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 . This office action is in response to an Amendment filed on 2/3/26. Claims 1-8 and 10-21 are pending.
Response to Amendments
Amendments filed on 2/3/2026 are under consideration. Claims 1, 3-8, 10-17 and 19 are amended. Claim 21 is newly added.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 2, 6, 8, 10-11, 13, and 18-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Krivokon et al. (US 2020/0135030 Al) in view of Ding et al.(CN 110816544 A) and in further view of Thibaux (US 11,749,000 B2) and in further view of Qibin (CN 118097588 A)
Regarding Claim 1 Krivokon teaches A method (Pg. 15 – [0002] – “Aspects of the disclosure provide a method of training a model for determining states of lanes of interest” ) comprising: data associated with one or more drives within an environment; (Pg. 15 – [0002] – “The method includes receiving, by one or more server computing devices, image data including an image and an associated label identifying at least one traffic light” & see Also Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” (equates to data associated with one or more drives within an environment; As the quote shows a detection of a traffic feature being a stop light and the second quote shows the data taken during a drive.)) and sending the map data to one or more machines for performing one or more control operations within the environment. (Pg. 15 - [0005] - "controlling the vehicle in the autonomous driving mode based on pre-stored map information " )
Yet Krivoken fails to teach determining, based at least on map data, plurality of candidate lines potentially correspond to a wait line for a traffic feature; located within the environment, the plurality of candidate lines at least partially crossing a lane; determine, based at least on the data, one or more locations at which one or more stops occurred within the environment during the one or more drives; determining, based at least on the one or more locations being associated with a candidate line of the plurality of candidate lines that the candidate line includes the wait line for the traffic feature; updating the map data to indicate that the candidate line includes the wait line for the traffic feature.
Ding teaches determine, based at least on the data, one or more locations at which one or more stops occurred within the environment during the one or more drives; (Pg. 3 - " when the vehicle stops between the first position and the target stop line, evaluating the driving behavior of the driver of the vehicle at this time according to the vehicle speed and a preset evaluation model" & See Also Pg. 1 - Abstract - " the speed of the vehicle when the vehicle passes through a first position is obtained," (equates to determine, based at least on the data, one or more locations at which one or more stops occurred within the environment during the one or more drives; as quote 1 shows the determination of a stop occurring , quote 2 shows the data being taken to determine the stop wherein the data is speed associated with the vehicle)))
Both fail to teach determining, based at least on map data, plurality of candidate lines potentially correspond to a wait line for a traffic feature; located within the environment, the plurality of candidate lines at least partially crossing a lane; determining, based at least on the one or more locations being associated with a candidate line of the plurality of candidate lines that the candidate line includes the wait line for the traffic feature; updating the map data to indicate that the candidate line includes the wait line for the traffic feature.
Thibaux teaches updating the map data to indicate that the candidate line includes the wait line for the traffic feature. (Pg. 15 – [0005] – “Regardless of whether it is a stop line or a no stop line situation, once the stop location is determined it is added to 15 the map (e.g., as a layer in a road graph).)
Yet all fail to teach Both fail to teach determining, based at least on map data, plurality of candidate lines potentially correspond to a wait line for a traffic feature; located within the environment, the plurality of candidate lines at least partially crossing a lane; determining, based at least on the one or more locations being associated with a candidate line of the plurality of candidate lines that the candidate line includes the wait line for the traffic feature;
Qibin teaches determining, based at least on map data, plurality of candidate lines potentially correspond to a wait line for a traffic feature; located within the environment, the plurality of candidate lines at least partially crossing a lane; (Pg. 1 – “and determining a road stop line from the at least one candidate recognition line based on map data and lane line data recognized during the driving of the vehicle, wherein the lane line data comprises lane lines indicating the driving direction of the vehicle on a driving road, and the lane line data does not comprise the candidate recognition line.” & See Also Fig. 3 (equates to determining, based at least on map data, plurality of candidate lines potentially correspond to a wait line for a traffic feature; located within the environment, the plurality of candidate lines at least partially crossing a lane as the quote shows the determination of a stop line based on at least one candidate line which can be more than one and thus a plurality of candidate recognition lines may be determined wherein the quote specifically shows the candidate recognition line not including lane lines and thus are crossing a lane. )) determining, based at least on the one or more locations being associated with a candidate line of the plurality of candidate lines that the candidate line includes the wait line for the traffic feature; (Pg. 2 – “According to the stop line identifying method provided in the first aspect of the embodiment of the present application, the determining a road stop line from the at least one candidate identifying line based on the map data and the lane line data identified during the driving of the vehicle includes: acquiring an intersection area of the next intersection in the vehicle driving direction based on the map data; determining the identification line to be selected located in the intersection area from the at least one identification line to be selected; and determining one of the identification lines to be selected from the identification lines to be selected located in the intersection area as the road stop line based on the lane line data.” & See Also Pg. 3 – “In this embodiment, first, one road stop line is selected from the respective candidate recognition lines by the map data and the lane line data.” (equates to determining, based at least on the one or more locations being associated with a candidate line of the plurality of candidate lines that the candidate line includes the wait line for the traffic feature; as the first quote shows the one or more location being the intersection area wherein the second quote shows the candidate recognition lines being acquired based on map data relating to the intersection detected. )) It would have been an advantageous addition to the method disclosed by Krivokon and Ding to include determining, based at least on map data, plurality of candidate lines potentially correspond to a wait line for a traffic feature; located within the environment, the plurality of candidate lines at least partially crossing a lane; determining, based at least on the one or more locations being associated with a candidate line of the plurality of candidate lines that the candidate line includes the wait line for the traffic feature; as these limitations allow for a plurality of potential stop lines to be included in search for the stop line in which the vehicle needs to remain ensuring the vehicle has more potential stop lines considered in the map data.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include determining, based at least on map data, plurality of candidate lines potentially correspond to a wait line for a traffic feature; located within the environment, the plurality of candidate lines at least partially crossing a lane; determining, based at least on the one or more locations being associated with a candidate line of the plurality of candidate lines that the candidate line includes the wait line for the traffic feature; as this allows for more potential candidate lines to be generated ensuring that the scene encompassed by the map is best represented for an accurate stop line to be estimated.
Regarding Claim 2 Krivoken-Ding-Thibaux-Qibin teaches The method of claim 1, further comprising: determining one or more rules associated with the traffic feature; (Pg. 15 – [0003] – “In another example, the method also includes generating the associated label by projecting a three-dimensional location of the at least one traffic light into the image. In this example, the method also includes determining the state by processing the image to identify a blob of color within an area of the projection. In another example, the lane state identifies whether a vehicle in that lane is required to go, stop, or use caution.” (equates to determining one or more rules associated with the traffic feature as the quote shows the detection and subsequent locating of a traffic feature and then determining a rule of go stop or caution to be associated with the traffic light being captured.)) and determining, based at least on the one or more rules, (Pg. 15 – [0003] – “In another example, the method also includes generating the associated label by projecting a three-dimensional location of the at least one traffic light into the image. In this example, the method also includes determining the state by processing the image to identify a blob of color within an area of the projection. In another example, the lane state identifies whether a vehicle in that lane is required to go, stop, or use caution.”) wherein the determining that the candidate line includes the wait line for the traffic feature (Pg. 21 – [0065] – “The area of this projection 1110, including its location, and in some cases the distance and direction from the traffic light 620 in the image, may then be used to generate another label which can be used as training output to train the model. As a result, the model may also be trained to provide the location and distance information for a stop line, providing the vehicle's computing devices with more information about how the vehicle should respond to the traffic light.” (equates to wherein the determining that the candidate line includes the wait line for the traffic feature as the quote shows a determination of attributes of a stop line and thus a determination of a stop line itself.))
Yet Krivoken fails to teach one or more scores associated with the one or more drives, further based at least on the one or more scores.
Ding teaches one or more scores associated with the one or more drives (Pg. 4 – “the driving behavior evaluation module is used for evaluating the driving behavior of the driver as a first score if the vehicle speed is less than a first vehicle speed;” (equates to one or more scores associated with the one or more drives as the quote shows the driving of the vehicle being associated with a score.)) further based at least on the one or more scores. (Pg. 7 – “when the vehicle stops between the first position and the target stop line, evaluating the driving behavior of the driver of the vehicle at this time according to the vehicle speed and a preset” & See Also Pg. 7 – “if the vehicle speed is greater than the third vehicle speed, the current driving behavior of the driver is evaluated as a third grade” & See Also Pg. 6 – “Optionally, the preset evaluation model is used for indicating a corresponding relationship between a vehicle speed and a driving score;” (equates to further based at least on the one or more scores as the first quote shows the vehicle’s relation with the stop line, second showing a speed being considered within the method wherein the last shows the speed correlating to the score associated with the vehicle stopping at or near the line.)) It would have been an advantageous addition to the method disclosed by Krivoken to include one or more scores associated with the one or more drives, further based at least on the one or more scores as this allows a numerical value to be associated with the determination of the stop line and thus the driving itself can be incorporated into the determination of a stop line.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include one or more scores associated with the one or more drives, further based at least on the one or more scores as this allows the driving rather than strictly imaging and map data to be incorporated into the determination of a stop line.
Regarding Claim 6 Krivokon-Ding-Thibaux-Qibin teaches (Krivokon discloses the following limitations:) The method of claim 1, further comprising: determining, based at least on the map data, that the candidate line are associated with the lane as the traffic feature, (Pg. 13 – [1210] – “Receive image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light” &see also Pg. 16 – [0021] – “Typically, such information is stored in a vehicle's map information (e.g. a roadgraph identifying lanes) and can be retrieved as needed to identify traffic lights and lane states.” (equates to determining, based at least on the map data, that the one or more candidate lines are associated with a same lane as the traffic feature, as the first quote shows the traffic feature being associated with the lane controlled by it and the second quote showing map data being used to make this lane identification possible.)) wherein the determining the candidate line associated with the traffic feature is based at least on candidate line being associated with the lane as the traffic feature. (Pg. 13 – [1210] – “Receive image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light” &see also Pg. 16 – [0021] – “Typically, such information is stored in a vehicle's map information (e.g. a roadgraph identifying lanes) and can be retrieved as needed to identify traffic lights and lane states.”)
Yet Krivokon-Ding fails to teach plurality of candidate lines.
Qibin teaches plurality of candidate lines (Pg. 3 – “In this embodiment, first, one road stop line is selected from the respective candidate recognition lines by the map data and the lane line data.” (equates to plurality of candidate lines as the art previously mapped shows the candidate recognition lines being separate from lane lines and the plurality of stop lines are determined. )) It would have been an advantageous addition to the method disclosed by Krivokon -Ding to include plurality of candidate lines as this allows for a plurality of potential stop lines to be included in search for the stop line in which the vehicle needs to remain ensuring the vehicle has more potential stop lines considered in the map data.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include plurality of candidate lines as this allows for more potential candidate lines to be generated ensuring that the scene encompassed by the map is best represented for an accurate stop line to be estimated.
Regarding Claim 8 Krivokon-Ding-Thibuax-Qibin (Krivokon discloses the following limitations: ) The method of claim 1, wherein: teaches the traffic feature comprises one or more of: a traffic signal; a stop sign; a crosswalk light; a crosswalk sign; a train crossing light; a train crossing sign; a yield sign; or a stop light; (Pg. 17 – [0035] – “In this example, the map information 200 includes information identifying the shape, location, and other characteristics of lane lines 210, 212, 214, traffic lights 220, 222, stop line 224, crosswalk 230, sidewalks 240, stop signs 250, 252.” (equates to wherein: teaches the traffic feature comprises one or more of: a traffic signal; a stop sign; a crosswalk light; a crosswalk sign; a train crossing light; a train crossing sign; a yield sign; or a stop light as the quote shows a stop sign being including in graph data.)) and the candidate line comprise one or more of: a stop line; a crosswalk line; an intersection entrance line; an intersection exit line; a train crossing line; or a yield line. (Pg. 17 – [0035] – “In this example, the map information 200 includes information identifying the shape, location, and other characteristics of lane lines 210, 212, 214, traffic lights 220, 222, stop line 224, crosswalk 230, sidewalks 240, stop signs 250, 252.”)
Yet Krivokon fails to teach plurality of candidate lines
Qibin teaches plurality of candidate lines (Pg. 3 – “In this embodiment, first, one road stop line is selected from the respective candidate recognition lines by the map data and the lane line data.” (equates to plurality of candidate lines as the art previously mapped shows the candidate recognition lines being separate from lane lines and the plurality of stop lines are determined. )) It would have been an advantageous addition to the method disclosed by Krivokon -Ding to include plurality of candidate lines as this allows for a plurality of potential stop lines to be included in search for the stop line in which the vehicle needs to remain ensuring the vehicle has more potential stop lines considered in the map data.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include plurality of candidate lines as this allows for more potential candidate lines to be generated ensuring that the scene encompassed by the map is best represented for an accurate stop line to be estimated.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Krivokon-Thibaux and in further view of Qibin (CN 118097588 A)
Regarding Claim 10 Krivokon teaches A system (Pg. 15 – [0001] – “important component of an autonomous vehicle is the perception system, which allows the vehicle to perceive and interpret its surroundings using sensors such as cameras, radar, LIDAR sensors, and other similar devices” ) comprising: one or more processors to: determine, based at least on map data, a traffic feature located within an environment; ((Pg. 15 – [0002] – “The method includes receiving, by one or more server computing devices, image data including an image and an associated label identifying at least one traffic light” & see Also Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” & See Also Pg. 15 – [0004] – “identifying, by the one or more processors, a lane of interest using, by the one or more processors, the image and the lane of interest as input into the model to output a state of the lane of interest according to a state of a traffic light in the image; and controlling, by the one or more processors, the vehicle in an autonomous driving mode based on the state of the lane of interest” (equates to comprising: one or more processors to: determine, based at least on map data, a traffic feature located within an environment; As the second quote shows a travelling of the vehicle, and the first showing detection of a traffic feature being a stop light and the third showing the processors configured to carry out the system’s configuration..))) obtain data representative of one or more drives associated with the traffic feature; (Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” & See Also Pg. 15 – [0004] – “identifying, by the one or more processors, a lane of interest using, by the one or more processors, the image and the lane of interest as input into the model to output a state of the lane of interest according to a state of a traffic light in the image; ) and update the map data to indicate that the wait line associated with the traffic feature. (Pg. 15 – [0005] – “controlling the vehicle in the autonomous driving mode based on pre-stored map information, and the image is input into the model when the vehicle is located in an area that is not up to date in the map information” & See Also Pg. 15 – [0003] – “in another example, the method also includes, training the model to identify stop lines in images relevant to the lane of interest. In this example, the training further includes using a label identifying a location of a stop line in the image.” (equates to and update the map data to indicate that the wait line associated with the traffic feature as the first quote shows the map data being updated with images based on the map data not having the image data being captured wherein the second quote shows how the image data is understood as a stop line and thus this image would be included for the map updating if not already pre-stored within the system.)) wherein the map data, as updated, is used by one or more second machines in performing one or more control operations. (Pg. 15 - [0005] - "controlling the vehicle in the autonomous driving mode based on pre-stored map information " )
Yet Krivokon fails to teach determine, based at least on the one or more locations, a wait line located within the environment that associated with the traffic feature and update the map data to indicate that the wait line associated with the traffic feature
Thibaux teaches updating the map data to indicate that the candidate line includes the wait line for the traffic feature. (Pg. 15 – [0005] – “Regardless of whether it is a stop line or a no stop line situation, once the stop location is determined it is added to 15 the map (e.g., as a layer in a road graph).)
Yet both fail to teach determine, based at least on the one or more locations, a wait line located within the environment that associated with the traffic feature
Qibin teaches determine, based at least on the one or more locations, a wait line located within the environment that associated with the traffic feature (Pg. 1 – “and determining a road stop line from the at least one candidate recognition line based on map data and lane line data recognized during the driving of the vehicle, wherein the lane line data comprises lane lines indicating the driving direction of the vehicle on a driving road, and the lane line data does not comprise the candidate recognition line.” & See Also Pg. 2 – “acquiring an intersection area of the next intersection in the vehicle driving direction based on the map data; determining the identification line to be selected located in the intersection area from the at least one identification line to be selected; and determining one of the identification lines to be selected from the identification lines to be selected located in the intersection area as the road stop line based on the lane line data.” (equates to determine, based at least on the one or more locations, a wait line located within the environment that associated with the traffic feature as the quotes show the stop line being determined based on the gathering of intersection and thus location data. )) It would have been an advantageous addition to the method disclosed by Krivokon -Ding to include determine, based at least on the one or more locations, a wait line located within the environment that associated with the traffic feature as this allows a way to determine the stop line based on being within a location and this allows for map data to be solely used to determine a stop line location.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include determine, based at least on the one or more locations, a wait line located within the environment that associated with the traffic feature as this limitation ensures a location can be solely used in determination of a stop line.
Regarding Claim 11 Krivokon-Thibaux-Qibin teaches (Krivokon discloses the following limitations: ) The system of claim 10, wherein the one or more processors are further to: determine, based at least on the map data, one or more candidate lines that potentially include the wait line associated with the traffic feature, ((Pg. 13 – [1210] – “Receive image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light” &see also Pg. 16 – [0021] – “Typically, such information is stored in a vehicle's map information (e.g. a roadgraph identifying lanes) and can be retrieved as needed to identify traffic lights and lane states.” & See Also Pg. 15 – [0003] – “the method also includes, training the model to identify stop lines in images relevant to the lane of interest” (equates to wherein the one or more processors are further to: determine, based at least on the map data, one or more candidate lines that potentially include the wait line associated with the traffic feature, as the quote shows a lane controlled by the traffic light and the information being stored within a map of the system to identified lanes.))) wherein the determination of the wait line that is associated with the traffic feature comprises determining, based at least on the one or more locations, (Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” & See Also Pg. 15 – [0003] – “training the model to identify stop lines in images relevant to the lane of interest.” & See Also Pg. 12 – Fig. 11 - & See Also Pg. 21 – [0065] – “FIG. 11, image 600 may also be processed by projecting the location of stop line 224 into the image 600 as shown by the area of projection 1110. The area of this projection 1110, including its location, and in some cases the distance and direction from the traffic light 620 in the image,” (equates to wherein the determination of the wait line that is associated with the traffic feature comprises determining, based at least on the one or more locations, as the first quote shows the traveling of the vehicles associated with the image capturing and the second quote showing the images pertaining to identifying the stop lines. And the third quote showing the map linked image having a wait line correspond to a traffic feature.) ) that a candidate line of the one or more candidate lines includes the wait line associated with the traffic feature. (Pg. 21 – [0065] – “As a result, the model may also be trained to provide the location and distance information for a stop line, providing the vehicle's computing devices with more information about how the vehicle should respond to the traffic light” (equates to that a candidate line of the one or more candidate lines includes the wait line associated with the traffic feature as the quote shows the stop lines associated with the vehicles response to the traffic feature and thus the correlation of the traffic feature with the stop line is formed.))
Regarding Claim 13 Krivoken-Thibaux-Qibin teaches (Krivokon discloses the following limitations: ) The system of claim 10, wherein the one or more processors are further to: determine, that one or more locations, are located proximate to the wait line within the environment (Pg. 20 – [0061] – “This projection, for instance either the line or the area, and in some instances the distance and direction from the traffic light 620 in the image, may then be used to generate a label 1030 for instance that colors or otherwise identifies the location of the lane of interest. As such, label 1030 identifies a lane of interest, here lane 640 and/or road segment 218.” & See Also Pg. 20 – [0056] – “predetermined distance from and oriented towards intersections of the map information that are controlled by traffic lights,” (equates to determine, that one or more locations, are located proximate to the wait line within the environment as the image taken is shown to be a distance away from a traffic feature in which a top line is determined to be proximate to the traffic feature. )) ) wherein the determination of the wait line that is associated with the traffic feature comprises determining based at least on the one or more locations being located proximate to the wait line, the wait line that is associated with the traffic feature (Pg. 20 – [0061] – “This projection, for instance either the line or the area, and in some instances the distance and direction from the traffic light 620 in the image, may then be used to generate a label 1030 for instance that colors or otherwise identifies the location of the lane of interest. As such, label 1030 identifies a lane of interest, here lane 640 and/or road segment 218.” & See Also Pg. 20 – [0056] – “predetermined distance from and oriented towards intersections of the map information that are controlled by traffic lights,”)
Regarding Claim 18 Krivokon-Thibaux-Qibin teaches (Krivokon discloses the following limitations:) The system of claim 10, wherein the system is comprised in at least one of: a control system for an autonomous or semi-autonomous machine; a perception system for an autonomous or semi-autonomous machine; a system for performing one or more simulation operations; a system for performing one or more digital twin operations; a system for performing light transport simulation; a system for performing collaborative content creation for 3D assets; a system for performing one or more deep learning operations; a system implemented using an edge device; a system implemented using a robot; a system for performing one or more generative Al operations; a system for performing operations using one or more large language models (LLMs); a system for performing one or more conversational Al operations; a system for generating synthetic data; a system for presenting at least one of virtual reality content, augmented reality content, or mixed reality content; a system incorporating one or more virtual machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources. ((Pg. 21 – [0071] – “The vehicle may then be controlled in an autonomous driving mode” & See Also Pg. 18 – [0040] – “A control system software module of the computing devices 110 may be configured to control movement of the vehicle, for instance by controlling braking, acceleration and steering of the vehicle, in order to follow a trajectory” ) (equates to The system of claim 10, wherein the system is comprised in at least one of: a control system for an autonomous or semi-autonomous machine; a perception system for an autonomous or semi-autonomous machine; a system for performing one or more simulation operations; a system for performing one or more digital twin operations; a system for performing light transport simulation; a system for performing collaborative content creation for 3D assets; a system for performing one or more deep learning operations; a system implemented using an edge device; a system implemented using a robot; a system for performing one or more generative Al operations; a system for performing operations using one or more large language models (LLMs); a system for performing one or more conversational Al operations; a system for generating synthetic data; a system for presenting at least one of virtual reality content, augmented reality content, or mixed reality content; a system incorporating one or more virtual machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources as the quotes shows the existence of a control system for autonomous control of the vehicle. ))
Regarding claim 21 Krivokon-Qibin teaches The system of claim 10, as previously mapped above.
Yet Krivokon-Qibin fails to teach wherein the determination of the wait line that is associated with the traffic feature comprises: determining, based at least on the map data, that the environment refrains from having a line marking associated with the traffic feature; and determining, based at least on the environment refraining from having the line marking, the wait line associated with the traffic feature by at least projecting the wait line at line at a second location within the environment that is based at least on the one or more locations within the environment that the one or more first machines stopped when approaching the traffic feature.
Thibaux teaches herein the determination of the wait line that is associated with the traffic feature comprises: determining, based at least on the map data, that the environment refrains from having a line marking associated with the traffic feature; (Pg. 1 – Abstract – “While many intersections have stop lines painted on the roadway, many others have no such lines. Even if a stop line is present, the physical location may not match what is in store map data, which may be out of date due to construction or line repainting. Aspects of the technology employ a neural network that utilizes input training data and detected sensor data to perform classification, localization and uncertain estimation processes”) determining, based at least on the environment refraining from having the line marking, the wait line associated with the traffic feature by at least projecting the wait line at line at a second location within the environment that is based at least on the one or more locations within the environment that the one or more first machines stopped when approaching the traffic feature. (Pg. 28 – Col. 2 – lines 19- 23 – “Performing the stop location detection includes: predicting a set of stop line points closest to an expected stop line; discarding any of the set of stop line points not located within a region of interest associated with the lane endpoint;” & See Also Pg. 28 – Col. 2 – lines 28 – 24 – “In one example, the set of stop line points is predicted based on (i) a heat map according to the received sensor data 30 and (ii) a vector field including a set of vectors, each vector being associated with a corresponding given pixel of a set of pixels in the heat map. Here, the stop line points may be weighted by scores at corresponding ones of the given pixels.” & See Also Pg. 41 – [Col 7 – lines 39-45] – “The autonomous driving computing system may employ a planner 40 module 223, in accordance with the navigation system 220 the positioning system 222 and/or other components of the system, e.g., for determining a route from a starting point to a destination, for identifying a stop location at an intersection,” (equates to determining, based at least on the environment refraining from having the line marking, the wait line associated with the traffic feature by at least projecting the wait line at line at a second location within the environment that is based at least on the one or more locations within the environment that the one or more first machines stopped when approaching the traffic feature. as the quote shows the absence of a stop line and a projection of stop line points being done wherein the last quote shows the knowing of the stopping location of the vehicle as well as the entirety of the route. )) It would have been an advantageous addition to the system disclosed by Krivokon-Qibin to include wherein the determination of the wait line that is associated with the traffic feature comprises: determining, based at least on the map data, that the environment refrains from having a line marking associated with the traffic feature; and determining, based at least on the environment refraining from having the line marking, the wait line associated with the traffic feature by at least projecting the wait line at line at a second location within the environment that is based at least on the one or more locations within the environment that the one or more first machines stopped when approaching the traffic feature as these limitations allow for a new stop line to be created in the mapping system when none are detected by use of environmental sensing.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include wherein the determination of the wait line that is associated with the traffic feature comprises: determining, based at least on the map data, that the environment refrains from having a line marking associated with the traffic feature; and determining, based at least on the environment refraining from having the line marking, the wait line associated with the traffic feature by at least projecting the wait line at line at a second location within the environment that is based at least on the one or more locations within the environment that the one or more first machines stopped when approaching the traffic feature as these limitations allow for trajectory based tracking to sensing and project a stop line when the environmental sensing cannot detect the presence of a stop line within the environment.
Claim(s) 19 and 20 is rejected under 35 U.S.C. 103 as being unpatentable over Krivokon-Ding- as mapped above and in view of Olof et al. (CN 114118658 A).
Regarding Claim 19 Krivoken teaches One or more processors comprising: processing circuitry to cause a first machine that is navigating within an environment to stop at a wait line associated with a traffic feature using a map, (Pg. 15 – [0005] – “controlling the vehicle in the autonomous driving mode based on pre-stored map information, and the image is input into the model when the vehicle is located in an area that is not up to date in the map information” & See Also Pg. 15 – [0003] – “in another example, the method also includes, training the model to identify stop lines in images relevant to the lane of interest. In this example, the training further includes using a label identifying a location of a stop line in the image.”) wherein the map that is updated to indicate the wait line, at least, by: (Pg. 15 – [0005] – “controlling the vehicle in the autonomous driving mode based on pre-stored map information, and the image is input into the model when the vehicle is located in an area that is not up to date in the map information” & See Also Pg. 15 – [0003] – “in another example, the method also includes, training the model to identify stop lines in images relevant to the lane of interest. In this example, the training further includes using a label identifying a location of a stop line in the image.”)and update the map to indicate that the wait line associated with the traffic feature.(Pg. 3 – Fig. 2 & See Also Pg. 17 – [0035] – “FIG. 2 is an example of map information 200 for a section of roadway including intersections 202 and 204. The map information 200 may be a local version of the map information stored in the memory 130 of the computing devices 110. Other versions of the map information may also be stored in the storage system 450 discussed further below. In this example, the map information 200 includes information identifying the shape, location, and other characteristics of lane lines 210, 212, 214, traffic lights 220, 222, stop line 224, crosswalk 230, sidewalks 240, stop signs 250, 252,”& See Also Pg. 15 – [0005] – “controlling the vehicle in the autonomous driving mode based on pre-stored map information, and the image is input into the model when the vehicle is located in an area that is not up to date in the map information” & See Also Pg. 15 – [0003] – “in another example, the method also includes, training the model to identify stop lines in images relevant to the lane of interest. In this example, the training further includes using a label identifying a location of a stop line in the image.” (equates to and update the map to indicate that the wait line associated with the traffic feature as the quote shows the local map information being updated as an image is being identified for wait lines.)))
Yet Krivokon fails to teach determine, based at least one or more drives associated with one or more second machines within the environment, one or more locations within the environment that the one or more second machines stopped when approaching the traffic feature; determine, based at least on the one or more locations, the wait line associated with the traffic feature;
Ding teaches determine, based at least on the one or more locations, the wait line associated with the traffic feature; (Pg. 3 - " when the vehicle stops between the first position and the target stop line, evaluating the driving behavior of the driver of the vehicle at this time according to the vehicle speed and a preset evaluation model" & See Also Pg. 1 - Abstract - " the speed of the vehicle when the vehicle passes through a first position is obtained," (equates to determine, based at least on the one or more locations, the wait line associated with the traffic feature; as quote 1 shows the determination of a stop occurring at location))
Yet Krivokon-Ding fails to teach determine, based at least one or more drives associated with one or more second machines within the environment, one or more locations within the environment that the one or more second machines stopped when approaching the traffic feature;
Olaf teaches determine, based at least one or more drives associated with one or more second machines within the environment, (Pg. 3 – “In an embodiment, a method includes: generating, using one or more processors, a set of trajectories for a vehicle operating in an environment, each trajectory of the set of trajectories being associated with a traffic scenario; predicting, using the one or more processors, a rationality score for each trajectory of the set of trajectories, wherein the rationality score is obtained from a machine learning model trained using inputs obtained from a plurality of human annotators, and a loss function for penalizing predictions of rationality scores that violate a rule book structure”) one or more locations within the environment that the one or more second machines stopped when approaching the traffic feature; ((Pg. 3 – “In an embodiment, a method includes: generating, using one or more processors, a set of trajectories for a vehicle operating in an environment, each trajectory of the set of trajectories being associated with a traffic scenario; predicting, using the one or more processors, a rationality score for each trajectory of the set of trajectories, wherein the rationality score is obtained from a machine learning model trained using inputs obtained from a plurality of human annotators, and a loss function for penalizing predictions of rationality scores that violate a rule book structure” & See Also Pg. 14 – “The objects are classified (e.g., grouped into types such as pedestrian, bicycle, automobile, traffic sign, etc.), and a scene description including the classified objects 416 is provided to the planning module 404.” (equates to one or more locations within the environment that the one or more second machines stopped when approaching the traffic feature; as the first quote shows a rationality score being given for the other vehicle trajectory traversing a region wherein the second quote shows the identification of the object within the traffic scenario wherein one of the traffic signs identified may be a stop sign and thus the vehicle stopping at an identified stop sign would be given the higher score in this system and thus a location of stopping is determined. )) It would have been an advantageous addition to the system disclosed by Krivoken-Ding to include determine, based at least one or more drives associated with one or more second machines within the environment, one or more locations within the environment that the one or more second machines stopped when approaching the traffic feature; as these limitations allow for other vehicle trajectories to be incorporated into the dataset wherein a following of rules or stopping when required is determined.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include determine, based at least one or more drives associated with one or more second machines within the environment, one or more locations within the environment that the one or more second machines stopped when approaching the traffic feature; as this allows more than just the host vehicle determining the situation to be used as the dataset allowing for a wider variety of data from other vehicles allowing for more data to be used in the system’s configuration.
Regarding Claim 20 Krivoken-Ding-Olaf teaches (Krivokon discloses the following limitations:)The one or more processors of claim 19, wherein the one or more processors are comprised in at least one of: a control system for an autonomous or semi-autonomous machine; a perception system for an autonomous or semi-autonomous machine; a system for performing one or more simulation operations; a system for performing one or more digital twin operations; a system for performing light transport simulation; a system for performing collaborative content creation for 3D assets; a system for performing one or more deep learning operations; a system implemented using an edge device; a system implemented using a robot; a system for performing one or more generative Al operations; a system for performing operations using one or more large language models (LLMs); a system for performing one or more conversational Al operations; a system for generating synthetic data; a system for presenting at least one of virtual reality content, augmented reality content, or mixed reality content; a system incorporating one or more virtual machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources. (Pg. 21 – [0071] – “The vehicle may then be controlled in an autonomous driving mode” & See Also Pg. 18 – [0040] – “A control system software module of the computing devices 110 may be configured to control movement of the vehicle, for instance by controlling braking, acceleration and steering of the vehicle, in order to follow a trajectory” & See Also Pg. 2 – [Fig. 1] – “110 & 120” (equates to The one or more processors of claim 19, wherein the one or more processors are comprised in at least one of: a control system for an autonomous or semi-autonomous machine; a perception system for an autonomous or semi-autonomous machine; a system for performing one or more simulation operations; a system for performing one or more digital twin operations; a system for performing light transport simulation; a system for performing collaborative content creation for 3D assets; a system for performing one or more deep learning operations; a system implemented using an edge device; a system implemented using a robot; a system for performing one or more generative Al operations; a system for performing operations using one or more large language models (LLMs); a system for performing one or more conversational Al operations; a system for generating synthetic data; a system for presenting at least one of virtual reality content, augmented reality content, or mixed reality content; a system incorporating one or more virtual machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources as the quote shows the autonomous control of the vehicle via a control system which from figure 1 contains a processor 120.) )
Claim(s) 14 are rejected under 35 U.S.C. 103 as being unpatentable over Krivoken-Thibaux-Qibin as mapped above previously and in view of Ding et al. (CN 110816544 A).
Regarding Claim 14 Krivoken-Thibaux-Qibin teaches (Krivokon discloses the following limitations: )The system of claim 10, wherein the one or more processors are further to: determine one or more rules associated with the traffic feature; (Pg. 15 – [0003] – “In another example, the method also includes generating the associated label by projecting a three-dimensional location of the at least one traffic light into the image. In this example, the method also includes determining the state by processing the image to identify a blob of color within an area of the projection. In another example, the lane state identifies whether a vehicle in that lane is required to go, stop, or use caution.” (equates to wherein the one or more processors are further to: determine one or more rules associated with the traffic feature as the traffic light correlates to rules the traffic light would provide , go ,stop, and caution.)) and determine, based at least on the one or more rules, , (Pg. 15 – [0003] – “In another example, the method also includes generating the associated label by projecting a three-dimensional location of the at least one traffic light into the image. In this example, the method also includes determining the state by processing the image to identify a blob of color within an area of the projection. In another example, the lane state identifies whether a vehicle in that lane is required to go, stop, or use caution.”) wherein the determination of the wait line that is associated with the traffic feature (Pg. 21 – [0065] – “The area of this projection 1110, including its location, and in some cases the distance and direction from the traffic light 620 in the image, may then be used to generate another label which can be used as training output to train the model. As a result, the model may also be trained to provide the location and distance information for a stop line, providing the vehicle's computing devices with more information about how the vehicle should respond to the traffic light.” (equates to wherein the determining that the candidate line includes the wait line for the traffic feature as the quote shows a determination of attributes of a stop line and thus a determination of a stop line itself.))
Yet Krivokon fails to teach one or more scores associated with the one or more drives, further based at least on the one or more scores.
Ding teaches one or more scores associated with the one or more drives (Pg. 4 – “the driving behavior evaluation module is used for evaluating the driving behavior of the driver as a first score if the vehicle speed is less than a first vehicle speed;” (equates to one or more scores associated with the one or more drives as the quote shows the driving of the vehicle being associated with a score.)) further based at least on the one or more scores. (Pg. 7 – “when the vehicle stops between the first position and the target stop line, evaluating the driving behavior of the driver of the vehicle at this time according to the vehicle speed and a preset” & See Also Pg. 7 – “if the vehicle speed is greater than the third vehicle speed, the current driving behavior of the driver is evaluated as a third grade” & See Also Pg. 6 – “Optionally, the preset evaluation model is used for indicating a corresponding relationship between a vehicle speed and a driving score;” (equates to further based at least on the one or more scores as the first quote shows the vehicle’s relation with the stop line, second showing a speed being considered within the method wherein the last shows the speed correlating ot the score associated with the vehicle stopping at or near the line.)) It would have been an advantageous addition to the method disclosed by Krivoken to include one or more scores associated with the one or more drives, further based at least on the one or more scores as this allows a numerical value to be associated with the determination of the stop line and thus the driving itself can be incorporated into the determination of a stop line.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include one or more scores associated with the one or more drives, further based at least on the one or more scores as this allows the driving rather than strictly imaging and map data to be incorporated into the determination of a stop line.
Claim(s) 3, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Krivokon-Ding-Thibaux-Qibin as mapped above and in view of Olof et al. (CN 114118658 A).
Regarding Claim 3 Krivokon-Ding-Thibaux-Qibin teaches The method of claim 2, as mapped above previously.
Yet Krivokon-Ding fails to teach wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a Second machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a third machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score.
Olof teaches wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a Second machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a third machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score. (Pg. 3 – “In an embodiment, a method includes: generating, using one or more processors, a set of trajectories for a vehicle operating in an environment, each trajectory of the set of trajectories being associated with a traffic scenario; predicting, using the one or more processors, a rationality score for each trajectory of the set of trajectories, wherein the rationality score is obtained from a machine learning model trained using inputs obtained from a plurality of human annotators, and a loss function for penalizing predictions of rationality scores that violate a rule book structure” (equates to wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a Second machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a third machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score as the quote shows the vehicle trajectories being assigned a score wherein the score is related to the following of a rule book structure. )) It would have been an advantageous addition to the method disclosed by Krivokon-Ding to include wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a Second machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a third machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score as this limitation allows for a following of rules to more accurately determine the existence of a stop line and thus ensure that law breakers are considered strongly into the data concerning decisions of safety for users.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a Second machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a third machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score as this allows for only data of drivers following the rules of the road to be incorporated into a determination of the stop line.
Regarding Claim 15 Krivoken-Thibaux-Qibin-Ding teaches The system of claim 14, as mapped above previously.
Yet Krivokon-Ding fails to teach wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on the first drive being associated with following the one or more rules; or determining a second score associated with a second drive based at least on the second drive being associated with not following the one or more rules, wherein the second score is less than the first score.
Olof teaches wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on the first drive being associated with following the one or more rules; or determining a second score associated with a second drive based at least on the second drive being associated with not following the one or more rules, wherein the second score is less than the first score. (Pg. 3 – “In an embodiment, a method includes: generating, using one or more processors, a set of trajectories for a vehicle operating in an environment, each trajectory of the set of trajectories being associated with a traffic scenario; predicting, using the one or more processors, a rationality score for each trajectory of the set of trajectories, wherein the rationality score is obtained from a machine learning model trained using inputs obtained from a plurality of human annotators, and a loss function for penalizing predictions of rationality scores that violate a rule book structure” (equates to determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a first machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a second machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score as the quote shows the vehicle trajectories being assigned a score wherein the score is related to the following of a rule book structure. )) It would have been an advantageous addition to the method disclosed by Krivokon-Ding to include wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a first machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a second machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score as this limitation allows for a following of rules to more accurately determine the existence of a stop line and thus ensure that law breakers are considered strongly into the data concerning decisions of safety for users.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include wherein the determining the one or more scores associated with the one or more drives comprises one or more of: determining a first score associated with a first drive based at least on a first machine associated with the first drive following the one or more rules; or determining a second score associated with a second drive based at least on a second machine associated with the second drive not following the one or more rules, wherein the second score is less than the first score as this allows for only data of drivers following the rules of the road to be incorporated into a determination of the stop line.
Claim(s) 4, 5, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Krivokon-Ding-Thibaux-Qibin as mapped above and in view of Wolff et al. (GB 2636268 A).
Regarding Claim 4 Krivokon-Ding-Thibaux-Qibin teaches (Krivokon discloses the following limitations:) The method of claim 2, and the determination of the wait line associated with the traffic feature (Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” & See Also Pg. 15 – [0003] – “training the model to identify stop lines in images relevant to the lane of interest.”)
Yet Krivokon-Ding fail to teach wherein: the one or more scores include a plurality of scores associated with the plurality of drives; the one or more processors are further to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, a second portion of the plurality of drives; based at least on the second portion of the plurality of drives.
Wolff teaches wherein: the one or more scores include a plurality of scores associated with the plurality of drives (Pg. 7 - [26] – “For example, the machine learning model may score individual trajectory features from the different trajectories and rank (or score) the trajectories based on the scores of the respective sets of trajectory features.”) the one or more processors are further to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score (Pg. 18 – [113] – “In some cases, certain actions can be omitted from potential inclusion in a trajectory if they are not physically possible (e.g., the vehicle is not physically capable of increasing its acceleration and/or increasing its turning angle at that point in time) and/or would violate a safety threshold, comfort threshold, or other criteria. For example, if the trajectory generator 504 includes a safety threshold of not moving onto a sidewalk and the scene data 502 indicates that a sidewalk is immediately to the right of the vehicle 200, the vehicle action policy can indicate that turning right is not to be considered an available action and can omit it from inclusion in a trajectory” (equates to the one or more processors are further to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score as the quote shows that trajectories that are less than a few different designated thresholds for vehicle safety and the likes are removed based on not being safe for the vehicle to travel on. )) , a second portion of the plurality of drives (Pg. 18 – [113] In some cases, certain actions can be omitted from potential inclusion in a trajectory if they are not physically possible” & See Also Pg. 19 – [122] – “identify a subset of the generated trajectories that most closely align with the traveled path”(equates to a second portion of the plurality of drives as the quote shows a trajectory failing to be included into a set and thus a second set is formed from omitting potentially hazardous trajectory recommendations. )) based at least on the second portion of the plurality of drives. (Pg. 18 – [113] In some cases, certain actions can be omitted from potential inclusion in a trajectory if they are not physically possible” & See Also Pg. 19 – [122] – “identify a subset of the generated trajectories that most closely align with the traveled path”) It would have been an advantageous addition to the system disclosed by Krivokon to include wherein: the one or more drives include a plurality of drives associated with the traffic feature; the one or more scores include a plurality of scores associated with the plurality of drives; the one or more processors are further to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, a second portion of the plurality of drives; based at least on the second portion of the plurality of drives as this limitation allows for a removal of trajectories that don’t fit the best the understanding of the scene and ensure an accurate scene is understood based on trajectories that obey the rules of the road.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include wherein: the one or more drives include a plurality of drives associated with the traffic feature; the one or more scores include a plurality of scores associated with the plurality of drives; the one or more processors are further to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, a second portion of the plurality of drives; based at least on the second portion of the plurality of drives as these limitations allow for a numerical value to be associated with the drives that vehicle is or can take upon and best determine the scene based on feasible data from the drives being taken in.
Regarding Claim 5 Krivoken teaches The method of claim 1, further comprising: determining that the one or more drives are associated with the lane of one or more lanes located within the environment; (Pg. 15 – [0005] – “controlling the vehicle in the autonomous driving mode based on pre-stored map information, and the image is input into the model when the vehicle is located in an area that is not up to date in the map information” & See Also Pg. 13 – [Fig. 12] – “1210 - Receive image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light” (equates to determining that the one or more drives are associated with a lane of one or more lanes located within the environment; as the first quote shows the imaging being input into mapping of a local environment if the image data isn’t associated with the map and thus a determination of images existing within the environment are made, wherein the images can include lane data as seen by the second quote.)) wherein the determination of the wait line associated with the traffic feature (Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” & See Also Pg. 15 – [0003] – “training the model to identify stop lines in images relevant to the lane of interest.”)
Yet Krivokon fails to teach and determine a group of drives based at least on merging the one or more drives that are associated with the lane, based at least on the group of drives.
Wolff teaches and determine a group of drives based at least on merging the one or more drives that are associated with the lane, (Pg. 16 – [94] – “During training, the training environment may evaluate the machine learning model based on how the machine learning model ranks (or scores) the trajectories in the set of trajectories and the respective trajectory features. In some cases, the training environment can calculate a loss based on a comparison of a primary trajectory with other trajectories in the set of trajectories. The primary trajectory may be selected from the set of trajectories, and in some cases, may correspond to a trajectory from the set of trajectories that is similar to a previously recorded or expert trajectory.” & See Also Pg. 8 – [33] – “Area 108 includes a physical area (e.g., a geographic region) within which vehicles 102 can navigate…road includes at least one lane associated with (e.g., identified based on) at least one lane marking.” (equates to and determine a group of drives based at least on merging the one or more drives that are associated with the lane as the quote shows a primary trajectory being selected based on the set of trajectories and is based on trajectory features, wherein the second quote shows features of the trajectories to be a drivable area of the vehicle including a lane. )) based at least on the group of drives. (Pg. 16 – [94] – “During training, the training environment may evaluate the machine learning model based on how the machine learning model ranks (or scores) the trajectories in the set of trajectories and the respective trajectory features. In some cases, the training environment can calculate a loss based on a comparison of a primary trajectory with other trajectories in the set of trajectories. The primary trajectory may be selected from the set of trajectories, and in some cases, may correspond to a trajectory from the set of trajectories that is similar to a previously recorded or expert trajectory.”)
It would have been an advantageous addition to the system disclosed by Krivoken to include and determine a group of drives based at least on merging the one or more drives that are associated with the lane, based at least on the group of drives as these limitations ensure that a variety of vehicle trajectories are being taken into account when considering a determination of a candidate line.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include and determine a group of drives based at least on merging the one or more drives that are associated with the lane, based at least on the group of drives as this limitation ensures a variety of vehicle paths were considered within the data set in order to accurately determine whether or not a stop line were to exist in the vicinity of the vehicle.
Regarding Claim 16 Krivokon-Thibaux-Qibin- Ding teaches The system of claim 14, as previously mapped above.
Yet Krivokon-Ding fail to teach wherein the one or more processors are further configured to: determine a plurality of drives associated with the traffic feature; determine a plurality of scores associated with the plurality of drives, the plurality of drives including at least the one or more drives; determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, the one or more of drives;
Wolff teaches wherein the one or more processors are further configured to: determine a plurality of drives associated with the traffic feature; (Pg. 1 – Abstract – “A number of features are extracted from a particular trajectory and can include whether a collision is detected during the trajectory, collision with other tracks, traffic light rules” & See Also Pg. 7 [26] – “To train the machine learning model, the training environment may repeatedly provide the machine learning model with sets of features extracted from a set of trajectories” (equates to wherein: the one or more drives include a plurality of drives associated with the traffic feature as the second quote shows the plurality of drive or set of trajectories and the first quote showing the features being extracted from the trajectories including feature of a traffic light.)) determine a plurality of scores associated with the plurality of drives, the plurality of drives including at least the one or more drives (Pg. 7 - [26] – “For example, the machine learning model may score individual trajectory features from the different trajectories and rank (or score) the trajectories based on the scores of the respective sets of trajectory features.”) determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, (Pg. 18 – [113] – “In some cases, certain actions can be omitted from potential inclusion in a trajectory if they are not physically possible (e.g., the vehicle is not physically capable of increasing its acceleration and/or increasing its turning angle at that point in time) and/or would violate a safety threshold, comfort threshold, or other criteria. For example, if the trajectory generator 504 includes a safety threshold of not moving onto a sidewalk and the scene data 502 indicates that a sidewalk is immediately to the right of the vehicle 200, the vehicle action policy can indicate that turning right is not to be considered an available action and can omit it from inclusion in a trajectory” (equates to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, as the quote shows that trajectories that are less than a few different designated thresholds for vehicle safety and the likes are removed based on not being safe for the vehicle to travel on. )) , the one or more of drives; (Pg. 18 – [113] In some cases, certain actions can be omitted from potential inclusion in a trajectory if they are not physically possible” & See Also Pg. 19 – [122] – “identify a subset of the generated trajectories that most closely align with the traveled path”(equates to the one or more of drives; as the quote shows a trajectory failing to be included into a set and thus a second set is formed from omitting potentially hazardous trajectory recommendations. )) It would have been an advantageous addition to the system disclosed by Krivokon to include wherein: the one or more drives include a plurality of drives associated with the traffic feature; the one or more scores include a plurality of scores associated with the plurality of drives; the one or more processors are further to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, a second portion of the plurality of drives; based at least on the second portion of the plurality of drives as this limitation allows for a removal of trajectories that don’t fit the best the understanding of the scene and ensure an accurate scene is understood based on trajectories that obey the rules of the road.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include wherein: the one or more drives include a plurality of drives associated with the traffic feature; the one or more scores include a plurality of scores associated with the plurality of drives; the one or more processors are further to determine, based at least on removing a first portion of the plurality of drives that are associated with a portion of the plurality of scores that are less than a threshold score, a second portion of the plurality of drives; based at least on the second portion of the plurality of drives as these limitations allow for a numerical value to be associated with the drives that vehicle is or can take upon and best determine the scene based on feasible data from the drives being taken in.
Claim(s) 17 are rejected under 35 U.S.C. 103 as being unpatentable over Krivokon-Ding-Thibaux-Qibin as mapped above and in view of Wolff et al. (GB 2636268 A).
Regarding Claim 17 Krivokon-Thibaux-Qibin teaches (Krivokon discloses the following limitations:) The system of claim 10, wherein the one or more processors are further to: determine that the one or more drives are associated with a lane of one or more lanes located within the environment; (Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” & See Also Pg. 13 – [Fig. 12] – “1210 - Receive image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light” (equates to wherein the one or more processors are further to: determine that the one or more drives are associated with a lane of one or more lanes located within the environment;; as the first quote shows imaging being associated with the drives, wherein the images can include lane data as seen by the second quote.)) wherein the determination of the wait line that is associated with the traffic feature (Pg. 15 – [0005] – “In one example, identifying the image with the lane of interest includes projecting a road segment corresponding to a lane in which the vehicle is currently driving into the image.” & See Also Pg. 15 – [0003] – “training the model to identify stop lines in images relevant to the lane of interest.”)
Yet Krivokon fails to teach and determine a group of drives based at least on merging the one or more drives that are associated with the lane, based at least on the group of drives.
Wolff teaches and determine a group of drives based at least on merging the one or more drives that are associated with the lane, (Pg. 16 – [94] – “During training, the training environment may evaluate the machine learning model based on how the machine learning model ranks (or scores) the trajectories in the set of trajectories and the respective trajectory features. In some cases, the training environment can calculate a loss based on a comparison of a primary trajectory with other trajectories in the set of trajectories. The primary trajectory may be selected from the set of trajectories, and in some cases, may correspond to a trajectory from the set of trajectories that is similar to a previously recorded or expert trajectory.” & See Also Pg. 8 – [33] – “Area 108 includes a physical area (e.g., a geographic region) within which vehicles 102 can navigate…road includes at least one lane associated with (e.g., identified based on) at least one lane marking.” (equates to and determine a group of drives based at least on merging the one or more drives that are associated with the lane as the quote shows a primary trajectory being selected based on the set of trajectories and is based on trajectory features, wherein the second quote shows features of the trajectories to be a drivable area of the vehicle including a lane. )) based at least on the group of drives. (Pg. 16 – [94] – “During training, the training environment may evaluate the machine learning model based on how the machine learning model ranks (or scores) the trajectories in the set of trajectories and the respective trajectory features. In some cases, the training environment can calculate a loss based on a comparison of a primary trajectory with other trajectories in the set of trajectories. The primary trajectory may be selected from the set of trajectories, and in some cases, may correspond to a trajectory from the set of trajectories that is similar to a previously recorded or expert trajectory.”)
It would have been an advantageous addition to the system disclosed by Krivoken to include and determine a group of drives based at least on merging the one or more drives that are associated with the lane, based at least on the group of drives as these limitations ensure that a variety of vehicle trajectories are being taken into account when considering a determination of a candidate line.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include and determine a group of drives based at least on merging the one or more drives that are associated with the lane, based at least on the group of drives as this limitation ensures a variety of vehicle paths were considered within the data set in order to accurately determine whether or not a stop line were to exist in the vicinity of the vehicle.
Claim(s) 7 is rejected under 35 U.S.C. 103 as being unpatentable over Krivokon-Ding-Thibaux-Qibin as mapped above and in view of Kuriyama (US 2021/0182576 Al).
Regarding Claim 7 Krivokon-Ding-Thibaux-Qibin teaches (Krivokon discloses the following limitations:) teaches The method of claim 1, further comprising: determining, based at least on the map data, that the candidate line are located within a distance to the traffic feature, (Pg. 21 – [0065] – “The area of this projection 1110, including its location, and in some cases the distance and direction from the traffic light 620 in the image, may then be used to generate another label which can be used as training output to train the model. As a result, the model may also be trained to provide the location and distance information for a stop line, providing the vehicle's computing devices with more information about how the vehicle should respond to the traffic light.” (equates to comprising: determining, based at least on the map data, that the one or more candidate lines are located within a threshold distance to the traffic feature as the quote shows a distance away a stop line is from a traffic light. ))
Yet Krivokon fails to teach plurality of candidate lines , within a threshold distance to the traffic feature, wherein the determining the plurality of candidate lines associated with the traffic feature is based at least on the one or more candidate lines being located within the threshold distance to the traffic feature.
Kuriyama teaches within a threshold distance to the traffic feature (Pg. 12 – [0004] – “recognizes that the traffic light just in front of the host vehicle on the host vehicle traveling lane is located within a preset distance L2 and the color of the traffic light is red, shifts to the stop line recognition mode and executes stop line recognition processing” (equates to within a threshold distance to the traffic feature as the quote shows the lane being within preset distance toa traffic light and thus a threshold distance to a traffic feature.) ) wherein the determining the candidate line associated with the traffic feature is based at least on the candidate line being located within the threshold distance to the traffic feature. (Pg. 12 – [0004] – “recognizes that the traffic light just in front of the host vehicle on the host vehicle traveling lane is located within a preset distance L2 and the color of the traffic light is red, shifts to the stop line recognition mode and executes stop line recognition processing” (equates to wherein the determining the one or more candidate lines associated with the traffic feature is based at least on the one or more candidate lines being located within the threshold distance to the traffic feature as the lane is shown to be within a preset distance to the traffic light and the determination of the stop line being made base on that distance and the vehicle stoppage.) )
Yet all fail to teach plurality of candidate lines.
Qibin teaches plurality of candidate lines (Pg. 3 – “In this embodiment, first, one road stop line is selected from the respective candidate recognition lines by the map data and the lane line data.” (equates to plurality of candidate lines as the art previously mapped shows the candidate recognition lines being separate from lane lines and the plurality of stop lines are determined. )) It would have been an advantageous addition to the method disclosed by Krivokon -Ding to include plurality of candidate lines as this allows for a plurality of potential stop lines to be included in search for the stop line in which the vehicle needs to remain ensuring the vehicle has more potential stop lines considered in the map data.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include plurality of candidate lines as this allows for more potential candidate lines to be generated ensuring that the scene encompassed by the map is best represented for an accurate stop line to be estimated.
Claim(s) 12 is rejected under 35 U.S.C. 103 as being unpatentable over Krivokon -Thibaux-Qibin as mapped above and in view of Kuriyama (US 2021/0182576 Al).
Regarding Claim 12 Krivokon-Thibaux-Qibin teaches (Krivokon disclose the following limitations: ) The system of claim 11, wherein the one or more processors are further to: determine, based at least on the map data, (Pg. 13 – [1210] – “Receive image data including an image and an associated label identifying at least one traffic light, a state of the at least one traffic light, and a lane controlled by the at least one traffic light” &see also Pg. 16 – [0021] – “Typically, such information is stored in a vehicle's map information (e.g. a roadgraph identifying lanes) and can be retrieved as needed to identify traffic lights and lane states.” (equates to wherein the one or more processors are further to: determine, based at least on the map data, as the quote shows the candidate lines being associated with mapping data.))
Yet Krivokon fails to teach that the one or more candidate lines are located within a threshold distance to the traffic feature, wherein the one or more candidate lines that potentially include the wait line associated with the traffic feature are determined based at least on the one or more candidate lines being within the threshold distance to the traffic feature.
Kuriyama teaches that the one or more candidate lines are located within a threshold distance to the traffic feature (Pg. 12 – [0004] – “recognizes that the traffic light just in front of the host vehicle on the host vehicle traveling lane is located within a preset distance L2 and the color of the traffic light is red, shifts to the stop line recognition mode and executes stop line recognition processing” (equates to that the one or more candidate lines are located within a threshold distance to the traffic feature as the quote shows the lane being within a threshold distance to the traffic light)) wherein the one or more candidate lines that potentially include the wait line associated with the traffic feature are determined based at least on the one or more candidate lines being within the threshold distance to the traffic feature. (Pg. 12 – [0004] – “recognizes that the traffic light just in front of the host vehicle on the host vehicle traveling lane is located within a preset distance L2 and the color of the traffic light is red, shifts to the stop line recognition mode and executes stop line recognition processing” (equates to wherein the one or more candidate lines that potentially include the wait line associated with the traffic feature are determined based at least on the one or more candidate lines being within the threshold distance to the traffic feature. as the lane is shown to be within a preset distance to the traffic light and the determination of the stop line being made base on that distance and the vehicle stoppage.) ) It would have been an advantageous addition to the method disclosed by Krivokon to that the one or more candidate lines are located within a threshold distance to the traffic feature, w wherein the one or more candidate lines that potentially include the wait line associated with the traffic feature are determined based at least on the one or more candidate lines being within the threshold distance to the traffic feature as this allows for a measurable amount of distance between the lines detected and traffic feature recognized to be used for another way of ensuring a candidate line detected is in fact a stop line.
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to include that the one or more candidate lines are located within a threshold distance to the traffic feature, wherein the one or more candidate lines that potentially include the wait line associated with the traffic feature are determined based at least on the one or more candidate lines being within the threshold distance to the traffic feature as having a threshold distance ensures throughout a wide variety of intersection a preset distance can be a determiner used for a candidate line and determining it to be a stop line.
Response to Arguments
Response to 35 U.S.C. § 101 rejection of claims 1-8 and 10-20 applicant’s amendments to the claim changes the scope. Applicant’s arguments have been considered and are persuasive.
Applicant argues on page 15 , “Claims 1-20 are rejected under 35 U.S.C. § 101 as allegedly being directed to an abstract idea without significantly more. However, Applicant cancels claim 9 by the present response, without prejudice. Additionally, Applicant respectfully disagrees with respect to the remaining claims. However, solely in the interest of advancing prosecution, Applicant amends independent claims 1, 10, and 19. Applicant then respectfully submits that amended independent claims 1, , 10, and 19 are not directed to an abstract idea and even assuming arguendo they are, amended independent claims 1, 10, and 19 include significantly more than any alleged abstract idea. Consequently, Applicant respectfully requests that the Office withdraw the § 101 rejections of claims 1-8 and 10-20.” – AS to Point A, Examiner Agrees with the arguments set forth and the amendments included to claim 1 that remove the current 35 U.S.C. § 101 in place of claims of claims 1-8 and 10-20, as the specific inclusion of “sending the map data to one or more machines for performing one or more control operations within the environment.” Allows for more than a mental process to be claimed as specific vehicle control elements are included in the method.
Response to 35 U.S.C. § 102 rejection of claims 1-20 applicant’s amendments to the claim changes the scope. Applicant’s arguments have been considered but are not persuasive.
b. Applicant argues on Pages 16-18, “Applicant respectfully submits that Krivokon does not teach or suggest, at least,
"determining, based at least on map data, a plurality of candidate lines that potentially correspond
to a wait line for a traffic feature located within the environment, the plurality of candidate lines
at least partially crossing a lane; determine, based at least on the data, one or more locations at
which one or more stops occurred within the environment during the one or more drives; [and]
determining, based at least on the one or more locations being associated with a candidate line of
the plurality of candidate lines, that the candidate line includes the wait line for the traffic feature," as amended claim 1 recites.
In the rejection of previously presented independent claim 1, the Office cites Krivokon as
allegedly teaching, "determining, based at least on map data, one or more candidate lines
associated with the traffic feature; determining, based at least on the one or more drives, that a
candidate line of the one or more candidate lines includes a wait line for the traffic feature." Office
Action, pp. 7 and 8. Additionally, in the rejection of previously presented dependent claim 13, the
Office cites Krivokon as allegedly teaching, "determine, based at least on the one or more drives,
one or more locations within the environment that one or more machines associated with the one
or more drives stop at when approaching the traffic features, wherein the determination of the wait
line comprises determining the wait line associated with the traffic features shown, Krivokon hen describes that the stop line from the map information may be
projected onto images in order to identify the stop line within the images. Id. However, Applicant
respectfully asserts that Krivokon does not teach or suggest determining, using the map
information, a "plurality of candidate lines that potentially correspond to" the stop line within the
environment. Rather, Krivokon merely describes that the map information is labeled with the stop
line.
Additionally, Krivokon describes that a controller may cause a vehicle to go or stop. Id.,
para. [0071]. However, Krivokon does not teach or suggest using a location at which the vehicle
stops to perform any other type of procedure. For instance, Krivokon does not teach or suggest
using a location at which the vehicle stops to determine that a "candidate line" from the map
information actually includes the stop line for a traffic feature, as Krivokon does not even teach or
suggest using the location at which the vehicle stops to determine the stop line. Rather, the stop
line in Krivokon is merely determined using the map information. Consequently, Krivokon does
not teach or suggest "determining, based at least on map data, a plurality of candidate lines that
potentially correspond to a wait line for a traffic feature located within the environment; determine,
based at least on the data, one or more locations at which one or more stops occurred within the
environment during the one or more drives; [and] determining, based at least on the one or more
locations being associated with a candidate line of the plurality of candidate lines, that the candidate line includes the wait line for the traffic feature," as amended claim 1 recites Additionally, and for at least similar reasons, Applicant respectfully submits that Krivokon
further does not teach or suggest, "updating the map data to indicate that the candidate line includes the wait line for the traffic feature," as amended claim 1 recites” - Applicant’s arguments with respect to claim(s) 1 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
c. Applicant argues on page 19 - “Thus, independent claim 1 is patentably distinguishable over the cited reference and
withdrawal of the rejection is respectfully requested. For at least reasons similar to amended
independent claim 1, amended independent claims 10 and 19 are also patentably distinguishable
over the cited reference and withdrawal of the rejections is respectfully requested. Thus, amended
independent claims 1, 10, and 19, along with each claim depending therefrom rejected under this
section, is patentably distinguishable over the cited reference and withdrawal of the rejections is
respectfully requested” – As to point C see point B
d. Applicant argues on page 19-21, “Claims 2 and 14 are rejected under 35 U.S.C. § 103 as allegedly being unpatentable over
Krivokon in view of Chinese Application No. 110816544 to Ding (hereinafter "Ding"). Applicant
respectfully traverses the rejections of these claims.
As described above, Krivokon fails to teach or suggest each and every feature of
independent claims 1 and 10. Further, the Ding reference fails to overcome the deficiencies
described above with regard to independent claims 1 and 10, nor was it cited to for doing so. As
such, the combination of the references used under this section to teach or suggest each and every
feature of dependent claims 2 and 14. Accordingly, Applicant respectfully requests withdrawal of
the 35 U.S.C. § 103 rejections of claims 2 and 14. Claims 3 and 15 are rejected under 35 U.S.C. § 103 as allegedly being unpatentable over
Krivokon in view of Ding and further in view of Chinese Application No. 114118658 to Olof
(hereinafter "Olof"). Applicant respectfully traverses the rejections of these claims.
As described above, Krivokon fails to teach or suggest each and every feature of
independent claims 1 and 10. Further, the Ding and Olof references fail to overcome the
deficiencies described above with regard to independent claims 1 and 10, nor was it cited to for
doing SO. As such, the combination of the references used under this section to teach or suggest
each and every feature of dependent claims 3 and 15. Accordingly, Applicant respectfully requests
withdrawal of the 35 U.S.C. § 103 rejections of claims 3 and 15.
Claims 4, 5, 16, and 17 are rejected under 35 U.S.C. § 103 as allegedly being unpatentable
over Krivokon in view of Ding and further in view of Great Britain Application No. 2636268 to
Wolff (hereinafter "Wolff"). Applicant respectfully traverses the rejections of these claims.
As described above, Krivokon fails to teach or suggest each and every feature of
independent claims 1 and 10. Further, the Ding and Wolff references fail to overcome the
deficiencies described above with regard to independent claims 1 and 10, nor was it cited to for
doing SO. As such, the combination of the references used under this section to teach or suggest
each and every feature of dependent claims 4, 5, 16, and 17. Accordingly, Applicant respectfully
requests withdrawal of the 35 U.S.C. § 103 rejections of claims 4, 5, 16, and 17.
Claims 7 and 12 are rejected under 35 U.S.C. § 103 as allegedly being unpatentable over
Krivokon in view of U.S. Publication No. 2021/0182576 to Kuriyama (hereinafter "Kuriyama").
Applicant respectfully traverses the rejections of these claims.
As described above, Krivokon fails to teach or suggest each and every feature of
independent claims 1 and 10. Further, the Kuriyama reference fails to overcome the deficiencies
described above with regard to independent claims 1 and 10, nor was it cited to for doing so. As
such, the combination of the references used under this section to teach or suggest each and every
feature of dependent claims 7 and 12. Accordingly, Applicant respectfully requests withdrawal of
the 35 U.S.C. § 103 rejections of claims 7 and 12.
” – As to point D see Point B
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US20200393265 According to an aspect of an embodiment, operations may comprise receiving a set of one or more lane line points each representing a location on a lane line in an HD map, determining an approximate lane line point representing an approximate location on the lane line in the HD map, identifying a region of the HD map surrounding the approximate lane line point, automatically calculating a predicted lane line point in the region representing a predicted location of the lane line in the HD map, displaying, on a user interface, the predicted lane line point on the lane line in the HD map, receiving, from a user through the user interface, confirmation that the predicted lane line point is an actual lane line point, and adding the actual lane line point to the set of one or more lane line points representing locations on the lane line in the HD map.
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 REECE ANTHONY WAKELY whose telephone number is (571)272-3783. The examiner can normally be reached Monday - Friday 8:30am-6:00pm 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, Hitesh Patel can be reached at (571) 270-5442. 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.
/R.A.W./Examiner, Art Unit 3667
/ANSHUL SOOD/Primary Examiner, Art Unit 3667
Prosecution Insights