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
This communication is in response to applicant’s filing dated 02/13/2026. Claims 1, 3, 5, 6, 9-11, 13-14, 17 and 19 have been amended. Claims 7-8 and 15-16 have been canceled. Claims 1-6, 9-14 and 17-22 are currently pending.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 03/17/2026 has been entered.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/17/2026 has been considered by the examiner.
Response to Arguments
Applicant’s arguments/amendments filed on 02/13/2026, with respect to the previous claim objection to claims 1, 3, 9, 11, 17 and 19 have been fully considered. Applicant has amended claims 1, 3, 9, 11, 17 and 19, thereby rendering previous claim objection moot.
Applicant’s arguments/amendments filed on 02/13/2026, with respect to the previous 35 U.S.C. 112(b) of claims 3, 6, 10, 11, 14 and 19 have been fully considered. Applicant has amended claims 3, 6, 10, 11, 14 and 19, thereby rendering previous 35 U.S.C. 112(b) rejection moot.
Applicant’s arguments, filed 08/20/2025, with respect to the rejection(s) of claim(s) 1-6, 9-14 and 17-22 under 35 U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Jeon et al., US 20160176309 A1, in view of Akella, US 20200406894 A1, in view of Wilkinson et al., US 20190025843 A1, in view of Wang et al., US 20130073113A1.
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.
Claim(s) 1, 3-4, 6, 9, 11-12, 14, 17, 19-22 are rejected under 35 U.S.C. 103 as being unpatentable over Jeon et al., US 20160176309 A1, in view of Akella, US 20200406894 A1, in view of Wilkinson et al., US 20190025843 A1, in view of Wang et al., US 20130073113A1, hereinafter referred to as Jeon, Akella, Wilkinson and Wang, respectively.
Regarding claim 1, Jeon discloses a method comprising:
identifying a speed limit of the route (The speed profile generator generates a speed profile, i.e. speed limit, for a driving route to a desired destination based on the driving history data of the driver. The speed profile may include an expected speed on the driving route – See at least ¶52);
generating a sequence of predicted speed values for the vehicle at future locations on the route based on execution of a direct learning model on the sensor data (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100);
determining a range estimation of the vehicle based on a current amount of charge of a rechargeable battery of the vehicle (The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103);
generating a travel route for the vehicle based on the range estimation (In operation, the battery SOC estimation apparatus receives route data from a map service application. In this example, a driving route may be received by sending an origin, a destination, and a waypoint to the map service application – See at least ¶131).
Jeon fails to explicitly disclose receiving sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route and controlling the vehicle to move autonomously along the travel route.
However, Akella teaches:
receiving sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route (The autonomous vehicle control system is a computer system containing one or more processors, and memory containing instructions that, as a result of being executed by the one or more processors, cause the autonomous vehicle control system to acquire sensor data via the vehicle sensor interface, perform various control operations, and output control signals to the autonomous vehicle via the vehicle control interface – See at least ¶35 and FIG. 4), and
controlling the vehicle to move autonomously along the travel route (In various examples, the autonomous vehicle control system may be used to control a passenger vehicle, a truck, a semi-tractor trailer, a forklift, a delivery van, a tractor, an agricultural vehicle, or a mining truck – See at least ¶36).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Jeon and include the feature of receiving sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route and controlling the vehicle to move autonomously along the travel route, as taught by Akella, to predictably enhance route decision-making and vehicle control.
The combination of Jeon and Akella fail to explicitly disclose generating, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations.
However, Wilkinson teaches generating, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations (To determine appropriate driving speed predictions for the autonomous vehicle, the autonomous vehicle computing system can include a machine-learned model (i.e. indirect learning model) that has been trained to determine driving speed predictions (i.e. predicted speeds) for regions of the vehicle's nominal path based at least in part on the obtained features. For example, the features can be provided to the machine-learned model as input (e.g., as a feature vector) and can be analyzed using the machine-learned model to predict a maximum speed limit value to be applied for the autonomous vehicle at a future moment, for example, to be applied one second in the future. In another example, the machine-learned model could predict a speed limit to be applied for each segment of the path ahead of the autonomous vehicle based on the obtained features. Alternatively or additionally, the machine-learned model could provide a target offset (i.e. deviation) from the nominal path based on the obtained features, for example, to optimize the positioning of the autonomous vehicle in a roadway based on the context around the vehicle – See at least ¶22).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon and Akella and include the feature of generating, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations, as taught by Wilkinson, so that an autonomous vehicle can use context awareness in limiting the travel speed and/or biasing the lane position and thereby achieve safer driving behavior (See at least ¶22 of Wilkinson).
The combination of Jeon, Akella and Wilkinson fail to explicitly disclose determining a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values.
However, Wang teaches determining a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values (FIG. 3 illustrates a simplified schematic for the method of calculating a DTE or a vehicle range. Taking into consideration both predicted future and current driving patterns, the algorithm performs a calculation with data fed from three main paths to estimate or provide a DTE for the vehicle – See at least ¶37. Future diving patterns and efficiencies are determined through sequence. Predicted speeds, road conditions, and/or traffic information is provided by a navigation system, cellular network, and/or vehicle to vehicle network. A traffic model may be present which provides additional predicted traffic considerations into the sequence. The predicted speeds of the vehicle and the other road and traffic conditions are provided to a pattern parameter extraction function, which in turn provides pattern parameters to a pattern recognition function. The pattern recognition function provides a predicted future driving pattern for use in sequence – See at least ¶39).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon, Akella and Wilkinson and include the feature of determining a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values, as taught by Wang, to provide information for a user for trip planning, minimizing driving cost, evaluating vehicle performance and performing maintenance (See at least ¶2 of Wang).
Regarding claim 3, Jeon as modified, discloses generating a sequence of predicted acceleration values for the vehicle at the future locations on the route based on execution of the indirect learning model on the sensor data and the speed limit of the route, and further determining the range estimation of the vehicle based on the sequence of predicted acceleration values for the vehicle at the future locations on the route (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100. The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103).
Regarding claim 4, Jeon as modified discloses wherein the determining the range estimation further comprises determining an estimated amount of energy needed to finish a trip along the route based on execution of the direct learning model on the current amount of charge of the rechargeable battery and the sequence of predicted speed values at the future locations (A speed and an acceleration representing a driving behavior of a driver during a driving may be significant parameters in estimation of a driving range of an electric vehicle. Also, the speed and the acceleration at which the vehicle is driven are closely related to a type of a route taken by the driver. A driver may drive at different speeds and different accelerations on various roads. When speed and acceleration data associated with driving on different roads are mixed, prediction of a future speed may be inaccurate. Thus, classification of a route to generate the driving profile may be a significant factor to increase an accuracy of a corresponding result. An apparatus for estimating an SOC of a battery in an electric vehicle may improve accuracy on a predictive range estimation algorithm, i.e. second machine learning model – See at least ¶81).
Regarding claim 6, Jeon as modified discloses wherein the method further comprises training the indirect learning model based on historical driving data of a user associated with the vehicle to generate a user-specific indirect learning model, and the determining comprises determining the range estimation of the vehicle based on execution the user-specific indirect learning model (The driving history data storage stores driving history data of a driver for each category generated based on a frequency of appearance of road data (data related to characteristics of a road). In response to the driving history data being stored by the driving history data storage, the driving profile generator reads, from the driving history data storage, information on a speed and an acceleration of the vehicle corresponding to a predetermined road – See at least ¶82).
Regarding claim 9, Jeon as modified discloses an apparatus comprising:
a storage configured to store a machine learning model (The transition probability matrix may be an example of a Markov chain. The Markov chain may be used to verify a relationship between a speed and an acceleration of a previous stage and a speed and an acceleration of a subsequent stage of vehicle driving route – See at least ¶142); and
processor configured to (processor – See at least ¶30);
identify a speed limit of the route (The speed profile generator generates a speed profile, i.e. speed limit, for a driving route to a desired destination based on the driving history data of the driver. The speed profile may include an expected speed on the driving route – See at least ¶52),
generate a sequence of predicted speed values for the vehicle at future locations on the route based on execution of a direct learning model on the sensor data (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100),
determine a range estimation of the vehicle based on a current amount of charge of a rechargeable battery of the vehicle (The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103);
generate a travel route for the vehicle based on the range estimation (In operation, the battery SOC estimation apparatus receives route data from a map service application. In this example, a driving route may be received by sending an origin, a destination, and a waypoint to the map service application – See at least ¶131).
Jeon fails to explicitly disclose receive sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route and control the vehicle to move autonomously along the travel route.
However, Akella teaches:
receive sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route (The autonomous vehicle control system is a computer system containing one or more processors, and memory containing instructions that, as a result of being executed by the one or more processors, cause the autonomous vehicle control system to acquire sensor data via the vehicle sensor interface, perform various control operations, and output control signals to the autonomous vehicle via the vehicle control interface – See at least ¶35 and FIG. 4), and
control the vehicle to move autonomously along the travel route (In various examples, the autonomous vehicle control system may be used to control a passenger vehicle, a truck, a semi-tractor trailer, a forklift, a delivery van, a tractor, an agricultural vehicle, or a mining truck – See at least ¶36).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Jeon and include the feature of receiving sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route and controlling the vehicle to move autonomously along the travel route, as taught by Akella, to predictably enhance route decision-making and vehicle control.
The combination of Jeon and Akella fail to explicitly disclose generate, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations.
However, Wilkinson teaches generate, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations (To determine appropriate driving speed predictions for the autonomous vehicle, the autonomous vehicle computing system can include a machine-learned model (i.e. indirect learning model) that has been trained to determine driving speed predictions (i.e. predicted speeds) for regions of the vehicle's nominal path based at least in part on the obtained features. For example, the features can be provided to the machine-learned model as input (e.g., as a feature vector) and can be analyzed using the machine-learned model to predict a maximum speed limit value to be applied for the autonomous vehicle at a future moment, for example, to be applied one second in the future. In another example, the machine-learned model could predict a speed limit to be applied for each segment of the path ahead of the autonomous vehicle based on the obtained features. Alternatively or additionally, the machine-learned model could provide a target offset (i.e. deviation) from the nominal path based on the obtained features, for example, to optimize the positioning of the autonomous vehicle in a roadway based on the context around the vehicle – See at least ¶22).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon and Akella and include the feature of generate, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations, as taught by Wilkinson, so that an autonomous vehicle can use context awareness in limiting the travel speed and/or biasing the lane position and thereby achieve safer driving behavior (See at least ¶22 of Wilkinson).
The combination of Jeon, Akella and Wilkinson fail to explicitly disclose determine a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values.
However, Wang teaches determine a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values (FIG. 3 illustrates a simplified schematic for the method of calculating a DTE or a vehicle range. Taking into consideration both predicted future and current driving patterns, the algorithm performs a calculation with data fed from three main paths to estimate or provide a DTE for the vehicle – See at least ¶37. Future diving patterns and efficiencies are determined through sequence. Predicted speeds, road conditions, and/or traffic information is provided by a navigation system, cellular network, and/or vehicle to vehicle network. A traffic model may be present which provides additional predicted traffic considerations into the sequence. The predicted speeds of the vehicle and the other road and traffic conditions are provided to a pattern parameter extraction function, which in turn provides pattern parameters to a pattern recognition function. The pattern recognition function provides a predicted future driving pattern for use in sequence – See at least ¶39).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon, Akella and Wilkinson and include the feature of determine a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values, as taught by Wang, to provide information for a user for trip planning, minimizing driving cost, evaluating vehicle performance and performing maintenance (See at least ¶2 of Wang).
Regarding claim 11, Jeon as modified discloses generate a sequence of predicted acceleration values for the vehicle at the future locations on the route based on execution of the indirect learning model on the sensor data and the speed limit of the route, and determine the range estimation of the vehicle based on sequence of predicted acceleration values for the vehicle at the future locations on the route (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100. The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103).
Regarding claim 12, Jeon as modified discloses wherein the processor is configured to determine an estimated amount of energy needed to finish a trip along the route based on execution of the direct learning model on the current amount of charge of the rechargeable battery and the sequence of predicted speed values at the future locations (A speed and an acceleration representing a driving behavior of a driver during a driving may be significant parameters in estimation of a driving range of an electric vehicle. Also, the speed and the acceleration at which the vehicle is driven are closely related to a type of a route taken by the driver. A driver may drive at different speeds and different accelerations on various roads. When speed and acceleration data associated with driving on different roads are mixed, prediction of a future speed may be inaccurate. Thus, classification of a route to generate the driving profile may be a significant factor to increase an accuracy of a corresponding result. An apparatus for estimating an SOC of a battery in an electric vehicle may improve accuracy on a predictive range estimation algorithm, i.e. second machine learning model – See at least ¶81).
Regarding claim 14, Jeon as modified discloses wherein the processor is further configured to train the indirect learning model based on historical driving data of a user associated with the vehicle to generate a user-specific indirect learning model, and determine the range estimation of the vehicle based on execution the user-specific indirect learning model (The driving history data storage stores driving history data of a driver for each category generated based on a frequency of appearance of road data (data related to characteristics of a road). In response to the driving history data being stored by the driving history data storage, the driving profile generator reads, from the driving history data storage, information on a speed and an acceleration of the vehicle corresponding to a predetermined road – See at least ¶82).
Regarding claim 17, Jeon as modified discloses a computer-readable storage medium comprising instructions, that when read by a processor, cause a computer to perform:
identifying a speed limit of the route (The speed profile generator generates a speed profile, i.e. speed limit, for a driving route to a desired destination based on the driving history data of the driver. The speed profile may include an expected speed on the driving route – See at least ¶52);
generating a sequence of predicted speed values for the vehicle at future locations on the route based on execution of a direct learning model on the sensor data (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100);
determining a range estimation of the vehicle based on a current amount of charge of a rechargeable battery of the vehicle (The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103);
generating a travel route for the vehicle based on the range estimation (In operation, the battery SOC estimation apparatus receives route data from a map service application. In this example, a driving route may be received by sending an origin, a destination, and a waypoint to the map service application – See at least ¶131).
Jeon fails to explicitly disclose receiving sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route and controlling the vehicle to move autonomously along the travel route.
However, Akella teaches:
receiving sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route (The autonomous vehicle control system is a computer system containing one or more processors, and memory containing instructions that, as a result of being executed by the one or more processors, cause the autonomous vehicle control system to acquire sensor data via the vehicle sensor interface, perform various control operations, and output control signals to the autonomous vehicle via the vehicle control interface – See at least ¶35 and FIG. 4), and
controlling the vehicle to move autonomously along the travel route (In various examples, the autonomous vehicle control system may be used to control a passenger vehicle, a truck, a semi-tractor trailer, a forklift, a delivery van, a tractor, an agricultural vehicle, or a mining truck – See at least ¶36).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Jeon and include the feature of receiving sensor data from a hardware sensor of a vehicle while the vehicle is travelling on a route and controlling the vehicle to move autonomously along the travel route, as taught by Akella, to predictably enhance route decision-making and vehicle control.
The combination of Jeon and Akella fail to explicitly disclose generating, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations.
However, Wilkinson teaches generating, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations (To determine appropriate driving speed predictions for the autonomous vehicle, the autonomous vehicle computing system can include a machine-learned model (i.e. indirect learning model) that has been trained to determine driving speed predictions (i.e. predicted speeds) for regions of the vehicle's nominal path based at least in part on the obtained features. For example, the features can be provided to the machine-learned model as input (e.g., as a feature vector) and can be analyzed using the machine-learned model to predict a maximum speed limit value to be applied for the autonomous vehicle at a future moment, for example, to be applied one second in the future. In another example, the machine-learned model could predict a speed limit to be applied for each segment of the path ahead of the autonomous vehicle based on the obtained features. Alternatively or additionally, the machine-learned model could provide a target offset (i.e. deviation) from the nominal path based on the obtained features, for example, to optimize the positioning of the autonomous vehicle in a roadway based on the context around the vehicle – See at least ¶22).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon and Akella and include the feature of generating, by execution of an indirect learning model, a sequence of predicted speed limit offset values representing learned deviations between predicted vehicle speeds and the speed limit at the future locations, as taught by Wilkinson, so that an autonomous vehicle can use context awareness in limiting the travel speed and/or biasing the lane position and thereby achieve safer driving behavior (See at least ¶22 of Wilkinson).
The combination of Jeon, Akella and Wilkinson fail to explicitly disclose determining a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values.
However, Wang teaches determining a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values (FIG. 3 illustrates a simplified schematic for the method of calculating a DTE or a vehicle range. Taking into consideration both predicted future and current driving patterns, the algorithm performs a calculation with data fed from three main paths to estimate or provide a DTE for the vehicle – See at least ¶37. Future diving patterns and efficiencies are determined through sequence. Predicted speeds, road conditions, and/or traffic information is provided by a navigation system, cellular network, and/or vehicle to vehicle network. A traffic model may be present which provides additional predicted traffic considerations into the sequence. The predicted speeds of the vehicle and the other road and traffic conditions are provided to a pattern parameter extraction function, which in turn provides pattern parameters to a pattern recognition function. The pattern recognition function provides a predicted future driving pattern for use in sequence – See at least ¶39).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon, Akella and Wilkinson and include the feature of determining a range estimation of the vehicle based on the sequence of predicted speed values, and the sequence of predicted speed limit offset values, as taught by Wang, to provide information for a user for trip planning, minimizing driving cost, evaluating vehicle performance and performing maintenance (See at least ¶2 of Wang).
Regarding claim 19, Jeon as modified discloses wherein the processor is further configured to perform generating a sequence of predicted acceleration values for the vehicle at the future locations on the route based on execution of the indirect learning model on the sensor data and the speed limit of the route, and further determining the range estimation of the vehicle based on sequence of predicted acceleration values for the vehicle at the future locations on the route (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100. The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103).
Regarding claim 20, Jeon as modified discloses wherein the determining the range estimation further comprises determining an estimated amount of energy needed to finish a trip along the route based on execution of the direct learning model on the current amount of charge of the rechargeable battery and the sequence of predicted speed values at the future locations (A speed and an acceleration representing a driving behavior of a driver during a driving may be significant parameters in estimation of a driving range of an electric vehicle. Also, the speed and the acceleration at which the vehicle is driven are closely related to a type of a route taken by the driver. A driver may drive at different speeds and different accelerations on various roads. When speed and acceleration data associated with driving on different roads are mixed, prediction of a future speed may be inaccurate. Thus, classification of a route to generate the driving profile may be a significant factor to increase an accuracy of a corresponding result. An apparatus for estimating an SOC of a battery in an electric vehicle may improve accuracy on a predictive range estimation algorithm, i.e. second machine learning model – See at least ¶81).
Regarding claim 21, Jeon, as modified, discloses wherein the generating the sequence of predicted speed values comprises outputting, by the direct learning model, a speed profile comprising a plurality of speed values at a plurality of future points in time, and the determining comprises determining the range estimation based on the speed profile (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100. The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103).
Regarding claim 22, Jeon, as modified, discloses wherein the generating the sequence of predicted speed values comprises outputting, by the indirect learning model, a speed profile comprising a plurality of speed limit offset values with respect to the speed limit at a plurality of future points in time, and the determining comprises determining the range estimation based on the speed profile (In an example, the driving profile generator may form the speed and acceleration profile of the driver using a Markov chain scheme. The Markov chain scheme may be performed by determining data in a subsequent stage of a route based on data in a previous stage of the route. Thus, the driving profile generator may determine to switch from a speed and acceleration on a previous stage of a route to a speed and acceleration on a subsequent stage of the route by using the transition probability matrix generated in the driving history data storage – See at least ¶100. The battery SOC estimator estimates an SOC of a vehicle battery with respect to the driving route based on the generated driving profile. In an example, the battery SOC estimator estimates an SOC of a battery of the electric vehicle with respect to the driving route based on the driving profile, and estimates the driving range of the electric vehicle based on the SOC – See at least ¶103).
Claim(s) 2, 10 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Jeon et al., US 20160176309 A1, in view of Akella, US 20200406894 A1, in view of Wilkinson et al., US 20190025843 A1, in view of Wang et al., US 20130073113A1, as applied to claims 1, 9 and 17 above and further in view of Nam Hyuk Kim, US 20230298461 A1, hereinafter referred to as Jeon, Akella, Wilkinson, Wang and Kim, respectively.
Regarding claim 2, the combination of Jeon, Akella, Wilkinson and Wang fail to explicitly disclose wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values.
However, Kim teaches wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values (According to an aspect of the present disclosure, an apparatus of predicting a congestion time point may include a first deep learning device that outputs first output data using traffic speed data during a first time – See at least ¶12. As an exemplary embodiment of the present disclosure, the apparatus for predicting the congestion time point may input the input data to the congestion time point prediction model, may predict a traffic speed from the current time to a specified time in the future based on at least a portion of data output to the output layer of the congestion time point prediction model through the plurality of layers, and may predict the congestion time point using the predicted traffic speed – See at least ¶57).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon, Akella, Wilkinson, Wang and include the feature of wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values, as taught by Kim, to accurately predict a possibility of congestion or a congestion time point.
Regarding claim 10, the combination of Jeon, Akella, Wilkinson and Wang fail to explicitly disclose wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values and the sequence of predicted speed values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values.
However, Kim teaches wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values and the sequence of predicted speed values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values (According to an aspect of the present disclosure, an apparatus of predicting a congestion time point may include a first deep learning device that outputs first output data using traffic speed data during a first time – See at least 12. As an exemplary embodiment of the present disclosure, the apparatus for predicting the congestion time point may input the input data to the congestion time point prediction model, may predict a traffic speed from the current time to a specified time in the future based on at least a portion of data output to the output layer of the congestion time point prediction model through the plurality of layers, and may predict the congestion time point using the predicted traffic speed – See at least ¶57).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon, Akella, Wilkinson and Wang and include the feature of wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values and the sequence of predicted speed values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values, as taught by Kim, to accurately predict a possibility of congestion or a congestion time point.
Regarding claim 18, the combination of Jeon, Akella, Wilkinson and Wang fail to explicitly disclose wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values.
However, Kim teaches wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values (According to an aspect of the present disclosure, an apparatus of predicting a congestion time point may include a first deep learning device that outputs first output data using traffic speed data during a first time – See at least ¶12. As an exemplary embodiment of the present disclosure, the apparatus for predicting the congestion time point may input the input data to the congestion time point prediction model, may predict a traffic speed from the current time to a specified time in the future based on at least a portion of data output to the output layer of the congestion time point prediction model through the plurality of layers, and may predict the congestion time point using the predicted traffic speed – See at least ¶57).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon and Akella and include the feature of wherein the indirect learning model comprises a deep learning neural network that comprises an input layer configured to receive the sequence of predicted speed limit offset values, an output layer configured to output an average speed limit offset, and one or more hidden layers configured to determine the average speed limit offset from the predicted speed limit offset values, as taught by Kim, to accurately predict a possibility of congestion or a congestion time point.
Claim(s) 5 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Jeon et al., US 20160176309 A1, in view of Akella, US 20200406894 A1, in view of Wilkinson et al., US 20190025843 A1, in view of Wang et al., US 20130073113A1, as applied to claims 1 and 9 above, and further in view of Albert Liu, US 20160375788 A1, hereinafter referred to as Jeon, Akella, Wilkinson, Wang and Liu, respectively.
Regarding claim 5, the combination of Jeon, Akella, Wilkinson and Wang fail to explicitly disclose wherein the method further comprises receiving one or more of a current setting of a heating ventilation and air conditioning (HVAC) setting within the vehicle and a tire pressure sensor value, and the determining further comprises determining the range estimation of the vehicle based on the one or more of the current setting of the HVAC and the tire pressure sensor value.
However, Liu teaches wherein the method further comprises receiving one or more of a current setting of a heating ventilation and air conditioning (HVAC) setting within the vehicle and a tire pressure sensor value, and the determining further comprises determining the range estimation of the vehicle based on the one or more of the current setting of the HVAC and the tire pressure sensor value (a typical HVAC system will automatically adjust fan settings as well as turn on and off the heating and air conditioning (A/C) systems based on the cabin temperature relative to the HVAC temperature settings – See at least ¶37. Interface may also be used to warn the driver of a vehicle condition low tire air pressure – See at least ¶40).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon and Akella and include the feature of wherein the method further comprises receiving one or more of a current setting of a heating ventilation and air conditioning (HVAC) setting within the vehicle and a tire pressure sensor value, and the determining further comprises determining the range estimation of the vehicle based on the one or more of the current setting of the HVAC and the tire pressure sensor value, as taught by Liu, to aid range optimization in an electric vehicle.
Regarding claim 13, the combination of Jeon and Akella fails to explicitly disclose wherein the method further comprises receiving one or more of a current setting of a heating ventilation and air conditioning (HVAC) setting within the vehicle and a tire pressure sensor value, and the determining further comprises determining the range estimation of the vehicle based on the one or more of the current setting of the HVAC and the tire pressure sensor value.
However, Liu teaches wherein the method further comprises receiving one or more of a current setting of a heating ventilation and air conditioning (HVAC) setting within the vehicle and a tire pressure sensor value, and the determining further comprises determining the range estimation of the vehicle based on the one or more of the current setting of the HVAC and the tire pressure sensor value (a typical HVAC system will automatically adjust fan settings as well as turn on and off the heating and air conditioning (A/C) systems based on the cabin temperature relative to the HVAC temperature settings – See at least ¶37. Interface may also be used to warn the driver of a vehicle condition low tire air pressure – See at least ¶40).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Jeon and Akella and include the feature of wherein the method further comprises receiving one or more of a current setting of a heating ventilation and air conditioning (HVAC) setting within the vehicle and a tire pressure sensor value, and the determining further comprises determining the range estimation of the vehicle based on the one or more of the current setting of the HVAC and the tire pressure sensor value, as taught by Liu, to aid range optimization in an electric vehicle.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MAHMOUD M KAZIMI whose telephone number is (571)272-3436. The examiner can normally be reached M-F 7am-5pm.
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, Erin Bishop can be reached at 5712703713. 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.
/MAHMOUD M KAZIMI/Examiner, Art Unit 3665