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 .
Response to Arguments
Applicant’s arguments, filed 12/5/2025, have been fully considered and the examiner’s responses are given below.
The claim objections are withdrawn.
The 112(b) rejections are withdrawn.
The 35 U.S.C. 101 rejections are withdrawn.
Applicant’s amendments of the independent claims regarding controlling a movement of a vehicle based on the trajectory is a practical application and overcomes the 35 U.S.C. 101 rejection.
The 35 U.S.C. 103 rejections are withdrawn, however new grounds is presented below.
No response has been provided by the examiner because the applicant has not provided any substantial arguments.
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 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.
Claims 1 and 3 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US 20230298362 A1) in view of Ma (US 10832439 B1) and Zheng (US 20180033148 A1).
Regarding claim 1, Zhang discloses a system comprising (Paragraphs 0032-0036);
one or more processors; and one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising (Paragraphs 0122-0125);
receiving sensor data associated with a vehicle traversing an environment along a path (Paragraphs 0032-0036);
one or more of receiving or determining, based on the sensor data, a lane boundary associated with the path (Paragraph 0032, 0036);
determining a representative line associated with the polygon (Paragraphs 0101-0111; Representative line is mapped to link);
determining a set of points along the representative line (Paragraph 0051, Figs. 3A-3B; Representative line is mapped to road link segment 305);
determining a set of intersections of a set of lines with the lane boundary, a line of the set of lines originating at a point of the set of points and extending laterally from the representative line (Paragraphs 0060, 0075, Fig. 4A);
determining, based on the first cluster, a representation of the lane boundary (Paragraphs 0059-0068, 0075; “identify lane marking detections 401a, 401d each intersecting one of the perpendicular lines thereby constituting qualified lane marking detections/lines”);
associating the representation of the lane boundary with a map (Paragraph 0032, 0068, Fig. 1);
and providing the map to a second system, wherein the second system is configured to generate a trajectory based on the map (Paragraph 0032, 0068, Fig. 1; “examples uses cases for using the output of the mapping platform 101 include, but is not limited to, providing a route for navigation (e.g., via a user interface), route determination, lane level speed determination, operating the vehicle along a lane level route, route travel time determination, lane maintenance, route guidance, provision of traffic information/data, provision of lane level traffic information/data, vehicle trajectory determination and/or guidance, route and/or maneuver visualization, and/or the like”).
and control a movement of a vehicle based on the trajectory (Paragraph 0032, 0068, 0086, Fig. 1; “route determination, lane level speed determination, operating the vehicle along a lane level route, route travel time determination, lane maintenance, route guidance, provision of traffic information/data, provision of lane level traffic information/data, vehicle trajectory determination and/or guidance, route and/or maneuver visualization, and/or the like).
Zhang does not specifically state determining, based at least in part on a set of drivable areas detected while traversing the path, a polygon.
However, Ma teaches determining, based at least in part on a set of drivable areas detected while traversing the path, a polygon (Abstract, Col. 1 Line 66 – Col. 2 Line 36, Col. 18 Line 11 – Col. 18 Line 58).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with determining a polygon based on the drivable areas detected while traversing a path of Ma with a reasonable expectation of success. One of ordinary skill in the art would understand that polygons can be used to determine locations of objects and lane markers on the road. This allows the scene to be transformed from a global system to a local segment-based coordinate system which enhances scene understanding. One would have been motivated to combine Zhang with Ma as this achieves efficient scene processing. As stated in Ma, “the techniques described with reference to FIGS. 7 and 8 may determine road and/or lane segments associated with entities based on these global coordinates. However, for planning at the autonomous vehicle, a segment-based coordinate system, such as the s,t coordinate system may be useful” (Col. 20 Line 51 – Col. 21 Line 7).
Zhang does not specifically state determining, based on clustering the set of intersections, a first cluster representing a first subset of the set of intersections, wherein clustering the set of intersections is based on a set of input features representing a set of curvature measures associated with the set of intersections.
However, Zheng teaches determining, based on clustering the set of intersections, a first cluster representing a first subset of the set of intersections, wherein clustering the set of intersections is based on a set of input features representing a set of curvature measures associated with the set of intersections (Paragraph 0070-0071; “edge points meeting a first pre-determined condition are in the same group, the first pre-determined condition includes that vertical coordinates of two points are adjacent, a distance difference between horizontal coordinates of the two points is less than a first distance threshold and a gradient angle difference is less than a threshold of gradient angle”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with clustering the intersections based on input features representing the curvature of Zheng with a reasonable expectation of success. One of ordinary skill in the art would understand that grouping clusters of intersections allows the machine learning model to quickly recognize lane boundaries without having to process the entire image. One would have been motivated to combine Zhang with Zheng as this improves lane boundary detection efficiency. As stated in Zheng, “since there is no need to perform analysis and recognition on the entire image with a machine learning model during detecting the lane boundaries, a calculation for the process of detecting the lane boundaries is simpler, and calculation resources and time consumed in the process of detecting the lane boundaries are reduced. Therefore, the lane boundary can be detected accurately and quickly” (Paragraph 0068).
Regarding claim 3, Zhang discloses determining the representation of the lane boundary is further based at least in part on: a curvature of the lane boundary (Paragraphs 0047-0048).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang, Ma, and Zheng, as applied to claim 1 above, and further in view of Park (US 12373689 B2).
Regarding claim 2, Zhang discloses determining a representative line from a polygon.
Zhang does not specifically state determining the representative line comprises: determining a medial axis associated with the polygon.
However, Park teaches determining the representative line comprises: determining a medial axis associated with the polygon (Col. 6 Lines 1-17).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with determining a representative line from a medial axis of a polygon of Park with a reasonable expectation of success. One of ordinary skill in the art would understand that polygons can represent a road lane and therefore the medial axis of the polygon represents the center line of a lane. This center line of a lane is recognized and used for vehicle navigation. One would have been motivated to combine Zhang with Park as this achieves autonomous vehicles efficiently recognizing the environment. As stated in Park, “less compute and time intensive post-processing techniques—such as clustering and temporal smoothing—may be executed to determine landmark locations and poses with precision and in real-time. As a result, and in contrast to conventional systems, the control points may be regressed similarly to an object detection approach, and the control points may then be used to reconstruct the curve corresponding to the landmark—e.g., lane line, road boundary line, crosswalk, pole, text, etc. —for each of the landmarks in a field of view of each of one or more sensors of a vehicle” (Col. 1 Line 63 – Col. 2 Line 15).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang, Ma, and Zheng, as applied to claim 1 above, and further in view of Yamashita (US 20010012981 A1).
Regarding claim 4, Zhang discloses a representative line.
Zhang does not specifically state the operations further comprising: removing a portion of the representative line associated with a junction.
However, Yamashita teaches the operations further comprising: removing a portion of the representative line associated with a junction (Paragraphs 0038-0041, 0070-0071).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with removing a portion of the representative line associated with a junction of Yamashita with a reasonable expectation of success. One of ordinary skill in the art would understand that a representative line can represent a center line of a lane. The representative line can extend into a junction, which causes the shape of the junction to be abnormal. Deleting the representative line in the junction allows the shape of the junction to closer to the actual shape in a map. One would have been motivated to combine Zhang with Yamashita as this achieves a more accurate map. As stated in Yamashita, “accessories among those belonging to the intersection-connected links that extend along the links, such as center lines, lanes, side strips, and sidewalls, portions of these accessories that overlap the generated intersection shape are deleted. This prevents these accessories from protruding into the area of the intersection, and thus the resultant intersection shape is closer to the actual shape” (Paragraph 0039).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang, Ma, and Zheng, as applied to claim 1 above, and further in view of Eriksson (US 20240425056 A1).
Regarding claim 5, Zhang discloses determining the representation of the lane boundary comprises (Paragraphs 0055-0060, Fig. 4A);
determining, based at least in part on a cluster that is determined based at least in part on the set of intersections (Paragraphs 0055-0060, Fig. 4A).
Zhang does not specifically state a polynomial curve having a minimal distance to the cluster.
However, Eriksson teaches a polynomial curve having a minimal distance to the cluster (Paragraph 0091; Minimal distance is taught by fitting).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with determining a polynomial curve having a minimal distance to the cluster of Eriksson with a reasonable expectation of success. One of ordinary skill in the art would understand that a polynomial curve can be fit to clusters of lane markers. The compatibility of two clusters can be determined by checking the fraction of inliers for each cluster for the polynomial curve. This allows lane markers to be more accurately determined by only using compatible lane marking clusters. One would have been motivated to combine Zhang with Eriksson as this improves accuracy in lane marking detection. As stated in Eriksson, “Thus, increasing the accuracy and redundancy in road estimation systems may therefore be crucial for improving driver safety and comfort. The herein disclosed technology seeks to mitigate, alleviate or eliminate one or more of the above-identified deficiencies and disadvantages in the prior art to address various problems relating to performance in complex environments and redundancy” (Paragraphs 0004-0005).
Claims 6-8, 10, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US 20230298362 A1) in view of Zheng (US 20180033148 A1).
Regarding claim 6, Zhang discloses one or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising (Paragraphs 0122-0125);
receiving first data associated with a drivable surface associated with a road (Paragraphs 0032-0036);
determining, based on the first data, a reference line associated with the drivable surface, wherein the reference line traverses along the road (Paragraphs 0033-0034, 0051-0054, Figs. 3A-3B, 4A);
determining, based on the cluster, representation of a lane boundary (Paragraphs 0055-0068, 0075; “identify lane marking detections 401a, 401d each intersecting one of the perpendicular lines thereby constituting qualified lane marking detections/lines”);
associating the first representation with a map (Paragraph 0032, 0068, Fig. 1);
and providing the map to a system configured to generate a trajectory based on the map (Paragraph 0032, 0068, 0086, Fig. 1; “examples uses cases for using the output of the mapping platform 101 include, but is not limited to, providing a route for navigation (e.g., via a user interface), route determination, lane level speed determination, operating the vehicle along a lane level route, route travel time determination, lane maintenance, route guidance, provision of traffic information/data, provision of lane level traffic information/data, vehicle trajectory determination and/or guidance, route and/or maneuver visualization, and/or the like”);
and control a movement of a vehicle based on the trajectory (Paragraph 0032, 0068, 0086, Fig. 1; “route determination, lane level speed determination, operating the vehicle along a lane level route, route travel time determination, lane maintenance, route guidance, provision of traffic information/data, provision of lane level traffic information/data, vehicle trajectory determination and/or guidance, route and/or maneuver visualization, and/or the like”).
Zhang does not specifically state determining, based on clustering a set of intersections associated with the reference line, a first cluster representing a first subset of the set of intersections, wherein clustering the set of intersections is based on a set of input features representing a set of curvature measures associated with the set of intersections.
However, Zheng teaches determining, based on clustering a set of intersections associated with the reference line, a first cluster representing a first subset of the set of intersections, wherein clustering the set of intersections is based on a set of input features representing a set of curvature measures associated with the set of intersections (Paragraph 0070-0071; “edge points meeting a first pre-determined condition are in the same group, the first pre-determined condition includes that vertical coordinates of two points are adjacent, a distance difference between horizontal coordinates of the two points is less than a first distance threshold and a gradient angle difference is less than a threshold of gradient angle”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with clustering the intersections based on input features representing the curvature of Zheng with a reasonable expectation of success. One of ordinary skill in the art would understand that grouping clusters of intersections allows the machine learning model to quickly recognize lane boundaries without having to process the entire image. One would have been motivated to combine Zhang with Zheng as this improves lane boundary detection efficiency. As stated in Zheng, “since there is no need to perform analysis and recognition on the entire image with a machine learning model during detecting the lane boundaries, a calculation for the process of detecting the lane boundaries is simpler, and calculation resources and time consumed in the process of detecting the lane boundaries are reduced. Therefore, the lane boundary can be detected accurately and quickly” (Paragraph 0068).
Regarding claim 7, Zhang discloses determining the first representation comprises (Paragraphs 0059-0068, 0075);
determining a line that intersects with the reference line at a first point and the lane boundary at a second point (Paragraphs 0060, 0074-0075, Fig. 4A, 4B; “identify lane marking detections 401a, 401d each intersecting one of the perpendicular lines thereby constituting qualified lane marking detections/lines”);
determining a second line that intersects with the reference line at a third point; determining that the second line intersects with the lane boundary at a fourth point (Paragraphs 0060, 0075, Fig. 4A);
determining the first representation based at least in part on the second point and the fourth point (Paragraphs 0059-0068, 0075).
Regarding claim 8, Zhang discloses determining the first representation comprises (Paragraphs 0059-0068, 0075);
determining a line that intersects with the reference line at a first point and the lane boundary at a second point (Paragraphs 0060, 0074-0075, Fig. 4A, 4B; “identify lane marking detections 401a, 401d each intersecting one of the perpendicular lines thereby constituting qualified lane marking detections/lines”);
determining that the line intersects with a second lane boundary at a third point (Paragraphs 0060, 0074-0075, Fig. 4B);
determining, based at least in part on the first point and the third point, a distance between the lane boundary and the second lane boundary (Paragraphs 0059, Fig. 4B);
determining that the distance falls below a threshold (Paragraphs 0065, 0077).
Regarding claim 10, Zhang discloses determining the first representation is based on a line that is perpendicular to the reference line (Paragraphs 0059-0061, 0073-0078, Fig. 4A-4B).
Regarding claim 14, Zhang discloses determining the first representation is based on a curvature associated with the lane boundary (Paragraphs 0047-0048).
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang and Zheng, as applied to claim 6 above, and further in view of Park (US 12373689 B2).
Regarding claim 11, Zhang discloses determining the reference line comprises (Paragraph 0100-0111);
determining, based on the first data, a set of features (Paragraph 0100-0111);
determining, based at least in part on the set of features, a polygon that comprises the drivable surface (Paragraph 0100-0111).
Zhang does not specifically state determining a medial axis associated with the polygon; determining the reference line based on the medial axis.
However, Park teaches determining a medial axis associated with the polygon (Col. 6 Lines 1-17);
determining the reference line based on the medial axis (Col. 6 Lines 1-17).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with determining a medial axis of the polygon and determining a reference line based on the medial axis of Park with a reasonable expectation of success. One of ordinary skill in the art would understand that polygons can represent a road lane and therefore the medial axis of the polygon represents the center line of a lane. This center line of a lane is recognized and used for vehicle navigation. One would have been motivated to combine Zhang with Park as this achieves autonomous vehicles efficiently recognizing the environment. As stated in Park, “less compute and time intensive post-processing techniques—such as clustering and temporal smoothing—may be executed to determine landmark locations and poses with precision and in real-time. As a result, and in contrast to conventional systems, the control points may be regressed similarly to an object detection approach, and the control points may then be used to reconstruct the curve corresponding to the landmark—e.g., lane line, road boundary line, crosswalk, pole, text, etc. —for each of the landmarks in a field of view of each of one or more sensors of a vehicle” (Col. 1 Line 63 – Col. 2 Line 15).
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang, Zheng, and Park, as applied to claim 11 above, and further in view of Yamashita (US 20010012981 A1).
Regarding claim 12, all limitations have been examined with respect to the system in claim 4. The non-transitory computer-readable media taught/disclosed in claim 12 can be clearly performed with the system of claim 4. Therefore, claim 12 is rejected under the same rationale.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang, and Zheng, as applied to claim 6 above, and further in view of Kumano (US 20180204075 A1) and Eriksson (US 20240425056 A1).
Regarding claim 13, Zhang discloses determining the first representation comprises (Paragraphs 0059-0068, 0075);
determining a line that intersects with the reference line at a first point and the lane boundary at a second point (Paragraphs 0060, 0074-0075, Fig. 4A, 4B; “identify lane marking detections 401a, 401d each intersecting one of the perpendicular lines thereby constituting qualified lane marking detections/lines”).
Zhang does not specifically state determining that a second line intersects with the lane boundary at a third point.
However, Kumano teaches determining that a second line intersects with the lane boundary at a third point (Paragraphs 0035-0037, Fig. 9).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with determining a second line that intersects with the lane boundary at a third point of Kumano with a reasonable expectation of success. One of ordinary skill in the art would understand that a second line can determine a maximal distance of the shape change point from the reference line to determine if the road is curved. If the road is curved, the deviation of the estimated boundary line and the extracted boundary line can be determined. When the deviation is large, the driver can be notified that the accuracy of lane estimation parameters is reduced. One would have been motivated to combine Zhang with Kumano as this achieves avoiding control associated with lane marker detection inaccuracies. As stated in Kumano, “In response to the determination result that deviation has been detected, the driving aid 5 performs control upon deviation to avoid or suppress disadvantages caused by deviation. More specifically, the control upon deviation may include notification control to notify the driver that the accuracy of estimating the travel lane parameters has been decreased and functionality suspension control to suspend some or all control functions using the travel lane parameters, such as inhibiting application of the travel lane parameters estimated beyond the determination object points” (Paragraphs 0050-0053).
Zhang does not specifically state determining an optimal polynomial curve based on the second point and the third point.
However, Eriksson teaches determining an optimal polynomial curve based on the second point and the third point (Paragraph 0091).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Zhang with determining a polynomial curve based on the second point and the third point of Eriksson with a reasonable expectation of success. One of ordinary skill in the art would understand that a polynomial curve can be fit to lane marking points in clusters. The compatibility of two clusters can be determined by checking the fraction of inliers for each cluster for the polynomial curve. This allows lane markers to be more accurately determined by only using compatible lane marking clusters. One would have been motivated to combine Zhang with Eriksson as this improves accuracy in lane marking detection. As stated in Eriksson, “Thus, increasing the accuracy and redundancy in road estimation systems may therefore be crucial for improving driver safety and comfort. The herein disclosed technology seeks to mitigate, alleviate or eliminate one or more of the above-identified deficiencies and disadvantages in the prior art to address various problems relating to performance in complex environments and redundancy” (Paragraphs 0004-0005).
Allowable Subject Matter
Claim 9 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 and any intervening claims.
Claims 15-20 are allowed.
The following is a statement of reasons for the indication of allowable subject matter:
claim 9 recites (emphasis added):
“The one or more non-transitory computer-readable media of claim 6, the operations further comprising: determining a line that intersects with the reference line at a first point and the lane boundary at a second point; receiving an indication of a user input representing that the line intersects with the lane boundary at a third point; based on receiving the indication, determining a second representation associated with the lane boundary based at least in part on the third point; and associating the map with the second representation.”
The prior art does not teach, disclose, or otherwise render obvious the above-noted features of the claims.
Zhang teaches a line that intersects the reference line at a first point and a lane boundary at a second point (Paragraphs 0060, 0074-0075, Fig. 4B).
Zhang, however, does not teach receiving an indication of a user input representing that the line intersects with the lane boundary at a third point.
Closest reference Chen (US 20200207353 A1) teaches a user input adjusting the distance of the vehicle travelling reference line from the lane boundary lines.
Chen, however, does not teach the line intersects with the lane boundary at a third point.
These differences between the subject matter of claim 9 and the prior art are not taught or otherwise rendered obvious by any available evidence in the remaining prior art. Accordingly, claim 9 is objected to.
Claim 15 is allowed because this claim recites similar allowable subject matter found in claim 9.
Claims 16-20 are allowed based upon their dependency from claim 15.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
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 extension fee 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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to Matthew Ho whose telephone number is (571) 272-1388. The examiner can
normally be reached on Mon-Thurs 9:00-5:30 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, Navid Z Mehdizadeh can be reached on (571)-272-7691. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications are available through Private PAIR only. For more information about the PAIR system, see https://ppairmy.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at (866) 217-9197 (tollfree). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call (800) 786-9199 (IN USA OR CANADA) or (571) 272-1000.
/MATTHEW HO/ Examiner, Art Unit 3669
/NAVID Z. MEHDIZADEH/Supervisory Patent Examiner, Art Unit 3669