DETAILED ACTION
This is a response to the Amendment to Application # 18/255,849 filed on February 11, 2026 in which no claims were amended.
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 4-7, 13, 15, and 17 are pending, which are rejected under 35 U.S.C. § 103.
Claim Rejections - 35 U.S.C. § 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 of this title, 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.
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. Applicants are advised of the obligation under 37 C.F.R. § 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 4-7, 13, 15, and 17 are rejected under 35 U.S.C. § 103 as being unpatentable over Peng et al., US Publication 2022/0306147 (hereinafter Peng) in view of Hazard et al., US Patent 11,941,542 (hereinafter Hazard).
Regarding claim 4, Peng discloses a method for operating an at least semi-autonomously driving vehicle, comprising “generating a representation of a situation the vehicle is in using measurement data of at least one sensor carried by the at least semi-autonomously driving vehicle.” (Peng ¶¶ 90-91). Additionally, Peng discloses “mapping the representation of the situation to a probability distribution by way of an algorithm, said probability distribution specifying a probability for every driving maneuver from a predefined catalog of available driving maneuvers” (Peng ¶¶ 74, 89, 102) where the sensor data is mapped to engineering parameters such as Time-To-Collision (TTC) values (Peng ¶ 102). This may be performed using a variety of algorithms such as the Kullback-Leibler divergence. (Peng ¶ 89). Further, Peng discloses “independently of the algorithm, determining a subset of at least one disallowed driving maneuver that is disallowed in the situation the at least semi-autonomously driving vehicle is in” (Peng ¶ 104, see also Fig. 11) by calculating, independently of the Kullback-Leibler divergence, threshold values for the parameters that are used to exclude certain driving maneuvers. Moreover, Peng discloses “selecting a selected driving maneuver from the predefined catalog of available maneuvers based on the probability distribution, the selected driving maneuver being in the subset of the at least one disallowed driving maneuver” (Peng ¶ 109) by determining, at step 1128, the action is not greater than the threshold value (i.e., the selected driving maneuver is in the subset of disallowed driving maneuvers). Likewise, Peng discloses “automatically selecting an alternative driving maneuver from the predefined catalog of available driving maneuvers based on the probability distribution” (Peng ¶ 109, Fig. 11) where the dotted line from step 1128 indicates that the process proceeds to step 1120 to select another operation. Finally, Peng discloses “operating the at least semi-autonomously driving vehicle to execute the alternative driving maneuver” (Peng ¶ 109) where the maneuver is performed when the operational value is greater than the threshold.
Peng does not appear to explicitly disclose “mapping the representation of the situation to a probability distribution by way of a trained machine learning model, said probability distribution specifying a probability for every driving maneuver from a predefined catalog of available driving maneuvers” or “independently of the machine learning model, determining a subset of at least one disallowed driving maneuver that is disallowed in the situation the at least semi-autonomously driving vehicle is in.”
However, Hazard discloses that it is well known to use a neural network (i.e., a trained machine learning model) to select an action for a vehicle using the Kullback-Leibler divergence algorithm. (Hazard col. 10, ll. 6-28). Thus, a person of ordinary skill in the art prior to the effective filing date of the present invention would have recognized that the machine learning model utilizing the Kullback-Leibler divergence algorithm of Hazard would be used in place of the non-machine learning usage of the Kullback-Leibler divergence algorithm in Peng. As a result, the combination of Peng and Hazard at least teaches and/or suggests the claimed limitations “mapping the representation of the situation to a probability distribution by way of a trained machine learning model, said probability distribution specifying a probability for every driving maneuver from a predefined catalog of available driving maneuvers” and “independently of the machine learning model, determining a subset of at least one disallowed driving maneuver that is disallowed in the situation the at least semi-autonomously driving vehicle is in,” rendering them obvious.
Peng and Hazard are analogous art because they are from the “same field of endeavor,” namely that of vehicle action selection.
Prior to the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Peng and Hazard before him or her to modify the Kullback-Leibler divergence algorithm of Peng to include the machine learning of Hazard.
The motivation for doing so would have been that the use of machine learning is well-known to those of ordinary skill in the art provides the ability to process larger amounts of data in a faster manner than non-machine learning methods.
Regarding claim 5, the combination of Peng and Hazard discloses the limitations contained in parent claim 4 for the reasons discussed above. In addition, the combination of Peng and Hazard discloses “wherein the determining of the subset of the at least one disallowed driving maneuver is based on information retrieved from a digital location-resolved map based on a current location of the vehicle” (Peng ¶¶ 102, 104) where the disallowed driving maneuvers are determined based on whether or not the parameters meet threshold values (Peng ¶ 104), which may be based on the location of the vehicle, both within a lane and a geographic location. (Peng ¶ 102).
Regarding claim 6, the combination of Peng and Hazard discloses the limitations contained in parent claim 4 for the reasons discussed above. In addition, the combination of Peng and Hazard discloses “wherein the at least one disallowed driving maneuver is a driving maneuver that presents a risk of at least one of: departing a roadway, violating general traffic rules, violating special conditions for autonomous driving operation, and the at least semi-autonomously driving vehicle colliding with another vehicle or other object” (Peng ¶ 102) where the disallowed driving maneuver present a risk of collision with another vehicle.
Regarding claim 7, the combination of Peng and Hazard discloses the limitations contained in parent claim 4 for the reasons discussed above. In addition, the combination of Peng and Hazard discloses “wherein the at least one disallowed driving maneuver includes at least one of: a lane change leading to departing a roadway, a lane change to a currently inaccessible lane, at least one of an acceleration and an overtaking maneuver prohibited by traffic rules, and driving behind another vehicle that is currently located behind the at least semi- autonomously driving vehicle” (Peng ¶ 102) where a left turn is a lane change leading to departing the current roadway and on to another roadway.
Regarding claim 13, the combination of Peng and Hazard discloses the limitations contained in parent claim 4 for the reasons discussed above. In addition, the combination of Peng and Hazard discloses “[a] non-transitory machine-readable storage medium comprising program instructions that, when executed by one or more computers, cause the one or more computers to execute the method according to claim 4.” (Peng ¶ 96).
Regarding claim 15, the combination of Peng and Hazard discloses the limitations contained in parent claim 13 for the reasons discussed above. In addition, the combination of Peng and Hazard discloses “[a] computer comprising the non-transitory machine-readable storage medium according to claim 13.” (Peng ¶¶ 95-96).
Regarding claim 17, the combination of Peng and Hazard discloses the limitations contained in parent claim 4 for the reasons discussed above. In addition, the combination of Peng and Hazard discloses “wherein the automatically selecting of the alternative driving maneuver includes repeating the selecting of the alternative driving maneuver until the alternative driving maneuver is not in the subset of the at least one disallowed driving maneuver” (Peng ¶ 109, Fig. 11) where the dotted line from step 1128 indicates that the process proceeds to step 1120 to select another operation.
Response to Arguments
Applicant's arguments filed February 11, 2026 have been fully considered but they are not persuasive.
Regarding the rejection of claim 4 under 35 U.S.C. § 103, Applicant first argues “Peng, therefore, discloses evaluating one single maneuver for a determination of whether that single maneuver can be executed” and concludes that “Peng does not teach or suggest ‘mapping the representation of the situation to a probability distribution …., said probability distribution specifying a probability for every driving maneuver from a predefined catalog of available driving maneuvers.’” (Remarks 6). The examiner disagrees.
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., the requirement for more than a single maneuver) are not recited in the rejected claims. 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).
Additionally, it is the examiner’s duty to give claims “their broadest reasonable interpretation consistent with the specification.” See MPEP § 2111, citing Phillips v. AWH Corp., 415 F.3d 1303, 75 USPQ2d 1321 (Fed. Cir. 2005). Further, if the specification is silent to the meaning of claim terminology, “words of the claim must be given their plain meaning.” See MPEP § 2111.01.
Under the broadest reasonable interpretation of this limitation, a catalog of a single maneuver is within the scope.
However, even if a plurality of maneuvers was required, Peng discloses this. Peng explicitly generates a probability distribution plot of both “reject events and accept events.” (Peng ¶ 74). Thus, Peng envisions a situation in which at least two events are included. Further, Peng discloses that these events are under different circumstances (Peng ¶ 73), and, thus, even if they are all “left-hand turns,” they are different left-hand turns and, therefore, different maneuvers.
Therefore, Applicant’s argument is unpersuasive.
Applicant next argues that “Peng does not determine any disallowed maneuvers independently of this algorithm” and, therefore, does not disclose “independently of the machine learning model, determining a subset of at least one disallowed driving maneuver that is disallowed in the situation the at least semi-autonomously driving vehicle is in.” (Remarks 6-7). The examiner disagrees.
Peng, at Fig. 11, (reproduced below) shows that these steps are independent of each other.
PNG
media_image1.png
700
510
media_image1.png
Greyscale
The calculation of the subset of disallowed driving maneuvers was mapped to step 1112, as discussed in Peng ¶ 104. Thus use of the Kullback-Leibler divergence occurs at step 1108, as discussed in Peng ¶ 103. As can clearly be seen in the flow chart, there is no connection between steps 1108 and 1112. Thus, these steps are “independent” of each other.
Therefore, Applicant’s argument is unpersuasive.
Applicant next argues that Peng does not disclose “automatically selecting an alternative driving maneuver” because “this dotted line [of Peng Fig. 11] simply means the analysis of the threshold value, operational information, and determination of whether to execute the same maneuver is repeated.” (Remarks 7). The examiner disagrees.
Applicant’s argument is based on an erroneous premise—namely that Peng only analyzes a single maneuver. As has been discussed above, Peng discloses a plurality of maneuvers. Therefore, Applicant’s argument is unpersuasive.
Applicant next appears to argues Hazard cannot be “reasonably be combined” with Peng to teach or suggests the claimed machine learning model” because the Kullback-Leibler divergence of each reference are used for different tasks. (Remarks 8).
In response to applicant's argument that the Kullback-Leibler divergences of each reference are used differently, the test for obviousness is not whether the features of a secondary reference may be bodily incorporated into the structure of the primary reference; nor is it that the claimed invention must be expressly suggested in any one or all of the references. Rather, the test is what the combined teachings of the references would have suggested to those of ordinary skill in the art. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981).
Therefore, Applicant’s argument is unpersuasive.
Applicant next argues that Hazard does not “remedy any of the deficiencies of Peng noted above.” (Remarks 8). Applicant’s argument is unpersuasive for the reasons discussed above.
Regarding the rejection of claims 5-7, 13, 14, and 17 under 35 U.S.C. § 103, Applicant argues that these claims are allowable for depending on claim 4. (Remarks 9). Applicant’s argument is unpersuasive for the reasons discussed above.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 C.F.R. § 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 C.F.R. § 1.17(a)) pursuant to 37 C.F.R. § 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 ANDREW R DYER whose telephone number is (571)270-3790. The examiner can normally be reached Monday-Thursday 7:30-4:30.
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, Aniss Chad can be reached on 571-270-3832. 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.
/ANDREW R DYER/Primary Examiner, Art Unit 3662