DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-20 are presented for examination based on the application filed on July 19, 2023.
Claims 1-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to judicial exception, an abstract idea, and it has not been integrated into practical application. The claims further do not recite significantly more than the judicial exception.
Claims 1-4, 6-9, 12-20 are rejected under 35 U.S.C. § 102(a)(1) as being anticipated by Liu, Xing, Fei Zhao, Shuzhi Sam Ge, Yuqiang Wu, and Xuesong Mei. "End-effector force estimation for flexible-joint robots with global friction approximation using neural networks." IEEE Transactions on Industrial Informatics 15, no. 3 (2018): 1730-1741 [herein “Liu”].
Claims 5 and 10-11 are rejected under 35 U.S.C. § 103 as being unpatentable over Liu as applied to claims 1 and 9, respectively, and in further view of Cannon, Howard, and Sanjiv Singh. "Models for automated earthmoving." In Experimental Robotics VI, Lecture Notes in Control and Information Sciences, vol 250. London: Springer London, 2000 [herein “Cannon”].
This action is made non-Final.
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 .
Drawings
The drawings are objected to because FIG. 10 – FIG. 13 do not have a legend to indicate what the different plots in the graph are. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Appropriate correction is required.
Specification
The disclosure is objected to because of the following informalities:
Para. 0044, which recites “The displacements of lift cylinder”, should be “The displacements (d) of lift cylinder”.
Equation (1) does not define t.
Equation (2) does not define ω.
Equations (10)-(12) does not define Q1 and Q2.
Equations (13)-(14) does not define θ, α, β, and Vs .
Equations (16)-(19) do not define Nγ, Nc, Nα, and Nq.
Equation (20) does not define kc, kΦ, and n.
Equation (21) does not define P.
Appropriate correction is required.
Claim Objections
Claims 1-20 are objected to because of the following informality: recitations of elements with no previous recitations. For example, claim 1, “the method” in Ln. 3, is improper because there has been no previous recitation of “the method”. For the purpose of examination, “the method” will be interpreted as “the computer-implemented method”. Claims 2-17, having similar limitations of claim 1, are also objected. Similarly, the following are objected under similar rationale:
Claim 1, which recites “the resistive force” in Ln. 8 should be “the resistive force predicted by the first model”. Claim 18, having similar limitations of claim 1, is also objected.
Claim 3, which recites “the sensor data” in Ln. 1 should be “the previously collected sensor data”. Claim 5, having similar limitations of claim 3, is also objected.
Claim 12, which recites “the model” in Ln. 1 should be “the tuned model”. Claims 13-14 and 16, having similar limitations of claim 12, are also objected.
Claim 17, which recites “the first model” in Ln. 2 should be “the tuned model”.
All claims dependent on an objected base claim are objected based on their dependency.
Appropriate correction is required.
Claims 1-20 are objected to because of the following informality: recitations of elements with a previous recitations. For example, claim 1, “an industrial machine” in Ln. 3, is improper because there has been a previous recitation of “an industrial machine” in Ln. 2. For the purpose of examination, “an industrial machine” in Ln. 3, will be interpreted as “the industrial machine”. Claims 9 and 18, having similar limitations of claim 1, are also objected. Similarly, the following are objected under similar rationale:
Claim 8, which recites “an external machine” in Ln. 6 should be “the external machine”. Claim 20, having similar limitations of claim 8, is also objected.
Claim 11, which recites “a tool of the industrial machine” in Ln. 2 should be “the tool of the industrial machine”.
All claims dependent on an objected base claim are objected based on their dependency.
Appropriate correction is required.
Claim Rejections - 35 U.S.C. § 101
35 U.S.C. § 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to judicial exception, an abstract idea, and it has not been integrated into practical application. The claims further do not recite significantly more than the judicial exception. Examiner has evaluated the claims under the framework provided in the 2019 Patent Eligibility Guidance published in the Federal Register 01/07/2019 and has provided such analysis below.
Step 1:
Claims 1-8 are directed to a method and fall within the statutory category of a process; claims 9-17 are directed to a method and fall within the statutory category of a process; and claims 18-20 are directed to a system and fall within the statutory category of a machine. Therefore, “Are the claims to a process, machine, manufacture or composition of matter?” Yes.
In order to evaluate the Step 2A inquiry “Is the claim directed to a law of nature, a natural phenomenon or an abstract idea?” we must determine, at Step 2A Prong 1, whether the claim recites a law of nature, a natural phenomenon or an abstract idea and further whether the claim recites additional elements that integrate the judicial exception into a practical application.
Continuing the analysis at Step 2A Prong 1 for claims 1-8 and 18-20 below:
Step 2A Prong 1:
Claims 1 and 18: The limitations of:
“(a) predicting by a first model a resistive force applied to an industrial machine from an external material using previously collected sensor data”,
“(b) predicting by a second model that is different from the first model an error of the resistive force predicted by the first model using the previously collected sensor data and the resistive force predicted by the first model”, and
“(c) determining a corrected prediction of the resistive force by combining the resistive force predicted by the first model with the error predicted by the second model”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, the limitations can be performed as the following:
a person can mentally determine or draw with a pen and paper the resistive contact force experienced by a machine by applying known kinematic equations using relative positions and measured pressure,
a person can mentally determine or draw with a pen and paper an updated resistive contact force experienced by a machine by applying a custom or altered kinematic equation using relative positions and measured pressure and determine the difference between the updated resistive contact force and the previous resistive contact force experienced to find an error, and
a person can mentally determine or draw with a pen and paper the final resistive contact force experienced by a machine by adding the error to the previous resistive contact force.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Therefore, yes, claims 1 and 18 recite judicial exceptions. The claims have been identified to recite judicial exceptions, Step 2A Prong 2 will evaluate whether the claims are directed to the judicial exception.
Step 2A Prong 2:
Claims 1 and 18: The judicial exception is not integrated into a practical application. In particular, the claims recite the following additional elements of “computer-implemented”, “A system for predicting external resistive forces encountered by an industrial machine, the system comprising: a processor; a non-transitory memory; and one or more applications stored in the non-transitory memory that, when executed by the processor”, and “stored in the non-transitory memory” which is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) with the broadest reasonable interpretation, which does not integrate a judicial exception into elements.
Therefore, “Do the claims recite additional elements that integrate the judicial exception into a practical application?” No, these additional elements do not integrate the abstract idea into a practical application and they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
After having evaluated the inquires set forth in Steps 2A Prong 1 and 2, it has been concluded that claims 1 and 18 not only recite a judicial exception but that the claims are directed to the judicial exception as the judicial exception has not been integrated into practical application.
Step 2B:
Claims 1 and 18: The claims do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than generic computing components.
Therefore, “Do the claims recite additional elements that amount to significantly more than the judicial exception?” No, these additional elements, alone or in combination, do not amount to significantly more than the judicial exception. Having concluded the analysis within the provided framework, claims 1 and 18 do not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claim 2, it recites an additional limitation of “wherein the first model comprises a physical model”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally determine or draw with a pen and paper the resistive contact force experienced by a machine by applying known kinematic equations using relative positions and measured pressure.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Furthermore, regarding claim 2, it recites an additional element recitation of “wherein the second model comprises one or more neural networks” is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) and/or a field of use/technological environment (see MPEP § 2106.05(h)) which does not integrate a judicial exception into practical application. Further, this claim does not recite any further additional elements and for the same reasons as above with regard to integration into practical application and whether additional element amounts to significantly more, this claim also fails both Step 2A prong 2, thus this claim is directed to the judicial exception as it has not been integrated into practical application, and fails Step 2B as not amounting to significantly more. Therefore, claim 2 does not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claim 3, it recites an additional limitation of “wherein the sensor data is collected from one or more sensors of the industrial machine”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally determine or draw with a pen and paper the resistive contact force experienced by an machine by applying known kinematic equations using relative positions and measured pressure that was collected from the machine’s sensors.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claim 4, it recites an additional limitation of “wherein the one or more sensors are associated with one or more actuators of the industrial machine”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally determine or draw with a pen and paper the resistive contact force experienced by an machine by applying known kinematic equations using relative positions and measured pressure that was collected from the machine arm’s sensors.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claim 5, it recites an additional limitation of “wherein the sensor data comprises pressure sensor data collected from one or more pressure sensors of the industrial machine”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally determine or draw with a pen and paper the resistive contact force experienced by an machine by applying known kinematic equations using relative positions and measured pressure that was collected from the machine’s sensors.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claims 6 and 19, they recite additional limitations of
“(d) extracting position data and velocity data of a tool of the industrial machine using the previously collected sensor data”,
“(e) providing as an input to the first model the position data of the tool”, and
“(f) providing as an input to the second model the velocity data of the tool”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, the limitations can be performed as the following:
a person can mentally identify or draw with a pen and paper velocity data from measurement and determine or draw with a pen and paper the position by integrating the velocity with respect to time,
a person can mentally determine or draw with a pen and paper the resistive contact force experienced by a machine by applying known kinematic equations using relative positions and measured pressure, and
a person can mentally determine or draw with a pen and paper an updated resistive contact force experienced by a machine by applying a custom or altered kinematic equation using velocity and measured pressure.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Furthermore, regarding claim 19, it recites an additional element recitation of “wherein the one or more applications stored in the non-transitory memory that, when executed by the processor” is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) and/or a field of use/technological environment (see MPEP § 2106.05(h)) which does not integrate a judicial exception into practical application. Further, this claim does not recite any further additional elements and for the same reasons as above with regard to integration into practical application and whether additional element amounts to significantly more, this claim also fails both Step 2A prong 2, thus this claim is directed to the judicial exception as it has not been integrated into practical application, and fails Step 2B as not amounting to significantly more. Therefore, claim 19 does not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claim 7, it recites an additional element recitation of “wherein the second model comprises a neural network having an input layer including the resistive force predicted by the first model, an output layer including the error predicted by the second model, and one or more hidden layers positioned between the input layer and the output layer” is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) and/or a field of use/technological environment (see MPEP § 2106.05(h)) which does not integrate a judicial exception into practical application. Further, this claim does not recite any further additional elements and for the same reasons as above with regard to integration into practical application and whether additional element amounts to significantly more, this claim also fails both Step 2A prong 2, thus this claim is directed to the judicial exception as it has not been integrated into practical application, and fails Step 2B as not amounting to significantly more. Therefore, claim 7 does not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claims 8 and 20, they recite additional limitations of “the previously collected sensor data comprises sensor data collected from the industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation” and “the corrected prediction of the resistive force corresponds to a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally determine or draw with a pen and paper the resistive contact force experienced by an machine during excavation by applying known kinematic equations using relative positions and measured pressure that was collected from the machine’s sensors, and a person can mentally determine or draw with a pen and paper determine the difference between the updated resistive contact force and the previous resistive contact force experienced to find an error which will be used to update the previous resistive contact force to predictions in a future excavation process.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Continuing the analysis at Step 2A Prong 1 for claims 9-17 below:
Step 2A Prong 1:
Claim 9: The limitations of: “(a) tuning a model using sensor data collected from an industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation”; and “(b) predicting by the tuned model a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally modify or draw with a pen and paper a model for determining resistive contact forces experienced by an machine during excavation that uses kinematic equations by applying relative positions and measured pressure that was collected from the machine’s sensors, and a person can mentally determine or draw with a pen and paper the resistive contact force experienced by a machine during excavation using the modified model on a planned excavation path of the machine during a future excavation process.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Therefore, yes, claim 9 recites judicial exceptions. The claim has been identified to recite judicial exceptions, Step 2A Prong 2 will evaluate whether the claim is directed to the judicial exception.
Step 2A Prong 2:
Claim 9: The judicial exception is not integrated into a practical application. In particular, the claims recite the following additional elements of “computer-implemented” which is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) with the broadest reasonable interpretation, which does not integrate a judicial exception into elements.
Therefore, “Do the claims recite additional elements that integrate the judicial exception into a practical application?” No, these additional elements do not integrate the abstract idea into a practical application and they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
After having evaluated the inquires set forth in Steps 2A Prong 1 and 2, it has been concluded that claim 9 not only recites a judicial exception but that the claim is directed to the judicial exception as the judicial exception has not been integrated into practical application.
Step 2B:
Claim 9: The claims do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than generic computing components.
Therefore, “Do the claims recite additional elements that amount to significantly more than the judicial exception?” No, these additional elements, alone or in combination, do not amount to significantly more than the judicial exception. Having concluded the analysis within the provided framework, claim 9 dos not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claim 10, it recites an additional limitation of “wherein the one or more prior working cycles and the future working cycle each comprise an excavating phase in which a tool of the industrial machine excavates a portion of the external material from a pile of the external material”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally modify or draw with a pen and paper a model for determining resistive contact forces experienced by an machine during the excavation of soil that uses kinematic equations by applying relative positions and measured pressure that was collected from the machine’s sensors, and a person can mentally determine or draw with a pen and paper the resistive contact force experienced by a machine during excavation of soil using the modified model on a planned excavation path of the machine during a future excavation process.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claim 11, it recites an additional limitation of “wherein the planned trajectory of the industrial machine comprises a planned trajectory of a tool of the industrial machine to be executed during the excavation phase of the future working cycle”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally determine or draw with a pen and paper the resistive contact force experienced by a machine during excavation of soil using the modified model on a planned excavation path of the machine during a future excavation process.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claim 12, it recites an additional element recitation of “wherein the model comprises a neural network” is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) and/or a field of use/technological environment (see MPEP § 2106.05(h)) which does not integrate a judicial exception into practical application. Further, this claim does not recite any further additional elements and for the same reasons as above with regard to integration into practical application and whether additional element amounts to significantly more, this claim also fails both Step 2A prong 2, thus this claim is directed to the judicial exception as it has not been integrated into practical application, and fails Step 2B as not amounting to significantly more. Therefore, claim 12 does not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claim 13, it recites an additional limitation of “wherein the model comprises an integrated model including a physical model”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally modify or draw with a pen and paper a model for determining resistive contact forces experienced by an machine during excavation that uses kinematic equations by applying relative positions and measured pressure that was collected from the machine’s sensors.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Furthermore, regarding claim 13, it recites an additional element recitation of “wherein the model comprises an integrated model including both a physical model and a black box model including one or more neural networks” is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) and/or a field of use/technological environment (see MPEP § 2106.05(h)) which does not integrate a judicial exception into practical application. Further, this claim does not recite any further additional elements and for the same reasons as above with regard to integration into practical application and whether additional element amounts to significantly more, this claim also fails both Step 2A prong 2, thus this claim is directed to the judicial exception as it has not been integrated into practical application, and fails Step 2B as not amounting to significantly more. Therefore, claim 13 does not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claim 14, it recites an additional limitation of “wherein the model comprises a physical model but not a black box model”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally modify or draw with a pen and paper a model for determining resistive contact forces experienced by an machine during excavation that uses kinematic equations by applying relative positions and measured pressure that was collected from the machine’s sensors.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claim 15, it recites an additional limitation of “wherein the sensor data is collected from one or more sensors of the industrial machine”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, a person can mentally modify or draw with a pen and paper a model for determining resistive contact forces experienced by an machine during excavation that uses kinematic equations by applying relative positions and measured pressure that was collected from the machine’s sensors.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claim 16, it recites additional limitations of
“(c) extracting position data and velocity data of a tool of the industrial machine using previously collected sensor data”,
“(d) providing as an input to the model the position data of the tool” and “(e) providing as an input to the model the velocity data of the tool”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper. For example, the limitations can be performed as the following:
a person can mentally identify or draw with a pen and paper velocity data from measurement and determine or draw with a pen and paper the position by integrating the velocity with respect to time, and
a person can mentally determine or draw with a pen and paper the resistive contact force experienced by a machine during excavation using the modified model on a planned excavation path of the machine during a future excavation process using the position and velocity.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong I step 2A.
Regarding claim 17, it recites an additional element recitation of “wherein the model comprises a neural network having an input layer including the resistive force predicted by the first model, an output layer, and one or more hidden layers positioned between the input layer and the output layer” is merely a recitation of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) and/or a field of use/technological environment (see MPEP § 2106.05(h)) which does not integrate a judicial exception into practical application. Further, this claim does not recite any further additional elements and for the same reasons as above with regard to integration into practical application and whether additional element amounts to significantly more, this claim also fails both Step 2A prong 2, thus this claim is directed to the judicial exception as it has not been integrated into practical application, and fails Step 2B as not amounting to significantly more. Therefore, claim 17 does not recite patent eligible subject matter under 35 U.S.C. § 101.
Therefore, having concluded the analysis within the provided framework, claims 1-20 do not recite patent eligible subject matter and are rejected under 35 U.S.C. § 101 because the claimed invention is directed to judicial exception, an abstract idea, that has not been integrated into a practical application. The claims further do not recite significantly more than the judicial exception. Claims 2-8, claims 10-17, and claims 19-20 are also rejected for incorporating the deficiency of their dependent claims 1, 9, and 18, respectively.
Claim Rejections - 35 U.S.C. § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. § 102 and 103 (or as subject to pre-AIA 35 U.S.C. § 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. § 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4, 6-9, 12-20 are rejected under 35 U.S.C. § 102(a)(1) as being anticipated by Liu, Xing, Fei Zhao, Shuzhi Sam Ge, Yuqiang Wu, and Xuesong Mei. "End-effector force estimation for flexible-joint robots with global friction approximation using neural networks." IEEE Transactions on Industrial Informatics 15, no. 3 (2018): 1730-1741 [herein “Liu”].
As per claim 1, Liu teaches “A computer-implemented method for predicting external resistive forces encountered by an industrial machine”. (Pg. 1731 Sect. 1, “This paper proposes an approach based on the disturbance observer and NN approximation method for the estimation of external force/torques felt by the robot during interaction tasks” [A computer-implemented method for predicting external resistive forces encountered by an industrial machine]. Further see Sect. 1-2. The examiner has interpreted that estimating external forces felt by a robot during interaction tasks based on a disturbance observer and neural network (NN) as a computer-implemented method for predicting external resistive forces encountered by an industrial machine.)
Liu teaches “(a) predicting by a first model a resistive force applied to an industrial machine from an external material using previously collected sensor data”. (Pg. 1731 Sect. 1, “the paper compares the two methods of using actuator torque data and joint torque data for the estimation of the external contact force” [predicting a resistive force applied to an industrial machine from an external material using previously collected sensor data]. Pg. 1732 Sect. 2, “we take advantage of the joint torque sensor available on our robot, which is shown in Fig. 1. Actually, every joint is equipped with a high-resolution absolute position encoder on the motor side and an integrated joint torque sensor, so that θ and τJ are available” [previously collected sensor data]. Pg. 1732 Sect. 2, “Therefore, by comparing (9) and (10), it can be known that when using the joint torque data to estimate the external force, only the inertia matrix M, the position data (
q
,
q
˙
,
q
¨
), the centrifugal-Coriolis matrix C(
q
,
q
˙
), and the friction term of the link side Fq are needed” [predicting by a first model a resistive force applied to an industrial machine from an external material using previously collected sensor data]. Further see Sect. 1-2 and Equation (10) which is the first model. The examiner has interpreted that estimating external contact forces felt by a robot during interaction tasks using a joint torque sensor available on the robot and dynamic equations for robot manipulator and joints as (a) predicting by a first model a resistive force applied to an industrial machine from an external material using previously collected sensor data.)
Liu teaches “(b) predicting by a second model that is different from the first model an error of the resistive force predicted by the first model using the previously collected sensor data and the resistive force predicted by the first model”. (Pg. 1731 Sect. 1, “this paper extends it to those cases where the analytic model of the robot friction force is not available/precise. The method is inspired by the learning and approximation of the inverse dynamics using regularization NNs” and see Pg. 1731 Sect. 2, “Although the momentum disturbance observer with joint torque data has great advantages, the dynamic uncertainties such as the unknown friction will reduce the estimation accuracy. To solve this problem, an improved momentum observer based on the modeling of the friction force is proposed in this paper.” [first model does not approximate the friction force in the external force estimation, i.e., an error of the resistive force predicted by the first model]. Pg. 1731 Sect. 2, “Assuming that the friction term of the link side is unknown, the estimated force value of the momentum observer will not be accurate because the result also includes the friction force. Only by modeling the friction of the link side can we achieve more accurate estimation of the external force. There are many ways to improve the dynamic model, such as the model parameter identification method, but the identification method is somewhat tedious. In view of this, this paper proposes a method that considers the observation results of the robot manipulator during free motion as the unmodeled friction. Then the observed residual is modeled via a suitable method. After that, the estimation accuracy of the observer will be improved. For (10), assuming that the terms M(q), C(
q
,
q
˙
), G(q) are accurate but the friction force of the link side Fq (
q
˙
) is unknown, the equation can be rewritten as τext = (M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
) + Fq(
q
˙
) . Let M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
=
τ
'
e
x
t
, which is equivalent to the observed residual
r
E
J
'
without considering the friction.… There are many ways to approximate the friction force. In this paper, the commonly used multilayer feedforward NN is utilized” [i.e.., (b) predicting by a second model that is different from the first model an error of the resistive force predicted by the first model using the previously collected sensor data and the resistive force predicted by the first model]. Further see Sect. 1-2. The examiner has interpreted that using a neural network (NN) to approximate the friction force that was unknown in the momentum disturbance observer external force estimation to model an observed residual using torque and generate a more accurate estimate of the external force as (b) predicting by a second model that is different from the first model an error of the resistive force predicted by the first model using the previously collected sensor data and the resistive force predicted by the first model.)
Liu teaches “(c) determining a corrected prediction of the resistive force by combining the resistive force predicted by the first model with the error predicted by the second model”. (Pg. 1734 Sect. 2, “Friction force modeling: The obtained residual value
r
E
J
'
is approximated by NNs…The learning results will be substituted into the disturbance observer in (21) to improve the observation results” and see Pg. 1731 Sect. 1, “The comparison results show that when using the joint torque sensor, the external force estimation only requires the partial dynamics of the link side. In addition, employing the joint torque sensor eliminates the inaccuracy caused by the asynchrony of the motor position and the link position. Therefore, the estimation accuracy can be improved. 2) The paper proposes a method to model the friction dynamics of the link side of the manipulator, thus increasing the estimation accuracy considerably. The NN approximation is adopted, which avoids the need of analytic models of the joint friction and is easy to implement. To the knowledge of the authors, this is the first time to integrate the disturbance observer with the NN approximation for external force estimation” [i.e., (c) determining a corrected prediction of the resistive force by combining the resistive force predicted by the first model with the error predicted by the second model]. Further see Sect. 1-2. The examiner has interpreted that integrating the disturbance observer with the residual of the NN approximation for external force estimation to improve the observation results as (c) determining a corrected prediction of the resistive force by combining the resistive force predicted by the first model with the error predicted by the second model.)
As per claim 2, Liu teaches “wherein the first model comprises a physical model and the second model comprises one or more neural networks.” (Equation (10) which is the first model, is a dynamic equation for robot manipulator and joints, i.e., wherein the first model comprises a physical model. Pg. 1731 Sect. 1, “The comparison results show that when using the joint torque sensor, the external force estimation only requires the partial dynamics of the link side. In addition, employing the joint torque sensor eliminates the inaccuracy caused by the asynchrony of the motor position and the link position. Therefore, the estimation accuracy can be improved. 2) The paper proposes a method to model the friction dynamics of the link side of the manipulator, thus increasing the estimation accuracy considerably. The NN approximation is adopted” [the second model comprises one or more neural networks]. Further see Pg. 1731 Sect. 1, “The comparison results show that when using the joint torque sensor, the external force estimation only requires the partial dynamics of the link side. In addition, employing the joint torque sensor eliminates the inaccuracy caused by the asynchrony of the motor position and the link position. Therefore, the estimation accuracy can be improved. 2) The paper proposes a method to model the friction dynamics of the link side of the manipulator, thus increasing the estimation accuracy considerably. The NN approximation is adopted, which avoids the need of analytic models of the joint friction and is easy to implement. To the knowledge of the authors, this is the first time to integrate the disturbance observer with the NN approximation for external force estimation…This hybrid modeling method including the analytic model and the NN model can provide important guidelines for system modeling” [wherein the first model comprises a physical model and the second model comprises one or more neural networks]. Further see Sect. 1-2. The examiner has interpreted that incorporating an analytical model that models the partial dynamics of the link side for robot manipulator and joints and integrating a neural network that models the friction dynamics as wherein the first model comprises a physical model and the second model comprises one or more neural networks.)
As per claim 3, Liu teaches “wherein the sensor data is collected from one or more sensors of the industrial machine.” (Pg. 1732 Sect. 2, “we take advantage of the joint torque sensor available on our robot, which is shown in Fig. 1. Actually, every joint is equipped with a high-resolution absolute position encoder on the motor side and an integrated joint torque sensor, so that θ and τJ are available” [wherein the sensor data is collected from one or more sensors of the industrial machine]. Further see Sect. 1-2.)
As per claim 4, Liu teaches “wherein the one or more sensors are associated with one or more actuators of the industrial machine.” (Pg. 1732 Sect. 2, “we take advantage of the joint torque sensor available on our robot, which is shown in Fig. 1. Actually, every joint is equipped with a high-resolution absolute position encoder on the motor side and an integrated joint torque sensor, so that θ and τJ are available” [the one or more sensors]. Pg. 1731 Sect. 1, “the paper compares the two methods of using actuator torque data and joint torque data for the estimation of the external contact force” [i.e., wherein the one or more sensors are associated with one or more actuators of the industrial machine]. Further see Sect. 1-2. The examiner has interpreted that using joint torque senor available on the robot in conjunction with actuator torque data as wherein the one or more sensors are associated with one or more actuators of the industrial machine.)
As per claim 6, Liu teaches “(d) extracting position data and velocity data of a tool of the industrial machine using the previously collected sensor data; (e) providing as an input to the first model the position data of the tool; and (f) providing as an input to the second model the velocity data of the tool.” (Pg. 1732 Sect. 2, “We installed the absolute position sensor between the harmonic reducer and the joint torque sensor. As the stiffness and damping of the joint torque sensor are known, the positions and velocities at both ends of the joint torque sensor can be obtained” [(d) extracting position data and velocity data of a tool of the industrial machine using the previously collected sensor data]. Pg. 1732 Sect. 2, “Therefore, by comparing (9) and (10), it can be known that when using the joint torque data to estimate the external force, only the inertia matrix M, the position data (
q
,
q
˙
,
q
¨
), the centrifugal-Coriolis matrix C(
q
,
q
˙
), and the friction term of the link side Fq are needed” [providing as an input to the first model the position data of the tool]. Pg. 1734 Sect. 3, “According to the literature [17], [18] and the above-mentioned analysis, it can be seen that the friction is continuous although it may be highly nonlinear and depends mainly on the velocity. The nonlinear friction function can be approximated either by a linear span of a set of continuous known functions, or by a NN of bounded basis functions” [(f) providing as an input to the second model the velocity data of the tool]. Further see Sect. 1-3. The examiner has interpreted that installing a position sensor on the robot to obtain the position and velocity of the joint, estimating the external force using the position data in Equation 10, and approximating the friction force using a neural network (NN) dependent on velocity as (d) extracting position data and velocity data of a tool of the industrial machine using the previously collected sensor data; (e) providing as an input to the first model the position data of the tool; and (f) providing as an input to the second model the velocity data of the tool.)
As per claim 7, Liu teaches “wherein the second model comprises a neural network having an input layer including the resistive force predicted by the first model, an output layer including the error predicted by the second model, and one or more hidden layers positioned between the input layer and the output layer.” (Pg. 1731 Sect. 2, “this paper proposes a method that considers the observation results of the robot manipulator during free motion as the unmodeled friction. Then the observed residual is modeled via a suitable method. After that, the estimation accuracy of the observer will be improved. For (10), assuming that the terms M(q), C(
q
,
q
˙
), G(q) are accurate but the friction force of the link side Fq (
q
˙
) is unknown, the equation can be rewritten as τext = (M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
) + Fq(
q
˙
) . Let M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
=
τ
'
e
x
t
, which is equivalent to the observed residual
r
E
J
'
without considering the friction.… There are many ways to approximate the friction force. In this paper, the commonly used multilayer feedforward NN is utilized” [i.e., wherein the second model comprises a neural network having an input layer including the resistive force predicted by the first model, an output layer including the error predicted by the second model]. Pg. 1735 Sect. 3, “the NNs with only one hidden layer is chosen in this paper and the parameters of the NNs are determined carefully” [i.e., one or more hidden layers positioned between the input layer and the output layer]. Further see Sect. 2-3. The examiner has interpreted that using a neural network (NN) to approximate the friction force that was unknown in the momentum disturbance observer external force estimation to model an observed residual having a hidden layer as wherein the second model comprises a neural network having an input layer including the resistive force predicted by the first model, an output layer including the error predicted by the second model, and one or more hidden layers positioned between the input layer and the output layer.)
As per claim 8, Liu teaches “the previously collected sensor data comprises sensor data collected from the industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation; and the corrected prediction of the resistive force corresponds to a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle.” (Pg. 1731 Sect. 1, “This paper proposes an approach based on the disturbance observer and NN approximation method for the estimation of external force/torques felt by the robot during interaction tasks” [i.e., a working cycle conducted by the industrial machine as part of an industrial operation]. Pg. 1732 Sect. 2, “we take advantage of the joint torque sensor available on our robot, which is shown in Fig. 1. Actually, every joint is equipped with a high-resolution absolute position encoder on the motor side and an integrated joint torque sensor, so that θ and τJ are available” [i.e., the previously collected sensor data comprises sensor data collected from the industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation]. Pg. 1735 Sect. 3, “The NN approximation methods are often used in local approximation problems on a compact set [27]. In this paper, the authors highlight that the completeness of the training data and the use of global basis functions are sufficient conditions for global friction force modeling. This is meaningful for physical system modeling using NNs. After analyzing the characteristics of the physical system and fully stimulating all the properties with suitable excitation trajectories, we can achieve accurate global modeling of the target. In this paper, the properties of the friction force are analyzed in detail and the appropriate excitation trajectory is chosen to guarantee global approximation using only limited but sufficient training data. After global approximation of the friction force, the NN just needs to be trained once for a relatively longer period.” and Pg. 1736 Sect. 5, “To illustrate the effectiveness of the proposed method, real-time experiments are also carried out on a 2-DOF robot manipulator” [i.e., the corrected prediction of the resistive force corresponds to a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle]. Further see Sect. 2-3 & 5. The examiner has interpreted that training a neural network (NN) once for a longer period of time to estimate friction forces for a suitable trajectory to accurately achieve estimations of external forces using joint torque sensor available on the robot during interaction tasks and then performing an experiment to illustrate the effectiveness of the method as the previously collected sensor data comprises sensor data collected from the industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation; and the corrected prediction of the resistive force corresponds to a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle.)
As per claim 9, Liu teaches “A computer-implemented method for predicting external resistive forces encountered by an industrial machine”. (Pg. 1731 Sect. 1, “This paper proposes an approach based on the disturbance observer and NN approximation method for the estimation of external force/torques felt by the robot during interaction tasks” [A computer-implemented method for predicting external resistive forces encountered by an industrial machine]. Further see Sect. 1-2. The examiner has interpreted that estimating external forces felt by a robot during interaction tasks based on a disturbance observer and neural network (NN) as a computer-implemented method for predicting external resistive forces encountered by an industrial machine.)
Liu also teaches “(a) tuning a model using sensor data collected from an industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation; and (b) predicting by the tuned model a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle.” (Pg. 1731 Sect. 1, “This paper proposes an approach based on the disturbance observer and NN approximation method for the estimation of external force/torques felt by the robot during interaction tasks” [i.e., prior working cycles conducted by the industrial machine as part of an industrial operation]. Pg. 1732 Sect. 2, “we take advantage of the joint torque sensor available on our robot, which is shown in Fig. 1. Actually, every joint is equipped with a high-resolution absolute position encoder on the motor side and an integrated joint torque sensor, so that θ and τJ are available” [i.e., sensor data collected from an industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation]. Pg. 1731 Sect. 2, “Assuming that the friction term of the link side is unknown, the estimated force value of the momentum observer will not be accurate because the result also includes the friction force. Only by modeling the friction of the link side can we achieve more accurate estimation of the external force. There are many ways to improve the dynamic model, such as the model parameter identification method, but the identification method is somewhat tedious. In view of this, this paper proposes a method that considers the observation results of the robot manipulator during free motion as the unmodeled friction. Then the observed residual is modeled via a suitable method. After that, the estimation accuracy of the observer will be improved. For (10), assuming that the terms M(q), C(
q
,
q
˙
), G(q) are accurate but the friction force of the link side Fq (
q
˙
) is unknown, the equation can be rewritten as τext = (M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
) + Fq(
q
˙
) . Let M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
=
τ
'
e
x
t
, which is equivalent to the observed residual
r
E
J
'
without considering the friction. In this paper, the commonly used multilayer feedforward NN is utilized” [i.e.., tuning a model using sensor data from an industrial machine and predicting by the tuned model a resistive force applied to the industrial machine from an external material]. Pg. 1735 Sect. 3, “The NN approximation methods are often used in local approximation problems on a compact set [27]. In this paper, the authors highlight that the completeness of the training data and the use of global basis functions are sufficient conditions for global friction force modeling. This is meaningful for physical system modeling using NNs. After analyzing the characteristics of the physical system and fully stimulating all the properties with suitable excitation trajectories, we can achieve accurate global modeling of the target. In this paper, the properties of the friction force are analyzed in detail and the appropriate excitation trajectory is chosen to guarantee global approximation using only limited but sufficient training data. After global approximation of the friction force, the NN just needs to be trained once for a relatively longer period.” and Pg. 1736 Sect. 5, “To illustrate the effectiveness of the proposed method, real-time experiments are also carried out on a 2-DOF robot manipulator” [i.e., a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle]. Further see Sect. 1-5. The examiner has interpreted that estimating external forces felt by the robot during interaction tasks using a joint torque sensor available on the robot to improve a dynamic model that approximates the friction force that was unknown in the momentum disturbance observer external force estimation and models an observed residual using torque by generating a more accurate estimate of the external force experienced by a robot manipulator and by training the neural network once for a longer period of time to estimate friction forces for a suitable trajectory to accurately achieve estimations of external forces using joint torque sensor available on the robot during interaction tasks and then performing an experiment to illustrate the effectiveness of the method as (a) tuning a model using sensor data collected from an industrial machine during one or more prior working cycles conducted by the industrial machine as part of an industrial operation; and (b) predicting by the tuned model a resistive force applied to the industrial machine from an external material during a future working cycle to be conducted by the industrial machine as part of the industrial operation based on a planned trajectory of the industrial machine corresponding to the future working cycle.)
As per claim 12, Liu teaches “wherein the model comprises a neural network.” (Pg. 1731 Sect. 1, “The comparison results show that when using the joint torque sensor, the external force estimation only requires the partial dynamics of the link side. In addition, employing the joint torque sensor eliminates the inaccuracy caused by the asynchrony of the motor position and the link position. Therefore, the estimation accuracy can be improved. 2) The paper proposes a method to model the friction dynamics of the link side of the manipulator, thus increasing the estimation accuracy considerably. The NN approximation is adopted” [wherein the model comprises a neural network]. Further see Sect. 1-2.)
As per claim 13, Liu teaches “wherein the model comprises an integrated model including both a physical model and a black box model including one or more neural networks.” (Pg. 1731 Sect. 1, “The comparison results show that when using the joint torque sensor, the external force estimation only requires the partial dynamics of the link side. In addition, employing the joint torque sensor eliminates the inaccuracy caused by the asynchrony of the motor position and the link position. Therefore, the estimation accuracy can be improved. 2) The paper proposes a method to model the friction dynamics of the link side of the manipulator, thus increasing the estimation accuracy considerably. The NN approximation is adopted, which avoids the need of analytic models of the joint friction and is easy to implement. To the knowledge of the authors, this is the first time to integrate the disturbance observer with the NN approximation for external force estimation…This hybrid modeling method including the analytic model and the NN model can provide important guidelines for system modeling” [wherein the model comprises an integrated model including both a physical model and a black box model including one or more neural networks]. Further see Sect. 1-2.)
As per claim 14, Liu teaches “wherein the model comprises a physical model but not a black box model.” (Pg. 1733 Sect. 2, “There are many ways to approximate the friction force. In this paper, the commonly used multilayer feedforward NN is utilized” and Pg. 1734 Sect. 3, “For the convenience of analysis and avoiding the dynamic coupling effects of the multi-DOF robot arm, the robot manipulator with 1-DOF is considered here. There are many kinds of friction models, such as the static friction model, Coulomb and viscous friction model, exponential model, Z model, and NN friction model” [i.e., the model can be modeled analytically or empirically]. Pg. 1734 Sect. 3, “The nonlinear friction function can be approximated either by a linear span of a set of continuous known functions” [the model is modeled analytically, i.e., wherein the model comprises a physical model but not a black box model. Further see Sect. 2-3. The examiner has interpreted that approximating the friction force in accurately modeling the external force using a linear span of a set of continuous known functions such as a static friction model as wherein the model comprises a physical model but not a black box model.)
As per claim 15, Liu teaches “wherein the sensor data is collected from one or more sensors of the industrial machine.” (Pg. 1732 Sect. 2, “we take advantage of the joint torque sensor available on our robot, which is shown in Fig. 1. Actually, every joint is equipped with a high-resolution absolute position encoder on the motor side and an integrated joint torque sensor, so that θ and τJ are available” [wherein the sensor data is collected from one or more sensors of the industrial machine]. Further see Sect. 1-2.)
As per claim 16, Liu teaches “(c) extracting position data and velocity data of a tool of the industrial machine using previously collected sensor data; (d) providing as an input to the model the position data of the tool; and (e) providing as an input to the model the velocity data of the tool.” (Pg. 1732 Sect. 2, “We installed the absolute position sensor between the harmonic reducer and the joint torque sensor. As the stiffness and damping of the joint torque sensor are known, the positions and velocities at both ends of the joint torque sensor can be obtained” [(c) extracting position data and velocity data of a tool of the industrial machine using the previously collected sensor data]. Pg. 1734 Sect. 3, “According to the literature [17], [18] and the above-mentioned analysis, it can be seen that the friction is continuous although it may be highly nonlinear and depends mainly on the velocity. The nonlinear friction function can be approximated either by a linear span of a set of continuous known functions, or by a NN of bounded basis functions” and further see Equations 16-17 which reply both on position and velocity data,
q
a
n
d
q
˙
, respectively, i.e., (d) providing as an input to the model the position data of the tool; and (e) providing as an input to the model the velocity data of the tool. Further see Sect. 1-3. The examiner has interpreted that installing a position sensor on the robot to obtain the position and velocity of the joint, estimating the external force using the position data in Equation 10, and approximating the friction force using a neural network (NN) dependent on position and velocity as (c) extracting position data and velocity data of a tool of the industrial machine using previously collected sensor data; (d) providing as an input to the model the position data of the tool; and (e) providing as an input to the model the velocity data of the tool.)
As per claim 17, Liu teaches “wherein the model comprises a neural network having an input layer including the resistive force predicted by the first model, an output layer, and one or more hidden layers positioned between the input layer and the output layer.” (Pg. 1731 Sect. 2, “this paper proposes a method that considers the observation results of the robot manipulator during free motion as the unmodeled friction. Then the observed residual is modeled via a suitable method. After that, the estimation accuracy of the observer will be improved. For (10), assuming that the terms M(q), C(
q
,
q
˙
), G(q) are accurate but the friction force of the link side Fq (
q
˙
) is unknown, the equation can be rewritten as τext = (M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
) + Fq(
q
˙
) . Let M(
q
)
q
¨
+ C(
q
,
q
˙
)
q
˙
+ G(q) − τJ – DK− 1
τ
˙
J
=
τ
'
e
x
t
, which is equivalent to the observed residual
r
E
J
'
without considering the friction.… There are many ways to approximate the friction force. In this paper, the commonly used multilayer feedforward NN is utilized” [i.e., wherein the model comprises a neural network having an input layer including the resistive force predicted by the first model]. Pg. 1735 Sect. 3, “the NNs with only one hidden layer is chosen in this paper and the parameters of the NNs are determined carefully” [i.e., one or more hidden layers positioned between the input layer and the output layer]. Further see Sect. 2-3. The examiner has interpreted that using a multilayer feedforward neural network (NN) to approximate the friction force to model an observed residual having a hidden layer as wherein the model comprises a neural network having an input layer including the resistive force predicted by the first model, an output layer, and one or more hidden layers positioned between the input layer and the output layer.)
Re Claim 18, it is a system claim, having similar limitations of claim 1. Thus, claim 18 is also rejected under the similar rationale as cited in the rejection of claim 1.
Furthermore, regarding claim 18, Liu teaches “A system for predicting external resistive forces encountered by an industrial machine, the system comprising: a processor; a non-transitory memory; and one or more applications stored in the non-transitory memory that, when executed by the processor” and “stored in the non-transitory memory”. (Pg. 1736 Sect. 5, “To illustrate the effectiveness of the proposed method, real-time experiments are also carried out on a 2-DOF robot manipulator which is shown in Fig. 4 with the nominal parameters (achieved from the CAD drawings) illustrated in Table II. For this manipulator, the friction terms of the link side are unknown. The dSPACE control system, in particular, the DS1005 board, is used, which integrates the whole development process seamlessly into a single environment” [i.e., a system for predicting external resistive forces encountered by an industrial machine, the system comprising: a processor; a non-transitory memory; and one or more applications stored in the non-transitory memory that, when executed by the processor and stored in the non-transitory memory]. Further see Sect. 1-3 & 5.)
Re Claim 19, it is a system claim, having similar limitations of claim 6. Thus, claim 19 is also rejected under the similar rationale as cited in the rejection of claim 6.
Re Claim 20, it is a system claim, having similar limitations of claim 8. Thus, claim 20 is also rejected under the similar rationale as cited in the rejection of claim 8.
Claim Rejections - 35 U.S.C. § 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. § 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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 5 and 10-11 are rejected under 35 U.S.C. § 103 as being unpatentable over Liu as applied to claims 1 and 9, respectively, and in further view of Cannon, Howard, and Sanjiv Singh. "Models for automated earthmoving." In Experimental Robotics VI, Lecture Notes in Control and Information Sciences, vol 250. London: Springer London, 2000 [herein “Cannon”].
As per claim 5, Liu does not specifically teach “wherein the sensor data comprises pressure sensor data collected from one or more pressure sensors of the industrial machine.”
However, in the same field of endeavor namely predicting external contact forces experienced by industrial machines, Cannon teaches “wherein the sensor data comprises pressure sensor data collected from one or more pressure sensors of the industrial machine”. (Pg. 167 Sect. 3, “In our system, reaction forces are estimated based on the measurement of pressure in the hydraulic actuators. These pressures can be transformed into joint torques (see [5] for details), which can subsequently be used to estimate the reaction forces” [wherein the sensor data comprises pressure sensor data collected from one or more pressure sensors]. Abstract, “Our models are used to both estimate soil properties and predict contact forces between the excavator and the terrain” [of the industrial machine]. Further see Sect. 3 & the Abstract. The examiner has interpreted that predicting contact forces between the excavator and the terrain based on a measurement of pressure in the hydraulic actuators as wherein the sensor data comprises pressure sensor data collected from one or more pressure sensors of the industrial machine.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the sensor data comprises pressure sensor data collected from one or more pressure sensors of the industrial machine” as conceptually seen from the teaching of Liu, into that of Cannon because this modification of using pressure data for the advantageous purpose of indicating the hardness of soil and extracting soil properties in the prediction of experienced forces (Cannon Pg. 170 Sect. 3 & Pg. 167 Sect. 2). Further motivation to combine be that Liu and Cannon are analogous art to the current claim as directed to predicting external contact forces experienced by industrial machines.
As per claim 10, Liu does not specifically teach “wherein the one or more prior working cycles and the future working cycle each comprise an excavating phase in which a tool of the industrial machine excavates a portion of the external material from a pile of the external material.”
However, Cannon teaches “wherein the one or more prior working cycles and the future working cycle each comprise an excavating phase in which a tool of the industrial machine excavates a portion of the external material from a pile of the external material.” Pg. 167 Sect. 3, “In our system, reaction forces are estimated based on the measurement of pressure in the hydraulic actuators. These pressures can be transformed into joint torques (see [5] for details), which can subsequently be used to estimate the reaction forces… The bucket is intersected with a terrain map resulting in an estimate of the intersection geometry” [i.e., wherein the one or more prior working cycles comprise an excavating phase in which a tool of the industrial machine excavates a portion of the external material from a pile of the external material]. Pg. 163 Sect. 1, “Here we report on models used to predict digging trajectories before they are executed. These models capture machine dynamics, soil properties and the soil-tool interaction” and Pg. 170 Sect. 4, “We have conducted approximately 1900 digging experiments. We find that most significant discrepancies between the model and measured trajectories are either due to non-homogeneous material effects such as boulders, or, errors in the range data required to estimate terrain shape. Figure 8 shows a qualitative comparison between the predicted and measured trajectories for four digs. Figure 9 shows a comparison between the digging statistics predicted by the forward model and the statistics calculated by monitoring the actual digging cycle. These quantities (time, energy, and swept volume) are important for evaluating the overall utility of a dig” [i.e., the future working cycle each comprise an excavating phase in which a tool of the industrial machine excavates a portion of the external material from a pile of the external material cycle]. Further see Sect. 1 and 3-4. The examiner has interpreted that a model for estimating forces based on pressure measurements when a bucket of an excavator intersects a terrain and predicts the digging trajectories of the excavator bucket and performs an experiment to validate the model as wherein the one or more prior working cycles and the future working cycle each comprise an excavating phase in which a tool of the industrial machine excavates a portion of the external material from a pile of the external material.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the one or more prior working cycles and the future working cycle each comprise an excavating phase in which a tool of the industrial machine excavates a portion of the external material from a pile of the external material” as conceptually seen from the teaching of Liu, into that of Cannon because this modification of estimating external for excavators for the advantageous purpose of indicating the hardness of soil and extracting soil properties in the prediction of experienced forces by excavators (Cannon Pg. 170 Sect. 3 & Pg. 167 Sect. 2). Further motivation to combine be that Liu and Cannon are analogous art to the current claim as directed to predicting external contact forces experienced by industrial machines.
As per claim 11, Liu does not specifically teach “wherein the planned trajectory of the industrial machine comprises a planned trajectory of a tool of the industrial machine to be executed during the excavation phase of the future working cycle.”
However, Cannon teaches “wherein the planned trajectory of the industrial machine comprises a planned trajectory of a tool of the industrial machine to be executed during the excavation phase of the future working cycle.” (Pg. 165 Sect. 3, “We have developed a feedforward model of the excavation process as shown in Figure 2. A model of the machine's actuators is used to predict the motion of the bucket in response to the actuator commands and reaction forces. The resultant motion is used by a soil-tool model to predict reaction forces on the bucket. Reaction forces and actuator positions are used by a control law to dictate actuator commands. This cycle is started with initial conditions (starting location and orientation of the bucket) and continued until the bucket is out of the ground. Predicted trajectories are scored by the use of a utility function composed of factors such as the time spent during digging, the energy expended, and the volume of soil captured” [i.e., wherein the planned trajectory of the industrial machine comprises a planned trajectory of a tool of the industrial machine to be executed during the excavation phase of the future working cycle]. Further see Sect. 3-4. The examiner has interpreted that using the starting location and orientation of a bucket of an excavator to predict the motion of the bucket while digging soil in the ground as wherein the planned trajectory of the industrial machine comprises a planned trajectory of a tool of the industrial machine to be executed during the excavation phase of the future working cycle.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the planned trajectory of the industrial machine comprises a planned trajectory of a tool of the industrial machine to be executed during the excavation phase of the future working cycle” as conceptually seen from the teaching of Liu, into that of Cannon because this modification of applying trajectories for excavators for the advantageous purpose of indicating the hardness of soil and extracting soil properties in the prediction of experienced forces by excavators (Cannon Pg. 170 Sect. 3 & Pg. 167 Sect. 2). Further motivation to combine be that Liu and Cannon are analogous art to the current claim as directed to predicting external contact forces experienced by industrial machines.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Jahnke, Jonathan. Efficient Numerical Simulation of Soil-Tool Interaction. Fraunhofer Verlag, 2022 teaches a method that uses a physics-based model and a neural network to determine the soil-tool interaction forces arising at an earthmoving tool.
Lee, Minhyeong, Hyelim Choi, ChangU Kim, Jihyun Moon, Dongmok Kim, and Dongjun Lee. "Precision motion control of robotized industrial hydraulic excavators via data-driven model inversion." IEEE Robotics and Automation Letters 7, no. 2 (2022): 1912-1919 teaches an excavator plant model and a data-driven inversion control supervised model to determine the trajectory of an machine during excavation.
Azure, Jessica WA, Prosper EA Ayawah, Azupuri GA Kaba, Forsyth A. Kadingdi, and Samuel Frimpong. "Hydraulic shovel digging phase simulation and force prediction using machine learning techniques." Mining, Metallurgy & Exploration 38, no. 6 (2021): 2393-2404 teaches a method of using a machine learning model for predicting rock formation reactive forces experienced by a hydraulic shovel bucket during excavation to improve accuracy of its prediction.
Examiner’s Note: The examiner has cited particular columns and line numbers in the reference that applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, to fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. In the case of amending the claimed invention, the applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for the proper interpretation and also to verify and ascertain the metes and bound of the claimed invention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Simeon P Drapeau whose telephone number is (571)-272-1173. The examiner can normally be reached Monday - Friday, 8 a.m. - 5 p.m. ET.
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, Ryan Pitaro can be reached on (571) 272-4071. 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.
/SIMEON P DRAPEAU/Examiner, Art Unit 2188
/RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
Prosecution Insights