DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-7 of U.S. Application No. 18/531901 filed on 05/08/2026 have been examined.
Office Action is in response to the Applicant's amendments and remarks filed 05/08/2026. Claims 1, & 5-7 are presently amended. Claims 1-7 are presently pending and are presented for examination.
Response to Arguments
In regards to the previous rejection under 35 U.S.C. § 103: Applicant argues that the prior art does not disclose the limitation “determine a number of trajectories of each class from the plurality of classes; select a class from the plurality of classes having a highest number of trajectories;”. Applicant further argues on page. 7-9 of the Remarks, “Accordingly, Stroila describes generating a plurality of trajectories, clustering the trajectories into bundles, classifying the bundles based on a trajectory count, and generating a representative trajectory for the bundle. However, while Stroila describes identifying a trajectory that is typical or atypical, as discussed during the interview, Stroila simply fails to disclose or suggest the feature of determining a number of trajectories in each bundle and selecting a bundle from a plurality of bundles having the highest trajectory count, and generating a representative trajectory from this selected bundle. That is, Stroila fails to disclose or suggest determining "a number of trajectories of each class from the plurality of classes," selecting "a class from the plurality of classes having a highest number of trajectories," and generating "a reference trajectory serving as a reference in the predetermined section by averaging individual trajectories included in the class selected from the plurality of classes," as recited in claim 1.”. Examiner respectfully disagrees. Applicant is reminded claims must be given their broadest reasonable interpretation. The prior art Stroila discloses that vehicles contain a plurality of different sensors including cameras to take in probe data, that takes in data regarding a geographic area for a specific time range and based on the data of the vehicles moving, the probe data generates a trajectory (see at least Stroila, para. [0048] & para. [0097-0099]). The time range can be set to be whatever time range required by the mapping platform and this occurs while the vehicles are traveling manned or unmanned through the region (see at least Stroila, para. [0035]). Based on the collection of data, Stroila is able to cluster the trajectory data and generates a reference trajectory that best fits the road structure. Further Stroila also discloses keeping a trajectory count of each of the trajectory bundles, considering they need to have a count over a threshold value in order to evaluate the trajectory bundle as typical or atypical (see at least Stroila, para. [0096]). Further the probe data of the trajectories collected by Stroila is trajectories that were traveled by the vehicles (see at least Stroila, para. [0046] & [0087]). Further Fowe is incorporated to teach the idea of selecting among a different groups of maneuvers the maneuver that is the most popular, which includes the largest number of vehicles that used this maneuver on the road (see at least Fowe, para. [0054] & [0061]). Further Phan is also incorporated to teach the idea of removing trajectories from the trajectory lattice that go against the rules of the road and are not considered when grouping the trajectory lattice (see at least Phan, para. [0144-0145]). In view of the arguments above, the 103 rejection is maintained.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1 & 3-6 is/are rejected under 35 U.S.C. 102(a)(1) as being unpatentable over US 2018/0066957A1 (“Stroila”), in view of US 2020/0124438A1 (“Fowe”).
As per claim 1 Stroila discloses
A reference trajectory generating device comprising (see at least Stroila, para. [0093]: In one embodiment, the mapping platform 107 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 15.):
at least one processor configured to (see at least Stroila, para. [0093]: In one embodiment, the mapping platform 107 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 15.):
acquire a plurality of trajectories of travel of at least one vehicle through a predetermined section of a road (see at least Stroila, para. [0059]: In one embodiment, the vehicles 101 and/or the UEs 103 are configured with various sensors for generating probe data…. camera/ imaging sensor for gathering image data ( e.g., the camera sensors may automatically capture obstruction for analysis and documentation purposes), & para. [0077]: In one embodiment, the curve similarity module 303 computes the similarity of the curves represented by each of the trajectories built by the collection module 301. As previously discussed, the curve similarity can be calculated using a similarity metric such as a discrete Frechet distance, a dynamic time warping analysis, or a combination thereof. In one embodiment, the curve similarity module 303 calculates similarity metrics (e.g., discrete Frechet distances) for all of the trajectories.),
the plurality of trajectories having been generated using a plurality of images in which each image is taken at an interval from at least one camera of the at least one vehicle as the at least one vehicle autonomously travels on the road (see at least Stroila, para. [0048]: In one embodiment, the system 100 can determine the trajectory and possible maneuvers over a time series ( e.g., for specific ranges of time over a larger time period) to detect changes in the classification of the maneuvers. & para. [0097-0099]: In step 601, the mapping platform 107 constructs and clusters the plurality of trajectories into the one or more trajectory bundles over a time series. By way of example, when determining what probe data to use or process, the mapping platform 107 can specify the time range that the probe data should cover. This time range can specify particular dates as well as a time span for the range…);
classify the plurality of trajectories into a plurality of classes by clustering the plurality of trajectories in the predetermined section (see at least Stroila, para. [0091]: In step 407, the mapping platform 107 clusters the plurality of trajectories into one or more trajectory bundles based on the similarities, wherein the one or more trajectory bundles respectively represent a possible maneuver within the bounded geographic area. & para. [0093]: FIG. 5 is a flowchart of a process for classifying trajectory bundles as typical/allowed versus a typical/nonallowed, according to one embodiment. In one embodiment, the mapping platform 107 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 15.),
determine a number of trajectories of each class from the plurality of classes (see at least Stroila, para. [0096]: In one embodiment, the classification is whether a maneuver associated with a trajectory bundle is typical/ atypical or allowed/non-allowed based on, e.g., traffic rules. Accordingly, in step 505, the mapping platform 107 classifies the possible maneuver associated with the one or more trajectory bundles that have a trajectory count above a threshold value as a typical/allowed maneuver.);
select a class from the plurality of classes (see at least Stroila, para. [0096]: In one embodiment, the classification is whether a maneuver associated with a trajectory bundle is typical/ atypical or allowed/non-allowed based on, e.g., traffic rules. Accordingly, in step 505, the mapping platform 107 classifies the possible maneuver associated with the one or more trajectory bundles that have a trajectory count above a threshold value as a typical/allowed maneuver.), and
generate a reference trajectory serving as a reference in the predetermined section by averaging individual trajectories included in the class selected from the plurality of classes (see at least Stroila, para. [0045]: Example selection methods include, but are not limited to, selecting a trajectory that is in a most central location of the trajectory bundle, selecting trajectory bundle based on a computed curve fit or distance (e.g., discrete Frechet distance), etc. In another embodiment, the system 100 may generate a representative trajectory by a statistical process (e.g., averaging or finding a mean of the trajectories within the trajectory bundle). & para. [0092]: In step 409, the mapping platform 107 generates a map of the bounded geographic area based on the one or more trajectory bundles.), and
add the reference trajectory to a map indicating road structure in the predetermined section (see at least Stroila, para. [0111]: FIG. 11 is a diagram illustrating a potential maneuver associated with a trajectory bundle, according to one embodiment. The trajectory bundle 1101 in map 1103 represents a possible turn at the intersection. In this example, the mapping platform 107 clustered all trajectories with this shape and heading to make the tum into the trajectory bundle 1101. Although the trajectory 1101 is depicted as being overlaid on a depiction of the intersection, the actual map topology of the intersection is not used to construct the trajectories from the probe data or cluster the trajectories according to a curve similarity to represent the turning maneuver at the intersection.),
However Stroila does not explicitly disclose
select a class from the plurality of classes having a highest number of trajectories;
wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory.
Fowe teaches
select a class from the plurality of classes having a highest number of trajectories (see at least Fowe, para. [0054]: Once the lane-level maneuvers for a group of vehicles having a similar origin and destination, and the lane-level maneuvers are clustered, the average time of travel for each medoid can be compared to indicate the fastest, most efficient lane-level maneuver strategy, while the cluster with the largest number of vehicles will represent the most popular approach. & para. [0061]: FIG. 5 illustrates a flowchart of a method according to an example embodiment of the present invention for establishing recommended lane-level guidance between an origin and a destination based on a safe, efficient, or popular path. At 510, a plurality of probe data points are received from a plurality of probe apparatuses traveling between origins and destinations.);
wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory (see at least Fowe, para. [0041]: Embodiments of the present disclosure create historical data that can advise on the best or more appropriate lanes for a vehicle to navigate on a road segment. To achieve this, data is obtained from drivers that have traversed similar origin/destination routes so that the lane choices taken may be focused on achieving a similar journey from the origin to the destination. Historical data is obtained that learns from how drivers have safely driven a road at a lane-level and that data may be used to guide new drivers traversing the same road segments. Further, embodiments may use data obtained from drivers to inform autonomous vehicles such that autonomous vehicles may be controlled according to the popular/safe/efficient routes selected by humans through machine learning of the lane-level routes.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Stroila to incorporate the teaching of select a class from the plurality of classes having a highest number of trajectories, wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory of Fowe, with a reasonable expectation of success in order to improves safety and efficiency in a proactive manner rather than reacting to abnormal or exceptional events on a roadway (see at least Fowe, para. [0039]).
As per claim 3 Stroila discloses
wherein among the plurality of trajectories, the at least one processor classifies, into the classes, trajectories that do not pass a prohibited area into which entry of the at least one vehicle is prohibited (see at least Stroila, para. [0047]: In another embodiment, the relative trajectory counts can be used to distinguish typical/allowed maneuvers from atypical/non-allowed maneuvers. For example, a possible maneuver represented by a trajectory bundle with a relatively high trajectory count can be classified by the system 100 to be a typical maneuver (e.g., a maneuver that a driver or traveler is typically expected to make in the bounded geographic area or at an intersection/interchange) or an allowed maneuver (e.g., a maneuver permitted by traffic rules based on an assumption that most drivers or travelers will perform only allowed maneuvers). On the other hand, the system 100 can classify a possible maneuver represented by a trajectory bundle with a relatively low trajectory count as an atypical (e.g., a maneuver a driver or traveler would not normally make at in an area or at an intersection/interchange) or a non-allowed maneuver (e.g., a maneuver not permitted by traffic rules based on an assumption that only a few drivers or travelers would break a traffic rule).).
As per claim 4 Stroila discloses
further comprising a memory configured to store the map (see at least Stroila, para. [0118]: The memory 1404, such as a random access memory (RAM) or other dynamic storage device, stores information including processor instructions for providing trajectory bundles for map data analysis.), wherein
in the clustering, the at least one processor uses data depending on the road structure in the predetermined section represented in the map as representing each of the plurality of trajectories (see at least Stroila, para. [0101]: In step 701, the mapping platform 107 performs an analysis of a bundle topology of the one or more trajectory bundles with respect to a map topology determined from mapping data. For example, the mapping platform 107 can determine whether the shape or topology of the trajectory bundle follows the shape or topology of a known road network in the area of interest. In one embodiment, the analysis by the mapping platform 107 can simply detect a deviation beyond a threshold value. In addition or alternatively, the analysis can detect the type of nature of the deviation. For example, based on the shape, heading, speed, etc. of the trajectories in the trajectory bundle at the point of deviation, the mapping platform 107 identifies specific types of travel or driving behaviors, or actions taken by a probe. The behaviors or actions can include making a U-turn in a parking lot, parking in a parking spot (e.g., indicated by a three-point turn or other path indicative of parking), etc.).
As per claim 5 Stroila discloses
A method for generating a reference trajectory (see at least Stroila, para. [0093]: In one embodiment, the mapping platform 107 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 15.), comprising:
acquiring a plurality of trajectories of travel of at least one vehicle through a predetermined section of a road (see at least Stroila, para. [0059]: In one embodiment, the vehicles 101 and/or the UEs 103 are configured with various sensors for generating probe data…. camera/ imaging sensor for gathering image data ( e.g., the camera sensors may automatically capture obstruction for analysis and documentation purposes), & para. [0077]: In one embodiment, the curve similarity module 303 computes the similarity of the curves represented by each of the trajectories built by the collection module 301. As previously discussed, the curve similarity can be calculated using a similarity metric such as a discrete Frechet distance, a dynamic time warping analysis, or a combination thereof. In one embodiment, the curve similarity module 303 calculates similarity metrics (e.g., discrete Frechet distances) for all of the trajectories.),
the plurality of trajectories having been generated using a plurality of images in which each image is taken at an interval from at least one camera of the at least one vehicle as the at least one vehicle autonomously travels on the road (see at least Stroila, para. [0048]: In one embodiment, the system 100 can determine the trajectory and possible maneuvers over a time series ( e.g., for specific ranges of time over a larger time period) to detect changes in the classification of the maneuvers. & para. [0097-0099]: In step 601, the mapping platform 107 constructs and clusters the plurality of trajectories into the one or more trajectory bundles over a time series. By way of example, when determining what probe data to use or process, the mapping platform 107 can specify the time range that the probe data should cover. This time range can specify particular dates as well as a time span for the range…);
classifying the plurality of trajectories into a plurality of classes by clustering the plurality of trajectories in the predetermined section (see at least Stroila, para. [0091]: In step 407, the mapping platform 107 clusters the plurality of trajectories into one or more trajectory bundles based on the similarities, wherein the one or more trajectory bundles respectively represent a possible maneuver within the bounded geographic area. & para. [0093]: FIG. 5 is a flowchart of a process for classifying trajectory bundles as typical/allowed versus atypical/nonallowed, according to one embodiment. In one embodiment, the mapping platform 107 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 15.);
determining a number of trajectories of each class from the plurality of classes (see at least Stroila, para. [0096]: In one embodiment, the classification is whether a maneuver associated with a trajectory bundle is typical/ atypical or allowed/non-allowed based on, e.g., traffic rules. Accordingly, in step 505, the mapping platform 107 classifies the possible maneuver associated with the one or more trajectory bundles that have a trajectory count above a threshold value as a typical/allowed maneuver.);
selecting a class from the plurality of classes (see at least Stroila, para. [0096]: In one embodiment, the classification is whether a maneuver associated with a trajectory bundle is typical/ atypical or allowed/non-allowed based on, e.g., traffic rules. Accordingly, in step 505, the mapping platform 107 classifies the possible maneuver associated with the one or more trajectory bundles that have a trajectory count above a threshold value as a typical/allowed maneuver.); and
generating a reference trajectory serving as a reference in the predetermined section by averaging individual trajectories included in the class selected from the plurality of classes (see at least Stroila, para. [0045]: Example selection methods include, but are not limited to, selecting a trajectory that is in a most central location of the trajectory bundle, selecting trajectory bundle based on a computed curve fit or distance (e.g., discrete Frechet distance), etc. In another embodiment, the system 100 may generate a representative trajectory by a statistical process (e.g., averaging or finding a mean of the trajectories within the trajectory bundle). & para. [0092]: In step 409, the mapping platform 107 generates a map of the bounded geographic area based on the one or more trajectory bundles.), and
adding the reference trajectory to a map indicating road structure in the predetermined section (see at least Stroila, Fig. 11 & para. [0111]: FIG. 11 is a diagram illustrating a potential maneuver associated with a trajectory bundle, according to one embodiment. The trajectory bundle 1101 in map 1103 represents a possible turn at the intersection. In this example, the mapping platform 107 clustered all trajectories with this shape and heading to make the tum into the trajectory bundle 1101. Although the trajectory 1101 is depicted as being overlaid on a depiction of the intersection, the actual map topology of the intersection is not used to construct the trajectories from the probe data or cluster the trajectories according to a curve similarity to represent the turning maneuver at the intersection.).
However Stroila does not explicitly disclose
selecting a class from the plurality of classes having a highest number of trajectories;
wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory.
Fowe teaches
selecting a class from the plurality of classes having a highest number of trajectories (see at least Fowe, para. [0054]: Once the lane-level maneuvers for a group of vehicles having a similar origin and destination, and the lane-level maneuvers are clustered, the average time of travel for each medoid can be compared to indicate the fastest, most efficient lane-level maneuver strategy, while the cluster with the largest number of vehicles will represent the most popular approach. & para. [0061]: FIG. 5 illustrates a flowchart of a method according to an example embodiment of the present invention for establishing recommended lane-level guidance between an origin and a destination based on a safe, efficient, or popular path. At 510, a plurality of probe data points are received from a plurality of probe apparatuses traveling between origins and destinations.);
wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory (see at least Fowe, para. [0041]: Embodiments of the present disclosure create historical data that can advise on the best or more appropriate lanes for a vehicle to navigate on a road segment. To achieve this, data is obtained from drivers that have traversed similar origin/destination routes so that the lane choices taken may be focused on achieving a similar journey from the origin to the destination. Historical data is obtained that learns from how drivers have safely driven a road at a lane-level and that data may be used to guide new drivers traversing the same road segments. Further, embodiments may use data obtained from drivers to inform autonomous vehicles such that autonomous vehicles may be controlled according to the popular/safe/efficient routes selected by humans through machine learning of the lane-level routes.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Stroila to incorporate the teaching of selecting a class from the plurality of classes having a highest number of trajectories, wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory of Fowe, with a reasonable expectation of success in order to improves safety and efficiency in a proactive manner rather than reacting to abnormal or exceptional events on a roadway (see at least Fowe, para. [0039]).
As per claim 6 Stroila discloses
A non-transitory recording medium that stores a computer program for generating a reference trajectory, the computer program causing a computer to execute a process comprising (see at least Stroila, para. [0093]: In one embodiment, the mapping platform 107 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 15.):
acquiring a plurality of trajectories of travel of at least one vehicle through a predetermined section of a road (see at least Stroila, para. [0059]: In one embodiment, the vehicles 101 and/or the UEs 103 are configured with various sensors for generating probe data…. camera/ imaging sensor for gathering image data ( e.g., the camera sensors may automatically capture obstruction for analysis and documentation purposes), & para. [0077]: In one embodiment, the curve similarity module 303 computes the similarity of the curves represented by each of the trajectories built by the collection module 301. As previously discussed, the curve similarity can be calculated using a similarity metric such as a discrete Frechet distance, a dynamic time warping analysis, or a combination thereof. In one embodiment, the curve similarity module 303 calculates similarity metrics (e.g., discrete Frechet distances) for all of the trajectories.),
the plurality of trajectories having been generated using a plurality of images in which each image is taken at an interval from at least one camera of the at least one vehicle as the at least one vehicle autonomously travels on the road (see at least Stroila, para. [0048]: In one embodiment, the system 100 can determine the trajectory and possible maneuvers over a time series ( e.g., for specific ranges of time over a larger time period) to detect changes in the classification of the maneuvers. & para. [0097-0099]: In step 601, the mapping platform 107 constructs and clusters the plurality of trajectories into the one or more trajectory bundles over a time series. By way of example, when determining what probe data to use or process, the mapping platform 107 can specify the time range that the probe data should cover. This time range can specify particular dates as well as a time span for the range…);
classifying the plurality of trajectories into a plurality of classes by clustering of the plurality of trajectories in the predetermined section (see at least Stroila, para. [0091]: In step 407, the mapping platform 107 clusters the plurality of trajectories into one or more trajectory bundles based on the similarities, wherein the one or more trajectory bundles respectively represent a possible maneuver within the bounded geographic area. & para. [0093]: FIG. 5 is a flowchart of a process for classifying trajectory bundles as typical/allowed versus atypical/nonallowed, according to one embodiment. In one embodiment, the mapping platform 107 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 15.);
determining a number of trajectories of each class from the plurality of classes (see at least Stroila, para. [0096]: In one embodiment, the classification is whether a maneuver associated with a trajectory bundle is typical/ atypical or allowed/non-allowed based on, e.g., traffic rules. Accordingly, in step 505, the mapping platform 107 classifies the possible maneuver associated with the one or more trajectory bundles that have a trajectory count above a threshold value as a typical/allowed maneuver.);
selecting a class from the plurality of classes (see at least Stroila, para. [0096]: In one embodiment, the classification is whether a maneuver associated with a trajectory bundle is typical/ atypical or allowed/non-allowed based on, e.g., traffic rules. Accordingly, in step 505, the mapping platform 107 classifies the possible maneuver associated with the one or more trajectory bundles that have a trajectory count above a threshold value as a typical/allowed maneuver.);
generating a reference trajectory serving as a reference in the predetermined section by averaging individual trajectories included in the class selected from the plurality of classes (see at least Stroila, para. [0045]: Example selection methods include, but are not limited to, selecting a trajectory that is in a most central location of the trajectory bundle, selecting trajectory bundle based on a computed curve fit or distance (e.g., discrete Frechet distance), etc. In another embodiment, the system 100 may generate a representative trajectory by a statistical process (e.g., averaging or finding a mean of the trajectories within the trajectory bundle). & para. [0092]: In step 409, the mapping platform 107 generates a map of the bounded geographic area based on the one or more trajectory bundles.), and
adding the reference trajectory to a map indicating road structure in the predetermined section (see at least Stroila, Fig. 11 & para. [0111]: FIG. 11 is a diagram illustrating a potential maneuver associated with a trajectory bundle, according to one embodiment. The trajectory bundle 1101 in map 1103 represents a possible turn at the intersection. In this example, the mapping platform 107 clustered all trajectories with this shape and heading to make the tum into the trajectory bundle 1101. Although the trajectory 1101 is depicted as being overlaid on a depiction of the intersection, the actual map topology of the intersection is not used to construct the trajectories from the probe data or cluster the trajectories according to a curve similarity to represent the turning maneuver at the intersection.).
However Stroila does not explicitly disclose
selecting a class from the plurality of classes having a highest number of trajectories;
wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory.
Fowe teaches
selecting a class from the plurality of classes having a highest number of trajectories (see at least Fowe, para. [0054]: Once the lane-level maneuvers for a group of vehicles having a similar origin and destination, and the lane-level maneuvers are clustered, the average time of travel for each medoid can be compared to indicate the fastest, most efficient lane-level maneuver strategy, while the cluster with the largest number of vehicles will represent the most popular approach. & para. [0061]: FIG. 5 illustrates a flowchart of a method according to an example embodiment of the present invention for establishing recommended lane-level guidance between an origin and a destination based on a safe, efficient, or popular path. At 510, a plurality of probe data points are received from a plurality of probe apparatuses traveling between origins and destinations.);
wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory (see at least Fowe, para. [0041]: Embodiments of the present disclosure create historical data that can advise on the best or more appropriate lanes for a vehicle to navigate on a road segment. To achieve this, data is obtained from drivers that have traversed similar origin/destination routes so that the lane choices taken may be focused on achieving a similar journey from the origin to the destination. Historical data is obtained that learns from how drivers have safely driven a road at a lane-level and that data may be used to guide new drivers traversing the same road segments. Further, embodiments may use data obtained from drivers to inform autonomous vehicles such that autonomous vehicles may be controlled according to the popular/safe/efficient routes selected by humans through machine learning of the lane-level routes.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Stroila to incorporate the teaching of selecting a class from the plurality of classes having a highest number of trajectories, wherein the at least one vehicle is autonomously controlled in the predetermined section of the road in accordance with the reference trajectory of Fowe, with a reasonable expectation of success in order to improves safety and efficiency in a proactive manner rather than reacting to abnormal or exceptional events on a roadway (see at least Fowe, para. [0039]).
Claim(s) 2 & 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stroila, in view of Fowe, in view of US 2023/0111121A1 (“Phan”).
As per claim 2 Stroila discloses
wherein each of the plurality of trajectories includes information indicating acceleration applied to a vehicle on a trajectory (see at least Stroila, para. [0048]: In one embodiment, these changes in traffic rules or classification can be automatically detected by the system 100 by generating the traffic bundles over a time series and comparing the characteristics of the bundles (e.g., trajectory counts) over the time series. Although trajectory count is discussed as an example characteristic, any other characteristic of the bundles or the trajectories/probe data within the bundles (e.g., speed, acceleration/deceleration as calculated form the speed and time information in the probe data, heading, etc.) can be analyzed over time to determine changes.).
However Stroila does not explicitly disclose
among the plurality of trajectories, the at least one processor classifies trajectories of which an absolute value of the acceleration is not greater than a predetermined threshold into the plurality of classes.
Phan teaches
among the plurality of trajectories, the at least one processor classifies trajectories of which an absolute value of the acceleration is not greater than a predetermined threshold into the plurality of classes (see at least Phan, para. [0039]: Thus, the system can calculate, using a metric, a value between each predicted trajectory and a trajectory that the agent has traveled to determine whether each value is within a threshold. For example, the function can cause a random trajectory to be selected (e.g., using a random number generator). In an embodiment, a function can use one or more templates (e.g., template trajectories) for selecting the best trajectory. The templates can be static or dynamically generated based on a current state of the agent (e.g., speed, acceleration, yaw rate, or other suitable state component). & para. [0159]: For example, the prediction system can analyze each traveled trajectory within the training set and determine a plurality of clusters of trajectories within that training set. For example, there may be a cluster of trajectories for turning right at a specific angle, a cluster of trajectories for turning left at a specific angle, a cluster of trajectories for moving straight, or another suitable cluster of trajectories. If the prediction system is configured to use templates while training, the angle comparison for each predicted trajectory is with each template trajectory (e.g., based on the angle between the predicted trajectory and the traveled trajectory being above the threshold). Thus, the predicted trajectory is selected based on the index of the template that was selected.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Stroila to incorporate the teaching of among the plurality of trajectories, the at least one processor classifies trajectories of which an absolute value of the acceleration is not greater than a predetermined threshold into the plurality of classes of Phan, with a reasonable expectation of success in order to predict movement of an agent (e.g., a vehicle, a bicycle, or a pedestrian) and perform motion planning based on that movement (see at least Phan, para. [0040]).
As per claim 7 Stroila discloses
wherein each trajectory of the plurality of trajectories corresponds to actual travel of a plurality of vehicles (see at least Stroila, para. [0046]: For example, the relative trajectory counts within each bundle ( e.g., number of trajectories clustered or grouped into each trajectory bundle) can be used to indicate a travel characteristic such as a mode of transportation ( e.g., driving, bicycling, pedestrians, etc.). & para. [0087]: In step 401, the mapping platform 107 receives probe data associated with the bounded geographic area. In one embodiment, the probe data are collected from one or more sensors of a plurality of devices (e.g., vehicles 101, UEs 103, etc.) traveling in the bounded geographic area. As previously discussed, the probe data includes probe points indicating a position, a heading, a speed, a time, or a combination thereof of each of the plurality of devices.).
However Stroila does not explicitly disclose
wherein a trajectory that violates at least one traffic law is excluded from the plurality of trajectories that are classified into the plurality of classes.
Phan teaches
wherein a trajectory that violates at least one traffic law is excluded from the plurality of trajectories that are classified into the plurality of classes (see at least Phan, para. [0144-0145]: The prediction system can identify, in the trajectory lattice, those trajectories that the agent cannot travel based on the one or more of the road rules data and the road marking data, and remove those trajectories from the trajectory lattice….Trajectory lattice 1708 illustrates a trajectory lattice with a number of trajectories removed based on road rules and/or road markings. The illustration shows that there is no trajectories for turning left (e.g., because turning left would require going against direction of the traffic.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Stroila to incorporate the teaching of wherein a trajectory that violates at least one traffic law is excluded from the plurality of trajectories that are classified into the plurality of classes of Phan, with a reasonable expectation of success in order to predict movement of an agent (e.g., a vehicle, a bicycle, or a pedestrian) and perform motion planning based on that movement (see at least Phan, para. [0040]).
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOHAMED ABDO ALGEHAIM whose telephone number is (571)272-3628. The examiner can normally be reached Monday-Friday 8-5PM 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, Fadey Jabr can be reached at 571-272-1516. 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.
/MOHAMED ABDO ALGEHAIM/Primary Examiner, Art Unit 3668
Prosecution Insights