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 10/12/2026 have been fully considered, but they are not persuasive.
In regards to independent claim 1, Applicant argues Sengupta (US 11560131) and Jiang (US 20210291862) fail to teach claim 1 as amended. Applicant argues that neither test of Sengupta amounts to the claimed first condition. Applicant argues Sengupta’s first test concerns visibility of lane markers and the second test determines concerns a change in angle between current and previous tangents of curvature, which compares magnitude of angular change against a threshold, not whether curvature change rate increases or decreases, curvature increases or decreases, or whether those two are in opposite directions. Therefore, Applicant argues a prima facie case of obviousness cannot be established. Applicant argues, Sengupta computes a radius of curvature of a circle which is used to compute a curvature tangent and circles have no change in curvature, where the curvature tangent is treated as an angle used to align curvatures. Applicant argues a quantity that has an angle and can be rotated toward another quantity is the direction of a tangent line, not a rate of change of curvature and therefore Sengupta’s change in tangent angle does not correspond to a curvature change rate of the road as recited in claim 1 or whether the curvature or curvature rate of change increases or decreases. Therefore, Applicant concludes the Office’s inherency assertion is incorrect. Applicant argues, even were Sengupta to disclose varying curvature, the curvature and change in curvature do not necessarily change in the same or opposite directions and Sengupta’s test responds identically, relying only on angle change exceeding a threshold, and therefore inherency has not been established. Applicant argues the Office’s assertion of negative product presupposes a determination Sengupta does not make and therefore Sengupta does not generate lane markers based on curvature and curvature change rate satisfying the first condition. Applicant argues Jiang does not cure the deficiencies of Sengupta and therefore even combined, would not amount to the claim as a whole. Therefore, Applicant concludes independent claim 1 is patentable.
However, while a quantity that has an angle and can be rotated certainly may be provide a direction of a tangent line, that is not what is performed within the disclosure. Instead the disclosure recites “comput[ing] a curvature tangent”, not merely a direction of a tangent line. A tangent is mathematically defined as the derivative of a function and the derivative of a function is the rate at which that function changes. A tangent line is a related, but different, unrecited mathematical phenomenon. While Sengupta certainly does compute a curvature using a circle, this is only the beginning of its operations as it particularly propagates the lane boundaries along n-points up to an electronic horizon by fitting a circular curvature to the n-points and by aligning the tangents of the fit with the previously determined lane curvatures. As the lane lines are not precisely the same circle the entire time, as the operations are repeated, the circular curvature is recomputed and the curvature and tangents change, which, in fact, would even include the Applicant’s pointed to tangent lines. This therefore does include a curvature and a curvature change rate. Still further, the tangent is explicitly smoothed which mathematically redefines the function it is tangent to and therefore fundamentally adjusts the radius of curvature as well. The Applicant appears to misunderstand or misrepresent Sengupta as performing solely a single fit, where the operations are performed once in total isolation and then ends, but this is not the case, as evidenced at least within figure 8, once the lane markers have been propagated, the method repeats until further conditions are met. In each propagation that curvature is re-fit, causing it to change, a new tangent determined, smoothed, and aligned. How precisely the Applicant believes this to occur with solely an unchanging curvature is unclear. Therefore, instead of the Applicant’s assertions, one of ordinary skill would have read the reference for what it plainly discloses, that as the lane markers are found lacking, the operations repeatedly compute circular curvatures of best fit, tangents of those curvatures, align and smooth the curvatures, and propagates these curvatures, thereby causing the curvatures and rates of change of the curvatures to change. One of ordinary skill would have recognized that this includes necessary cases in which the curvature becomes more steeply positive and more steeply negative as well as becoming less steeply positive and less steeply negative. These cases are precisely the cases in which the curvature increases and the rate of change of the curvature decreases and the curvature decreases and the rate of change of the curvature increases. Further, as all curvatures are determined and tangents, which are the rates of change of curvature, these cases too are mathematically identified. Then, one of ordinary skill would have recognized that every single propagated curvature and tangent is necessarily fed into the next curvature and tangent until lane marker conditions are met, including such that when the above opposite direction conditions are met, the next propagation is based upon the determined previous curvatures and rates of change of curvatures.
Further, the claim does not require at any point that the device operates differently based upon the first condition being met, only that the calibrated line information is generated based on the met conditions, which is the case in Sengupta as all conditions of curvature are used to generate lane line information. As such, even were identical response recited within Sengupta, the reference still reads comfortably upon the claim.
Claim 1 does not recite any sort of negative product and no reference appears to have ever been applied for such a feature. As such, it is unclear why this would affect the rejection of the claim using these references. Jiang comfortably supplies the teachings it has been cited for.
As such, this argument is unpersuasive and a prima facie case of obviousness is readily established.
Applicant argues independent claim 9 is patentable for the same reasons as independent claim 1.
This argument is unpersuasive for the same reasons as given above.
In regards to independent claim 16, Applicant argues Sengupta does not determine whether a product of curvature change rate and curvature is negative and the rejection relies on improper inherency. Therefore, Applicant argues the claim is patentable for these reasons as well as the same reasons argued above.
However, the claim does not recite determining the product of curvature change rate difference and curvature difference is negative, but instead solely recites that the condition is satisfied when this product is negative. As such, provided the reference discloses explicitly or implicitly a situation where the product is negative, the limitation is met. Necessarily, when the curvature and curvature rate of change are opposite in sign, which is when the curvature is positive and the curvature rate of change is negative or the curvature is negative and the curvature rate of change is positive, the product of the curvature and curvature rate of change will always be negative. As such, in these cases as they are required to be within Sengupta, the condition is met. Were this case to be removed, the reference would cease to function for its intended purpose with arbitrary and unclear boundaries placed without logic or clarity. As such, one of ordinary skill would not have taken such an interpretation and instead read the reference for what it discloses, curvatures of all varieties, both increasing and decreasing, and rate of changes of curvatures of all varieties, both increasing and decreasing.
As such, for these reasons and the reasons above, this argument is unpersuasive.
Applicant argues the dependent claims are patentable by virtue of their dependency.
This argument is unpersuasive for the same reasons as given above.
Claim Objections
Claim 2 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. In particular, the claim recites “wherein the calibrated line information is generated further based on the curvature satisfying a second condition wherein the second condition is satisfied when the curvature changes by more than a threshold value,” and “determine, as the target point, a target point candidate, among the plurality of target point candidates, for which a difference between a curvature change rate of the candidate new line information and the reference curvature change rate is smallest.” No single prior art has been found to teach these limitations in combination, nor any combination of prior art references to render these limitations obvious, when viewed in the context of the remaining limitations of the claim and the limitations to which the claim depends. As such, all of these limitations amended into independent form including all intervening limitations, the claim would be found to be allowable.
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, 3-9, 11-16, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sengupta et al. (US 11560131), in view of Jiang et al. (US 20210291862).
In regards to claim 1, Sengupta teaches a device comprising: (Figs 1-7.)
a sensor; (Col 23 lines 33-50, camera sensors of vehicle observe environment and lane markings.)
memory storing instructions; (Col 10 lines 8-11, memory stores instructions for processing data.) and
a controller operatively connected to the sensor and the memory, (Col 10 lines 8-23, Col 24 lines 10-18, control system performs operations based on sensor information and instructions.)
wherein the instructions, when executed by the controller, cause the device to: (Col 10 lines 8-23, Col 24 lines 10-18, control system performs operations based on sensor information and instructions.)
obtain, via the sensor, a line recognition result associated with a road on which a vehicle is traveling; (Col 24 lines 8-37, image data is retrieved from the cameras and other sensors depicting lane markers and analyzed to determine if there are enough lane markers within the captured images to produce an adequate look-ahead horizon.)
determine, based on the line recognition result, whether a curvature of the road and a curvature change rate of the road satisfying a first condition, wherein the first condition is satisfied when the curvature change rate increases and the curvature decreases, or when the curvature change rate decreases and the curvature increases; (Col 24 lines 8-57, image data is retrieved from the cameras and other sensors depicting lane markers and analyzed to determine if there are enough lane markers within the captured images to produce an adequate look-ahead horizon. The last n points are used to compute a radius of curvature of longest present lane marker, curvature is calculated and propagated to predict lane markers ahead by calculating a moving average from the curvature and curvature tangent. Curvature tangent is the rate of change of curvature. Col 25 lines 15-53, outlier points are detected and smoothed if the outlier is the first outlier in a row or taken into further account with curvature and curvature tangent if more than a threshold number of outliers are found in a row. Col 24 lines 8-67, Col 25 lines 1-53, angle between curvature tangents over time is determined and smoothed using a weighted average and compared against a threshold to determine outliers, which includes cases of the first tangent being smaller than or larger than the second tangent, while curvature is continued to be determined, and by definition of having a changing tangent curvature is either increasing or decreasing. This particularly necessarily includes at least the case of an increase in the curvature change rate and a decrease in the curvature and includes the case of at least a decrease in the curvature change range and an instead in the curvature.)
based on the curvature and curvature change rate satisfying the first condition, generate calibrated line information using an expected curvature change rate; (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line using an expected curvature and rate of change of curvature, where the curvature and curvature change rate are both based on the increasing and decreasing curvature and increasing and decreasing curvature, including the necessary cases where the curvature increases while curvature change rate decreases and curvature decreases while curvature change rate increases.) and
control movement of the vehicle based on the calibrated line information, wherein the expected curvature change rate is determined using: (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using an expected curvature and rate of change of curvature. Col 23 lines 51-67, Col 24 lines 1-6, Col 29 lines 1-22, vehicle is controlled based on predictive lane markers ahead of the vehicle.)
the curvature change rate, (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using the determined curvature and rate of change of curvature.)
an expected curvature at a target point on the road, (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using an expected curvature and rate of change of curvature, which occurs over the n-second look-ahead requirement of the vehicle, which includes at least an expected curvature and rate of change of curvature at start and end points of the predictions, as well as every intermediate point.) and
Sengupta does not teach:
at least one of an expected heading angle of the vehicle at the target point on the road, or an expected lateral error at the target point.
However, Jiang teaches predicting a path of a vehicle over points including predicting heading ([0016]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the application to modify the vehicle control device of Sengupta, by incorporating the teachings of Jiang, such that an expected heading of the vehicle is determined and used to further control movement of the vehicle while propagating lane curvature, including expected curvature change rate, which incorporates the predicted heading as the vehicle moves and the lane lines are updated with new information.
The motivation to do so is that, as acknowledged by Jiang, this allows for safer autonomous or semi-autonomous driving ([0005]).
In regards to claim 3, Sengupta, as modified by Jiang, teaches the device of claim 1, wherein the movement of the vehicle, based on the calibrated line information, is controlled, during a time duration after a time at which the first condition is satisfied. (Col 29 lines 1-22, vehicle controls steering according to the predicted lane markers at least for the look-ahead horizon, which is a time duration of n-seconds, which is a time duration after curvature and curvature rates are assessed.)
In regards to claim 4, Sengupta, as modified by Jiang, teaches the device of claim 1, wherein the instructions, when executed by the controller, further cause the device to:
determine at least one target point candidate that the vehicle is expected to reach within a time duration after a time at which the first condition is satisfied; (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line using an expected curvature and rate of change of curvature, which occurs over the n-second look-ahead requirement of the vehicle, which includes at least an expected curvature and rate of change of curvature at start and end points of the predictions, as well as every intermediate point, where the vehicle is expected to reach the start point, end point, and the intermediate points within a duration after curvature and curvature change rate are identified.) and
determine the expected curvature change rate at the target point based on a curvature change rate at a first point included in the line recognition result, wherein the target point is one of the at least one target point candidate. (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line using an expected curvature and rate of change of curvature, which occurs over the n-second look-ahead requirement of the vehicle, which includes at least an expected curvature and rate of change of curvature at start and end points of the predictions, as well as every intermediate point, and is based on the curvature change rate at a first point included in the line recognition result.)
In regards to claim 5, Sengupta, as modified by Jiang, teaches the device of claim 4, wherein the instructions, when executed by the controller, further cause the device to:
determine, among curvatures included in the line recognition result, a reference curvature associated with a second time before the time at which the first condition is satisfied; (Col 24 lines 8-57, when lane markers are recognized, if there are sufficient lane markers to acquire the required look-ahead horizon, then the vehicle is navigated based on the analyzed lane markers up to the look-ahead horizon, which includes using the corresponding curvature to navigate the vehicle. Additionally, curvature of the longest lane marker is determined when there are insufficient lane makers to reach the look-ahead horizon, which includes lane marker information and curvature acquired before the time when the first condition is satisfied.) and
determine, among the at least one target point candidate, the target point such that a difference between a calibrated curvature at a time point when the first condition is satisfied and the reference curvature is smallest. (Col 24 lines 8-57, Col 25 lines 15-53, Col 26 lines 33-42, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line using an expected curvature and rate of change of curvature, which occurs over the n-second look-ahead requirement of the vehicle, which includes at least an expected curvature and rate of change of curvature at start and end points of the predictions, as well as every intermediate point, where the vehicle is expected to reach the start point, end point, and the intermediate points. When the vehicle travels on straight sections of road, the rate of change of curvature and curvature are smallest, which is found as a particular point within the look ahead horizon.)
In regards to claim 6, Sengupta, as modified by Jiang, teaches the device of claim 1, wherein the instructions, when executed by the controller, further cause the device to:
determine, based on curvature change rates included in the line recognition result, a first curvature change rate at a time at which the first condition is satisfied; (Col 24 lines 8-57, Col 25 lines 15-53, curvature tangents of the last n points of the longest lane marker are determined and propagated to predict the lane markers ahead. The curvature tangents are curvature change rates included in the line recognition result associated with a time associated with the information.)
determine, based on the curvature change rates included in the line recognition result, a second curvature change rate representing an overall curvature change rate of the road; (Col 24 lines 8-57, Col 25 lines 15-53, a moving average of the curvature tangent is determined which is an overall curvature change rate of the road.) and
determine, based on at least one of the first curvature change rate, the second curvature change rate, or a weight of each of the first curvature change rate and the second curvature change rate, the expected curvature change rate for a time duration starting at the time at which the first condition is satisfied, (Col 24 lines 8-57, Col 25 lines 15-53, curvature tangents of the last n points of the longest lane marker are determined and propagated to predict the lane markers ahead, including the curvature and curvature tangents of the lane markers ahead. Fitting is performed to fit the lane markers by using weights inversely proportional to the variance of the associated with the n points.)
wherein the weight of each of the first curvature change rate and the second curvature change rate comprises a first weight of the first curvature change rate, wherein the first weight is one at the time at which the first condition is satisfied and decreases to zero at a second time point after the time during the time duration. (Col 24 lines 8-57, Col 25 lines 15-53, fitting is performed over the last n points during a moving average which averages the last set of a number of points, weighting is performed on the last n points, which while the moving average moves, adjusts the weighting applied with the moving average as fewer points are selected and variance is reduced through smoothing, which at least at some point fully weights the point and at some point when the lane has propagated a number n+1 points past the relevant point, decreases weight of the point to zero, the propagated lane markers use reducing weights because variance is reduced.)
In regards to claim 7, Sengupta, as modified by Jiang, teaches the device of claim 6, wherein the instructions, when executed by the controller, further cause the device to:
generate new line information based on the expected curvature change rate; (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a new lane line using an expected curvature and rate of change of curvature.) and
generate the calibrated line information by replacing information on at least a portion of a line section included in the line recognition result with the new line information. (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a new lane line using an expected curvature and rate of change of curvature by replacing information after the last n points with new information included in the line recognition result with the new line information.)
In regards to claim 8, Sengupta, as modified by Jiang, teaches the device of claim 1, wherein the instructions, when executed by the controller, further cause the device to:
determine, via the sensor, a travel speed of the vehicle; (Col 7 lines 28-56, Col 10 lines 27-30, odometry sensors may operate to determine wheel speed, which indicates vehicle speed, and control the vehicle.) and
determine the target point based on at least one of the travel speed or a predetermined time duration. (Col 24 lines 8-37, an n-second look ahead requirement may be determined for safe driving within which the lane markers are propagated.)
In regards to claim 9, Sengupta teaches a method comprising: (Figs 8-10.)
obtaining, by a controller and via a sensor, a line recognition result associated with a road on which a vehicle is traveling; (Col 24 lines 8-37, image data is retrieved from the cameras and other sensors depicting lane markers and analyzed to determine if there are enough lane markers within the captured images to produce an adequate look-ahead horizon.)
determining, by the controller and based on the line recognition result, whether a curvature of the road and a curvature change rate of the road satisfying a first condition, wherein the first condition is satisfied when the curvature change rate increases and the curvature decreases, or when the curvature change rate decreases and the curvature increases; (Col 24 lines 8-57, image data is retrieved from the cameras and other sensors depicting lane markers and analyzed to determine if there are enough lane markers within the captured images to produce an adequate look-ahead horizon. The last n points are used to compute a radius of curvature of longest present lane marker, curvature is calculated and propagated to predict lane markers ahead by calculating a moving average from the curvature and curvature tangent. Curvature tangent is the rate of change of curvature. Col 25 lines 15-53, outlier points are detected and smoothed if the outlier is the first outlier in a row or taken into further account with curvature and curvature tangent if more than a threshold number of outliers are found in a row. Col 24 lines 8-67, Col 25 lines 1-53, angle between curvature tangents over time is determined and smoothed using a weighted average and compared against a threshold to determine outliers, which includes cases of the first tangent being smaller than or larger than the second tangent, while curvature is continued to be determined, and by definition of having a changing tangent curvature is either increasing or decreasing. This particularly necessarily includes at least the case of an increase in the curvature change rate and a decrease in the curvature and includes the case of at least a decrease in the curvature change range and an instead in the curvature.)
based on the curvature and curvature change rate satisfying the first condition, generating, by the controller, calibrated line information using an expected curvature change rate; (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line using an expected curvature and rate of change of curvature, where the curvature and curvature change rate are both based on the increasing and decreasing curvature and increasing and decreasing curvature, including the necessary cases where the curvature increases while curvature change rate decreases and curvature decreases while curvature change rate increases.) and
controlling, by the controller, movement of the vehicle based on the calibrated line information, wherein the expected curvature change rate is determined using: (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using an expected curvature and rate of change of curvature. Col 23 lines 51-67, Col 24 lines 1-6, Col 29 lines 1-22, vehicle is controlled based on predictive lane markers ahead of the vehicle.)
the curvature change rate, (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using the determined curvature and rate of change of curvature.)
an expected curvature at a target point on the road, (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using an expected curvature and rate of change of curvature, which occurs over the n-second look-ahead requirement of the vehicle, which includes at least an expected curvature and rate of change of curvature at start and end points of the predictions, as well as every intermediate point.) and
Sengupta does not teach:
at least one of an expected heading angle of the vehicle at the target point on the road, or an expected lateral error at the target point.
However, Jiang teaches predicting a path of a vehicle over points including predicting heading ([0016]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the application to modify the vehicle control method of Sengupta, by incorporating the teachings of Jiang, such that an expected heading of the vehicle is determined and used to further control movement of the vehicle while propagating lane curvature, including expected curvature change rate, which incorporates the predicted heading as the vehicle moves and the lane lines are updated with new information.
The motivation to do so is that, as acknowledged by Jiang, this allows for safer autonomous or semi-autonomous driving ([0005]).
In regards to claim 11, Sengupta, as modified by Jiang, teaches the method of claim 9.
Claim 11 recites a method having substantially the same features of claim 3 above, therefore claim 11 is rejected for the same reasons as claim 3.
In regards to claim 12, Sengupta, as modified by Jiang, teaches the method of claim 9.
Claim 12 recites a method having substantially the same features of claim 4 above, therefore claim 12 is rejected for the same reasons as claim 4.
In regards to claim 13, Sengupta, as modified by Jiang, teaches the method of claim 12.
Claim 13 recites a method having substantially the same features of claim 5 above, therefore claim 13 is rejected for the same reasons as claim 5.
In regards to claim 14, Sengupta, as modified by Jiang, teaches the method of claim 9.
Claim 14 recites a method having substantially the same features of claim 6 above, therefore claim 14 is rejected for the same reasons as claim 6.
In regards to claim 15, Sengupta, as modified by Jiang, teaches the method of claim 14.
Claim 15 recites a method having substantially the same features of claim 7 above, therefore claim 15 is rejected for the same reasons as claim 7.
In regards to claim 16, Sengupta teaches a non-transitory computer-readable medium storing instructions that, when executed, cause: (Col 10 lines 8-23, Col 24 lines 10-18, control system performs operations based on sensor information and instructions stored in memory.)
obtaining, by a controller and via a sensor, a line recognition result associated with a road on which a vehicle is traveling; (Col 24 lines 8-37, image data is retrieved from the cameras and other sensors depicting lane markers and analyzed to determine if there are enough lane markers within the captured images to produce an adequate look-ahead horizon.)
determining, by the controller and based on the line recognition result, whether a curvature of the road and a curvature change rate of the road satisfying a first condition, wherein the first condition is satisfied when a product of a curvature change rate difference and a curvature difference is negative; (Col 24 lines 8-57, image data is retrieved from the cameras and other sensors depicting lane markers and analyzed to determine if there are enough lane markers within the captured images to produce an adequate look-ahead horizon. The last n points are used to compute a radius of curvature of longest present lane marker, curvature is calculated and propagated to predict lane markers ahead by calculating a moving average from the curvature and curvature tangent. Curvature tangent is the rate of change of curvature. Col 25 lines 15-53, outlier points are detected and smoothed if the outlier is the first outlier in a row or taken into further account with curvature and curvature tangent if more than a threshold number of outliers are found in a row. Col 24 lines 8-67, Col 25 lines 1-53, angle between curvature tangents over time is determined and smoothed using a weighted average and compared against a threshold to determine outliers, which includes cases of the first tangent being smaller than or larger than the second tangent, while curvature is continued to be determined, and by definition of having a changing tangent curvature is either increasing or decreasing. This particularly necessarily includes at least the case of an increase in the curvature change rate and a decrease in the curvature and includes the case of at least a decrease in the curvature change range and an instead in the curvature. Necessarily, when the tangent difference is increasing or decreasing and the curvature difference is traveling in the opposite direction, a product of these is negative because they are of opposite signs and will always multiply to a negative number, which is satisfied when generating lane line data.)
based on the curvature and curvature change rate satisfying the first condition, generating, by the controller, calibrated line information using an expected curvature change rate; (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line using an expected curvature and rate of change of curvature, where the curvature and curvature change rate are both based on the increasing and decreasing curvature and increasing and decreasing curvature, including the necessary cases where the curvature increases while curvature change rate decreases and curvature decreases while curvature change rate increases.) and
controlling movement of the vehicle based on the calibrated line information, wherein the expected curvature change rate is determined using: (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using an expected curvature and rate of change of curvature. Col 23 lines 51-67, Col 24 lines 1-6, Col 29 lines 1-22, vehicle is controlled based on predictive lane markers ahead of the vehicle.)
the curvature change rate, (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using the determined curvature and rate of change of curvature.)
an expected curvature at a target point on the road, (Col 24 lines 8-57, Col 25 lines 15-53, when there are not enough lane markers within the captured images to provide an adequate look-ahead horizon, the last n points of the longest lane marker are used to compute a radius of curvature, which is then used to predict the lane markers up to a look-ahead horizon by propagating the curvature and tangent of curvature, while accounting for outliers and providing appropriate smoothing. This generates a calibrated lane line, including expected curvature change rate, using an expected curvature and rate of change of curvature, which occurs over the n-second look-ahead requirement of the vehicle, which includes at least an expected curvature and rate of change of curvature at start and end points of the predictions, as well as every intermediate point.) and
Sengupta does not teach:
at least one of an expected heading angle of the vehicle at the target point on the road, or an expected lateral error at the target point, wherein the at least one of the expected heading angle of the vehicle or the expected lateral error is used to determine the expected curvature change rate.
However, Jiang teaches predicting a path of a vehicle over points including predicting heading ([0016]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the application to modify the vehicle control instructions of Sengupta, by incorporating the teachings of Jiang, such that an expected heading of the vehicle is determined and used to further control movement of the vehicle while propagating lane curvature, including expected curvature change rate, which incorporates the predicted heading as the vehicle moves and the lane lines are updated with new information.
The motivation to do so is that, as acknowledged by Jiang, this allows for safer autonomous or semi-autonomous driving ([0005]).
In regards to claim 18, Sengupta, as modified by Jiang, teaches the non-transitory computer-readable medium of claim 16.
Claim 18 recites a medium having substantially the same features of claim 3 above, therefore claim 18 is rejected for the same reasons as claim 3.
In regards to claim 19, Sengupta, as modified by Jiang, teaches the non-transitory computer-readable medium of claim 16.
Claim 19 recites a medium having substantially the same features of claim 4 above, therefore claim 19 is rejected for the same reasons as claim 4.
In regards to claim 20, Sengupta, as modified by Jiang, teaches the non-transitory computer-readable medium of claim 19.
Claim 20 recites a medium having substantially the same features of claim 5 above, therefore claim 20 is rejected for the same reasons as claim 5.
Claims 10 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Sengupta, in view of Jiang, in further view of Nakamura et al. (US 20200307612).
In regards to claim 10, Sengupta, as modified by Jiang, teaches the method of claim 9.
Sengupta, as modified by Jiang, does not teach:
wherein the generating of the calibrated line information is further based on the curvature satisfying a second condition
wherein the second condition is satisfied when the curvature changes by more than a threshold value.
However, Nakamura teaches performing a check on the difference between a first and second curvature against a threshold value, which prompts different control settings based on result of the comparison ([0038]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the application to modify the vehicle control method of Sengupta, by incorporating the teachings of Nakamura, such that a check on the curvature change against a threshold is determined and used along with the criteria for generating lane markings as in Sengupta.
The motivation to do so is that, as acknowledged by Nakamura, this allows for improved control and improved comfort ([0004]-[0006]).
In regards to claim 17, Sengupta, as modified by Jiang, teaches the non-transitory computer-readable medium of claim 16.
Claim 17 recites a medium having substantially the same features of claim 10 above, therefore claim 17 is rejected for the same reasons as claim 10.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Ryu et al. (US 20160159394) teaches determining that lane lines have been misrecognized and correcting the lane line misrecognition for vehicle control.
Sato et al. (US 20240294185) teaches determining changing curvature for vehicle paths to improve navigation of curving roads.
Kobayashi (US 8346427) teaches determining expected curvature and rate of change of curvature of lane markers.
Matsunaga (US 20180374352) teaches determining curvature and curvature rate of change over time of a lane centerline.
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 MATTHIAS S WEISFELD whose telephone number is (571)272-7258. The examiner can normally be reached Monday-Thursday 7:00 AM - 4:00 PM.
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, Ramya Burgess can be reached at Ramya.Burgess@USPTO.GOV. 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.
/MATTHIAS S WEISFELD/Examiner, Art Unit 3661