DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-11 and 13-19 are pending in this application.
Claims 1, 10, 14, and 4* are presented as currently amended claims.
No claims newly presented.
Claims 12 and 20 are newly cancelled.
Examiner's Note
Examiner has cited particular paragraphs / columns and line numbers or figures in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, in preparing the responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. Applicant is reminded that the Examiner is entitled to give the broadest reasonable interpretation to the language of the claims. Furthermore, the Examiner is not limited to Applicants’ definition which is not specifically set forth in the claims.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-5, 9-11, 13-15, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Song et al. (US 20250117625 A1) in view of Thomas (US 20170144659 A1) (the combination of which will be referred to as 'combination Song' hereinafter). As regards the individual claims:
Regarding claim 1, Song teaches a system for:
online learning adaptive cruise control (ACC) for driving a vehicle comprising: (Song: ¶ 279; part of a cooperative adaptive cruise control functionality of vehicle)
one or more non-transitory memories storing an ACC model pool comprising one or more (Song: ¶ 097; a variational autoencoder 308 comprising one or more trained neural networks) ACC models; and (Song: ¶ 279; part of a cooperative adaptive cruise control functionality of vehicle) one or more processors operably causing the system to: (Song: ¶ 168; processor) generate, using a trained meta algorithm (Song: ¶ 094; VAE 208 is trained (e.g., using neural network training, as described herein at least in connection with FIG. 10) using an expectation-maximization meta-algorithm such as, for example, probabilistic principal components analysis)
To the extent Song is silent about or does not explicitly teach: and based on historical user inputs and user preferences of a user, one or more personalized ACC models associated with the user, and include the one or more personalized ACC models in the ACC model pool; determine whether the user triggers a real-time ACC disengagement; in response to determining that the user triggers the real-time ACC disengagement, select, based on real-time user inputs, a predicted ACC model from the ACC model pool including the one or more personalized ACC models; and engage the vehicle with the predicted ACC model. Thomas does teach:
and based on historical user inputs and user preferences of a user, one or more personalized ACC models associated with the user, (Thomas: ¶ 022; ECU 14 queries the driver memory 40 to determine a total number of times the driver and/or the other drivers (e.g., previous drivers) have overrode the cruise control system) (Thomas: ¶ 020; creates a current driver behavior profile identifying the cruise control system 12 override based on the current geographic location of the vehicle 10 where the cruise control override occurred,) and include the one or more personalized ACC models in the ACC model pool; (Thomas: Clm. 010; creating [Examiner note: one of a multiple of ] profile of the driver behavior associated with the vehicle location based on the respective actions by the driver at the vehicle location after the driver overrode the cruise control;) determine whether the user triggers a real-time ACC disengagement; (Thomas: ¶ 014; ECU 14 also identifies when the current driver and/or other (e.g., previous) drivers override the cruise control system 12 (e.g., the ACC system) (e.g., disengage and/or change the cruise control system) (Thomas: ¶ 023; If, on the other hand, the driver consistently (e.g., at least the predetermined number of tunes) overrides the cruise control system 12 at a particular location, the driver's behavior is considered to be statistically relevant so that it becomes desirable to create a profile of the driver's behavior at that location) in response to determining that the user triggers the real-time ACC disengagement, select, based on real-time user inputs, a predicted ACC model from the ACC model pool including the one or more personalized ACC models, (Thomas: Clm. 010; determining if the profile of the driver behavior associated with the vehicle location is acceptable for the road terrain associated with the vehicle location; and wherein the setting step includes: based on the determination, setting the profile of the driver behavior associated with the vehicle location as the default cruise control profile for the driver behavior at the vehicle location) (Thomas: Fig. 002; [[Examiner's Note: showing that after real-time input, assess if new profile need and if so apply it]]) wherein one or more vehicle operation parameters of the predicted ACC model are different than the real-time user inputs, and the real-time user inputs comprise vehicle speeds, accelerating, decelerating, following distances, lane changing, or vehicle operation mode selection; (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying [inter alia] the road terrain of the current geographic location of the vehicle 10, the current road condition) (Thomas: ¶ 025; a determination is made whether the profile (e.g., the behavior profile) created in the step 142 is acceptable (e.g., safe) for the road terrain at the current geographic location and the additional previous vehicle locations. In one embodiment, the determination in the step 144 is also made based on the current road condition. If it is determined in the step 144 that the behavior profile created in the step 142 is not acceptable, control returns to the step 110.) and engage the vehicle with the predicted ACC model. (Thomas: ¶ 010; the current condition identifier 36 may identify one of clear and snow covered as a current road condition (e.g., driving condition). It is contemplated that the dry, wet, or icy current road condition (e.g., driving condition) may be identified) (Thomas: Clm. 010; controlling a cruise control system on a vehicle)
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Thomas with the teachings of Song because doing so would result in the predicable benefit of reducing the likelihood of drivers needing to employ manual control to override an ACC system when traversing “non-typical driving terrain” (Thomas: ¶ 002). Furthermore, applying the data inputs taught and suggested by Thomas to the AI model taught by Song would be within the capabilities of a person of ordinary skill in the art because that person would recognize that a mathematical model can be refined for better performance by considering a wide variety of data based on the specific application and inputs available (Song: ¶ 197).
Regarding claim 2, as detailed above, combination Song teaches the invention as detailed with respect to claim 1. Song further teaches:
wherein each personalized ACC model is generated by an aggregation of the one or more ACC models in the ACC model pool. (Song: ¶ 094; trained (e.g., using neural network training, as described herein at least in connection with FIG. 10) using an expectation-maximization meta-algorithm) (Song: ¶ 089; cause first information to be selected for inferencing by one or more neural networks based, at least in part, on a similarity of the first information to information used to train the one or more neural networks)
Regarding claim 3, as detailed above, combination Song teaches the invention as detailed with respect to claim 2. Song further teaches:
wherein each personalized ACC model is generated by the aggregation of the one or more (Song: ¶ 098; variational autoencoder 308 comprises one or more trained neural networks (e.g., trained neural network 310, trained neural network 312, and/or trained neural network 314))
And Thomas further teaches:
personalized ACC models associated with the user. (Thomas: ¶ 023; If, on the other hand, the driver consistently (e.g., at least the predetermined number of tunes) overrides the cruise control system 12 at a particular location, the driver's behavior is considered to be statistically relevant so that it becomes desirable to create a profile of the driver's behavior at that location)
Regarding claim 4, as detailed above, combination Song teaches the invention as detailed with respect to claim 3. Song further teaches:
wherein the meta algorithm comprises an aggregator performing the aggregation. (Song: ¶ 117; neural network parameters and/or hyperparameters 514 include a learning rate of one or more neural networks, a number of local iterations of one or more neural networks, aggregation weights of one or more neural networks,)
Regarding claim 5, as detailed above, combination Song teaches the invention as detailed with respect to claim 2. Song further teaches:
wherein each ACC model of the one or more ACC models has a corresponding weight, and the one or more ACC models are aggregated based on the corresponding weights. (Song: ¶ 117; neural network parameters and/or hyperparameters 514 include a learning rate of one or more neural networks, a number of local iterations of one or more neural networks, aggregation weights of one or more neural networks,)
Regarding claim 9, as detailed above, combination Song teaches the invention as detailed with respect to claim 5. Thomas further teaches:
wherein the predicted ACC model is one of the one or more personalized ACC models. (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying the cruise control system 12 override based on the current geographic location of the vehicle 10 where the cruise control override occurred, the road terrain of the current geographic location of the vehicle) (Thomas: Clm. 005; if the predetermined number of the actions of the other drivers at the vehicle location are consistent with the actions of the driver, updating a central cruise control database to set a default profile for behaviors of all drivers at the vehicle location)
Regarding claim 10, as detailed above, combination Song teaches the invention as detailed with respect to claim 1. Thomas further teaches:
wherein the vehicle operation parameters of the predicted ACC model (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying [inter alia] the road terrain of the current geographic location of the vehicle 10, the current road condition) (Thomas: ¶ 025; a determination is made whether the profile (e.g., the behavior profile) created in the step 142 is acceptable (e.g., safe) for the road terrain at the current geographic location and the additional previous vehicle locations. In one embodiment, the determination in the step 144 is also made based on the current road condition. If it is determined in the step 144 that the behavior profile created in the step 142 is not acceptable, control returns to the step 110.)are closer to the real-time user inputs compared with the vehicle operation parameters of the one or more ACC models other than the predicted ACC model. (Thomas: ¶ 010; the current condition identifier 36 may identify one of clear and snow covered as a current road condition (e.g., driving condition). It is contemplated that the dry, wet, or icy current road condition (e.g., driving condition) may be identified)
Regarding claim 11, as detailed above, combination Song teaches the invention as detailed with respect to claim 10. Thomas further teaches:
wherein the one or more vehicle operation parameters comprise a vehicle speed, a following distance, a deceleration limit, an acceleration limit, a minimum operation speed, vehicle operation mode selection, weather (Thomas: ¶ 020; road terrain of the current geographic location of the vehicle 10, the current road condition, the respective actions taken by the driver and, optionally, the other drivers (e.g., at least one of the throttle position set by the driver and/or the other drivers, the gear position set by the driver and/or the other drivers, and the brake demanded by the driver and/or the other drivers) following the cruise control override, the presence of the forward vehicle 24, and if the forward vehicle 24 is present, distance to the forward vehicle 24.) and road condition adaptation, and vehicle speed adjustments in curves. (Thomas: ¶ 021; road grade and/or road curve at the current geographic location.)
Regarding claim 13, as detailed above, combination Song teaches the invention as detailed with respect to claim 1. Thomas further teaches:
wherein the one or more ACC models comprise one or more default ACC settings. (Thomas: ¶ 017; set the profile of the driver behavior associated with the vehicle location and the any additional previous vehicle locations as a default cruise control profile for the driver behavior at the vehicle location)
Regarding claim 14, Song teaches a method for
online learning adaptive cruise control (ACC) for driving a vehicle comprising: (Song: ¶ 279; part of a cooperative adaptive cruise control functionality of vehicle)
generating, using a trained meta algorithm (Song: ¶ 094; VAE 208 is trained (e.g., using neural network training, as described herein at least in connection with FIG. 10) using an expectation-maximization meta-algorithm such as, for example, probabilistic principal components analysis)
To the extent Song is silent about or does not explicitly teach: and based on historical user inputs and user preferences of a user, one or more personalized ACC models associated with the user, and including the one or more personalized ACC models in an ACC model pool comprising one or more ACC models; determining whether the user triggers a real-time ACC disengagement; in response to determining that the user triggers the real-time ACC disengagement, selecting, based on real-time user inputs, a predicted ACC model from the ACC model pool including the one or more personalized ACC models; and engaging the vehicle with the predicted ACC model. Thomas does teach:
and based on historical user inputs and user preferences of a user, one or more personalized ACC models associated with the user, (Thomas: ¶ 022; ECU 14 queries the driver memory 40 to determine a total number of times the driver and/or the other drivers (e.g., previous drivers) have overrode the cruise control system) (Thomas: ¶ 020; creates a current driver behavior profile identifying the cruise control system 12 override based on the current geographic location of the vehicle 10 where the cruise control override occurred,) and including the one or more personalized ACC models in an ACC model pool comprising one or more ACC models; (Thomas: Clm. 010; creating [Examiner note: one of a multiple of ] profile of the driver behavior associated with the vehicle location based on the respective actions by the driver at the vehicle location after the driver overrode the cruise control;) determining whether the user triggers a real-time ACC disengagement; (Thomas: ¶ 014; ECU 14 also identifies when the current driver and/or other (e.g., previous) drivers override the cruise control system 12 (e.g., the ACC system) (e.g., disengage and/or change the cruise control system) (Thomas: ¶ 023; If, on the other hand, the driver consistently (e.g., at least the predetermined number of tunes) overrides the cruise control system 12 at a particular location, the driver's behavior is considered to be statistically relevant so that it becomes desirable to create a profile of the driver's behavior at that location) in response to determining that the user triggers the real-time ACC disengagement, selecting, based on real-time user inputs, a predicted ACC model from the ACC model pool including the one or more personalized ACC models, (Thomas: Clm. 010; determining if the profile of the driver behavior associated with the vehicle location is acceptable for the road terrain associated with the vehicle location; and wherein the setting step includes: based on the determination, setting the profile of the driver behavior associated with the vehicle location as the default cruise control profile for the driver behavior at the vehicle location) (Thomas: Fig. 002; [[Examiner's Note: showing that after real-time input, assess if new profile need and if so apply it]]) wherein one or more vehicle operation parameters of the predicted ACC model are different than the real-time user inputs, and the real- time user inputs comprise vehicle speeds, accelerating, decelerating, following distances, lane changing, or vehicle operation mode selection; (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying [inter alia] the road terrain of the current geographic location of the vehicle 10, the current road condition) (Thomas: ¶ 010; the current condition identifier 36 may identify one of clear and snow covered as a current road condition (e.g., driving condition). It is contemplated that the dry, wet, or icy current road condition (e.g., driving condition) may be identified) (Thomas: ¶ 025; a determination is made whether the profile (e.g., the behavior profile) created in the step 142 is acceptable (e.g., safe) for the road terrain at the current geographic location and the additional previous vehicle locations. In one embodiment, the determination in the step 144 is also made based on the current road condition. If it is determined in the step 144 that the behavior profile created in the step 142 is not acceptable, control returns to the step 110.) and engaging the vehicle with the predicted ACC model. (Thomas: Clm. 010; controlling a cruise control system on a vehicle)
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Thomas with the teachings of Song because doing so would result in the predicable benefit of reducing the likelihood of drivers needing to employ manual control to override an ACC system when traversing “non-typical driving terrain” (Thomas: ¶ 002). Furthermore, applying the data inputs taught and suggested by Thomas to the AI model taught by Song would be within the capabilities of a person of ordinary skill in the art because that person would recognize that a mathematical model can be refined for better performance by considering a wide variety of data based on the specific application and inputs available (Song: ¶ 197).
Regarding claim 15, as detailed above, combination Song teaches the invention as detailed with respect to claim 14. Song further teaches:
wherein: each personalized ACC model is generated by an aggregation of the one or more ACC models in the ACC model pool; (Song: ¶ 094; an expectation-maximization meta-algorithm)
And Thomas further teaches:
each personalized ACC model is generated by the aggregation of the one or more personalized ACC models associated with the user; and (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying the cruise control system 12 override based on the current geographic location of the vehicle 10 where the cruise control override occurred, the road terrain of the current geographic location of the vehicle) (Thomas: Clm. 005; if the predetermined number of the actions of the other drivers at the vehicle location are consistent with the actions of the driver, updating a central cruise control database to set a default profile for behaviors of all drivers at the vehicle location) the meta algorithm comprises an aggregator performing the aggregation. (Song: ¶ 098; variational autoencoder 308 comprises one or more trained neural networks (e.g., trained neural network 310, trained neural network 312, and/or trained neural network 314))
Regarding claim 18, as detailed above, combination Song teaches the invention as detailed with respect to claim 14. Song further teaches:
wherein: the predicted ACC model is one of the one or more personalized ACC models; and (Song: ¶ 089; cause first information to be selected for inferencing by one or more neural networks based, at least in part, on a similarity of the first information to information used to train the one or more neural networks)
And Thomas further teaches:
the one or more ACC models comprise one or more default ACC settings. (Thomas: ¶ 017; set the profile of the driver behavior associated with the vehicle location and the any additional previous vehicle locations as a default cruise control profile for the driver behavior at the vehicle location)
Regarding claim 19, as detailed above, combination Song teaches the invention as detailed with respect to claim 14. Thomas further teaches:
wherein: the one or more vehicle operation parameters comprise vehicle speed, a following distance, a deceleration limit, an acceleration limit, a minimum operation speed, vehicle operation mode selection, weather and road condition adaptation, and vehicle speed adjustments in curves; and (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying [inter alia] the road terrain of the current geographic location of the vehicle 10, the current road condition) (Thomas: ¶ 025; a determination is made whether the profile (e.g., the behavior profile) created in the step 142 is acceptable (e.g., safe) for the road terrain at the current geographic location and the additional previous vehicle locations. In one embodiment, the determination in the step 144 is also made based on the current road condition. If it is determined in the step 144 that the behavior profile created in the step 142 is not acceptable, control returns to the step 110.)the vehicle operation parameters of the predicted ACC model are closer to the real-time user inputs compared with the vehicle operation parameters of the one or more ACC models other than the predicted ACC model. (Thomas: ¶ 013; current condition identifier 36 may identify one of dry, wet, and icy as a current road condition (e.g., driving condition). In addition, the current condition identifier 36 may identify one of clear and snow covered as a current road condition (e.g., driving condition). It is contemplated that the dry, wet, or icy current road condition (e.g., driving condition) may be identified by applying braking pressures to different wheels on the vehicle 10 to identify if respective wheel slips occur. Furthermore, the clear and snow covered current road condition (e.g., driving condition) may be identified via cameras on the vehicle 10.) (Thomas: ¶ 010; the current condition identifier 36 may identify one of clear and snow covered as a current road condition (e.g., driving condition). It is contemplated that the dry, wet, or icy current road condition (e.g., driving condition) may be identified)
Claims 6, 7-8 and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over combination Song as applied to claims 5, 1, and 14 respectively above, and further in view of Jang et al. (US 20170341660 A1).
Regarding claim 6, as detailed above, combination Song teaches the invention as detailed with respect to claim 5. To the extent Song is silent or does not explicitly teach:
wherein the aggregation comprises dividing a sum of products of each ACC model and the corresponding weight by a sum of the corresponding weights. Jang does teach: wherein the aggregation comprises dividing a sum of products of each ACC model and the corresponding weight by a sum of the corresponding weights. (Jang: ¶ 057; Locally weighted scatterplot smoothing techniques are “LOESS” and “LOWESS” which are two strongly related non-parametric regression methods that combine multiple regression models in a k-nearest-neighbor-based meta-model. D).
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Jang with the teachings of Song because doing so would result in the predicable benefit of "improv[ing] model smoothness and prevent[ing] discontinuities" (Jang: ¶ 049).
Regarding claim 7, as detailed above, combination Song teaches the invention as detailed with respect to claim 1. To the extent Song is silent or does not explicitly teach:
wherein the meta algorithm is trained by minimizing a difference between the generated personalized ACC models and the historical user inputs and the user preferences of the user. Jang does teach: wherein the meta algorithm is trained by minimizing a difference (Jang: ¶ 057; Locally weighted scatterplot smoothing techniques are “LOESS” and “LOWESS” which are two strongly related non-parametric regression methods that combine multiple regression models in a k-nearest-neighbor-based meta-model. D) between the generated personalized ACC models and the historical user inputs and the user preferences of the user. (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying the cruise control system 12 override based on the current geographic location of the vehicle 10 where the cruise control override occurred, the road terrain of the current geographic location of the vehicle)
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Jang with the teachings of Song because doing so would result in the predicable benefit of "improv[ing] model smoothness and prevent[ing] discontinuities" (Jang: ¶ 049).
Regarding claim 8, as detailed above, combination Song teaches the invention as detailed with respect to claim 1. To the extent Song is silent or does not explicitly teach:
wherein the meta algorithm is continuously trained by minimizing a difference Jang does teach:
wherein the meta algorithm is continuously trained by minimizing a difference (Jang: ¶ 057; Locally weighted scatterplot smoothing techniques are “LOESS” and “LOWESS” which are two strongly related non-parametric regression methods that combine multiple regression models in a k-nearest-neighbor-based meta-model. D).
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Jang with the teachings of Song because doing so would result in the predicable benefit of "improv[ing] model smoothness and prevent[ing] discontinuities" (Jang: ¶ 049).
And Thomas further teaches:
between the predicted ACC model and the real-time user inputs. (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying the cruise control system 12 override based on the current geographic location of the vehicle 10 where the cruise control override occurred, the road terrain of the current geographic location of the vehicle)
Regarding claim 16, as detailed above, combination Song teaches the invention as detailed with respect to claim 14. Song teaches:
wherein: each personalized ACC model is generated by an aggregation of the one or more ACC models in the ACC model pool; (Song: ¶ 094; trained (e.g., using neural network training, as described herein at least in connection with FIG. 10) using an expectation-maximization meta-algorithm) (Song: ¶ 089; cause first information to be selected for inferencing by one or more neural networks based, at least in part, on a similarity of the first information to information used to train the one or more neural networks) each ACC model of the one or more ACC models has a corresponding weight, and the one or more ACC models are aggregated based on the corresponding weights; and (Song: ¶ 117; neural network parameters and/or hyperparameters 514 include a learning rate of one or more neural networks, a number of local iterations of one or more neural networks, aggregation weights of one or more neural networks,)
To the extent Song is silent about or does not explicitly teach: the aggregation comprises dividing a sum of products of each ACC model and the corresponding weight by a sum of the corresponding weights. Jang does teach:
the aggregation comprises dividing a sum of products of each ACC model and the corresponding weight by a sum of the corresponding weights. (Jang: ¶ 057; Locally weighted scatterplot smoothing techniques are “LOESS” and “LOWESS” which are two strongly related non-parametric regression methods that combine multiple regression models in a k-nearest-neighbor-based meta-model. D).
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Jang with the teachings of Song because doing so would result in the predicable benefit of "improv[ing] model smoothness and prevent[ing] discontinuities" (Jang: ¶ 049).
Regarding claim 17, as detailed above, combination Song teaches the invention as detailed with respect to claim 14. To the extent Song is silent or does not explicitly teach:
wherein: the meta algorithm is trained by minimizing a difference between Jang does teach: wherein: the meta algorithm is trained by minimizing a difference between (Jang: ¶ 057; Locally weighted scatterplot smoothing techniques are “LOESS” and “LOWESS” which are two strongly related non-parametric regression methods that combine multiple regression models in a k-nearest-neighbor-based meta-model. D).
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Jang with the teachings of Song because doing so would result in the predicable benefit of "improv[ing] model smoothness and prevent[ing] discontinuities" (Jang: ¶ 049).
And combination Song further teaches:
the generated personalized ACC models and the historical user inputs and the user preferences of the user; (Thomas: ¶ 020; ECU 14 creates a current driver behavior profile identifying the cruise control system 12 override based on the current geographic location of the vehicle 10 where the cruise control override occurred, the road terrain of the current geographic location of the vehicle) and the meta algorithm is continuously trained by minimizing a difference between the predicted ACC model and the real-time user inputs. (Song: ¶ 089; cause first information to be selected for inferencing by one or more neural networks based, at least in part, on a similarity of the first information to information used to train the one or more neural networks)
Response to Arguments
Applicant's remarks filed April 9, 2026 have been fully considered.
Applicant’s argument and amendments with respect to the previous applied drawing objection is persuasive and the objection is hereby withdrawn. Applicant’s argument and amendments with respect to the previous applied 35 U.S.C. § 103 rejection is not persuasive. Applicant argues that
The cited references do not teach the features of "in response to determining that the user triggers the real-time ACC disengagement, selecting, based on real-time user inputs, a predicted ACC model from the ACC model pool including the one or more personalized ACC models, wherein one or more vehicle operation parameters of the predicted ACC model are different than the real-time user inputs, and the real-time user inputs comprise vehicle speeds, accelerating, decelerating, following distances, lane changing, or vehicle operation mode selection," recited in amended claim 1 and similarly recited in claim 14. Thomas is directed to a method for controlling a cruise control system on a vehicle, which includes identifying a vehicle location and identifying a number of respective cruise control overrides by a driver at the vehicle location . . . Thomas describes that after determining a user disengaging from a cruise control, "a profile of the driver's behavior at a particular location is created" for cruise control at that location. Thomas, para. [0023]. However, Thomas does not describe that the created user profile includes vehicle operation parameters that are different than the user behavior at that location. Applicant’s Arguments filed April 9, 2026, pg. 8.
Examiner disagrees and points to applied prior art Thomas teaching considering one or more vehicle operation parameters which are different than the real-time user inputs when reciting “the current condition identifier 36 may identify one of dry, wet, and icy as a current road condition” (Thomas: ¶ 010) and “ECU 14 identifies a deviation of 1% from a flat road (e.g., a −1% road grade or a 1% road grade) as a non-flat road and a deviation of 1% from a straight road (e.g., a −1% curve or a 1% curve) as a non-straight road” (Thomas: ¶ 012) and others (Thomas: ¶ 010-020).
Applicant further argues that “Thomas describes that after determining a user disengaging from a cruise control, "a profile of the driver's behavior at a particular location is created" for cruise control at that location. Thomas, para. [0023]. However, Thomas does not describe that the created user profile includes vehicle operation parameters that are different than the user behavior at that location.
However, Thomas does teach that during “step 134, additional previous vehicle locations having similar road terrain are identified. Similar road terrain, for example, is a road grade and/or road curve [and in] step 136, the ECU 14 queries the driver memory 40 to determine a total number of times the driver and/or the other drivers (e.g., previous drivers) have overrode the cruise control system 12 at the current geographic location and/or additional previous vehicle locations that have similar road terrain.” Thomas: ¶ 021-022. Thomas further teaches “a determination is made whether the profile (e.g., the behavior profile) created in the step 142 is acceptable (e.g., safe) for the road terrain at the current geographic location [and if] the behavior profile created in the step 142 is not acceptable, control returns to the step 110. “ Thomas: ¶ 025. Therefore, Thomas is storing the road conditions such as grade and curve in the created driver profile and specifically searching for previous similar sections of road conditions and assessing if a predicted ACC model should even be created based on those other non-driver inputs.
In other words Thomas is, at a minimum, considering road grade and curve when (i) creating, (ii) vetting for safety, and (iii) storing the predicative model and therefore is considering one or more vehicle operation parameters (road grade and curve) of the predicted ACC model (profile) are different than the real-time user inputs, and the real-time user inputs comprise vehicle speeds, accelerating, decelerating, following distances, lane changing, or vehicle operation mode selection; (road grade and curve are not speed, de/accelerating, following distance, lane changing, or vehicle mode selection) when deciding to create or discard a particular ACC profile (safety vetting of location). In particular, Applicant’s claim limitations relying on “weather and road condition adaptation, and vehicle speed adjustments in curves” as supported in Applicant’s Specification at ¶ 020 is obvious in light of Thomas’s profile safety vetting “made based on the current road condition” (Thomas: ¶ 025). Consequently, Applicant’s amendments and arguments are not persuasive.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure Valverde et al. (US 20240367650 A1) which discloses methods of determining distance bounds for adaptive cruise control.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLES PALL whose telephone number is (571)272-5280. The examiner can normally be reached on M-F 9:30 - 18:30.
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, Angela Ortiz can be reached on 571-272-1206. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/C.P./ Examiner, Art Unit 3663
/ANGELA Y ORTIZ/Supervisory Patent Examiner, Art Unit 3663
Prosecution Insights