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 .
Status of Claims
This Office Action is in response to the application filed on 5/15/2024. Claims 1-20 are presently pending and are presented for examination.
Claim Objections
Claim 10 objected to because of the following informalities. Appropriate correction is required.
Claim 10 recites such that a first sample event count of the first sample events is in a same order as a second sample event count of the second sample events. The meaning of in a same order is unclear. Examiner will interpret the limitation as such that a first sample event count of the first sample events has the same order of magnitude as a second sample event count of the second sample events.
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.
Claim(s) 9-13 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Independent claim 1 is directed toward a method, independent claim 9 is directed to a method, and independent claim 14 is directed to a machine Therefore, each of the independent claim(s) 1, 9, and 14 along with the corresponding dependent claims 2-8, 10-13, and 15-20 are directed to a statutory category of invention under Step 1.
Under Step 2A, Prong 1, the claims are analyzed to determine whether one or more of the claims recites subject matter that falls within one of the following groups of abstract ideas: (1) mental processes, (2) certain methods of organizing human activity, and/or (3) mathematical concepts. In this case, the independent claim(s) 9 is/are directed to an abstract idea without significantly more. Specifically, the claim(s), under its/their broadest reasonable interpretation(s) cover(s) certain mental processes. The language of independent claim 9 is used for illustration:
A method for training an uncertainty model, the method comprising:
obtaining sample driving event data relating to sample events, each of the sample events belonging to one of a plurality of driving scenarios; and
generating the uncertainty model by machine learning using the sample driving event data based on a multivariate probability prediction algorithm, wherein the uncertainty model is configured to predict uncertainty information that relates to a deviation of an operation of a vehicle according to an intended control instruction from an intended operation of the vehicle according to planning information, the intended control instruction being determined based on the planning information (A human could mentally estimate the likelihood that a given control operation, i.e. use of the steering, acceleration, and braking of a vehicle, would deviate from their intended operation of the vehicle. This is a mental process.).
As explained above, independent claim 9 recites at least one abstract idea a under Step 2A, Prong 1.
Under Step 2A, Prong 2, the claims are analyzed to determine whether the claim, as a whole, integrates the abstract idea into a practical application. As noted in the 2019 PEG, it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements such as merely using a computer to implement an abstract idea, adding insignificant extra-solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a "practical application"; see at least MPEP 2106.04(d).
In this case, the mental processes are not integrated into a practical application. For example, independent claim 9recites additional elements. These/this limitation(s) amount to implementing the abstract idea on a computer, add insignificant extra-solution activity, and/or generally link use of the judicial exception to a particular technological environment or field of use; see at least MPEP 2106.04(d). More specifically,
obtaining sample driving event data… found in independent claim(s) 9. This limitation amounts to insignificant extra-solution activity.
generating the uncertainty model by machine learning… found in independent claim(s) 9. This limitation amounts to generally linking the use of the abstract idea to a particular technological environment or field of use.
Therefore, taken alone, the additional elements do not integrate the abstract idea into a practical application. Furthermore, looking at the additional limitation(s) as an ordered combination or as a whole, the limitations add nothing significant that is not already present when looking at the elements taken individually. Because the additional elements do not integrate the abstract idea into a practical application by imposing meaningful limits on practicing the abstract idea, independent claim(s) 9 is/are directed to an abstract idea.
Under Step 2B, the claims do not include any additional elements 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 in Step 2A, Prong Two, the additional element of limiting the use of the idea to one particular environment employs generic computer functions to execute an abstract idea and, therefore, does not add significantly more. Mere limiting the use of the abstract idea to a particular environment or field of use cannot provide an inventive concept. Additionally, as discussed above, the limitation(s) of obtaining sample driving event data…, as recited above, is/are considered insignificant extra-solution activity.
A conclusion that an additional element is insignificant extra-solution activity in Step 2A must be re-evaluated in Step 2B to determine if the element is more than what is well-understood, routine, and conventional in the field. The following element(s) has/have been deemed insignificant extra-solution activity by one or more courts; see at least MPEP 2106.05(d) and MPEP 2106.05(g):
obtaining sample driving event data… is considered well-understood, routine, and conventional activity under CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011) (Mere data gathering).
Because the claims fail to recite anything sufficient to amount to significantly more than the judicial exception, independent claim(s) 9 is/are patent ineligible under 35 U.S.C. 101.
Dependent claims 10-13 have been given the full two-part analysis, including analyzing the additional limitations, both individually and in combination. Dependent claims 10-13, when analyzed both individually and in combination, are also patent ineligible under 35 U.S.C. 101 based on the same analysis as above. The additional limitations recited in the dependent claims fail to establish that the dependent claims are not directed to an abstract idea. The additional limitations of the dependent claims, when considered individually and as an ordered combination, do not amount to significantly more than the abstract idea. Accordingly, claims 10-13 are patent ineligible under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
Claims 1-7 and 14-20 are rejected under 35 U.S.C. 103 as being obvious over US 9568915 B1, hereinafter “Berntorp”, in view of US 20210383040 A1, hereinafter “Cho”.
Regarding claim 1, Berntorp discloses A method for operating a vehicle (See Abstract, the method controls the operation of the vehicle.), comprising:
obtaining planning information relating to an intended operation of the vehicle over a prediction horizon (See column 6 paragraph 5, the system attempts to bound deviation from a desired velocity profile. The velocity profile is planning information.);
inputting the planning information into an uncertainty model to determine uncertainty information (See column 6 paragraph 5, the system attempts to probabilistically bound deviation from a desired velocity profile, i.e. determine which future motion plan has the highest probability of satisfying the various constraints, including deviation from the velocity profile. This means there is uncertainty information associated with the variables that motion planning system attempts to constrain, which necessarily comes from an uncertainty model. This means the velocity profile is inputted into an uncertainty model), wherein:
the uncertainty model is data based on a multivariate probability prediction algorithm (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted.); and
the uncertainty model is configured to predict the uncertainty information that relates to a deviation of an operation of the vehicle according to an intended control instruction from the intended operation, the intended control instruction being determined based on the planning information (See column 4 paragraph 8-9 and Fig. 1A, the model predicts uncertainty relating to position of the vehicle in the future corresponding to the given control input, i.e. intended control instruction and operation. The proposed vehicle controls are also planning information.);
generating a control instruction based on the planning information and the uncertainty information (See column 6 paragraph 5, the system attempts to probabilistically bound deviation from a desired velocity profile, i.e. determine which future motion plan has the highest probability of satisfying the various constraints. This is the generated control instruction based on planning and uncertainty information. The system determines the vehicle motion. See Fig. 7 and column 4 paragraph 3, the motion planning system is used to control the vehicle.) ; and
operating the vehicle based on the control instruction (See Fig. 7 and column 4 paragraph 3, the control instruction determined by the motion planning system is used to control the vehicle).
Berntorp does not explicitly disclose the uncertainty model is trained using sample driving event data.
Cho, in the same field of endeavor, renders obvious the uncertainty model is trained using sample driving event data (See [0021], the tire friction coefficient model is trained using training data, i.e. raw data. See [0091], the raw data can correspond to data gathered in a period where the vehicle is driving, i.e. the raw data is sample driving event data.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for generating vehicle control instructions under uncertainty disclosed by Berntorp to include using driving event training data of Cho. One of ordinary skill in the art would have been motivated to make this modification to accurately estimate the friction coefficient of the brake material and therefore the vehicle’s deceleration in real time, as suggested by Cho at [0020].
Regarding claim 2, Berntorp combined with Cho renders obvious the limitations of claim 1. Berntorp discloses the planning information and the intended operation relate to a plurality of operation parameters of the vehicle (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted. Proposed future inputs are planning information and intended operation relating to a plurality of operation parameters.), and
the uncertainty information comprises multiple deviation components each of which relates to one of the plurality of operation parameters (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted. These are deviation components of the uncertainty information).
Regarding claim 3, Berntorp combined with Cho renders obvious the limitations of claim 2. Berntorp renders obvious the plurality of operation parameters comprise at least one of velocity, position, or acceleration of the vehicle (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle. These are operation parameters that define velocity, acceleration, and position of the vehicle.).
Regarding claim 4, Berntorp combined with Cho renders obvious the limitations of claim 2. Berntorp renders obvious the uncertainty model comprises a plurality of component uncertainty predictors each of which is configured to predict a deviation component of the uncertainty information for one of the plurality of operation parameters (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted. Uncertainties are inherently determined by an uncertainty predictor. The probability of moving the vehicle into a good state are associated with each sampled control input, i.e. deviation components are predicted for each of the operating parameters.).
Regarding claim 5, Berntorp combined with Cho renders obvious the limitations of claim 1. Berntorp renders obvious inputting a target confidence level into the uncertainty model to determine the uncertainty information, wherein the target confidence level indicates a probability that the deviation of the operation of the vehicle from the intended operation falls within the uncertainty information (See column 5 paragraph 2-3, a threshold that can be fixed or is dependent on the vehicle environment is used in determining that the given control input moves the vehicle into a good state. This corresponds to a target confidence level used, i.e. inputted into, the uncertainty model and corresponding to probability of the deviation of the vehicle from the intended operation.).
Regarding claim 6, Berntorp combined with Cho renders obvious the limitations of claim 1. Berntorp renders obvious inputting context information into the uncertainty model to determine the uncertainty information, wherein the context information comprises at least one of a prior operation of the vehicle at a time point that precedes the prediction horizon, environmental information of an environment where the intended operation is to occur, or a known condition of the vehicle (See column 9 paragraph 2, the vehicle state evolves according to a nonlinear function, i.e. uncertainty model. The predicted future state is a function of the current state. The inputs to the function include conditions of the vehicle such as mass, location, velocity, heading, and orientation. Location, velocity, heading, and orientation are also context information that represent prior operation of the vehicle preceding the prediction horizon, i.e. the predicted future state.).
Regarding claim 7, Berntorp combined with Cho renders obvious the limitations of claim 1. Berntorp renders obvious uncertainty information relates to at least one of a mechanical capacity of the vehicle, an irregularity in the vehicle or a portion thereof, a difference between the intended operation and a prior operation of the vehicle at a time point that precedes the prediction horizon, a magnitude or rate of change of the operation during the intended operation or a portion thereof, an environment where the intended operation is to occur, or an irregularity of the planning information (See column 9 paragraph 2, the vehicle state evolves according to a nonlinear function, i.e. uncertainty model. The predicted future state is a function of the current state. The function outputs a predicted future state that includes a velocity vector. Predicted velocity is the rate of change of the vehicle’s position at the predicted future state during a portion of the intended operation.).
Regarding claim 14, Berntorp discloses A system for operating a vehicle (See Abstract, the system controls the operation of the vehicle), comprising:
a mission planner configured to provide planning information of the vehicle over a prediction horizon (See column 6 paragraph 5, the system attempts to bound deviation from a desired velocity profile. The velocity profile is planning information. The subsystem responsible for the production of the planned velocity profile is a mission planner because it relates to future operation of the vehicle. Desired future operations terminate, i.e. have a prediction horizon because computer memory is finite.);
a model predictive control (MPC) controller coupled to the mission planner (See column 6 paragraph 5, the system attempts to probabilistically bound deviation from a desired velocity profile, i.e. determine which future motion plan has the highest probability of satisfying the various constraints, including deviation from the velocity profile. This is model predictive control and the corresponding subsystem is therefore a model predictive control controller. This subsystem is necessarily coupled to the subsystem producing the desired future operation profile of the vehicle, i.e. the mission planner, because the future operation profile is used in the calculations.)
and configured to perform steps including:
obtaining, from the mission planner, the planning information relating to an intended operation of the vehicle over the prediction horizon (See column 6 paragraph 5, the system attempts to bound deviation from a desired velocity profile. The velocity profile is planning information. Desired future operations terminate, i.e. have a prediction horizon because computer memory is finite.);
inputting the planning information into an uncertainty model to determine uncertainty information (See column 6 paragraph 5, the system attempts to probabilistically bound deviation from a desired velocity profile, i.e. determine which future motion plan has the highest probability of satisfying the various constraints, including deviation from the velocity profile. This means there is uncertainty information associated with the variables that motion planning system attempts to constrain, which necessarily comes from an uncertainty model. This means the velocity profile is inputted into an uncertainty model.), wherein:
the uncertainty model is based on a multivariate probability prediction algorithm (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted.); and
the uncertainty model is configured to predict the uncertainty information that relates to a deviation of an operation of the vehicle according to an intended control instruction from the intended operation, the intended control instruction being determined based on the planning information (See column 4 paragraph 8-9 and Fig. 1A, the model predicts uncertainty relating to position of the vehicle in the future corresponding to the given control input, i.e. intended control instruction and operation. The proposed vehicle controls are also planning information.); and
generating a control instruction based on the planning information and the uncertainty information (See column 6 paragraph 5, the system attempts to probabilistically bound deviation from a desired velocity profile, i.e. determine which future motion plan has the highest probability of satisfying the various constraints. This is the generated control instruction based on planning and uncertainty information. The system determines the vehicle motion. See Fig. 7 and column 4 paragraph 3, the motion planning system is used to control the vehicle.); and
a vehicle control interface coupled to the MPC controller to obtain the control instruction and configured to cause the vehicle to operate based on the control instruction (See Fig. 7 and column 4 paragraph 3, the control instruction determined by the motion planning system is used to control the vehicle. The control instruction determined by the optimization procedure is necessarily provided to the vehicle control subsystem for use, i.e. the subsystems are coupled by means of an interface.).
Berntorp does not explicitly disclose the uncertainty model is trained using sample driving event data.
Cho, in the same field of endeavor, renders obvious the uncertainty model is trained using sample driving event data (See [0021], the tire friction coefficient model is trained using training data, i.e. raw data. See [0091], the raw data can correspond to data gathered in a period where the vehicle is driving, i.e. the raw data is sample driving event data.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for generating vehicle control instructions under uncertainty disclosed by Berntorp to include using driving event training data of Cho. One of ordinary skill in the art would have been motivated to make this modification to accurately estimate the friction coefficient of the brake material and therefore the vehicle’s deceleration in real time, as suggested by Cho at [0020].
Regarding claim 15, Berntorp combined with Cho renders obvious the limitations of claim 14. Berntorp renders obvious wherein the prediction horizon is at least 2 seconds (See Fig. 5B and column 10 paragraph 4, the motion planner computes a complex motion plan corresponding to passing a moving obstacle and traveling over a significant distance of road. The preponderance of evidence indicates that this takes at least 2 seconds in typical, legal driving conditions. See further Fig. 8 and column 16 paragraph 2-3, the system extends its prediction horizon by using intermediary points of the distance to the desired target point is too long. It would therefore be obvious to use a prediction horizon of at least two seconds.).
Regarding claim 16, Berntorp combined with Cho renders obvious the limitations of claim 14. Berntorp renders obvious wherein the MPC controller is configured to complete the determination of the uncertainty information and the generation of the control instruction with respect to the prediction horizon within less than 1 second (See Abstract, the system is used to control the operation of the vehicle. Examiner asserts that this cannot occur if the control determination process, which comprises the MPC controller’s functions, takes more than 1 second.).
Regarding claim 17, Berntorp combined with Cho renders obvious the limitations of claim 14. Berntorp renders obvious perception module configured to acquire environmental information of an environment, wherein the mission planner is configured to generate the planning information based on the environmental information (See column 2 paragraph 3, the desired state of the vehicle determines the planning information, i.e. control inputs and the corresponding vehicle motion. The characteristics of the desired state and therefore the corresponding planning information can dependent on characteristics of the environment, i.e. environmental information. This means that the environmental information is necessarily obtained. The corresponding subsystem is a perception module.).
Regarding claim 18, Berntorp combined with Cho renders obvious the limitations of claim 17. Berntorp renders obvious wherein the MPC controller is further configured to input the environmental information into the uncertainty model to determine the uncertainty information (See column 4 paragraph 9, the motion model, which is used in determining the vehicle controls, accounts for uncertainty in the sensing of the environment. Uncertainty in the sensing of the environment necessarily comes from an uncertainty model.).
Regarding claim 19, Berntorp combined with Cho renders obvious the limitations of claim 14. Berntorp renders obvious the MPC controller is further configured to input context information into the uncertainty model to determine the uncertainty information, the context information relates to a state of the vehicle during the operation of the vehicle (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted. Uncertainty information necessarily comes from an uncertainty model.).
Regarding claim 20, Berntorp combined with Cho renders obvious the limitations of claim 14. Berntorp renders obvious the planning information and the intended operation relate to a plurality of operation parameters of the vehicle (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted. Proposed future inputs are planning information and intended operation relating to a plurality of operation parameters.); and
the uncertainty model comprises a plurality of component uncertainty predictors each of which is configured to predict a deviation component of the uncertainty information for one of the plurality of operation parameters (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted. These are deviation components of the uncertainty information.).
Claim 8 is rejected under 35 U.S.C. 103 as being obvious over Berntorp and Cho in view of NPL document “Extrapolating from neural network models: a cautionary tale”, hereinafter “Pastore”.
Regarding claim 8, Berntorp combined with Cho renders obvious the limitations of claim 1. Berntorp combined with Cho does not explicitly disclose the sample driving event data relates to sample events, each of the sample events belonging to one of a plurality of driving scenarios, and the plurality of driving scenarios comprise at least one of light braking whose braking pressure is below a first brake pressure threshold, hard braking whose braking pressure is above a second brake pressure threshold, on-ramp acceleration, passing, cruising at a constant speed, front vehicle cut-in, or a turning whose angular velocity exceeds an angular velocity threshold.
Pastore renders obvious the sample driving event data relates to sample events, each of the sample events belonging to one of a plurality of driving scenarios, and the plurality of driving scenarios comprise at least one of light braking whose braking pressure is below a first brake pressure threshold, hard braking whose braking pressure is above a second brake pressure threshold, on-ramp acceleration, passing, cruising at a constant speed, front vehicle cut-in, or a turning whose angular velocity exceeds an angular velocity threshold (Section IV. Error Estimate, the authors train a neural network and use different uncertainty quantification techniques (epoch averaging, bootstrap, and dropout) to produce a corresponding uncertainty model. See Section 2A. Fitting a parabola, the authors train a neural network to represent a simple parabola function. Prediction accuracy of the network deteriorates when the network is used to extrapolate outside the range of the training data. It would be obvious to include braking data inside all ranges of operation, i.e. including both light and hard braking, to avoid unnecessary extrapolation error.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for generating vehicle control instructions under uncertainty, including modeling of braking forces using a trained model from sample road events, as disclosed by Berntorp and Cho to include braking data in all ranges of operation, including, at least one of hard or light braking events, as suggested by Pastore. One of ordinary skill in the art would have been motivated to make this modification to avoid extrapolation error in the trained model, as suggested by Pastore at Section 2A. Fitting a parabola.
Claim 9 is rejected under 35 U.S.C. 103 as being obvious over Cho in view of Berntorp.
Regarding claim 9, Cho discloses A method for training a model (See Abstract, a model generation device generates, i.e. trains a friction coefficient model for a vehicle.), the method comprising:
obtaining sample driving event data relating to sample events, each of the sample events belonging to one of a plurality of driving scenarios (See [0021], the tire friction coefficient model is trained using training data, i.e. raw data. See [0091], the raw data can correspond to data gathered in a period where the vehicle is driving, i.e. the raw data is sample driving event data. See [0091], the raw data is partitioned into two driving scenarios, specifically below and above 1km/hr. All driving data belongs to one of these scenarios.); and
generating the model by machine learning using the sample driving event data based on a multivariate prediction algorithm (See Abstract, the raw data is used to determine the friction coefficient model. See Fig. 9 and [0032], multiple variables, including hydraulic pressure and disc temperature, are used by the model, i.e. it is multivariate.).
Cho does not explicitly disclose an uncertainty model, a probability multivariate prediction algorithm or wherein the uncertainty model is configured to predict uncertainty information that relates to a deviation of an operation of a vehicle according to an intended control instruction from an intended operation of the vehicle according to planning information, the intended control instruction being determined based on the planning information.
Berntorp discloses an uncertainty model (See column 6 paragraph 5, the system attempts to probabilistically bound deviation from a desired velocity profile, i.e. determine which future motion plan has the highest probability of satisfying the various constraints, including deviation from the velocity profile. This is an uncertainty model.);
a probability multivariate prediction algorithm (See column 7 paragraph 4, the control inputs can comprise steering, brake, and throttle, i.e. multiple inputs. These are multiple variables. See Fig. 1E and column 5 paragraph 6-7, the probabilities, i.e. uncertainties, of each control input are determined, i.e. predicted.); and
wherein the uncertainty model is configured to predict uncertainty information that relates to a deviation of an operation of a vehicle according to an intended control instruction from an intended operation of the vehicle according to planning information, the intended control instruction being determined based on the planning information (See column 6 paragraph 5, the system attempts to bound deviation from a desired velocity profile. The velocity profile is planning information. See column 4 paragraph 8-9 and Fig. 1A, the model predicts uncertainty relating to position of the vehicle in the future corresponding to the given control input, i.e. intended control instruction and operation. The proposed vehicle controls are also planning information.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for training a tire friction model, as disclosed by Cho to include incorporating the friction model into a system based on predicting deviation of the vehicle from its intended operation and uncertainties of Berntorp. One of ordinary skill in the art would have been motivated to make this modification in order to allow more effective real-time control of a vehicle, incorporating the teachings of Cho specifically as a way of more accurately determining the response of the vehicle control inputs for braking, as suggested by Berntorp at column 2 paragraph 5.
Claims 10-11 are rejected under 35 U.S.C. 103 as being obvious over Berntorp and Cho in view of NPL document “Sample allocation balancing overall representativeness and stratum precision”, hereinafter “Diaz-Quijano”.
Regarding claim 10, Cho combined with Berntorp renders obvious the limitations of claim 10. Cho discloses sample driving event data comprises first training data sets of first sample events belonging to a first driving scenario and second training data sets of second sample events belong to a second driving scenario (See [0091], the raw data is partitioned into two driving scenarios, specifically below and above 1km/hr. These are first and second driving scenarios.).
Cho does not explicitly disclose the sample driving event data are balanced such that a first sample event count of the first sample events is in a same order as a second sample event count of the second sample events.
Diaz-Quijano renders obvious the sample driving event data are balanced such that a first sample event count of the first sample events is in a same order as a second sample event count of the second sample events (See page 570 column 2,
e
h
refers to sampling error. See page 572 column 2 paragraph 1, equal sampling, which corresponds to data from events being balanced, produces the lowest variation in sampling error. See page 571 column 1 paragraph 5, low variation of the sampling error indicates that the model produces high precision predictions in all models strata, corresponding to the different driving scenarios. Equal numbers of data have the same order of magnitude.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for generating vehicle control instructions under uncertainty, including modeling of braking forces using a trained model from sample road events, as disclosed by Berntorp and Cho to include equal quantities of data in each scenario, as suggested by Diaz-Quijano. One of ordinary skill in the art would have been motivated to make this modification ensure that the model is precise in all driving scenarios, as suggested by Diaz-Quijano at page 571 column 1 paragraph 5 and page 572 column 2 paragraph 1.
Regarding claim 11, Cho combined with Berntorp and Diaz-Quijano renders obvious the limitations of claim 10. Cho discloses obtaining the sample driving event data comprises: retrieving candidate sample driving event data of candidate sample events (See [0021], the tire friction coefficient model is trained using training data, i.e. raw data. See [0091], the raw data can correspond to data gathered in a period where the vehicle is driving, i.e. the raw data is sample driving event data. The data must be retrieved, i.e. from storage, before it can be used in training.);
identifying at least a portion of the candidate sample events as belonging to one of the plurality of driving scenarios based on respective candidate sample driving event data of each of the candidate sample events (See [0091], the raw data is partitioned into two driving scenarios, specifically below and above 1km/hr. These are first and second driving scenarios).
Cho does not explicitly disclose compiling the sample driving event data based on a sample event count of candidate sample events in each of the plurality of driving scenarios such that the sample driving event data are balanced.
Diaz-Quijano renders obvious compiling the sample driving event data based on a sample event count of candidate sample events in each of the plurality of driving scenarios such that the sample driving event data are balanced (See page 570 column 2,
e
h
refers to sampling error. See page 572 column 2 paragraph 1, equal sampling, which corresponds to data from events being balanced, produces the lowest variation in sampling error. See page 571 column 1 paragraph 5, low variation of the sampling error indicates that the model produces high precision predictions in all models strata, corresponding to the different driving scenarios. Equal numbers of data have the same order of magnitude. Using subsets of the data instead of gathering exactly the same amount is obvious and requires use of a count to determine equality.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for generating vehicle control instructions under uncertainty, including modeling of braking forces using a trained model from sample road events, as disclosed by Berntorp and Cho to include equal quantities of data in each scenario, as suggested by Diaz-Quijano. One of ordinary skill in the art would have been motivated to make this modification ensure that the model is precise in all driving scenarios, as suggested by Diaz-Quijano at page 571 column 1 paragraph 5 and page 572 column 2 paragraph 1.
Claims 12-13 are rejected under 35 U.S.C. 103 as being obvious over Cho, Berntorp, and Diaz-Quijano in view of Pastore.
Regarding claim 12, Cho combined with Berntorp and Diaz-Quijano renders obvious the limitations of claim 10. Cho combined with Berntorp and Diaz-Quijano does not explicitly disclose the plurality of driving scenarios comprises at least one of light braking whose braking pressure is below a first brake pressure threshold, hard braking whose braking pressure is above a second brake pressure threshold, on-ramp acceleration, passing, cruising at a constant speed whose acceleration is below an acceleration threshold, front vehicle cut-in, or a turning whose angular velocity exceeds an angular velocity threshold.
Pastore renders obvious the plurality of driving scenarios comprises at least one of light braking whose braking pressure is below a first brake pressure threshold, hard braking whose braking pressure is above a second brake pressure threshold, on-ramp acceleration, passing, cruising at a constant speed whose acceleration is below an acceleration threshold, front vehicle cut-in, or a turning whose angular velocity exceeds an angular velocity threshold (See Section IV. Error Estimate, the authors train a neural network and use different uncertainty quantification techniques (epoch averaging, bootstrap, and dropout) to produce a corresponding uncertainty model. See Section 2A. Fitting a parabola, the authors train a neural network to represent a simple parabola function. Prediction accuracy of the network deteriorates when the network is used to extrapolate outside the range of the training data. It would be obvious to include braking data inside all ranges of operation, i.e. including both light and hard braking, to avoid unnecessary extrapolation error.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for generating vehicle control instructions under uncertainty, including modeling of braking forces using a trained model from sample road events, as disclosed by Cho, Berntorp, and Diaz-Quijano to include braking data in all ranges of operation, including, at least one of hard or light braking events, as suggested by Pastore. One of ordinary skill in the art would have been motivated to make this modification to avoid extrapolation error in the trained model, as suggested by Pastore at Section 2A. Fitting a parabola.
Regarding claim 13, Cho combined with Berntorp, Diaz-Quijano, and Pastore renders obvious the limitations of claim 12. Diaz-Quijano renders obvious obvious identifying at least a portion of a candidate sample events as belonging to one of the plurality of driving scenarios comprises: for each of the candidate sample events, comparing candidate sample driving event data with at least one of the first brake pressure threshold, the second brake pressure threshold, the acceleration threshold, or the angular velocity threshold (See page 570 column 2,
e
h
refers to sampling error. See page 572 column 2 paragraph 1, equal sampling, which corresponds to data from events being balanced, produces the lowest variation in sampling error. See page 571 column 1 paragraph 5, low variation of the sampling error indicates that the model produces high precision predictions in all models strata, corresponding to the different driving scenarios. Equal numbers of data have the same order of magnitude. Using subsets of the data instead of gathering exactly the same amount is obvious and requires use of a count to determine equality. It would be obvious to use this method for different braking thresholds to ensure that the model performs well in the different braking threshold scenarios.); and
identifying the at least a portion of the candidate sample events as belonging to one of the plurality of driving scenarios based on a result of the comparison (See page 570 column 2,
e
h
refers to sampling error. See page 572 column 2 paragraph 1, equal sampling, which corresponds to data from events being balanced, produces the lowest variation in sampling error. See page 571 column 1 paragraph 5, low variation of the sampling error indicates that the model produces high precision predictions in all models strata, corresponding to the different driving scenarios. Equal numbers of data have the same order of magnitude. Using subsets of the data instead of gathering exactly the same amount is obvious and requires use of a count to determine equality. It would be obvious to use this method for different braking thresholds to ensure that the model performs well in the different braking threshold scenarios.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system for generating vehicle control instructions under uncertainty, including modeling of braking forces using a trained model from sample road events, as disclosed by Berntorp and Cho to include equal quantities of data in each scenario, specifically high and low pressure braking scenarios identified according to a pressure threshold, as suggested by Diaz-Quijano. One of ordinary skill in the art would have been motivated to make this modification ensure that the model is precise in all driving scenarios, as suggested by Diaz-Quijano at page 571 column 1 paragraph 5 and page 572 column 2 paragraph 1.
Additional Relevant Art
The prior art made of record and not relied upon is considered pertinent to the applicant’s disclosure and may be found on the accompanying PTO-892 Notice of References Cited:
EP 3257714 A1 which relates to predicting a vehicle’s driving operations including braking and long stops to optimize use of energy.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AUSTIN ROBERT CHENNAULT whose telephone number is (571)272-4606. The examiner can normally be reached Monday - Friday 9:00am - 5:00pm EST.
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, Hitesh Patel can be reached at (571) 270-5442. 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.
/AUSTIN ROBERT CHENNAULT/Examiner, Art Unit 3667
/ANISS CHAD/Supervisory Patent Examiner, Art Unit 3662