other noise data. In order to normally denoise the collected data to obtain denoised data when the current time is the first time the motion process of the robot's main hand is collected, in an embodiment of the present invention, initial estimated data, initial jitter noise data, and initial other noise data can be determined based on at least one first sample data, at least one second sample data, and at least one third sample data; after the data denoising model is established, the initial estimated data, initial jitter noise data, and initial other noise data can be stored in the data denoising model; when the current time is the first time the motion process of the robot's main hand is collected, the initial estimated data is used as the historical estimated data, the initial jitter noise data is used as the historical jitter noise data, and the initial other noise data is used as the historical other noise data, so as to determine the denoised data based on the historical estimated data, historical jitter noise data, and historical other noise data.

[0095] In the embodiment of the present invention, there is no specific limitation on the manner of determining the initial estimation data, the initial jitter noise data and the initial other noise data based on the at least one first sample data, the at least one second sample data and the at least one third sample data.

[0096] In an embodiment of the present invention, it is also possible to collect and obtain the preceding data obtained by collecting the motion process of the robot's main hand before the current time is the time when the motion process of the robot's main hand is collected for the first time. The preceding data is the collected data obtained by collecting the motion process of the robot's main hand before the current time; the initial estimated data is determined based on the preceding data. For example, the preceding data can be used as the initial estimated data. In an embodiment of the present invention, there is no specific limitation on the method of determining the initial estimated data based on the preceding data.

[0097] The above technical solution can obtain denoised data after normally denoising the collected data when the current time is the time when the motion process of the robot's main hand is first collected.

[0098] In order to better understand the technical solution of the above embodiment of the present invention, an optional example is provided here. Figure 5 , the initial jitter noise data N1_0(x) and the initial other noise data N2_0(x) can be determined according to the accuracy error, at least one first sample data, at least one second sample data, and at least one third sample data; the initial estimated data can be determined according to the pre-data g(k-1|k-1) (x); the initial estimated data As historical estimates (k|k-1), the initial jitter noise data N1_0(x) is used as the historical jitter noise data N1(k|k-1), and the initial other noise data N2_0(x) is used as the historical other noise data N2(k|k-1); the collected data g(k|k) collected at the current time for the movement process of the robot main hand, and the established data denoising model for the robot main hand; the collected data is input into the data denoising model so that the data denoising model is based on the historical jitter noise data N1(k|k-1) and the historical other noise data N2(k|k-1), through the formula K k =N1(k|k-1) / (N1(k|k-1)+N2(k|k-1)) to determine the Kalman gain coefficient K k , and based on the historical estimated data, collected data and Kalman gain coefficient, through the formula Determine current estimates (k|k); according to the Kalman gain coefficient K k , by the formula N1(k|k)=(1-K k )N1(k|k-1) and the formula N2(k|k)=(1-K k )N2(k|k-1), determine the current jitter noise data N1(k|k) and the current other noise data N2(k|k); according to the current jitter noise data and the current other noise data, update the historical jitter noise data N1(k|k-1) and the historical other noise data N2(k|k-1) stored in the data denoising model through the formula N1(k|k-1)=N1(k|k) and the formula N2(k|k-1)=N2(k|k); according to the current estimated data (k|k), updates the historical estimated data stored in the data denoising model (k|k-1); get the current estimated data output by the data denoising model (k|k), and the current estimated data is used as the denoised data obtained after denoising the collected data (k|k).

[0099] In order to better understand the technical solution of the above embodiment of the present invention, an optional example is provided here. Figure 6, based on at least one first sample data, at least one second sample data and at least one third sample data, model basic information can be determined, and the model basic information can include information such as function formula and / or model parameters required for establishing a data denoising model, for example, the model basic information can include the function formula g(x)=f(x)*h(x)+N1(x)+N2(x); according to the model basic information, a data denoising model is established; according to the at least one first sample data, at least one second sample data and at least one third sample data, initial estimation data, initial jitter noise data and initial other noise data are determined; the initial estimation data is used as historical estimation data and stored in the data denoising model, and the initial jitter noise data is used as historical estimation data The historical jitter noise data is collected and stored in the data denoising model, and the initial other noise data is used as the historical other noise data and stored in the data denoising model; the data denoising model is updated based on the Kalman filter algorithm, and the data denoising model is updated to a data denoising model that can be adaptively processed; the collected data collected at the current time for the movement process of the robot main hand, and the established data denoising model for the robot main hand are obtained; the collected data is input into the data denoising model, so that the data denoising model determines the current estimated data based on the historical estimated data and the collected data; the current estimated data output by the data denoising model is obtained, and the current estimated data is used as the denoised data obtained after denoising the collected data.

[0100] Figure 7 This is a structural block diagram of a data denoising device provided in an embodiment of the present invention. The device is used to perform the data denoising method provided in any of the above embodiments. The device and the data denoising method of the above embodiments belong to the same inventive concept. For details not fully described in the embodiments of the data denoising device, please refer to the embodiments of the above data denoising method. Figure 7 The device may specifically include: a data denoising model acquisition module 510, a current estimated data determination module 520 and a denoising data as module 530.

[0101] The data denoising model acquisition module 510 is configured to acquire the collected data collected from the motion process of the robot's main hand at the current time, and the established data denoising model for the robot's main hand, wherein the data denoising model stores historical estimated data.

[0102] a current estimated data determination module 520 for inputting the collected data into a data denoising model so that the data denoising model determines the current estimated data based on the historical estimated data and the collected data;

[0103] Denoised data is used as module 530 to obtain current estimated data output by the data denoising model, and use the current estimated data as the denoised data obtained after denoising the collected data;

[0104] The historical estimation data is determined based on the collected data collected from the motion process of the robot's main hand at the previous time, and the previous time includes the historical time closest to the current time among multiple historical times collected from the motion process of the robot's main hand.

[0105] Optionally, the data denoising model also stores historical jitter noise data and historical other noise data;

[0106] The current estimated data determination module 520 may include:

[0107] A Kalman gain coefficient determination unit, configured to determine a Kalman gain coefficient based on historical jitter noise data and historical other noise data;

[0108] a current estimation data determination unit, configured to determine current estimation data based on historical estimation data, collected data, and a Kalman gain coefficient;

[0109] The historical jitter noise data is the jitter noise data estimated at a previous time, and the historical other noise data is the noise data other than the jitter noise data estimated at a previous time.

[0110] Optionally, based on the above device, the device may further include:

[0111] The historical other noise data updating module is used to update the historical jitter noise data and historical other noise data stored in the data denoising model according to the Kalman gain coefficient after determining the Kalman gain coefficient according to the historical jitter noise data and historical other noise data.

[0112] Optionally, based on the above device, the device may further include the following modules to establish a data denoising model:

[0113] a third sample data acquisition module, configured to acquire at least one first sample data generated by operating the robot's main hand without shaking, at least one second sample data generated by manually operating the robot's main hand smoothly, and at least one third sample data generated by manually operating the robot's main hand with shaking;

[0114] The data denoising model establishing module is used to establish a data denoising model based on at least one first sample data, at least one second sample data and at least one third sample data.

[0115] Optionally, based on the above device, when the data denoising model further stores historical jitter noise data and historical other noise data, the device may further include:

[0116] an initial other noise data determining module, configured to determine initial estimation data, initial jitter noise data, and initial other noise data based on at least one first sample data, at least one second sample data, and at least one third sample data;

[0117] The historical other noise data is used as a module, which is used to use the initial estimation data as the historical estimation data, the initial jitter noise data as the historical jitter noise data, and the initial other noise data as the historical other noise data when the current time is the time when the motion process of the robot's main hand is first collected.

[0118] Optionally, based on the above device, the data denoising model establishment module may include:

[0119] an accuracy error determining unit, configured to determine, based on at least one first sample data, an accuracy error in a case where a main hand of the robot is moved without jitter operation;

[0120] The data denoising model establishing unit is used to establish a data denoising model according to the precision error, at least one first sample data, at least one second sample data and at least one third sample data.

[0121] Optionally, the device may further include:

[0122] The historical estimation data updating module is used to update the historical estimation data stored in the data denoising model according to the current estimation data after obtaining the current estimation data output by the data denoising model.

[0123] The data denoising device provided in an embodiment of the present invention acquires, through a data denoising model acquisition module, collected data obtained from the motion process of a robot master hand at the current time, and a data denoising model for the robot master hand that has been established, wherein the data denoising model stores historical estimated data; inputs the collected data into the data denoising model through a current estimated data determination module, so that the data denoising model determines current estimated data based on the historical estimated data and the collected data; obtains current estimated data output by the data denoising model through a denoising data as module, and uses the current estimated data as the denoised data obtained after denoising the collected data; wherein the historical estimated data is determined based on collected data obtained from the motion process of the robot master hand at a previous time, wherein the previous time includes the historical time closest to the current time among multiple historical times collected for the motion process of the robot master hand. The above-mentioned device, in combination with the historical estimated data, uses a model to determine denoising data, thereby improving the denoising effect of the master-end robot hand data.

[0124] The data denoising device provided in the embodiment of the present invention can execute the data denoising method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0125] It is worth noting that in the embodiment of the above-mentioned data denoising device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0126] Figure 8 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0127] like Figure 8As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0128] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0129] The processor 11 may be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the data denoising method.

[0130] In some embodiments, the data denoising method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the data denoising method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the data denoising method in any other suitable manner (e.g., by means of firmware).

[0131] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0133] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0134] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0135] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0136] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0137] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0138] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A data denoising method, characterized in that: include: Acquire collected data obtained from a motion process of a robot master hand at a current time, and a data denoising model established for the robot master hand, wherein the data denoising model stores historical estimation data; inputting the collected data into the data denoising model so that the data denoising model determines current estimated data based on the historical estimated data and the collected data; Obtaining the current estimated data output by the data denoising model, and using the current estimated data as denoised data obtained after denoising the collected data; The historical estimated data is determined based on collected data collected from a motion process of the robot's main hand at a previous time, wherein the previous time includes a historical time closest to the current time among multiple historical times collected from the motion process of the robot's main hand; The data denoising model also stores historical jitter noise data and historical other noise data; The determining of current estimated data based on the historical estimated data and the collected data includes: Determining a Kalman gain coefficient according to the historical jitter noise data and the historical other noise data; Determining current estimated data based on the historical estimated data, the collected data, and the Kalman gain coefficient; The historical jitter noise data is the jitter noise data estimated at the previous time, and the historical other noise data is the noise data other than the jitter noise data estimated at the previous time; The data denoising model is established through the following steps: Acquire at least one first sample data generated by operating the robot's main hand without shaking, at least one second sample data generated by manually operating the robot's main hand smoothly, and at least one third sample data generated by manually operating the robot's main hand with shaking; Establishing the data denoising model based on the at least one first sample data, the at least one second sample data, and the at least one third sample data; In the case where the data denoising model further stores historical jitter noise data and historical other noise data, the method further includes: determining initial estimation data, initial jitter noise data, and initial other noise data based on the at least one first sample data, the at least one second sample data, and the at least one third sample data; When the current time is the time when the motion process of the robot main hand is first collected, the initial estimated data is used as the historical estimated data, the initial jitter noise data is used as the historical jitter noise data, and the initial other noise data is used as the historical other noise data.

2. The method according to claim 1, characterized in that After determining the Kalman gain coefficient according to the historical jitter noise data and the historical other noise data, the method further includes: The historical jitter noise data and the historical other noise data stored in the data denoising model are updated according to the Kalman gain coefficient.

3. The method according to claim 1, characterized in that The establishing the data denoising model based on the at least one first sample data, the at least one second sample data, and the at least one third sample data includes: determining, based on the at least one first sample data, an accuracy error in a case where the robot master hand moves in the jitter-free operation; The data denoising model is established according to the precision error, the at least one first sample data, the at least one second sample data, and the at least one third sample data.

4. The method according to claim 1, wherein After obtaining the current estimated data output by the data denoising model, the method further includes: The historical estimation data stored in the data denoising model is updated according to the current estimation data.

5. A data denoising device, characterized in that: include: a data denoising model acquisition module, configured to acquire collected data collected from the motion process of the robot's main hand at the current time, and a data denoising model established for the robot's main hand, wherein the data denoising model stores historical estimated data; a current estimated data determination module, configured to input the collected data into the data denoising model, so that the data denoising model determines current estimated data based on the historical estimated data and the collected data; Denoising data as a module, used to obtain the current estimated data output by the data denoising model, and use the current estimated data as the denoised data obtained after denoising the collected data; The historical estimated data is determined based on collected data collected from a motion process of the robot's main hand at a previous time, wherein the previous time includes a historical time closest to the current time among multiple historical times collected from the motion process of the robot's main hand; The data denoising model also stores historical jitter noise data and historical other noise data; The current estimated data determination module includes: a Kalman gain coefficient determining unit, configured to determine a Kalman gain coefficient based on the historical jitter noise data and the historical other noise data; a current estimation data determining unit, configured to determine current estimation data based on the historical estimation data, the collected data, and the Kalman gain coefficient; The historical jitter noise data is the jitter noise data estimated at the previous time, and the historical other noise data is the noise data other than the jitter noise data estimated at the previous time; The device also includes the following modules to establish the data denoising model: a third sample data acquisition module, configured to acquire at least one first sample data generated by operating the robot's main hand without jitter, at least one second sample data generated by manually and smoothly operating the robot's main hand, and at least one third sample data generated by manually operating the robot's main hand with jitter; a data denoising model establishing module, configured to establish the data denoising model based on the at least one first sample data, the at least one second sample data, and the at least one third sample data; In a case where the data denoising model further stores historical jitter noise data and historical other noise data, the apparatus further includes: an initial other noise data determining module, configured to determine initial estimation data, initial jitter noise data, and initial other noise data based on the at least one first sample data, the at least one second sample data, and the at least one third sample data; The historical other noise data is used as a module, which is used to use the initial estimation data as the historical estimation data, the initial jitter noise data as the historical jitter noise data, and the initial other noise data as the historical other noise data when the current time is the time when the motion process of the robot main hand is first collected.

6. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the data denoising method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the data denoising method according to any one of claims 1 to 4 when executed.

Images