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 .
Applicant(s) Response to Official Action
The response filed on 12/11/2025 has been entered and made of record.
Response to Arguments/Amendments
Presented arguments have been fully considered but are held unpersuasive. Examiner’s response to the presented arguments follows below.
Claim Rejections - 35 USC § 102/103
Summary of Arguments:
Regarding claim 1, the Applicant argues:
Tal fails to teach determining a set of images “for a particular geographic area” because Tal's image capture is “opportunistic” rather than proactive. The Applicant also argues that Tal does not classify images to determine “overall road conditions” (like snow or ice), but rather only detects discrete point-specific incidents like pavement damage. [Remarks: Page 8]
Regarding claim 2, the Applicant argues:
Claim 2 recites targeting particular geographic areas based on data indicating potential risk. Tal fails to disclose or render obvious such a feature. Indeed, Tal's capture is not targeted but incidental to vehicle travel. [Remarks: Page 8]
Regarding claim 3, the Applicant argues:
Tal merely determines discrete incidents, not area-wide risks. Claim 4
specifies current or recent images, but Tal's real-time capture is not tied to targeted selection. [Remarks: Page 8]
Regarding claim 6, Applicant argues Tal in view of Terrazas:
The Applicant argues that combining Tal and Terrazas is improper because Terrazas "merely teaches using a majority voting scheme" for commercial characteristics, not for road classifications. [Remarks: Page 5]
Regarding claim 7, Applicant argues Tal in view of Huang:
The Applicant argues that combining Tal and Huang is improper because Huang merely teaches averaging confidence scores to enhance neural network training for object detection in suboptimal images, and this teaching is "not applied to road condition classifications per segment". The Applicant asserts that because Huang does not explicitly address "road condition predictions," there is no motivation to combine the teachings. [Remarks: Page 5]
Regarding claims 19-20, Applicant argues Tal in view of Magnusson:
The Applicant argues that neither Tal nor Magnusson discloses adjusting an ADAS parameter or aggregating road classifications from multiple vehicles on or recently traveling a segment. [Remarks: Page 6]
Examiner’s Response:
Regarding claim 1, the Examiner contends:
The Applicant attempts to import limitations from the specification into the claims. Claim 1 broadly recites “determine a set of road classifications for a set of road segments associated with the particular geographic area”. Tal discloses capturing images along a roadway (the geographic area) and using a server to associate identified incidents to a road network segment via GPS coordinates, which fully satisfies the broad claim language regardless of whether the image capture is “opportunistic”. Furthermore, the Applicant's own specification explicitly defines “road classification” to include “a presence of an object or debris in/on a road” and “a presence of a pothole(s)”. Therefore, Tal's detection of discrete objects like potholes perfectly anticipates the claimed “road classifications”.
Regarding claim 2, the Examiner contends:
The Applicant implies that the data indicating potential risk is based on “prior” data. However, the claim simply recites “data”. In other words, Tal targets (identifies) particular geographic areas based on data (captured image and identified potential risk, such as potholes) indicating those areas are at potential risk. Furthermore, claim 2 recites: “wherein the one or more processors is further configured to target particular geographic areas based on data indicating those areas are at potential risk.” In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., targeting particular geographic areas based on data indicating potential risk.) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Regarding claim 3, the Examiner contends:
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., area-wide risks) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Regarding claim 6, the Examiner contends:
The Applicant improperly attacks the references individually rather than addressing the rationale for the combination. The Examiner does not allege that Terrazas teaches road classifications; rather, the Examiner asserts that it would be obvious to modify Tal's classification system with Terrazas's well-known mathematical majority voting scheme to improve inference accuracy by leveraging characteristics from numerous images.
Regarding claim 7, the Examiner contends:
The Applicant's argument fails because it improperly demands that the secondary reference (Huang) explicitly disclose the specific use case of the primary reference (road segments) and attempts to attack the references individually. The test for obviousness does not require the secondary reference to address the exact same specific problem or be bodily incorporated into the primary reference. Furthermore, the Examiner is correct in stating that both Tal and Huang are in the same field of endeavor (i.e., image classification using machine learning/neural networks). Huang explicitly teaches that image classifications derived from multiple images of a region can be ensembled to generate a final classification for that region. The Examiner properly formulated an obviousness rationale: it would have been obvious to a person of ordinary skill in the art to apply Huang's known mathematical/algorithmic technique of averaging a set of predicted classifications to Tal's road classification system. The motivation is standard and sound (to improve the accuracy of the final classification prediction by leveraging multiple data points (images)).
Regarding claims 19-20, the Examiner contends:
This argument is factually incorrect based on the explicit text of Magnusson. Magnusson explicitly states that “automatic braking systems can adapt to the friction on the road,” which is a direct disclosure of adjusting an ADAS parameter. Furthermore, Magnusson explicitly teaches mapping road surfaces to cells and calculating probabilities based on aggregated sensor data from a plurality of vehicles traveling on that road surface.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-5, 8-18, 21-22, 23-24 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Tal et al., hereinafter referred to as Tal (US 2022/0019829 A1).
As per claim 1, Tal discloses a system (Tal: Abstract), comprising:
a memory (Tal: [0012] - Memory); and
one or more processors configured to (Tal: [0012], [0030], claim 1):
determine a set of one or more images for a particular geographic area (Tal: Paras. [0012], [0027], [0047] disclose capturing digital images containing objects of interest along a first section of a roadway [i.e., particular geographic area]. For example, the system determines which image frames 16b and 16d contain objects 12, while image frames 16a and 16c do not, thus determining a relevant set of images.);
obtain the set of one or more images for the particular geographic area (Tal: Paras. [0012], [0030], [0040] disclose the system includes a device having a camera for obtaining the digital images. The program/software collects image data 16 (the digital images 16) from the device's 101 camera(s) 500 as the vehicle travels along the roadway.);
determine a set of road classifications for a set of road segments associated with the particular geographic area that are based at least in part on querying a machine learning model to classify the set of one or more images (Tal: Paras. [0009], [0030], [0129], [0154] disclose using neural network(s) and machine learning to process images and infer/determine objects present. These objects are defined as road related incidents/conditions ([0027]), which are equivalent to road classifications. The system can assess environmental conditions including “heavy rain, heavy fog, heavy snowfall” and can classify a road as “completely covered in snow”. This is a road classification based on an image. The server then associates these classified incidents through their GPS coordinates, to a road 14 network segment, thus determining classifications for road segments.); and
store the set of road classifications in association with the set of road segments (Tal: Paras. [0066], [0068], [0154] disclose a server is responsible for organizing, storing, processing and disseminating of the object data 21. The object data, which includes the identified road condition and location, is stored into one or more database(s) 30 on the server 107. The server can associate incidents 12 [road classifications], through their GPS coordinates, to a road 14 network segment, thus storing the classifications in association with road segments.).
As per claim 2, Tal discloses the system of claim 1, wherein the one or more processors is further configured to target particular geographic areas based on data indicating those areas are at potential risk (Tal: Paras. [0068]-[0069], [0154] disclose identifying and associating incidents 12, through their GPS coordinates.).
As per claim 3, Tal discloses the system of claim 1, wherein the one or more processors is further configured to:
receive an image associated with a geographic area (Tal: Paras. [0012], [0049] disclose capturing digital images containing objects of interest along a first section of a roadway. Geo coordinates GCa,b,c,d can represent physical geographical coordinates (e.g. provided by sensors 700 of the device 101 associated with at what geographical position the vehicle 102 was at on the road surface 14 when the particular image frame 16 a,b,c,d was recorded).); and
determine whether there is a risk associated with the geographic area (Tal: Para. [0027] discloses determining risk by road related incidents/conditions/objects 12 (e.g. pavement damage, street sign damage, debris on road, etc.) with respect to a road surface 14.).
As per claim 4, Tal discloses the system of claim 1, wherein the set of one or more images are current images or images captured within a predefined time period (Tal: Paras. [0012], [0027]-[0028] disclose automating identification and reporting of road related incidents/conditions/objects 12 in real time or on a scheduled basis.).
As per claim 5, Tal discloses the system of claim 1, wherein determining the set of road classifications for the set of road segments comprises:
determining a road classification for a particular road segment based on a plurality of images associated with the particular road segment (Tal: Paras. [0036], [0047]-[0051] disclose the concept of discarding or retaining/processing images of road segments associated with previous image frames containing road segments to determine classification.).
As per claim 8, Tal discloses the system of claim 1, wherein the set of one or more images are obtained from one or more vehicles having a location matching the set of road segments (Tal: Paras. [0029], [0047] disclose device 101 mounted on a vehicle 102 capturing the set of images as the vehicle travels along the road surface 14.).
As per claim 9, Tal discloses the system of claim 1, wherein the set of road classifications is an indication of a road condition (Tal: Para. [0031] disclose the resultant processed data 20 can also include metadata (e.g. descriptions/descriptors) of the objects 12 identified from the images 16 by the image processing instructions 905. For example, the descriptions/descriptors of the objects 12 can include object type (e.g. road sign, pothole, road debris, etc.), object size (e.g. 10 cm wide by 20 cm deep), etc.).
As per claim 10, Tal discloses the system of claim 9, wherein the road condition includes one or more of:
(i) a clear road, (ii) a presence of snow, presence of ice, (iii) a wet surface, a flooded road, (iv) amount of precipitation accumulation, (v) low visibility, (vi) a crash, (vii) traffic, (viii) construction, a lane closure (), road closure, (ix) a fire on or near the road, (x) the presence of emergency response vehicles such as police cars, fire trucks, and ambulances, (xi) objects on the road such as tires, automobile parts, or fallen cargo, oil slicks, (xii) an animal on the road, (xiii) a pedestrian on the road, (xiv) a cyclist on the road, pavement conditions such as rough, smooth, dirt, or gravel road, potholes, (xxiii) lighting conditions such as darkness or glare from the sun, and (xxv) posted speed limits including variable limits (Tal: Paras. [0118]-[0130] disclose the different types of road conditions including presence of snow.).
As per claim 11, Tal discloses the system of claim 1, wherein the one or more processors are further configured to:
capture an image of at least part of a particular road segment (Tal: Figs. 2, 4 & Paras. [0012], [0027] disclose capturing an image of particular road segments.);
query a classifier for a road classification of the particular road segment based at least in part on the image (Tal: Fig. 4 & Para. [0036] disclose using neural network 905 for detection and classification of objects 12 of interest in the acquired images 16 in order to infer (e.g. determine) what object(s) 12 are present in images 16 and/or the position of the object 12 in the images 16.);
determine whether the road classification satisfies one or more predefined criteria (Tal: Paras. [0031], [0036] disclose classified images not containing objects 12 (of interest) are excluded (e.g. the image discard data 19) from the resultant processed data 20 sent over the server 107 over the network 18.); and
in response to determining that the road classification satisfies the one or more predefined criteria, send to a server an indication of the road classification for the particular road segment (Tal: Figs. 2, 4 & Paras. [0027], [0036] disclose only selected data portions 20 (e.g. image frames 16 a,b,c,d—see FIG. 2) of the images 16 can be transmitted over the network 18 by the device 101 to a server 107 for subsequent processing/reporting, as further described below, such that image discard data 19 is excluded (see FIG. 4) from object data 21 transmitted to the server 107.).
As per claim 12, Tal discloses the system of one or more of claim 11, wherein the one or more predefined criteria includes a match between the road classification and one or more interesting road classifications (Tal: Paras. [0027], [0031], [0036] disclose only classified objects that are objects of interest 12 will be considered a match to send to the server 107 and classified images not containing objects 12 (of interest) are excluded.).
As per claim 13, Tal discloses the system of claim 12, wherein the one or more interesting road classifications correspond to road conditions that are deemed to have elevated risk (e.g., pothole) to a vehicle (Tal: Para. [0031] discloses the resultant processed data 20 can also include metadata (e.g. descriptions/descriptors) of the objects 12 identified from the images 16 by the image processing instructions 905. For example, the descriptions/descriptors of the objects 12 can include object type (e.g. road sign, pothole, road debris, etc.), object size (e.g. 10 cm wide by 20 cm deep), etc.).
As per claim 14, Tal discloses the system of claim 11, wherein in response to receiving the indication of the road classification for the particular road segment, the server stores the road classification in a geospatial database (Tal: Paras. [0066], [0154] disclose the Server(s) 107 can also associate incidents 12, through their GPS coordinates, to a road 14 network segment, which is a representation of a segment of a road 14, which typically includes geospatial and descriptive data, such as points, features and other fields—for example the class of the road (highway, local, regional), the street name, and/or the address range which it covers.).
As per claim 15, Tal discloses the system of claim 14, wherein the indication of the road classification for the particular road segment comprises (i) the road classification, and (ii) a current location of a vehicle from which the image is captured or a location at which the image was captured (Tal: Paras. [0139]-[0147] disclose longitude/latitude and detected object data.).
As per claim 16, Tal discloses the system of claim 14, wherein the indication of the road classification for the particular road segment comprises (i) the road classification, (ii) a current location of a vehicle from which the image is captured or a location at which the image was captured, and (iii) a date, time, and/or time zone associated with the image (Tal: Paras. [0139]-[0147] disclose a date and time associated with the image.).
As per claim 17, Tal discloses the system of claim 1, wherein the set of road classifications is determined based at least in part on obtaining vehicle data from one or more vehicles, the vehicle data comprising a current location of a vehicle and an indication of a road classification for the current location (Tal: Paras. [0139]-[0147] disclose for example, the direction to which the Vehicle 102 is travelling may be determined based on the Device's 101 sensors 700. Other examples of other data may include the road segment on which the incident was obtained, or the direction that the Vehicle 102 was facing, or a geo-zone in which the incident was obtained.).
As per claim 18, Tal discloses the system of claim 1, wherein the one or more processors are further configured to:
obtain, from the set of road classifications, a particular road classification for a particular road segment (Tal: Figs. 2, 4 & Paras. [0031], [0107]-[0108], [0154] disclose obtaining a road classification (e.g., road sign, pothole, road debris, etc.) of a road segment 14 from a set of classified road segment images 16a-d.);
determine that the particular road classification satisfies a predefined criteria (Tal: Paras. [0031], [0036] disclose classified images not containing objects 12 (of interest) are excluded (e.g. the image discard data 19) from the resultant processed data 20 sent over the server 107 over the network 18, thus the predefined criteria would be images having objects of interest.); and
in response to determining that the particular road classification satisfies the predefined criteria, perform an active measure (Tal: Figs. 2, 4 & Paras. [0027], [0036] disclose in response to objects of interest 12 being present in images 16, the images 16 can be transmitted over the network 18 by the device 101 to a server 107 for subsequent processing/reporting [i.e., perform an active measure].).
As per claim 21, Tal discloses the system of claim 1, wherein a processor of the one or more processors comprises a vehicle data server processor (Tal: Para. [0066] discloses server processing object data.).
As per claim 22, Tal discloses the system of claim 1, wherein a processor of the one or more processors comprises a vehicle event recorder processor (Tal: Paras. [0027]-[0030] disclose device 101 for capturing events.).
As per claims 23-24, the claim(s) recites analogous limitations to claim(s) 1 above, and is/are therefore rejected on the same premise.
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.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Tal in view of Terrazas et al., hereinafter referred to as Terrazas (US 2016/0063516 A1).
As per claim 6, Tal discloses the system of claim 5, wherein the road classification for the particular road segment corresponds to a predicted road classification (Tal: Paras. [0027], [0036] disclose predicted road classifications for corresponding road segments.).
However, Tal does not explicitly disclose “… classification … corresponds to a predicted … classification for a majority of images …”.
Further, Terrazas is in the same field of endeavor and teaches classification corresponds to a predicted classification for a majority of images (Terrazas: Paras. [0186]-[0188] disclose classifying areas of interest and/or points based on the number of matching reference images corresponding to features in an image, using a majority voting scheme.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Tal and Terrazas before him or her, to modify the classification algorithm of Tal to include the majority of images feature as described in Terrazas. The motivation for doing so would have been to improve inference accuracy with reduced computation load by providing a configuration that leverages characteristics from numerous images.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Tal in view of Huang et al., hereinafter referred to as Huang (US 2022/0092756 A1).
As per claim 7, Tal discloses the system of claim 5, wherein the road classification for the particular road segment corresponds to (Tal: Paras. [0027], [0036] disclose predicted road classifications for corresponding road segments.).
However, Tal does not explicitly disclose “… an average of a set of predicted … classifications.”.
Further, Huang is in the same field of endeavor and teaches an average of a set of predicted classifications (Huang: Para. [0037] discloses image classifications are ensembled (e.g., combined or otherwise analyzed as a grouped set), wherein image confidence scores may be averaged to generate a final classification for the region of the particular object.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Tal and Huang before him or her, to modify the classification algorithm of Tal to include the average set of predicted classifications feature as described in Huang. The motivation for doing so would have been to improve classification accuracy by providing a technique that is used to enhance training of a neural network model to detect less visible forms of features found in images captured under less than ideal conditions.
Claims 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Tal in view of Magnusson et al., hereinafter referred to as Magnusson (US 2020/0139976 A1).
As per claim 19, Tal discloses the system of claim 18 (Tal: Abstract),
However, Tal does not explicitly disclose “… wherein performing the active measure includes one or more of: (i) rerouting one or more vehicles that are (a) expected to pass through the particular road segment within a predetermined period of time, or (b) within a predefined vicinity of the particular road segment within the predetermined period of time; (ii) sending an alert to a vehicle that is (x) expected to pass through the particular road segment within the predetermined period of time, or (y) within the predefined vicinity of the particular road segment within the predetermined period of time; (iii) providing the alert to a user interface to be displayed at a client system; and (iv) adjusting an ADAS parameter.”
Further, Magnusson is in the same field of endeavor and teaches wherein performing the active measure includes one or more of:
(i) rerouting one or more vehicles that are (a) expected to pass through the particular road segment within a predetermined period of time, or (b) within a predefined vicinity of the particular road segment within the predetermined period of time;
(ii) sending an alert to a vehicle that is (x) expected to pass through the particular road segment within the predetermined period of time, or (y) within the predefined vicinity of the particular road segment within the predetermined period of time;
(iii) providing the alert to a user interface to be displayed at a client system; and
(iv) adjusting an ADAS parameter (Magnusson: Paras. [0002], [0036], [0038]-[0039] disclose alerting the driver/vehicle, adapting the vehicle to the road condition (e.g., automatic braking systems adapting to the friction on the road) or proposing the best route in a navigating system.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Tal and Magnusson before him or her, to modify the road condition detection system of Tal to include the adjusting ADAS feature as described in Magnusson. The motivation for doing so would have been to improve automated road condition monitoring by providing a configuration that enables advanced safety control protocols for autonomous vehicles.
As per claim 20, Tal discloses the system of claim 1 (Tal: Abstract),
However, Tal does not explicitly disclose “… wherein determining the set of road classifications for the set of road segments comprises: determining an aggregate road classification for a particular road segment based at least in part on a plurality of indications of the aggregate road classification for the particular road segment comprised in vehicle data obtained from a plurality of vehicles on, or having recently travelled on, the particular road segment.”
Further, Magnusson is in the same field of endeavor and teaches wherein determining the set of road classifications for the set of road segments comprises:
determining an aggregate road classification for a particular road segment based at least in part on a plurality of indications of the aggregate road classification for the particular road segment comprised in vehicle data obtained from a plurality of vehicles on, or having recently travelled on, the particular road segment (Magnusson: Paras. [0010], [0036], [0038]-[0039] disclose classifying road segments using aggregate road surface data from multiple vehicles travelling on the respective road segments.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Tal and Magnusson before him or her, to modify the road condition detection system of Tal to include the aggregate road classification feature as described in Magnusson. The motivation for doing so would have been to improve classification accuracy for road segments by leveraging a multitude of different quantifiable sources that facilitate inference.
Claim 25 is rejected under 35 U.S.C. 103 as being unpatentable over Tal in view of Hartmann et al., hereinafter referred to as Hartmann (US 2020/0406897 A1).
As per claim 25, Tal discloses the system of claim 2 (Tal: Abstract.),
However, Tal does not explicitly disclose wherein the potential risk is a potential weather-related risk including one or more of precipitation, snow, ice, or fog, for the particular geographic area.
Further, Hartmann is in the same field of endeavor and teaches wherein the potential risk is a potential weather-related risk including one or more of precipitation, snow, ice, or fog, for the particular geographic area (Hartmann: Paras. [0016], [0044], [0060], [0099] disclose classifying weather-related environmental influences and distinguishing between roadway conditions such as Snow, Black ice and further utilizes algorithms to recognize roadway conditions such as dry, wet, snowy, icy and hazardous situations.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Tal and Hartmann before him or her, to modify the classification algorithm of Tal to include the potential weather-related risk feature as described in Hartmann. The motivation for doing so would have been to improve the road classification system by providing precise assessments of the physical state and environmental conditions of the road surface.
Claim 27 is rejected under 35 U.S.C. 103 as being unpatentable over Tal in view of Hartmann in further view of Tal 230 et al., hereinafter referred to as Tal 230 (US 2022/0020230 A1).
As per claim 27, Tal discloses the system of claim 11, wherein:
the one or more predefined criteria (Tal: Paras. [0031], [0036] disclose classified images not containing objects 12 (of interest) are excluded (e.g. the image discard data 19) from the resultant processed data 20 sent over the server 107 over the network 18.);
However, Tal does not explicitly disclose “… predefined criteria comprises the road classification indicating an elevated weather-related risk to the vehicle; the elevated weather-related risk includes one or more of snow, ice, and flooding; and the machine learning model deployed at a vehicle-side client system is a lighter model trained on fewer features than a server-side machine learning model used to perform classifications with greater latency than the vehicle-side machine learning model.”
Further, Hartmann is in the same field of endeavor and teaches the one or more predefined criteria comprises the road classification indicating an elevated weather-related risk to the vehicle (Hartmann: Paras. [0016], [0044] disclose distinction of the following five relevant roadway conditions: Dry, Wet, Snow, Ice (black ice), Very wet (danger of aquaplaning) and classifying the roadway condition into one of the following five roadway condition classes: Snowy, Icy, Aquaplaning hazard.);
the elevated weather-related risk includes one or more of snow, ice, and flooding (Hartmann: Paras. [0016], [0044] disclose distinction of the following five relevant roadway conditions: Dry, Wet, Snow, Ice (black ice), Very wet (danger of aquaplaning) and classifying the roadway condition into one of the following five roadway condition classes: Snowy, Icy, Aquaplaning hazard.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Tal and Hartmann before him or her, to modify the classification algorithm of Tal to include the elevated weather-related risk to the vehicle feature as described in Hartmann. The motivation for doing so would have been to improve the road classification system by providing precise assessments of the physical state and environmental conditions of the road surface.
However, Tal-Hartmann do not explicitly disclose “… the machine learning model deployed at a vehicle-side client system is a lighter model trained on fewer features than a server-side machine learning model used to perform classifications with greater latency than the vehicle-side machine learning model.”.
Furthermore, Tal 230 is in the same field of endeavor and teaches the machine learning model deployed at a vehicle-side client system is a lighter model trained on fewer features than a server-side machine learning model used to perform classifications with greater latency than the vehicle-side machine learning model (Tal 230: Paras. [0109], [0113], [0129] disclose device 101 and the server 107a can have different variations, configurations, and parameters relating to the image processing instructions and neural network(s) 905 used, where the one or more of the neural networks 905 can be simplified for the purpose of reducing the memory and processing requirements. Such reduced neural networks are then used on the Device 101 [a lighter model trained on fewer features]. For example, the larger the model 'input shape' or resolution, the slower the images 16 will be processed, however the larger the 'input shape' resolution is, the more details will be retained in the image 16.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Tal-Hartmann and Tal 230 before him or her, to modify the road classification system of Tal-Hartmann to include the lighter model trained on fewer features than a server-side machine learning model feature as described in Tal 230. The motivation for doing so would have been to improve classification processing efficiency and speed by providing a configuration that facilitates the systems execution of the AI algorithms.
Allowable Subject Matter
Claim 26 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure and can be viewed in the list of references.
THIS ACTION IS MADE FINAL. 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 PEET DHILLON whose telephone number is (571)270-5647. The examiner can normally be reached M-F: 5am-1:30pm. 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, Sath V. Perungavoor can be reached at 571-272-7455. 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.
/PEET DHILLON/Primary Examiner
Art Unit: 2488
Date: 03-07-2026