DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Claims 1, 5-13, and 15-20 have been amended. Claims 3, 4, and 14 have been newly canceled. Claim 21 has been newly added. Claims 1-2, 5-13, and 15-21 remain pending in the present application. The previous objections to the specification, the objections to claims 7, 13-14, 17, 19, and 20, and the 35 U.S.C. § 112(b) rejection of claim 17, have been withdrawn as a result of amendment.
Response to Arguments
Applicant's arguments with respect to the 35 U.S.C. § 103 rejection of claim 1 have been fully considered but they are not persuasive.
Regarding claim 1, Applicant argues that the combination of Yang, Yamanaka, and Xiong fails to teach claim 1 as amended. Specifically, Applicant argues that while Xiong does disclose wherein edge devices directly transmit the upgraded control model to another edge server, Xiong fails to teach wherein “the more evolved/accurate models are provided to a lower level device that is in a same group as the supervisor device, where the group is based on distance from a cloud server.” The examiner asserts, however, that the combination of Yamanaka and Xiong does render the asserted difference obvious (see the 35 U.S.C. § 103 rejection of at least claim 1 below).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 5, 15-16, 18-19, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Yang (CN111360813A), hereafter Yang, in view of Yamanaka (JP20181484321A), and further in view of Xiong (US 20190079898 A1), hereafter Xiong.
Regarding claim 1, Yang teaches a cloud-based robot system comprising:
A plurality of robots (0015, robot control unit is the core system layer of the controller, providing analytical methods for robot models of various configurations to support the motion control of multiple robots and realize real-time control of multiple robots);
A cloud server generating a control base model applicable to the plurality of robots (0025, atomic robot control function in the edge robot cloud service used to build a multi-robot control application using a service combination method, and generates an application execution script based on the edge multi-robot controller); and
An edge server (0031, multi-robot controller based on edge cloud services utilizes the distributed characteristics of the edge computing framework to realize multi-robot control and has good multi-machine scalability),
Wherein the edge server is allocated to a corresponding space of a plurality of spaces, communicates with the cloud server, and receives the control base model, the edge server controlling a corresponding subset of the plurality of robots deployed in the corresponding space based on the control base model (0026-0029, in the multi-robot controller, the application execution script is parsed to generate an executable multi-robot control program, in the kernel system layer of the multi-robot controller, a multi-robot control task is formed, in the kernel driver layer of the multi-robot controller, the motion control instructions of each robot in the multi-robot control task are sent to the corresponding robot through the real-time bus by the virtualization unit, robot cluster responds to the control tasks of the multi-robot controller to complete the multi-robot collaborative control),
Wherein the corresponding subset of the plurality of robots comprises different types of robots in the corresponding space (0015, robot control unit is the core system layer of the controller, providing analytical methods for robot models of various configurations to support the motion control of multiple robots and realize real-time control of multiple robots), and
Wherein the edge server upgrades the control base model according to the different types of robots in the corresponding space to control the corresponding subset of the plurality of robots based on the upgraded control base model (0027, the multi-robot control task is formed by utilizing the artificial intelligence unit, 0059, multi-robot controller including an artificial intelligence unit, 0047, artificial intelligence unit automatically optimizes the solution process to obtain the optimal motion trajectory of the robot within the control cycle, and provides advanced intelligent control methods including intelligent algorithms, machine vision, and force control to improve the autonomy of multi-robot control).
Yang fails to teach, however, wherein the system comprises:
A plurality of edge servers classified by the server into a plurality of groups based on distance from the cloud server, and
Wherein the edge server directly transmits the upgraded control base model to a second edge server that is in a same group as the edge server.
Yamanaka, however, in an analogous field of endeavor, does teach wherein the system comprises:
A plurality of edge servers classified by the server into a plurality of groups based on distance from the cloud server (0033, The aggregation network 3 has a tree structure, and is composed of, for example, a relay router 3_3_1 to which an automobile 1_2_1 is connected, a relay router 3_3_2_ to which an automobile 1_2_s is connected, a relay router 3_2_1 directly above the relay routers 3_3_1 and 3_3_2, and a relay router 3_1_1 directly above the relay router 3_2_1. The root of the tree structure in this aggregation network 3 is the service cloud 2, which includes a control server 2_2. Examiner's note: the naming convention of the relay routers is x_y_z, with x representing the type of device (i.e., "3" indicates a relay router), y representing the "layer" of the device (i.e., the distance from the cloud server, where, for example, 3_1_z is one step away from the cloud server, while 3_3_z is three steps away from the cloud server), and z representing the number of devices in that "layer" (i.e., 3_3_1 would be the first relay router in the third layer from the cloud server, while 3_3_n would be the nth router in the third layer from the cloud server). The examiner is interpreting the "layer" of the device as reading on the "distance from the cloud server" as claimed, as the "layer" represents the number of devices between the device itself and the cloud server, i.e., the distance.), and
Wherein the upgraded control base model is shared between the edge server and a second edge server in a same group as the edge server (0099, Fig. 13C is a diagram showing a state in which the control module M of the relay router 3_e_1 is copied as a control module M' to each of the relay routers 3_f_1 and 3_f_2 directly below it…).
Yang and Yamanaka are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the plurality of edge servers in order to provide a means of further distributing the control system. The motivation to combine is to expand the ability to control multiple robots across multiple spaces.
The combination of Yang and Yamanaka fails to teach, however, wherein the edge server directly transmits the upgraded control base model to the second edge server.
Xiong, however, in an analogous field of endeavor, does teach wherein the edge server directly transmits the upgraded control base model to the second edge server (0030, cloud server 4 may identify a particular edge device or a particular fog node may be assigned as a supervisor device, supervisor device may provide the lower level devices having inferior models with the models of the supervisor devices that are more evolved or more accurate, supervisor device may select for inferior devices the machine learning model to be used by the inferior devices, cloud server 4 may receive a copy of a locally trained machine learning model from edge)
Yang, Yamanaka, and Xiong are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the control model updating and transmission of Xiong in order to provide a means of distributing a superior control model. The motivation to combine is to ensure the edge devices are using as superior of a control model as possible.
Claim 15 is similar in scope to claim 1, and is similarly rejected.
Regarding claim 2, the combination of Yang, Yamanaka, and Xiong teaches the cloud-based robot system of claim 1, and Yang further teaches wherein the control base model is packaged with respective control models for a plurality of functions of the different types of robots (0015, robot control unit is the core system layer of the controller, providing analytical methods for robot models of various configurations to support the motion control of multiple robots and realize real-time control of multiple robots).
Claim 16 is similar in scope to claim 2, and is similarly rejected.
Regarding claim 5, the combination of Yang, Yamanaka, and Xiong teaches the cloud-based robot system of claim 1, and Yang further teaches wherein the edge server executes the control base model by tuning the control base model according to the different types of robots controlled by the edge server (0026-0028, in the multi-robot controller, the application execution script is parsed to generate an executable multi-robot control program, in the kernel system layer of the multi-robot controller, a multi-robot control task is formed by utilizing the scheduling of the robot control unit, the high-performance computing unit, and the artificial intelligence unit, in the kernel driver layer of the multi-robot controller, the motion control instructions of each robot in the multi-robot control task are sent to the corresponding robot through the real-time bus by the virtualization unit).
Regarding claim 18, the combination of Yang, Yamanaka, and Xiong teaches the method of claim 15, and Xiong teaches it further comprising:
Obtaining, by the cloud server, information about the upgraded control base model (0030, cloud server 4 may request and receive a copy of a locally trained machine learning model from edge devices 3 or fog nodes 2 that have developed better machine learning models);
Selecting the second edge server to apply the upgraded the control base model (030, cloud server 4 may identify a particular edge device or a particular fog node may be assigned as a supervisor device, supervisor device may provide the lower level devices having inferior models with the models of the supervisor devices that are more evolved or more accurate, supervisor device may select for inferior devices the machine learning model to be used by the inferior devices);
Transmitting information of the second edge server to the first edge server where the upgrading is performed (030, cloud server 4 may identify a particular edge device or a particular fog node may be assigned as a supervisor device, supervisor device may provide the lower level devices having inferior models with the models of the supervisor devices that are more evolved or more accurate, supervisor device may select for inferior devices the machine learning model to be used by the inferior devices).
Yang, Yamanaka, and Xiong are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the control model updating and transmission of Xiong in order to provide a means of distributing a superior control model. The motivation to combine is to ensure the edge devices are using as superior of a control model as possible
Regarding claim 19, the combination of Yang, Yamanaka, and Xiong teaches the method of claim 15, and Yang further teaches wherein the devices are robots (0026-0029, in the multi-robot controller, the application execution script is parsed to generate an executable multi-robot control program, in the kernel system layer of the multi-robot controller, a multi-robot control task is formed, in the kernel driver layer of the multi-robot controller, the motion control instructions of each robot in the multi-robot control task are sent to the corresponding robot through the real-time bus by the virtualization unit, robot cluster responds to the control tasks of the multi-robot controller to complete the multi-robot collaborative control), and Xiong further teaches receiving, by the first edge server, error values from the corresponding subset of the plurality of robots while controlling the corresponding subset of the plurality of robots using the upgraded control base model (0039, if it is determined that the inference quality is not acceptable, selected data or information may be collected based on the unacceptable inference and sent to the cloud server 4);
Upgrading, by the cloud server, based on an error value from a specific robot in a specific space, the control base model to a cloud-server upgraded control base model for the specific space (0039, cloud server 4 may receive the selected data and retrain the model using learning algorithms); and
Distributing the cloud-server upgraded control base model to an edge server allocated to the specific space, so as to control the specific robot using the cloud-server upgraded control base model (0039, the cloud sends the retrained model generated using the received data to the lower level devices).
Yang, Yamanaka, and Xiong are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the control model updating and transmission of Xiong in order to provide a means of distributing a superior control model. The motivation to combine is to ensure the edge devices are using as superior of a control model as possible.
Regarding claim 21, the combination of Yang, Yamanaka, and Xiong teaches the cloud-based robot system of claim 1, and Yamanaka further teaches wherein the edge server transmits the upgraded control base model to edge servers that are in the same group as the edge server (0099, Fig. 13C is a diagram showing a state in which the control module M of the relay router 3_e_1 is copied as a control module M' to each of the relay routers 3_f_1 and 3_f_2 directly below it…, see also the rejection of Claim 1 above), while Xiong further teaches wherein the edge server directly transmits the upgraded control base models to other edge servers (0030, cloud server 4 may identify a particular edge device or a particular fog node may be assigned as a supervisor device, supervisor device may provide the lower level devices having inferior models with the models of the supervisor devices that are more evolved or more accurate, supervisor device may select for inferior devices the machine learning model to be used by the inferior devices, cloud server 4 may receive a copy of a locally trained machine learning model from edge).
Yang, Yamanaka, and Xiong are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the transmission between edge servers of Yamanaka, as well as the direct transmission of Xiong, in order to provide a means of further distributing the control system. The motivation to combine is to expand the ability to control multiple robots across multiple spaces.
The combination of Yang, Yamanaka, and Xiong fails to explicitly teach, however, wherein the upgraded control model is exclusively sent to edge servers in the same group as the edge server. The examiner asserts, however, that it would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have sent the upgraded control base model to only the edge servers in the same group, as to do so would have been obvious to try. The examiner notes that there is both a design need (i.e., to transmit a control model) as well as a finite number of solutions (i.e., transmitting the control model to all of the edge servers, or transmitting the control model to a subset of edge servers based on a specific criterion).
Claims 6-13, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yang in view of Yamanaka and Xiong, and further in view of Kim (KR20200063340A), hereafter Kim.
Regarding claim 6, the combination of Yang, Yamanaka, and Xiong teaches the cloud-based robot system of claim 5, and Yang further teaches wherein the edge server performs training on the tuned control base model to generate the upgraded control base model (0026-0028, in the multi-robot controller, the application execution script is parsed to generate an executable multi-robot control program, in the kernel system layer of the multi-robot controller, a multi-robot control task is formed by utilizing the scheduling of the robot control unit, the high-performance computing unit, and the artificial intelligence unit, in the kernel driver layer of the multi-robot controller, the motion control instructions of each robot in the multi-robot control task are sent to the corresponding robot through the real-time bus by the virtualization unit).
The combination of Yang, Yamanaka, and Xiong fails to teach, however, wherein the training is deep learning error training.
Kim, however, in an analogous field of endeavor, does teach wherein the training is deep learning error training (0157, some functions of the operation and image deep learning of the central processing server 200 related to the quality inspection service can be performed in the edge cloud 100, 0144-0145, central processing server 200 that receives the feedback information can retrain the image deep learning neural network based on the feedback information received from the factory, central processing server 200 can perform image deep learning neural network retraining, such as updating deep learning information for misprocessed images and continuously clustering correctly processed images based on feedback information).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to have included the deep learning of Kim in order to provide further means of updating the control model. The motivation to combine is to ensure that the control model is as updated as possible.
Regarding claim 7, the combination of Yang, Yamanaka, Xiong, and Kim teaches the cloud-based robot system of claim 6, and Xiong further teaches wherein the cloud server obtains information about the upgraded control base model, and selects the second edge server to apply the upgraded control base model so that the upgraded control base model is transmitted directly from the edge server to the second edge server (0030, cloud server 4 may identify a particular edge device or a particular fog node to be assigned as a supervisor device, supervisor device may provide the lower level devices having inferior models with the models of the supervisor devices that are more evolved or more accurate, supervisor device may select for inferior devices the machine learning model to be used by the inferior devices, cloud server 4 may receive a copy of a locally trained machine learning model from edge device or fog node).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the control model updating and transmission of Xiong in order to provide a means of distributing a superior control model. The motivation to combine is to ensure the edge devices are using as superior of a control model as possible.
Regarding claim 8, the combination of Yang, Yamanaka, Xiong, and Kim teaches the cloud-based robot system of claim 7, and Yang further teaches wherein the device is a robot (0026-0029, in the multi-robot controller, the application execution script is parsed to generate an executable multi-robot control program, in the kernel system layer of the multi-robot controller, a multi-robot control task is formed, in the kernel driver layer of the multi-robot controller, the motion control instructions of each robot in the multi-robot control task are sent to the corresponding robot through the real-time bus by the virtualization unit, robot cluster responds to the control tasks of the multi-robot controller to complete the multi-robot collaborative control), and Xiong further teaches wherein the cloud server selects the second edge server including a device to which the upgraded control base model is to be applied, so as to transmit the upgraded control base model (0045, cloud server may demand that a lower level device use a new model).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the control model updating and transmission of Xiong in order to provide a means of distributing a superior control model. The motivation to combine is to ensure the edge devices are using as superior of a control model as possible.
Regarding claim 9, the combination of Yang, Yamanaka, Xiong, and Kim teaches the cloud-based robot system of claim 8, and Kim further teaches wherein, the edge server, when an error value exceeding a threshold value occurs a predetermined number or more while executing the control base model, generates the upgraded control base model by performing the deep learning error training (0144-0145, central processing server 200 that receives the feedback information can retrain the image deep learning neural network based on the feedback information received from the factory, central processing server 200 can perform image deep learning neural network retraining, such as updating deep learning information for misprocessed images and continuously clustering correctly processed images based on feedback information, 0157, some functions of the operation and image deep learning of the central processing server 200 related to the quality inspection service can be performed in the edge cloud, Examiner's note: feedback information sent to the server reasonably constitutes an error value exceeding a threshold value, when the error value is a Boolean value, i.e., if the image is properly classified or misclassified, in which the "threshold value" would be a 0 or false, wherein the predetermined number of times is at least one time).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to have included the deep learning of Kim in order to provide further means of updating the control model. The motivation to combine is to ensure that the control model is as updated as possible.
Regarding claim 10, the combination of Yang, Yamanaka, and Xiong teaches the cloud-based robot system of claim 2, and Yang further teaches wherein the devices are the plurality of robots (0015, robot control unit is the core system layer of the controller, providing analytical methods for robot models of various configurations to support the motion control of multiple robots and realize real-time control of multiple robots), and Xiong further teaches wherein the cloud server receives error values from the devices in real time, and, when an error value, from one of the plurality of devices, exceeding a threshold value occurs a predetermined number or more, performs training to generate a cloud-server upgraded control base model and transmits the upgraded control base model to the edge server (0046, fog node 2 and/or edge device 3 may decide whether the inference quality is acceptable, consideration of whether the inference quality is acceptable may involve monitoring data distribution, monitoring the confidence level of inferences, and/or testing with unused historical data, if it is determined at decision 56 that the inference quality is not acceptable, selected data or information such as inputs and outputs of the inference may be collected and sent to the cloud server 4, and the cloud may retrain the model based on more recent data/information, after retraining the previous model, the process may start over again, wherein the model is sent to the lower level devices).
Yang, Yamanaka, and Xiong are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the model retraining of Xiong in order to provide a means of updating a control model. The motivation to combine is to ensure that the control model sent to the devices is as updated as possible.
The combination of Yang, Yamanaka, and Xiong fails to teach, however, wherein the training is deep learning error training.
Kim, however, in an analogous field of endeavor, does teach wherein the training is deep learning error training (0144-0145, central processing server 200 that receives the feedback information can retrain the image deep learning neural network based on the feedback information received from the factory, central processing server 200 can perform image deep learning neural network retraining, such as updating deep learning information for misprocessed images and continuously clustering correctly processed images based on feedback information).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to have included the deep learning of Kim in order to provide further means of updating the control model. The motivation to combine is to ensure that the control model is as updated as possible.
Regarding claim 11, the combination of Yang, Yamanaka, Xiong, and Kim teaches the cloud-based robot system of claim 10, and Xiong further teaches wherein the cloud server obtains environment information from the edge server and performs training on the control base model to generate the cloud-server upgraded control base model (0050-0051, lower level device collects useful selected data or information based on the action taken, lower level device sends this data or information to the cloud, which may use the selected data or information to retrain a model which is distributed to other lower level devices within the network).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the control model updating of Xiong in order to provide a means of distributing a superior control model. The motivation to combine is to ensure the edge devices are using as superior of a control model as possible.
Kim further teaches wherein the training is deep learning error training (0144-0145, central processing server 200 that receives the feedback information can retrain the image deep learning neural network based on the feedback information received from the factory, central processing server 200 can perform image deep learning neural network retraining, such as updating deep learning information for misprocessed images and continuously clustering correctly processed images based on feedback information).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to have included the deep learning of Kim in order to provide further means of updating the control model. The motivation to combine is to ensure that the control model is as updated as possible.
Regarding claim 12, the combination of Yang, Yamanaka, Xiong, and Kim teaches the cloud-based robot system of claim 11, and Xiong further teaches wherein the cloud server selects another edge server to apply the cloud-server upgraded control base model so as to transmit the cloud-server upgraded control base model to the selected another edge server (0030, supervisor device may provide the lower level devices having inferior models with the models of the supervisor devices that are more evolved or more accurate, supervisor device may select for inferior devices the machine learning model to be used by the inferior devices).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention, with a reasonable expectation of success, to have included the control model transmission of Xiong in order to provide a means of distributing a superior control model. The motivation to combine is to ensure the edge devices are using as superior of a control model as possible.
Regarding claim 13, the combination of Yang, Yamanaka, Xiong, and Kim teaches the cloud-based robot system of claim 12, and Kim further teaches wherein, when an error value, from one of the plurality of robots, exceeding a threshold value occurs a predetermined number or more and a pattern in a user response to the error value is detected, the cloud server generates a deep learning model for a new function (0135, feedback information refers to inspection information of a user regarding the quality information transmitted by the central processing server, 0144-0145, central processing server 200 that receives the feedback information can retrain the image deep learning neural network based on the feedback information received from the factory, central processing server 200 can perform image deep learning neural network retraining, such as updating deep learning information for misprocessed images and continuously clustering correctly processed images based on feedback information, 0157, some functions of the operation and image deep learning of the central processing server 200 related to the quality inspection service can be performed in the edge cloud, Examiner's note: feedback information sent to the server reasonably constitutes an error value exceeding a threshold value, when the error value is a Boolean value, i.e., if the image is properly classified or misclassified, in which the "threshold value" would be a 0 or false, wherein the predetermined number of times is at least one time).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to have included the deep learning of Kim in order to provide further means of updating the control model. The motivation to combine is to ensure that the control model is as updated as possible.
Regarding claim 17, the combination of Yang, Yamanaka, and Xiong teaches the method of claim 15, and Yang further teaches wherein the upgrading of the control base model comprises:
Tuning the control base model according to the different types of robots controlled by the first edge server (0026-0028, in the multi-robot controller, the application execution script is parsed to generate an executable multi-robot control program, in the kernel system layer of the multi-robot controller, a multi-robot control task is formed by utilizing the scheduling of the robot control unit, the high-performance computing unit, and the artificial intelligence unit, in the kernel driver layer of the multi-robot controller, the motion control instructions of each robot in the multi-robot control task are sent to the corresponding robot through the real-time bus by the virtualization unit); and
Generating an upgraded control model by performing training on the control base model that is tuned (0027, the multi-robot control task is formed by utilizing the artificial intelligence unit, 0059, multi-robot controller including an artificial intelligence unit, 0047, artificial intelligence unit automatically optimizes the solution process to obtain the optimal motion trajectory of the robot within the control cycle, and provides advanced intelligent control methods including intelligent algorithms, machine vision, and force control to improve the autonomy of multi-robot control).
The combination of Yang, Yamanaka, and Xiong fails to teach, however, wherein the training is deep learning error training.
Kim, however, in an analogous field of endeavor, does teach wherein the training is deep learning error training (0144-0145, central processing server 200 that receives the feedback information can retrain the image deep learning neural network based on the feedback information received from the factory, central processing server 200 can perform image deep learning neural network retraining, such as updating deep learning information for misprocessed images and continuously clustering correctly processed images based on feedback information).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to have included the deep learning of Kim in order to provide further means of updating the control model. The motivation to combine is to ensure that the control model is as updated as possible.
Regarding claim 20, the combination of Yang, Yamanaka, and Xiong teaches the method of claim 19, but fails to teach wherein the upgrading of the control base model by the cloud server comprises, when the cloud server receives an error value from the specific robot that exceeds a threshold value a predetermined number or more and a pattern in a user response to the error value is detected, generating a deep learning model for a new function.
Kim, however, in an analogous field of endeavor, does teach wherein the upgrading of the control base model by the cloud server comprises, when the cloud server receives an error value from the specific robot that exceeds a threshold value a predetermined number or more and a pattern in a user response to the error value is detected, generating a deep learning model for a new function (0135, feedback information refers to inspection information of a user regarding the quality information transmitted by the central processing server, 0144-0145, central processing server 200 that receives the feedback information can retrain the image deep learning neural network based on the feedback information received from the factory, central processing server 200 can perform image deep learning neural network retraining, such as updating deep learning information for misprocessed images and continuously clustering correctly processed images based on feedback information, 0157, some functions of the operation and image deep learning of the central processing server 200 related to the quality inspection service can be performed in the edge cloud, Examiner's note: feedback information sent to the server reasonably constitutes an error value exceeding a threshold value, when the error value is a Boolean value, i.e., if the image is properly classified or misclassified, in which the "threshold value" would be a 0 or false, wherein the predetermined number of times is at least one time).
Yang, Yamanaka, Xiong, and Kim are analogous because they are in a similar field of endeavor, e.g., distributed control systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to have included the deep learning of Kim in order to provide further means of updating the control model. The motivation to combine is to ensure that the control model is as updated as possible.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BLAKE A WOOD whose telephone number is (571)272-6830. The examiner can normally be reached M-F, 8:00 AM to 4:30 PM Eastern.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Thomas Worden can be reached at (571) 272-4876. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/B.A.W./ Examiner, Art Unit 3658 /JASON HOLLOWAY/ Primary Examiner, Art Unit 3658