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 .
Priority
Acknowledgement is made of the applicant's claim for Foreign priority to German Patent
Application No. 20212128572 filed on November 16, 2021.
Claim Rejections - 35 USC § 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 16-29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
101 Subject Matter Eligibility Analysis
Step 1: Claims 16-29 are within the four statutory categories (a process, machine, manufacture or composition of matter).
Step 2A Prong One, Step 2A Prong Two, and Step 2B Analysis:
Step 2A Prong One asks if the claim recites a judicial exception (abstract idea, law of nature, or natural phenomenon). If the claim recites a judicial exception, analysis proceeds to Step 2A Prong Two, which asks if the claim recites additional elements that integrate the abstract idea into a practical application. If the claim does not integrate the judicial exception, analysis proceeds to Step 2B, which asks if the claim amounts to significantly more than the judicial exception. If the claim does not amount to significantly more than the judicial exception, the claim is not eligible subject matter under 35 U.S.C. 101.
None of the claims represent an improvement to technology.
Claims 16-26 are directed to a method consisting of a series of steps, meaning that it is directed to the statutory category of process Claims 27-29 are directed to storage mediums and processors which are machines.
Regarding claim 16, the following claim elements are abstract ideas:
determining trajectories from the set for which a measure of uncertainly indicates a greater or equal uncertainty than a measure of uncertainty for others of the trajectories from the set (This is an abstract idea of a mental process. The limitation involves reviewing uncertainty values associated with different trajectories and determining which trajectories have uncertainty values greater than or equal to the uncertainty of values of other trajectories. A person could review a list of trajectories with corresponding uncertainty scores, compare the scores, and select the trajectories having the higher uncertainty using observation and judgement. This type of comparison, ranking, and selection can be practically performed in the human mind or with pen and paper, and therefore falls within the mental process grouping of abstract ideas. See MPEP 2106.04(a)(2)(III).); and
wherein: (i) the order in which the measurements are performed is an order in which the trajectories are determined from the set, or (ii) the order in which the measurements are performed is determined depending on the order in which the trajectories are determined from the set (This is an abstract idea of a mental process. The limitation involves using observation and judgement to decide how measurements should be performed based on the order in which the trajectories were determined. A person could review the determined trajectories, evaluate the order in which the trajectories were selected, and decide whether to perform measurements in that same order or in an order based on that selection. This type of observation, evaluation, judgement, and decision-making can be practically performed in the human mind or with pen and paper, and therefore falls within the mental process grouping of abstract ideas.).
The following claim elements are additional elements which, taken alone or in combination with the other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
a technical system (This a high-level recitation of generic computer components for performing the abstract idea. See MPEP 2106.05(f).)
a predictive model (This a high-level recitation of generic computer components for performing the abstract idea. See MPEP 2106.05(f).)
performing measurements with trajectories from the set on the technical system in an order (The step of “performing measurements” is merely well-understood, routine, and conventional data gathering activity in conjunction with the abstract idea. See MPEP 2106.05(d).)
Regarding claim 17, the rejection of claim 16 is incorporated herein. Further, claim 17 recites the following additional elements, which taken alone or in combination with other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
wherein the predictive model includes: (i) a non-linear network mapping its input to its output with a time delay, or (ii) a non-linear autoregressive neural network with an exogenous input, or a Gaussian process, or a machine learning model with a predictive covariance (This limitation adds insignificant extra-solution activity to the judicial exception. The limitation merely identifies the type of predictive models used in conjunction with the abstract idea and does not provide a meaningful limitation.)
Regarding claim 18, the rejection of claim 16 is incorporated herein. Further, claim 18 recites the following abstract ideas:
wherein the measure includes a determinant of a covariance that depends on trajectories from the set (This is an abstract idea of a mental process. The limitation involves using a mathematical calculation to determine a measure based on trajectories from the set. A person could review trajectory data, calculate covariance values, determine the determinant of the covariance, and use the calculated values as the measure. The type of mathematical evaluation and judgement can be practically performed in the human mind with the aid of pen and paper or basic computational tools, and therefore falls within the mental process grouping of abstract ideas.).
Regarding claim 19, the rejection of claim 16 is incorporated herein. Further, claim 19 recites the following additional elements, which taken alone or in combination with other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
wherein a measurement with at least one of the trajectories is performed on the technical system (This limitation constitutes mere instructions to apply the abstract idea and insignificant extra-solution activity. See MPEP 2106.05(f) and 2106.05(g).).
Regarding claim 20, the rejection of claim 19 is incorporated herein. Further, claim 20 recites the following abstract ideas:
a quality measure that depends on the at least one trajectory and the measurement assigned to the at least one trajectory (This is an abstract idea of a mental process. The limitation involves evaluating a trajectory and an assigned measurement using a quality measure. A person could review a trajectory, review the measurement result associated with that trajectory, and assign a quality value or rating based on the relationship between the trajectory and the measurement using observation, evaluation, and judgement. This type of evaluation can be practically performed in the human mind or with the aid of pen and paper and therefore falls within the mental process grouping of abstract ideas.)
The following claim elements are additional elements which, taken alone or in combination with the other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
wherein the predictive model is trained (This limitation constitutes mere instructions to apply the abstract idea and insignificant extra-solution activity. See MPEP 2106.05(f) and 2106.05(g).)
Regarding claim 21, the rejection of claim 20 is incorporated herein. Further, claim 21 recites the following abstract ideas:
wherein trajectories are iteratively determined from the set (This is an abstract idea of a mental process. This limitation involves repeatedly reviewing trajectories from a set and determining which trajectories to use. A person could review a set of trajectories, evaluate the trajectories based on observation and judgement, and repeatedly select trajectories from the set. This type of evaluation and decision-making can be practically performed in the human mind or with the aid of pen and paper or computational tools, and therefore falls within the mental process grouping of abstract ideas.)
The following claim elements are additional elements which, taken alone or in combination with the other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
measurements are carried out with the iteratively determined trajectories (The limitation adds insignificant extra-solution activity to the judicial exception. The limitation merely carries out measurements in conjunction with the abstract idea and does not provide a meaningful limitation.),
the predictive model is trained on the quality measure, depending on the trajectories and the measurements assigned to the quality measure (This limitation constitutes mere instructions to apply the abstract idea and insignificant extra-solution activity. See MPEP 2106.05(f) and 2106.05(g).).
Regarding claim 22, the rejection of claim 16 is incorporated herein. Further, claim 22 recites the following additional elements, which taken alone or in combination with other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
wherein the technical system is a computer-controlled machine, or a robot, or a vehicle, or a household appliance, or a tool, or a manufacturing machine, or a personal assistance system, or an access control system (This limitation adds insignificant extra-solution activity to the judicial exception. The limitation merely identifies the type of technical system used in conjunction with the abstract idea and does not provide a meaningful limitation.).
Regarding claim 23, the rejection of claim 16 is incorporated herein. Further, claim 23 recites the following abstract ideas:
wherein a respective index is assigned to the trajectories, wherein the indices of the trajectories for which the measure indicates the greater or equal uncertainty are determined (This is an abstract idea of a mental process. The limitation involves assigning index positions to trajectories and determining which index positions correspond to trajectories having a greater or equal uncertainty measure. A person could review a list or matrix of trajectories, identify the index position for each trajectory, compare the uncertainty measures for the trajectories, identify the index position for each trajectory, compare the uncertainty measures for the trajectories having greater or equal uncertainty using observation, evaluation, and judgement with pen or paper. This type of evaluation can be practically performed in the human mind or with the aid of pen and paper and therefore falls within the mental process grouping of abstract ideas.).
Regarding claim 24, the rejection of claim 16 is incorporated herein. Further, claim 24 recites the following abstract ideas:
wherein a number of trajectories are selected from the set, wherein the measure is determined for the number of trajectories (This is an abstract idea of a mental process. The limitation involves selecting a number of trajectories from a set and determine the uncertainty measure from the selected trajectories by evaluating the covariance values associated with the selected trajectories using observation, evaluation, and judgement with pen and paper or basic computational tools. This type of evaluation can be practically performed in the human mind or with the aid of pen and paper or computational tools, and therefore falls within the mental process grouping of abstract ideas.).
Regarding claim 25, the rejection of claim 16 is incorporated herein. Further, claim 25 recites the following abstract ideas:
wherein the measure is determined in iterations, wherein, per iteration, a portion of the measure is determined depending on a respective trajectory (This is an abstract idea of a mental process. The limitation involves repeatedly determining portions of a measure based on respective trajectories. A person could review respective trajectory, determine a portion of the uncertainty measure for that trajectory, and then repeatedly perform the same determination for additional trajectories using observation, evaluation, and judgement with pen and paper or basic computational tools. This type of repeated evaluation can be practically performed in the human mind or with the aid of pen and paper or basic computational tools, and therefore falls within the mental process grouping of abstract ideas.)
Regarding claim 26, the rejection of claim 16 is incorporated herein. Further, claim 26 recites the following abstract ideas:
wherein a subset of trajectories is determined from the set, wherein, for each trajectory from the subset, a probability is determined that the technical system is damaged by a measurement with the trajectory or that the technical system remains undamaged in a measurement with the trajectory, wherein the subset of trajectories is either provided or used for measurement when the probability for each trajectory satisfies a condition or when the probabilities of the trajectories from the subset together satisfy a condition, and wherein the subset of trajectories is otherwise not provided or used for measurement (This is an abstract idea of a mental process. The limitation involves selecting a subset of trajectories, evaluating a probability that each trajectory will damage or not damage a technical system, comparing the probability or probabilities to a condition, and deciding whether the subset should be provided or used for measurement. A person could review trajectories, evaluate the risk associated with measuring each trajectory, compare the probability of damage or no damage to a safety condition, and decide whether to use or not use the trajectories based on observation, evaluation, and judgement with pen or paper or basic computational tools. This type of risk evaluation and decision-making can be practically performed in the human mind or with the aid of pen and paper or basic computational tools, and therefore falls within the mental process grouping of abstract ideas.).
Regarding claim 27, the following claim elements are abstract ideas:
determine trajectories from the set for which a measure of uncertainly indicates a greater or equal uncertainty than a measure of uncertainty for others of the trajectories from the set (This is an abstract idea of a mental process. The limitation involves reviewing uncertainty values associated with different trajectories and determining which trajectories have uncertainty values greater than or equal to the uncertainty of values of other trajectories. A person could review a list of trajectories with corresponding uncertainty scores, compare the scores, and select the trajectories having the higher uncertainty using observation and judgement. This type of comparison, ranking, and selection can be practically performed in the human mind or with pen and paper, and therefore falls within the mental process grouping of abstract ideas. See MPEP 2106.04(a)(2)(III).); and
wherein: (i) the order in which the measurements are performed is an order in which the trajectories are determined from the set, or (ii) the order in which the measurements are performed is determined depending on the order in which the trajectories are determined from the set (This is an abstract idea of a mental process. The limitation involves using observation and judgement to decide how measurements should be performed based on the order in which the trajectories were determined. A person could review the determined trajectories, evaluate the order in which the trajectories were selected, and decide whether to perform measurements in that same order or in an order based on that selection. This type of observation, evaluation, judgement, and decision-making can be practically performed in the human mind or with pen and paper, and therefore falls within the mental process grouping of abstract ideas.).
The following claim elements are additional elements which, taken alone or in combination with the other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
A device for determining trajectories (This a high-level recitation of generic computer components for performing the abstract idea. See MPEP 2106.05(f).)
a predictive model of the technical system (This a high-level recitation of generic computer components for performing the abstract idea. See MPEP 2106.05(f).)
perform measurements with trajectories from the set on the technical system in an order (The step of “performing measurements” is merely well-understood, routine, and conventional data gathering activity in conjunction with the abstract idea. See MPEP 2106.05(d).)
Regarding claim 28, the rejection of claim 27 is incorporated herein. Further, claim 28 recites the following additional elements, which taken alone or in combination with other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
wherein the device comprises at least one processor, at least one memory and at least one interface (This a high-level recitation of generic computer components for performing the abstract idea. See MPEP 2106.05(f).),
wherein the at least one processor configured to perform the determination and perform the measurements (The limitation merely uses a generic processor to perform the abstract idea and does not provide a meaningful limitation.)
wherein the at least one memory is configured to store the set of trajectories, and/or the predictive model, and/or the trajectories determined from the set (This limitation constitutes mere instructions to apply the abstract idea and insignificant extra-solution activity. See MPEP 2106.05(f) and 2106.05(g).)
wherein the interface is configured, for performing and/or for recording the measurements on the technical system, to communicate with a test bench for the technical system (This limitation constitutes mere instructions to apply the abstract idea and insignificant extra-solution activity. See MPEP 2106.05(f) and 2106.05(g).).
Regarding claim 29, the following claim elements are abstract ideas:
determining trajectories from the set for which a measure of uncertainly indicates a greater or equal uncertainty than a measure of uncertainty for others of the trajectories from the set (This is an abstract idea of a mental process. The limitation involves reviewing uncertainty values associated with different trajectories and determining which trajectories have uncertainty values greater than or equal to the uncertainty of values of other trajectories. A person could review a list of trajectories with corresponding uncertainty scores, compare the scores, and select the trajectories having the higher uncertainty using observation and judgement. This type of comparison, ranking, and selection can be practically performed in the human mind or with pen and paper, and therefore falls within the mental process grouping of abstract ideas. See MPEP 2106.04(a)(2)(III).); and
wherein: (i) the order in which the measurements are performed is an order in which the trajectories are determined from the set, or (ii) the order in which the measurements are performed is determined depending on the order in which the trajectories are determined from the set (This is an abstract idea of a mental process. The limitation involves using observation and judgement to decide how measurements should be performed based on the order in which the trajectories were determined. A person could review the determined trajectories, evaluate the order in which the trajectories were selected, and decide whether to perform measurements in that same order or in an order based on that selection. This type of observation, evaluation, judgement, and decision-making can be practically performed in the human mind or with pen and paper, and therefore falls within the mental process grouping of abstract ideas.).
The following claim elements are additional elements which, taken alone or in combination with the other elements, do not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception:
A non-transitory computer-readable medium on which is stored a computer program including computer-readable instructions (This a high-level recitation of generic computer components for performing the abstract idea. See MPEP 2106.05(f).)
a predictive model of the technical system (This a high-level recitation of generic computer components for performing the abstract idea. See MPEP 2106.05(f).)
a computer (This limitation constitutes mere instructions to apply the abstract idea and insignificant extra-solution activity. See MPEP 2106.05(f) and 2106.05(g).)
performing measurements with trajectories from the set on the technical system in an order (The step of “performing measurements” is merely well-understood, routine, and conventional data gathering activity in conjunction with the abstract idea. See MPEP 2106.05(d).)
Claim Rejections - 35 USC § 103
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 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.
Claims 16-17, 19-23 and 25-29 are rejected under the 35 U.S.C. 103 as being unpatentable over Navarro et al., (Pub. No.: US 20160343258 A1 (Filed: 2014)) in view of Nikovski et al., (Pub. No.: US 20200230815 A1 (Filed: 2019)).
Regarding claim 16, Navarro teaches the following limitations:
A computer-implemented method for determining trajectories from a set of trajectories for measurements on a technical system, wherein a predictive model of the technical system includes a measure of uncertainty of a prediction of the predictive model, wherein the measure depends on trajectories from the set, the method comprising the following steps: determining trajectories from the set for which a measure of uncertainly indicates a greater or equal uncertainty than a measure of uncertainty for others of the trajectories from the set (Navarro, paragraph [0081] “an aircraft performance model including one or more parameters which define aircraft response upon external conditions;” [0092] “calculates, based on the ensemble of atmospheric forecasts, an ensemble of predicted trajectories, each calculated predicted trajectory based on a corresponding atmosphere scenario” [0093] “assesses at least one figure of merit of each predicted trajectory within an ensemble of predicted trajectories, to obtain a population of values of these figures of merit” [0095] “obtains, according to a certain statistical criterion, a dispersion of the values of the at least one figure of merit assessed, associated with the remaining trajectories of the ensemble of predicted trajectories” [0159] “a preferred FOM to be optimized is selected, and the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” [0226] “ The capability to manage uncertainty inputs and produce a stochastic trajectory prediction and its uncertainty measure in terms of FOM” [0227] “the use of customized figures of merit (FOM's) to characterize the uncertainty of TP for its exploitation in automated decision support “ – Navarro teaches an aircraft performance model that calculates an ensemble of predicted trajectories. Under the broadest reasonable interpretation, the aircraft performance model corresponds to the claimed predictive model, and the ensemble of predicted trajectories corresponds to the claimed set of trajectories. Navarro further teaches assessing a FOM for each predicted trajectory and obtaining a dispersion of the FOM values, where the FOM is used to characterize trajectory prediction uncertainty. Accordingly, the FOM-based dispersion corresponds to the claimed measure of uncertainty that depends on the trajectories from the set. Navarro also teaches re-ordering the predicted trajectories according to a statistical criterion referred to the FOM, which teaches or at least renders obvious determining trajectories having greater or equal uncertainty than other trajectories in the set.) and
However, Navarro does not teach but Navarro in view of Nikovski teaches the following limitation:
performing measurements with trajectories from the set on the technical system in an order, wherein: (i) the order in which the measurements are performed is an order in which the trajectories are determined from the set, or (ii) the order in which the measurements are performed is determined depending on the order in which the trajectories are determined from the set (Navarro, paragraph [0092] “calculates, based on the ensemble of atmospheric forecasts, an ensemble of predicted trajectories, each calculated predicted trajectory based on a corresponding atmosphere scenario “ [0159] “the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” Nikovski, paragraph [0040] “The robotic assembly 100 is configured to perform an insertion operation, e.g., insert a component 103 into a component 104, along an insertion line. As used herein, the insertion line is a trajectory of a motion of the wrist 102 defining a trajectory of the motion of the component 103…the wrist 102 has multiple degrees of freedom, so the insertion line can have a motion profile spanning in multi-dimensional space.” [0041] “The robotic assembly 100 also includes a force sensor 110 operatively connected to the wrist of the robotic arm to measure the force tensor experienced by the end-effector of the robot during a manipulation and insertion operation. For example, the force sensor can be mounted on the wrist joint of the robot. For example, the force tensor includes measurements 115 of force and moments along the axis of the robot (Fx, Fy, Fz, Mx, My, Mz) in addition to position and orientation along three axis. Because of the flexibility of the motion of the robotic arm having a wrist, the measurement space provided by the sensor is 12 dimensional or 18 dimensional when velocities along all the axis are considered.” – Navarro teaches calculating an ensemble of predicted trajectories and re-ordering the predicted trajectories according to a statistical criterion referred to the FOM> As mapped above, the re-ordered predicted trajectories corresponds to trajectories determined from the set. Nikovski teaches that a robotic assembly performs an insertion operation along an insertion line, where the insertion line is a trajectory of motion of the wrist and component. Nikovski further teaches a force sensor measures force, moments, position, and orientation during the insertion operation. Under the broadest reasonable interpretation, Nikovski’s robotic assembly corresponds to the claimed technical system, the insertion line corresponds to the claimed trajectory, and the force sensor data corresponds to the claimed measurements. Accordingly, Navarro in view of Nikovski teaches performing measurements with trajectories from the set on the technical system in order determined depending on the order in which the trajectories are determined from the set.)
Accordingly, it would have been obvious to person of ordinary skill in the art, before the effective filing date of the claimed invention, having a combination of Navarro and Nikovski before them, to incorporate the trajectory-based sensor movement techniques of Nikovski into the uncertainty-based trajectory determination system of Navarro. One would have been motivated to make such a combination in order to physically test trajectories identified as having higher uncertainty, rather than testing every possible trajectory of the technical system. This would allow the system to obtain actual measured response data for the trajectories most likely to reveal weak spots, abnormal behavior, or less reliable operating regions of the technical system. By using Navarro’s uncertainty analysis to identify which trajectories should be tested, and Nikovski’s sensor-based measurements to evaluate a technical system while performing those trajectories, the combination would reduce unnecessary testing while identifying portions of the system operation that may require correction, adjustment, or further evaluation.
Regarding claim 17, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. Navarro in view of Nikovski further teaches:
wherein the predictive model includes: (i) a non-linear network mapping its input to its output with a time delay, or (ii) a non-linear autoregressive neural network with an exogenous input, or a Gaussian process, or a machine learning model with a predictive covariance (Nikovski, paragraph [0060] “some embodiments model the underlying stable relationship between the force experienced by the robot along the direction of insertion and the position along that direction using a Gaussian process regression. A Gaussian process regression is a non-parametric statistical model where every point in the input space is associated with a normally distributed random variable. More concretely, a Gaussian process is a collection of random variables, any finite number of which is represented by a joint Gaussian distribution. As a result, a Gaussian process is completely defined by only two parameters, i.e., their mean and covariance function (also known as the kernel function)…. In such a manner, force distribution at any test point along a trajectory is completely defined by the mean and covariance obtained from the Gaussian process.” [0061] “To fit the Gaussian process regression model, some embodiments determine a posterior mean and a posterior covariance function by maximizing a negative log likelihood of the Gaussian process regression model using the training data” – Nikovski teaches a Gaussian process regression with mean and covariance, including a posterior covariance function. Accordingly, Navarro in view of Nikovski teaches the predictive model including a Gaussian process or a machine learning model with predictive covariance.).
Regarding claim 19, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. Navarro in view of Nikovski further teaches:
wherein a measurement with at least one of the trajectories is performed on the technical system (Nikovski, paragraph [0040] “The robotic assembly 100 is configured to perform an insertion operation, e.g., insert a component 103 into a component 104, along an insertion line. As used herein, the insertion line is a trajectory of a motion of the wrist 102 defining a trajectory of the motion of the component 103.” [0041] “The robotic assembly 100 also includes a force sensor 110 operatively connected to the wrist of the robotic arm to measure the force tensor experienced by the end-effector of the robot during a manipulation and insertion operation… For example, the force tensor includes measurements 115 of force and moments along the axis of the robot (Fx, Fy, Fz, Mx, My, Mz) in addition to position and orientation along three axis.” – Nikovski teaches that the robotic assembly performs an insertion operation along an insertion line, where the insertion line is a trajectory motion. Nikovski further teaches measuring force, moments, positions, and orientation during an insertion operation. Under BRI, the robotic assembly corresponds to the claimed technical system, the insertion line corresponds to at least one trajectory, and the force sensor data corresponds to a measurement performed with the trajectory on the technical system.).
Regarding claim 20, Navarro in view of Nikovski teaches all the elements of claim 19, therefore is rejected for the same reasons as those presented for claim 19. Navarro in view of Nikovski further teaches:
wherein the predictive model is trained on a quality measure that depends on the at least one trajectory and the measurement assigned to the at least one trajectory (Navarro, paragraph [0253] “As far as what is concerned on determining errors and metrics in trajectory prediction, any rigorous framework to study TP uncertainty requires defining what TP error means for the different trajectory aspects of potential interest to r-DST's, as well as establishing proper metrics to measure them.” [0254] “To start with, FIG. 12 is considered, which depicts a typical predicted trajectory and the aircraft at a given predicted position denoted as “P”. Bearing in mind that there is uncertainty present, the actual position “A” of the aircraft at that same time instant is expected to differ from the predicted one, P. For this purpose, the concept of covariance ellipsoid is useful, an ellipsoid centered in P, which contains the actual position A with a given probability… a measure of the geometric TP errors: along track error in distance (ATER), cross-track error (XTE) and vertical error (VE).” Nikovski, paragraph [0056] “one embodiment fits a regression 202 to training data 201 for learning/estimating a probabilistic relationship between force experienced by the wrist of the robotic arm at different positions of the wrist of the robotic arm along the line of insertion.” [0061] “ To fit the Gaussian process regression model, some embodiments determine a posterior mean and a posterior covariance function by maximizing a negative log likelihood of the Gaussian process regression model using the training data” – Navarro teaches defining trajectory prediction error by comparing a predicted trajectory position P with an actual aircraft position A and establishing metrics, including ATER, XTE, and VE, to measure the trajectory prediction error. Under BRI, Navarro’s trajectory prediction error metrics correspond to a quality measure that depends on the predicted trajectory and the actual position measurement assigned to that trajectory. Nikovski teaches fitting a predictive model using training data and maximizing a negative log likelihood using the training data. Under BRI, Nikovski’s negative likelihood corresponds to training the predictive model on a quality measure based on the trajectory measurement data. Accordingly, Navarro’s predictive model, as modified by Nikovski’s model training technique, teaches the predictive model being trained on a quality measure that depends on the at least one trajectory and the measurement assigned to the at least one trajectory.).
Regarding claim 21, Navarro in view of Nikovski teaches all the elements of claim 20, therefore is rejected for the same reasons as those presented for claim 20. Navarro in view of Nikovski further teaches:
wherein trajectories are iteratively determined from the set, measurements are carried out with the iteratively determined trajectories, and the predictive model is trained on the quality measure, depending on the trajectories and the measurements assigned to the quality measure (Navarro, paragraph [0335] “ the approach is based on Monte Carlo simulation. Thus the randomization engine unit (4), RE, works iteratively with the underlying trajectory computation unit (5), TC, which computes one trajectory for each combination of all the stochastic variables selected by the randomization engine unit (4), RE… the randomization engine unit (4), RE, collects all “possible” predicted trajectories and performs the FOM analysis explained above” [0338] “The randomization engine unit (4), RE, is in charge of building up the randomization sequence, which typically consists on a series of nested loops.. Every time that one specific combination is made, the randomization engine unit (4), RE, calls interface 8 and retrieves the predicted trajectory associated to such combination.” Nikovski, paragraph [0056] “ one embodiment fits a regression 202 to training data 201 for learning/estimating a probabilistic relationship between force experienced by the wrist of the robotic arm at different positions of the wrist of the robotic arm along the line of insertion.” [0061] “the probabilistic function is learned by fitting a Gaussian process regression model to training data defined by the measurements of the operation repeatedly performed by one or multiple robotic arms having the configuration of the robotic arm under control… To fit the Gaussian process regression model, some embodiments determine a posterior mean and a posterior covariance function by maximizing a negative log likelihood of the Gaussian process regression model using the training data” – Navarro teaches iteratively computing predicted trajectories using Monte Carlo simulation, nested loops, and stochastic variable combinations, then collecting the possible predicted trajectories and performing FOM analysis. Under BRI, Navarro teaches trajectories iteratively determined from a set. Nikovski teaches measurements carried out along a trajectory and fitting a Gaussian process regression model using training data defined by measurements of the repeated robotic operation. As mapped above, the negative log likelihood corresponds to the claimed quality measure, and the training data depends on trajectory positions and assigned force measurements. Accordingly, Navarro in view of Nikovski teaches iteratively determining trajectories, carrying out measurements with the iteratively determined trajectories, and training the predictive model on the quality measure depending on the trajectories and assigned measurements.).
Regarding claim 22, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. Navarro in view of Nikovski further teaches:
wherein the technical system is a computer-controlled machine, or a robot, or a vehicle, or a household appliance, or a tool, or a manufacturing machine, or a personal assistance system, or an access control system (Nikovski, [Abstract] “A system for controlling a robotic arm performing insertion of a component along an insertion line accepts measurements of force experienced by the wrist of robotic arm at current position along insertion line” – teaches a system for controlling a robotic arm. Under BRI, the robotic arm corresponds to the claim technical system being a robot.).
Regarding claim 23, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. Navarro in view of Nikovski further teaches:
wherein a respective index is assigned to the trajectories, wherein the indices of the trajectories for which the measure indicates the greater or equal uncertainty are determined (Navarro, paragraph [0092] “calculates, based on the ensemble of atmospheric forecasts, an ensemble of predicted trajectories, each calculated predicted trajectory based on a corresponding atmosphere scenario” [0159] “ the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” [0160] “the selected predicted trajectory is obtained, said measure of dispersion obtained from the FOM population that corresponds to the trajectory sample space (i.e. the given ensemble of trajectories).” – Navarro teaches that each predicted trajectory in the ensemble is associated with a corresponding atmosphere scenario or a stochastic variable combination. Under BRI, the corresponding scenario or combination identifies the respective trajectory and corresponds to the claimed index. Navarro further teaches retrieving the predicted trajectory associated with each combination and re-ordering the predicted trajectories according to a statistical criterion referred to the FOM. Thus, the system determines which identified trajectories occupy the positions in the re-ordered trajectory set, which teaches or at least renders obvious determining the indices of the trajectories for which the measure is greater or equal uncertainty.).
Regarding claim 25, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. Navarro in view of Nikovski further teaches:
wherein the measure is determined in iterations, wherein, per iteration, a portion of the measure is determined depending on a respective trajectory (Navarro, paragraph [0093] “assesses at least one figure of merit of each predicted trajectory within an ensemble of predicted trajectories, to obtain a population of values of these figures of merit” [0095] “obtains, according to a certain statistical criterion, a dispersion of the values of the at least one figure of merit assessed, associated with the remaining trajectories of the ensemble of predicted trajectories,” [0335] “Thus the randomization engine unit (4), RE, works iteratively with the underlying trajectory computation unit (5), TC, which computes one trajectory for each combination of all the stochastic variables selected by the randomization engine unit (4), RE… the randomization engine unit (4), RE, collects all “possible” predicted trajectories and performs the FOM analysis explained above (single trajectory and multiple trajectory analysis) or a similarly generalized one” – Navarro teaches iteratively computing trajectories and performing FOM analysis on the resulting predicted trajectories. Navarro further teaches assessing a FOM for each predicted trajectory to obtain a population of FOM values, and determining a dispersion from those FOM values. Under BRI, each per-trajectory FOM value corresponds to a portion of the uncertainty measure, and the dispersion determined from the population of FOM values corresponds to the measure determined from those portions. Accordingly, Navarro teaches or at least renders obvious determining the measure in iterations, where a portion of the measure is determined depending on a respective trajectory.).
Regarding claim 25, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. Navarro in view of Nikovski further teaches:
wherein a subset of trajectories is determined from the set, wherein, for each trajectory from the subset, a probability is determined that the technical system is damaged by a measurement with the trajectory or that the technical system remains undamaged in a measurement with the trajectory, wherein the subset of trajectories is either provided or used for measurement when the probability for each trajectory satisfies a condition or when the probabilities of the trajectories from the subset together satisfy a condition, and wherein the subset of trajectories is otherwise not provided or used for measurement (Navarro, paragraph [0159] “Then, a preferred FOM to be optimized is selected, and the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” [0291] “The FOM in this case is a function of multiple trajectories.” Nikovski, paragraph [0078] “A third method is to select the threshold that minimizes a weighted combination of true and false positive rates, where the weights come from economic considerations (e.g., how does the cost of a failure to detect an anomaly, possibly resulting in defective product or damage to the equipment, compares to the cost of a false positive, possibly resulting in unnecessary stoppage).” [0079] “the probabilistic relationship defines a confidence interval for non-anomalous values of the force for each position of a sequence of positions on the insertion line, wherein each of the non-anomalous values of the force for the current position has a probability above a confidence level according to the probabilistic function learned for the current position, and wherein the anomaly detector declares the current value of the force anomalous when the current value of the force is outside of the confidence interval for non-anomalous values of the force of the current position.” [0081] “ Through the interface 910 or NIC 950, the system 900 can receive values of a confidence threshold and/or anomaly detection threshold.” [0085] “ an anomaly detector 937 configured to determine the probability of the current value of the force conditioned on the current value of the position according to the probabilistic function and determine a result of anomaly detection based on the probability of the current value of the force.” – Navarro teaches determining trajectories from a set and evaluating multiple trajectories using an FOM. Under BRI, the evaluated multiple trajectories correspond to a subset of trajectories determined from the set. Nikovski teaches determining a probability of a current force value along a trajectory, comparing the force value to a confidence interval or anomaly threshold, and declaring an anomaly may result in damage to the equipment. Thus, the probability and threshold-based anomaly determination teaches or at least renders obvious determining whether measurement with the trajectory is associated with damage risk or non-anomalous operation. Since Nikovski controls the robotic arm based on the anomaly detection result, the trajectory is used when the probability satisfies the safety/anomaly condition and is otherwise not used or continued for measurement.).
Regarding claim 27, Navarro teaches the following limitations:
A device for determining trajectories from a set of trajectories for measurements on a technical system, wherein a predictive model of the technical system includes a measure of uncertainty of a prediction of the predictive model, wherein the measure depends on trajectories from the set, wherein the device is configured to: determine trajectories from the set for which a measure of uncertainly indicates a greater or equal uncertainty than a measure of uncertainty for others of the trajectories from the set (Navarro, paragraph [0068] “a processor unit, for calculating predicted trajectories for each segment of an aircraft flight utilizing a specific Aircraft Intent Description Language, each calculated predicted trajectory being calculated based on stochastic input data, therefore each calculated predicted trajectory being stochastic and having an associated probability, the input data selected from at least the following “ [0081] “an aircraft performance model including one or more parameters which define aircraft response upon external conditions;” [0092] “calculates, based on the ensemble of atmospheric forecasts, an ensemble of predicted trajectories, each calculated predicted trajectory based on a corresponding atmosphere scenario” [0093] “assesses at least one figure of merit of each predicted trajectory within an ensemble of predicted trajectories, to obtain a population of values of these figures of merit” [0095] “obtains, according to a certain statistical criterion, a dispersion of the values of the at least one figure of merit assessed, associated with the remaining trajectories of the ensemble of predicted trajectories” [0159] “a preferred FOM to be optimized is selected, and the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” [0226] “ The capability to manage uncertainty inputs and produce a stochastic trajectory prediction and its uncertainty measure in terms of FOM” [0227] “the use of customized figures of merit (FOM's) to characterize the uncertainty of TP for its exploitation in automated decision support “ – Navarro teaches an aircraft performance model that calculates an ensemble of predicted trajectories. Under the broadest reasonable interpretation, the aircraft performance model corresponds to the claimed predictive model, and the ensemble of predicted trajectories corresponds to the claimed set of trajectories. Navarro further teaches assessing a FOM for each predicted trajectory and obtaining a dispersion of the FOM values, where the FOM is used to characterize trajectory prediction uncertainty. Accordingly, the FOM-based dispersion corresponds to the claimed measure of uncertainty that depends on the trajectories from the set. Navarro also teaches re-ordering the predicted trajectories according to a statistical criterion referred to the FOM, which teaches or at least renders obvious determining trajectories having greater or equal uncertainty than other trajectories in the set.) and
However, Navarro does not teach but Navarro in view of Nikovski teaches the following limitation:
perform measurements with trajectories from the set on the technical system in an order, wherein: (i) the order in which the measurements are performed is an order in which the trajectories are determined from the set, or (ii) the order in which the measurements are performed is determined depending on the order in which the trajectories are determined from the set (Navarro, paragraph [0092] “calculates, based on the ensemble of atmospheric forecasts, an ensemble of predicted trajectories, each calculated predicted trajectory based on a corresponding atmosphere scenario “ [0159] “the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” Nikovski, paragraph [0040] “The robotic assembly 100 is configured to perform an insertion operation, e.g., insert a component 103 into a component 104, along an insertion line. As used herein, the insertion line is a trajectory of a motion of the wrist 102 defining a trajectory of the motion of the component 103…the wrist 102 has multiple degrees of freedom, so the insertion line can have a motion profile spanning in multi-dimensional space.” [0041] “The robotic assembly 100 also includes a force sensor 110 operatively connected to the wrist of the robotic arm to measure the force tensor experienced by the end-effector of the robot during a manipulation and insertion operation. For example, the force sensor can be mounted on the wrist joint of the robot. For example, the force tensor includes measurements 115 of force and moments along the axis of the robot (Fx, Fy, Fz, Mx, My, Mz) in addition to position and orientation along three axis. Because of the flexibility of the motion of the robotic arm having a wrist, the measurement space provided by the sensor is 12 dimensional or 18 dimensional when velocities along all the axis are considered.” – Navarro teaches calculating an ensemble of predicted trajectories and re-ordering the predicted trajectories according to a statistical criterion referred to the FOM> As mapped above, the re-ordered predicted trajectories corresponds to trajectories determined from the set. Nikovski teaches that a robotic assembly performs an insertion operation along an insertion line, where the insertion line is a trajectory of motion of the wrist and component. Nikovski further teaches a force sensor measures force, moments, position, and orientation during the insertion operation. Under the broadest reasonable interpretation, Nikovski’s robotic assembly corresponds to the claimed technical system, the insertion line corresponds to the claimed trajectory, and the force sensor data corresponds to the claimed measurements. Accordingly, Navarro in view of Nikovski teaches performing measurements with trajectories from the set on the technical system in order determined depending on the order in which the trajectories are determined from the set.)
Accordingly, it would have been obvious to person of ordinary skill in the art, before the effective filing date of the claimed invention, having a combination of Navarro and Nikovski before them, to incorporate the trajectory-based sensor movement techniques of Nikovski into the uncertainty-based trajectory determination system of Navarro. One would have been motivated to make such a combination in order to physically test trajectories identified as having higher uncertainty, rather than testing every possible trajectory of the technical system. This would allow the system to obtain actual measured response data for the trajectories most likely to reveal weak spots, abnormal behavior, or less reliable operating regions of the technical system. By using Navarro’s uncertainty analysis to identify which trajectories should be tested, and Nikovski’s sensor-based measurements to evaluate a technical system while performing those trajectories, the combination would reduce unnecessary testing while identifying portions of the system operation that may require correction, adjustment, or further evaluation.
Regarding claim 28, Navarro in view of Nikovski teaches all the elements of claim 27, therefore is rejected for the same reasons as those presented for claim 27. Navarro in view of Nikovski further teaches:
wherein the device comprises at least one processor, at least one memory and at least one interface, wherein the at least one processor configured to perform the determination and perform the measurements, wherein the at least one memory is configured to store the set of trajectories, and/or the predictive model, and/or the trajectories determined from the set, and wherein the interface is configured, for performing and/or for recording the measurements on the technical system, to communicate with a test bench for the technical system (Navarro, paragraph [0067] “wherein the system comprises: [0068] a. a processor unit, for calculating predicted trajectories” [0072] “ c. a robust Decision Support Tool unit, being configured for: [0073] providing the processor unit for calculating predicted trajectories with input data necessary for predicting trajectories, and; [0074] selecting a predicted trajectory from among the predicted trajectories calculated by the processor unit” [0162] “ the system providing for the necessary equipment to carry out the described method.” Nikovski, paragraph [0044] “ the system 105 includes an input interface 120 configured to accept measurements of a force sensor operatively connected to the wrist of the robotic arm.” [0045] “The system 105 also includes a memory 130 configured to store a probabilistic relationship” [0080] “Through the network 990, either wirelessly or through the wires, the system 900 can receive the measurements 995 of the force and positions of the robotic assembly.“ [0082] “The system 900 includes a processor 920 configured to execute stored instructions, as well as a memory 940 that stores instructions that are executable by the processor.”).
Regarding claim 29, Navarro teaches the following limitations:
determining trajectories from the set for which a measure of uncertainly indicates a greater or equal uncertainty than a measure of uncertainty for others of the trajectories from the set (Navarro, paragraph [0068] “a processor unit, for calculating predicted trajectories for each segment of an aircraft flight utilizing a specific Aircraft Intent Description Language, each calculated predicted trajectory being calculated based on stochastic input data, therefore each calculated predicted trajectory being stochastic and having an associated probability, the input data selected from at least the following “ [0081] “an aircraft performance model including one or more parameters which define aircraft response upon external conditions;” [0092] “calculates, based on the ensemble of atmospheric forecasts, an ensemble of predicted trajectories, each calculated predicted trajectory based on a corresponding atmosphere scenario” [0093] “assesses at least one figure of merit of each predicted trajectory within an ensemble of predicted trajectories, to obtain a population of values of these figures of merit” [0095] “obtains, according to a certain statistical criterion, a dispersion of the values of the at least one figure of merit assessed, associated with the remaining trajectories of the ensemble of predicted trajectories” [0159] “a preferred FOM to be optimized is selected, and the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” [0226] “ The capability to manage uncertainty inputs and produce a stochastic trajectory prediction and its uncertainty measure in terms of FOM” [0227] “the use of customized figures of merit (FOM's) to characterize the uncertainty of TP for its exploitation in automated decision support “ – Navarro teaches an aircraft performance model that calculates an ensemble of predicted trajectories. Under the broadest reasonable interpretation, the aircraft performance model corresponds to the claimed predictive model, and the ensemble of predicted trajectories corresponds to the claimed set of trajectories. Navarro further teaches assessing a FOM for each predicted trajectory and obtaining a dispersion of the FOM values, where the FOM is used to characterize trajectory prediction uncertainty. Accordingly, the FOM-based dispersion corresponds to the claimed measure of uncertainty that depends on the trajectories from the set. Navarro also teaches re-ordering the predicted trajectories according to a statistical criterion referred to the FOM, which teaches or at least renders obvious determining trajectories having greater or equal uncertainty than other trajectories in the set.) and
However, Navarro does not teach but Navarro in view of Nikovski teaches the following limitation:
A non-transitory computer-readable medium on which is stored a computer program including computer-readable instructions for determining trajectories from a set of trajectories for measurements on a technical system, wherein a predictive model of the technical system includes a measure of uncertainty of a prediction of the predictive model, wherein the measure depends on trajectories from the set, the instructions, when executed by a computer, causing the computer to perform the following steps (Nikovski, paragraph [0082] “he system 900 includes a processor 920 configured to execute stored instructions, as well as a memory 940 that stores instructions that are executable by the processor. The processor 920 can be a single core processor, a multi-core processor, a computing cluster, or any number of other configurations. The memory 940 can include random access memory (RAM), read only memory (ROM), flash memory, or any other suitable memory systems. The processor 920 is connected through the bus 906 to one or more input and output devices. These instructions implement a method for controlling a robotic arm.”)
performing measurements with trajectories from the set on the technical system in an order, wherein: (i) the order in which the measurements are performed is an order in which the trajectories are determined from the set, or (ii) the order in which the measurements are performed is determined depending on the order in which the trajectories are determined from the set (Navarro, paragraph [0092] “calculates, based on the ensemble of atmospheric forecasts, an ensemble of predicted trajectories, each calculated predicted trajectory based on a corresponding atmosphere scenario “ [0159] “the predicted trajectories are re-ordered in terms of a certain statistical criterion referred to that FOM.” Nikovski, paragraph [0040] “The robotic assembly 100 is configured to perform an insertion operation, e.g., insert a component 103 into a component 104, along an insertion line. As used herein, the insertion line is a trajectory of a motion of the wrist 102 defining a trajectory of the motion of the component 103…the wrist 102 has multiple degrees of freedom, so the insertion line can have a motion profile spanning in multi-dimensional space.” [0041] “The robotic assembly 100 also includes a force sensor 110 operatively connected to the wrist of the robotic arm to measure the force tensor experienced by the end-effector of the robot during a manipulation and insertion operation. For example, the force sensor can be mounted on the wrist joint of the robot. For example, the force tensor includes measurements 115 of force and moments along the axis of the robot (Fx, Fy, Fz, Mx, My, Mz) in addition to position and orientation along three axis. Because of the flexibility of the motion of the robotic arm having a wrist, the measurement space provided by the sensor is 12 dimensional or 18 dimensional when velocities along all the axis are considered.” – Navarro teaches calculating an ensemble of predicted trajectories and re-ordering the predicted trajectories according to a statistical criterion referred to the FOM> As mapped above, the re-ordered predicted trajectories corresponds to trajectories determined from the set. Nikovski teaches that a robotic assembly performs an insertion operation along an insertion line, where the insertion line is a trajectory of motion of the wrist and component. Nikovski further teaches a force sensor measures force, moments, position, and orientation during the insertion operation. Under the broadest reasonable interpretation, Nikovski’s robotic assembly corresponds to the claimed technical system, the insertion line corresponds to the claimed trajectory, and the force sensor data corresponds to the claimed measurements. Accordingly, Navarro in view of Nikovski teaches performing measurements with trajectories from the set on the technical system in order determined depending on the order in which the trajectories are determined from the set.)
Accordingly, it would have been obvious to person of ordinary skill in the art, before the effective filing date of the claimed invention, having a combination of Navarro and Nikovski before them, to incorporate the trajectory-based sensor movement techniques of Nikovski into the uncertainty-based trajectory determination system of Navarro. One would have been motivated to make such a combination in order to physically test trajectories identified as having higher uncertainty, rather than testing every possible trajectory of the technical system. This would allow the system to obtain actual measured response data for the trajectories most likely to reveal weak spots, abnormal behavior, or less reliable operating regions of the technical system. By using Navarro’s uncertainty analysis to identify which trajectories should be tested, and Nikovski’s sensor-based measurements to evaluate a technical system while performing those trajectories, the combination would reduce unnecessary testing while identifying portions of the system operation that may require correction, adjustment, or further evaluation.
Claims 18 and 24 are rejected under the 35 U.S.C. 103 as being unpatentable over Navarro et al., (Pub. No.: US 20160343258 A1 (Filed: 2014)) in view of Nikovski et al., (Pub. No.: US 20200230815 A1 (Filed: 2019)) further in view of Kallenberger et al., (Pub. No.: US 20220406434 A1 (Filed: 2020)).
Regarding claim 18, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. Navarro in view of Nikovski does not teach, but Navarro in view of Nikovski further in view of Kallenberger teaches:
wherein the measure includes a determinant of a covariance that depends on trajectories from the set (Kallenberger, paragraph [0063] “The updated stimulus trajectory determines a sequence of updated experimental stimuli. The updated stimulus trajectory may be determined such that a covariance of the one or more model parameters as a function of the stimulus trajectory is minimised. Thereby, confidence intervals of the one or more model parameters can be minimized to reduce an uncertainty of estimated values thereof.” [0066] “the process of determining a further updated stimulus trajectory and refitting the model parameters may be repeated until the trace or the determinant of a covariance matrix of the model parameters does not vary between subsequent refittings by more than a predefined threshold.” [0194] “ the covariance matrix of the model parameters can be defined as an expected value C.sub.θ=E ({circumflex over (θ)}−θ)({circumflex over (θ)}−θ).sup.T).” [0195] “Thus, the processing module can be configured to determine the updated stimulus trajectory such that the covariance of the one or more model parameters as a function of the stimulus trajectory, i.e. the trace or the determinant of C.sub.θ or of F.sup.−1 be minimised to obtain more accurate estimates of model parameters.” – Kallenberger teaches determining a trajectory such that a covariance of model parameters is minimized as a function of the trajectory. Kallenberger further teaches using the determinant of a covariance matrix to reduce uncertainty and obtain more accurate model parameter estimates. Under BRI, Kallenberger’s determinant of a covariance matrix corresponds to the claimed determinant of a covariance, and the covariance dependents on trajectories since the covariance is determined as a function of the stimulus trajectory. Accordingly, Navarro in view of Nikovski further in view of Kallenberger teaches wherein the measure includes a determinant of a covariance that depends on trajectories from the set.).
Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, having a combination of Navarro, Nikovski, and Kallenberger before them, to use a determinant of a covariance as the uncertainty measure in the uncertainty-based trajectory determination system of Navarro and Nikovski, as taught by Kallenberger. One would have been motivated to make such a combination in order to optimize experimental conditions and obtain higher model accuracy in a more efficient manner by minimizing a covariance value, including a determinant or trace of a covariance matrix. Applying Kallenberger’s determinant of covariance criterion to the trajectory based measurement system of Navarro and Nikovski would allow the system to identify more informative trajectories for testing and reducing uncertainty in the technical system evaluation (Kallenberger, paragraph [0067]).
Regarding claim 24, Navarro in view of Nikovski teaches all the elements of claim 16, therefore is rejected for the same reasons as those presented for claim 16. However, Navarro in view of Nikovski does not teach but Navarro in view of Nikovski further in view of Kallenberger further teaches:
wherein a number of trajectories are selected from the set, wherein the measure is determined for the number of trajectories (Navarro, paragraph [0275] “Given W, a corresponding ensemble T of possible predicted trajectories T.sub.i can be obtained, each one computed based on the corresponding atmosphere scenario W.sub.i” [0290] “ In other applications, the DST is interested in an aggregate figure of merit of a set of trajectories “S”, which are evaluated simultaneously” [0291] “The FOM in this case is a function of multiple trajectories.” Kallenberger, paragraph [0063] “The updated stimulus trajectory may be determined such that a covariance of the one or more model parameters as a function of the stimulus trajectory is minimised.” [0066] “In the event of having more than one model parameter, the process of determining a further updated stimulus trajectory and refitting the model parameters may be repeated until the trace or the determinant of a covariance matrix of the model parameters does not vary between subsequent refittings by more than a predefined threshold.” [0195] “Thus, the processing module can be configured to determine the updated stimulus trajectory such that the covariance of the one or more model parameters as a function of the stimulus trajectory, i.e. the trace or the determinant of C.sub.θ or of F.sup.−1 be minimised to obtain more accurate estimates of model parameters.” – Navarro teaches an ensemble of possible predicted trajectories and further teaches an aggregate FOM for a set of trajectories evaluated simultaneously, where the FOM is a function of multiple trajectories. Under BRI, Navarro’s set of trajectories evaluated simultaneously corresponds to a number of trajectories selected from a trajectory set, and the aggregate FOM corresponds to a measure determined for that number of trajectories. Kallenberger teaches determining a covariance as a function of a trajectory and using the trace or determinant of the covariance in the trajectory optimization. This is consistent with the Applicant’s specification (paragraphs [0039], [0044]-[0046] and [0056]) , which describes the claimed measure as a determinant of covariance depending on the selected trajectories. Accordingly, Navarro in view of Kallenberger teaches or at least renders obvious selecting a number of trajectories from the set and determining the measure for the number of trajectories.).
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant’s disclosure because it relates to trajectory prediction, Gaussian process motion models, uncertainty-based trajectory selection, and probabilistic safety constraints for executing selected trajectories on technical systems:
1. Aoude, G.S., Luders, B.D., Joseph, J.M. et al. Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns. Auton Robot 35, 51–76 (2013). https://doi.org/10.1007/s10514-013-9334-3
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Daravanh Phakousonh whose telephone number is (571)272-6324. The examiner can normally be reached Mon - Thurs 7 AM - 5 PM, Every other Friday 7 AM - 4PM.
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, Li B Zhen can be reached at 571-272-3768. 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.
/Daravanh Phakousonh/Examiner, Art Unit 2121
/Li B. Zhen/Supervisory Patent Examiner, Art Unit 2121
Prosecution Insights