DETAILED ACTION
Status of Claims
This Office action is in response to the amendment filed on 09/24/2025. Claims 12-13 were previously canceled. With the filed amendment, claims 2 and 11 have also been canceled. Claims 1 and 3-10 are currently pending and are presented for examination.
Response to Amendment/Arguments
The amendment filed 09/24/2025 has been entered and applicant’s arguments filed 09/24/2025 have been fully considered.
Regarding claim objections:
Applicant has argued that the claim objections are overcome by the filed amendment. The examiner notes that claim 1 is still objected to because of the amendment incorporating “the first road user” language from canceled claim 2.
Regarding claim rejections under 35 U.S.C. § 101:
Applicant has argued that the claims as amended should not be rejected under 35 U.S.C. § 101 because they do not recite a mental process and because the alleged mental process is integrated into a practical application. While the examiner maintains that the claims recite some steps that could be performed in the human mind, the examiner agrees that the amended step of outputting a control signal to control an operation integrates the abstract idea into a practical application. The claim rejections have been withdrawn accordingly.
Regarding claim rejections under 35 U.S.C. §§ 102 and 103:
Regarding the claim rejections under 35 U.S.C. §§ 102 and 103, applicant has argued that “Van Heukelom does not teach or suggest obtaining two separate covariance matrices (each with probabilities associated with the presence of a vehicle) and then performing a location-dependent superimposition of the probabilities of presence of the first road user as included with the first covariance matrix with the probabilities of presence of the second road user as included with the second covariance matrix.” Applicant has argued that the heat map of Van Heukelom “could be associated with a matrix but is always associated with an object in the environment, not the moving vehicle,” and further argued that “Since Van Heukelom at best only has one matrix that represents an object, the claimed superposition as between two matrices cannot occur in Van Heukelom’s system. Even if two objects had a heat map, the moving vehicle does not and any comparison is made between an object and the vehicle.”
Regarding the argument that Van Heukelom fails to disclose two separate covariance matrices for a road user and a second road user, the examiner respectfully disagrees since under the broadest reasonable interpretation of the claims, the recited “road user” and “second road user” encompass two objects in the surrounding environment of a host vehicle (i.e., neither road user has to be the host vehicle). Therefore, Van Heukelom discloses the creation of two covariance matrices representing the probabilities of presence of the road user and the second road user since Van Heukelom ¶ 13 discloses that “The sensor data captured by the vehicle representing objects in the environment can be used to generate a discretized probability distribution representing possible locations of the object in the environment over time. For example, a prediction system can determine a covariance matrix associated with an uncertainty of an object at an initial state or time.” Based on this disclosure, a person having ordinary skill in the art would have understood that this step of generating a covariance matrix could be performed for each object in the environment.
Applicant’s remaining arguments are moot in view of the new grounds of rejection under 35 U.S.C. § 103 which are necessitated by the filed amendment.
Claim Objections
Claim 1 is objected to because of the following informalities:
It appears that the word “and” should be added before the last paragraph of claim 1.
In line 17 of claim 1, it appears that “the first road user” should be changed to “the
In the last paragraph of claim 1, it appears that “the driver assist system” should be changed to “the driver assistance system.”
Appropriate correction is required.
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.
Claims 1, 3-4 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Van Heukelom et al. (US 2020/0174481 A1), hereinafter referred to as Van Heukelom, in view of Obata et al. (US 2017/0210379 A1).
Regarding claim 1:
Van Heukelom discloses the following limitations:
“A method for determining an adverse traffic situation of a road user, the method comprising: acquiring first position information indicating a first position of the road user and first uncertainty information indicating a first position detection uncertainty of the road user; acquiring second position information for ascertaining a second position of a second road user and second uncertainty information indicating a second position detection uncertainty of the second road user.” (Van Heukelom ¶ 81: “prediction component 728 can generate one or more probability maps representing prediction probabilities of possible locations of one or more objects in an environment. For example, the prediction component 728 can generate one or more probability maps for vehicles, pedestrians, animals, and the like within a threshold distance from the vehicle 702.”)
“converting the first uncertainty information into a first covariance matrix for describing a first location-dependent probability of presence of the road user in connection with a first position of the road user; converting the second uncertainty information road user into a second covariance matrix for describing a second location-dependent probability of presence of the second road user in connection with a second position of the second road user.” (Van Heukelom ¶ 13: “The sensor data captured by the vehicle representing objects in the environment can be used to generate a discretized probability distribution representing possible locations of the object in the environment over time. For example, a prediction system can determine a covariance matrix associated with an uncertainty of an object at an initial state or time. The covariance matrix can include a variance with respect to a longitudinal and/or lateral position in the environment.” Further, Van Heukelom ¶ 18: “individual discretized probability distributions can be generated for individual objects in the environment.”)
“and determining the presence of an adverse traffic situation [based on] performing a location-dependent superimposition.” (Van Heukelom ¶¶ 62-63 and FIG. 5 shown below: “the planning system of the vehicle 320 can determine an overlapping region 516 representing an overlap between the region 320** and the aggregated prediction probabilities 514. Further, the planning system of a vehicle 320 can determine a region probability 518 associated with the overlapping region 516. In some instances, the region probability 518 associated with the N-th time TN can represent a summing, accumulation, integration, or aggregation of the portion of the aggregation prediction probabilities 514 associated with the overlapping region 516. In some examples, if an individual region probability 510 or 518 is above a threshold the trajectory 504 can be rejected as representing too high of a risk associated with a collision or a near-collision.”)
PNG
media_image1.png
691
466
media_image1.png
Greyscale
“outputting a control signal to an electronic control device of a driver assistance system or an automated driving control system to control an operation of the driver assist system or the automated driving control system based on presence of the adverse traffic situation.” (Van Heukelom ¶ 22: “a trajectory can be selected based at least in part on the trajectory probability, and the vehicle can be controlled to follow the trajectory to traverse the environment.” Also, Van Heukelom ¶ 80: “the vehicle computing device 704 can include one or more system controllers 726, which can be configured to control steering, propulsion, braking, safety, emitters, communication, and other systems of the vehicle 702.” Further, Van Heukelom ¶ 29 discloses that the method can be applied to “a vehicle capable of performing all safety critical functions for the entire trip, with the driver (or occupant) not being expected to control the vehicle at any time” or can be used for “vehicles that need to be manually controlled by a driver at all times.”)
Although Van Heukelom discloses the prediction of a collision between a host vehicle and a second road user, Van Heukelom does not specifically disclose “determining the presence of an adverse traffic situation between the road user and the second road user based on the first covariance matrix and the second covariance matrix, wherein the determining comprises performing a location-dependent superimposition of the probabilities of presence of the first road user as described by the first covariance matrix with the probabilities of presence of the second road user as described by the second covariance matrix.” However, this limitation is taught by Obata. (Obata ¶¶ 83-86 and FIG. 4 reproduced below disclose that estimation of a collision probability can be performed based on the predicted centers of covariance matrices for multiple vehicles around a user’s vehicle, where “the center of an ellipse in the figure represents a predicted position of movement, and the area of an ellipse represents a standard deviation of a prediction error covariance matrix. In this case, it is estimated, from overlap between the predicted ellipses, that the vehicle 60b collides with the vehicle 60a.”)
PNG
media_image2.png
714
336
media_image2.png
Greyscale
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Van Heukelom by estimating a collision probability based on a superimposition of covariance matrices of the road user and the second road user as taught by Obata with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this because Obata ¶¶ 98 and 110 teach that with this modification, a collision possibility of a host vehicle can be identified based on the collision analysis of the surrounding vehicles, and a braking command can be executed by the host vehicle to avoid any identified possible collisions.
Regarding claim 3:
The combination of Van Heukelom and Obata teaches “The method as claimed in claim 1,” and Van Heukelom further teaches “wherein the determining comprises performing a matrix operation of the first covariance matrix and the second covariance matrix.” (Van Heukelom ¶ 14: “In some instances, the possible locations of the object in the future based on covariance matrices can be represented as Gaussian distributions that can be discretized into a cells or portions of the environment proximate to the object or proximate to the vehicle.” Further, Van Heukelom ¶ 18: “individual discretized probability distributions can be generated for individual objects in the environment and aggregated to generate an aggregated discretized probability distributions representing aggregated prediction probabilities of a plurality of objects in an environment. For example, discretized probability distributions for objects can be aligned and individual prediction probabilities can be summed to represent summed or aggregated prediction probabilities.”)
Regarding claim 4:
The combination of Van Heukelom and Obata teaches “The method as claimed in claim 1,” and Van Heukelom further teaches “wherein the determining comprises performing a linear combination of the first covariance matrix and the second covariance matrix or an addition or subtraction of the first covariance matrix and the second covariance matrix” (Van Heukelom ¶ 18: “discretized probability distributions for objects can be aligned and individual prediction probabilities can be summed to represent summed or aggregated prediction probabilities.” This at least teaches to perform an addition of the matrices as claimed.)
Note that under the broadest reasonable interpretation (BRI) of claim 4, consistent with the instant specification, “performing a linear combination of the first covariance matrix and the second covariance matrix or an addition or subtraction of the first covariance matrix and the second covariance matrix” is treated as an alternative limitation. Applicant has elected to use the word “or” in the claim language, and therefore, the BRI covers the scenario in which only one of the limitations applies. Accordingly, while only the addition of the matrices has been addressed here, the claim is still rejected in its entirety.
Regarding claim 6:
The combination of Van Heukelom and Obata teaches “The method as claimed in claim 1,” and Obata additionally teaches “wherein the determining comprises: determining a risk area describing an area impaired for the road user determined; and assessing location-dependent superimposition of the probabilities of presence of the road user and the second road user within the risk area, described by the first covariance matrix and the second covariance matrix.” (Obata ¶ 86 and FIG. 4 disclose the use of ellipses surrounding each vehicle when superimposing the covariance matrices, where “the center of an ellipse in the figure represents a predicted position of movement, and the area of an ellipse represents a standard deviation of a prediction error covariance matrix. In this case, it is estimated, from overlap between the predicted ellipses, that the vehicle 60b collides with the vehicle 60a.” Note that the examiner interprets the “risk area describing an area impaired for the road user” as encompassing any area surrounding the road user, where the “impaired” limitation conveys that there is a risk of collision if another road user enters the risk area; this interpretation is consistent with ¶ 17 and FIG. 1B of the specification, which describe the risk area as a rectangular area surrounding the road user and representing a safety distance that extends from the road user.)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method of Van Heukelom by using risk areas surrounding the vehicles when performing the matrix superimposition as taught by Obata with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this because Obata ¶ 86 teaches that with this modification, a collision can be predicted if there are overlapping risk areas of multiple vehicles.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Van Heukelom in view of Obata as applied to claim 1 above, and further in view of Takhirov (US 2019/0234751 A1).
Regarding claim 5:
The combination of Van Heukelom and Obata teaches “The method as claimed in claim 1,” but does not specifically teach “wherein the determining comprises applying correlation assumptions of position detection uncertainty of the road user and position detection uncertainty of the second road user.” However, Takhirov does teach this limitation. (Takhirov ¶ 34: “a map 200 of an environment comprising one or more first objects 201-209 each associated with a probability model may be obtained, and one or more global factors and local factors may be obtained to update the probability models. In one global factor example, a weather condition affecting the entire environment may be accounted for as a global factor to update the respective probability models. In one local factor example, the one or more of the first objects along the navigation path 3 include first objects 206-209, and their properties (e.g., positions, moving speeds, moving directions) are monitored as local factors and used to update the probability models since their real-time status are more likely to affect a second object travelling along path 3.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method disclosed by the combination of Van Heukelom and Obata by accounting for factors such as weather conditions and environmental objects when assessing the position uncertainty of objects as taught by Takhirov with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this since Takhirov ¶ 30 teaches that this can help to improve accuracy when mapping a traffic environment.
Claims 7-8 are rejected under 35 U.S.C. 103 as being unpatentable over Van Heukelom in view of Obata as applied to claim 6 above, and further in view of Min (US 2020/0079364 A1).
Regarding claim 7:
The combination of Van Heukelom and Obata teaches “The method as claimed in claim 6,” but does not specifically teach “wherein the risk area corresponds to a detection area of a surroundings detection device of the road user.” However, Min does teach this limitation. (Min ¶ 8: “a vehicle driving control apparatus includes a position estimation processor that tracks a vehicle detected by a front radar or a rear-side radar and estimates a position of the vehicle in a blind spot located between a detection area of the front radar and a detection area of the rear-side radar.” The “blind spot” reads on the risk area as claimed.)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method disclosed by the combination of Van Heukelom and Obata by determining whether another road user is entering a blind spot of an ego vehicle as taught by Min with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this since Min ¶ 8 teaches that with this modification, the ego vehicle can be controlled “such that the ego vehicle follows a path where a collision with the vehicle is avoided.”
Regarding claim 8:
The combination of Van Heukelom, Obata, and Min teaches “The method as claimed in claim 7,” and Obata also teaches the method “further comprising determining a scalar probability value using the location-dependent superimposition of the probabilities of presence of the road user and the second road user within the risk area.” (Obata ¶¶ 83-84 disclose estimating the collision possibility by calculating a scalar probability and comparing it to a threshold.)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method disclosed by the combination of Van Heukelom and Min by using a scalar probability value as taught by Obata with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this because Obata ¶¶ 83-84 teaches that the scalar probability can be compared to a threshold. A person having ordinary skill in the art would have recognized that using a scalar probability that could be compared to a threshold would provide an objective measure when identifying whether a collision is predicted to occur.
Claims 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Van Heukelom in view of Obata and Min as applied to claim 8 above, and further in view of Wang et al. (the article “Fast Risk Assessment for Autonomous Vehicles Using Learned Models of Agent Futures”), hereinafter referred to as Wang.
Regarding claim 9:
The combination of Van Heukelom, Obata, and Min teaches “The method as claimed claim 8,” but does not specifically teach the method “further comprising determining the scalar probability value by way of univariate conditioning.” However, Wang does teach this limitation. (Wang § IV(D) first paragraph: “for any measurable function g, an univariate SOS program can be used to upper-bound P(g(xt) ≤ 0) – the SOS program is univariate in the sense that it searches for a polynomial in a single indeterminant, not in the sense that there is only one decision variable.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method disclosed by the combination of Van Heukelom, Obata, and Min by using univariate conditioning to calculate the probability value as taught by Wang with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this because Wang § IV(D) first paragraph teaches that “the key disadvantages of SOS, scalability and conservatism, are not as limiting for univariate SOS because: 1) the number of decision variables in the resulting SDP scales quadratically w.r.t. the order of the polynomial we are searching for and 2) the set of non-negative univariate polynomials is equivalent to the set of univariate SOS polynomials, allowing univariate SOS to explore the full space of possible solutions.”
Regarding claim 10:
The combination of Van Heukelom, Obata, Min, and Wang teaches “The method as claimed in claim 9,” and Obata further teaches “wherein the determining comprises determining the presence of the adverse traffic situation between the road user and the second road user if the scalar probability value is equal to or greater than a predefined threshold value.” (Note that this determination step is a contingent limitation that is not required consistent with MPEP 2111.04, since it only applies “if the scalar probability value is equal to or greater than a predefined threshold value.” Regardless, the examiner notes that this limitation is taught by Obata ¶¶ 83-84, which disclose estimating the collision possibility by calculating a scalar probability and comparing it to a threshold.)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to modify the method disclosed by the combination of Van Heukelom, Min, and Wang by predicting a collision occurrence between road users by comparing a scalar probability to a set threshold value as taught by Obata with a reasonable expectation of success. A person having ordinary skill in the art could have been motivated to do this based on the recognition that this would provide an objective metric for deciding whether or not a collision is predicted to occur.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Madison R Inserra whose telephone number is (571)272-7205. The examiner can normally be reached Monday - Friday: 9:30 AM - 6:30 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Aniss Chad can be reached at 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.
/Madison R. Inserra/Examiner, Art Unit 3662