CTFR 18/815,421 CTFR 100876 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. 12-151 AIA 26-51 12-51 Status of claims The following claims have been rejected or allowed for the following reasons: Claim(s) 1-20 is rejected under 35 USC § 103 Information Disclosure Statement 06-52 The information disclosure statement/statements (IDS) were filed on 8/26/24, 2/17/26. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA 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. 07-20-02-aia AIA This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. 07-21-aia AIA Claim (s) 1-3, and 5-6 is/are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev (US 20240242618 A1), in further view of Kanagarajan (US 20210150922 A1), in further view of Schonefeld (Runway incursion prevention systems: A review of runway incursion avoidance and alerting system approaches | NPL | 2012) . Regarding claim 1 Osipychev teaches A method for determining a probability of runway incursion during aircraft landing, the method comprising: integrating object detections of objects possibly within a runway safety area (Osipychev [0011] reads “At controlled airports, air traffic controllers maintain a safe operating environment by keeping aircraft separated from each other and from ground vehicles. In some examples, an airplane is not allowed to take off or land until all other aircraft and ground vehicles are clear of its designated runway. This ensures that aircraft maintain an appropriate separation distance to other aircraft and ground vehicles.” And figure 1 depicts areas in which runway collisions may occur.); PNG media_image1.png 513 321 media_image1.png Greyscale Osipychev Figure 1 over time by detecting possible new and existing object tracks of the objects, assigning the object detections to the object tracks of the objects, and filtering the object detections of the objects to smooth the tracks; (Osipychev abstract reads “the computing system is further configured to determine an intersection probability value that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect. A behavior probability value that comprises a confidence level of a predicted behavior classification for the intruder vehicle is determined based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft. Based at least on the intersection probability value and the behavior probability value, the computing system is configured to output a recommended collision avoidance action.”); estimating an object state based on the integrated detections; (Osipychev [0017] reads “The computing system 102 poses collision avoidance as a data-driven object detection problem. The computing system 102 is configured to identify a possible collision by analyzing a dynamic state of the aircraft 104 and an intruder vehicle 106.”); predicting future object motion of the objects and trajectory previews of the detected new and existing object tracks based on the estimated object state, a dynamic model, and a track history; (Osipychev [0022] “With reference again to FIG. 2, the computing system 102 further comprises a trajectory prediction module 118 configured to model a trajectory of the intruder vehicle 106 based at least on the run-time position data 110 for the intruder vehicle. The trajectory prediction module 118 also models a trajectory of the aircraft 104 based at least on the run-time position data 112 for the aircraft 104. In some examples, the trajectories are further modeled based upon a map 120 of an airport. For example, the trajectory of the intruder vehicle 106 may be based upon constraints prescribed by the map 120, such as locations where ground vehicles can turn and distances between a ground vehicle to intersections and runway thresholds. In this manner, the map 120 may guide the determination of the trajectory of the intruder vehicle 106.”); determining a first outcome, a second outcome, or a third outcome based on the probability of the runway incursion based on the predicted future object motion, (Osipychev [0013] reads “Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); and the third outcome including that the runway incursion is ongoing indicating at least one of the detected new and existing object tracks is predicted to be within the runway safety area when an aircraft touches down; (Osipychev [0057] reads “As indicated at 522, in some examples, the recommended collision avoidance action is output at a “sweet spot” in a landing approach. The term “sweet spot” refers to a predetermined location (e.g. a predetermined time and/or geographic location, or predetermined range of times and/or range of geographic locations) in a landing approach. For example, the computing system 102 may be configured to determine, based upon historical landing information or modeled landing information, a predetermined time and/or a predetermined location at which there is adequate time to redirect the aircraft 104 or to instruct the aircraft 104 to continue the landing approach.”); Osipychev does not teach the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria, and adapting the detection over time to new environments based on accuracy of the probability. Kanagarajan in analogous art, teaches and adapting the detection over time to new environments (Kanagarajan [0052] reads “Camera 310 is configured to capture images within a field of view 312 and may be configured to send the captured images to collision awareness system 100. Camera 310 can be mounted at a fixed location (e.g., on a pole or building) or at a movable location (e.g., on a vehicle such as vehicle 140 or an unmanned aerial vehicle (UAV)) and, in some example, may be configured to rotate to increase field of view 312. The captured images may be visible-light images, infrared images, and/or any other type of images. Vehicle 140, object 150, and/or a potential collision location may be shown in the captured images.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev with that of Kanagarajan to include an aspect that would allow for the system to adapt to its surroundings. This would then improve the alerting process of a pilot before a collision. (Kanagarajan [0006] reads “In general, this disclosure relates to systems, devices, and techniques for providing collision awareness using one or more lights mounted on a vehicle. A system implementing the techniques of this disclosure can determine whether the likelihood of a collision at a potential collision location involving the vehicle and an object is greater than or equal to a threshold level. In response to determining that the collision likelihood is greater than or equal to the threshold level, the system may cause one or more lights mounted on the vehicle to direct light towards the potential collision location and/or towards the object. The light may, therefore, notify an occupant of the object (if occupied) of the potential collision, as well as provide the operator of the vehicle (e.g., a pilot of an aircraft) with a notification of the potential collision and a potentially more clear view of the potential collision location.”); Osipychev/Kanagarajan does not teach the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria. Schonefeld in analogous art, teaches the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, (Schonefeld section 2.2 reads “False or insufficient information (in gray) leads to poor decisions (such as crossing a closed hold line), which result in dangerous operations. RIPAS attempts to provide reliable information that is sufficient for good decisions (such as showing the status of a hold line by signals). The remaining poor decisions should be detected by RIPAS, and a warning should be issued to prevent dangerous operations. If dangerous operations occur anyway, then the system shall issue an alert so that the operation can be cancelled and a status of safe operation can be obtained.”); the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria, (Schonefeld section 3.1.3.2. reads “Surface Movement Radar (SMR): A global and usually non-cooperative sensor that detects vehicles over the whole airport area. Its update rate is usually approximately 1 Hz. Its capabilities for locating smaller vehicles and pedestrians are limited. Even high performance systems such as Airport Surface Detection Equipment Model 3(ASDE-3) radar and Airport Surface Detection Equipment-Model X (ASDE-X) radar suffer from Multipath reflections that can lead to false target reports”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan with that of Schonefeld to include a system for better dealing with edge cases in a runway incursion system. This improvement would allow for improved safety around airports with regards to runway incursions. (Schonefeld introduction reads “Runway incursions are occurrences at an aerodrome that involve the incorrect presence of an aircraft, a ground vehicle, or a person on the protected area designated for the landing and take-off of aircraft. The growing traffic volume has kept avoiding runway incursions on the National Transportation Safety Board (NTSB) “Most Wanted” list for safety improvements for over a decade [1]. In the past, runway incursions have led to accidents with significant loss of life.”); Regarding claim 2 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 1, wherein detecting possible new and existing object tracks comprises: accessing the track history, (Osipychev [0029] reads “In some other examples, the computing system comprises a recurrent neural network. The recurrent neural network receives, as inputs, a sequence of position data for the intruder vehicle and a sequence of position data for the aircraft. In this manner, the recurrent neural network is configured to use a previous state of the intruder vehicle and/or the aircraft to predict the likelihood of a collision.”); sensor measurements associated with the possible new and existing object tracks, (Kanagarajan [0022] reads “Processing circuitry 110 may be configured to predict potential collisions based on data received by receiver 120 and/or data stored by memory 122. For example, receiver 120 may include a radar sensor that is configured to receive reflected signals indicating the locations and velocities of vehicle 140 and object 150. Additionally or alternatively, receiver 120 may be configured to receive a surveillance message from vehicle 140 or object 150 indicating the location and velocity of vehicle 140 or object 150. Other potential data sources for processing circuitry 110 to predict potential collisions include traffic controller clearances, images of vehicle 140 or object 150, and Global Navigation Satellite System (GNSS) data.”); and the trajectory previews. (Osipychev [0022] “With reference again to FIG. 2, the computing system 102 further comprises a trajectory prediction module 118 configured to model a trajectory of the intruder vehicle 106 based at least on the run-time position data 110 for the intruder vehicle.”); Regarding claim 3 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 2, further comprising: detecting and tracking non-cooperative objects in a pre-selected region during the aircraft landing; (Osipychev [0022] reads “In some examples, the trajectories are further modeled based upon a map 120 of an airport. For example, the trajectory of the intruder vehicle 106 may be based upon constraints prescribed by the map 120, such as locations where ground vehicles can turn and distances between a ground vehicle to intersections and runway thresholds. In this manner, the map 120 may guide the determination of the trajectory of the intruder vehicle 106.”); and determining the probability of the runway incursion based on vision detection probabilities, a number of scans of the pre-selected region associated with the aircraft landing, a number of updates to the detected existing and new tracks of objects, (Osipychev [0013] reads “Based at least on the run- time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); a pre-selected false negative threshold, and a pre-selected false positive threshold. (Osipychev [0034] reads “The recommended collision avoidance action is output in some examples based at least on a determination that the collision probability value is greater than a threshold value. In some examples, the threshold value is in a range of 5% to 100%. In other examples, the threshold value is in a range of 20% to 100%. In yet other examples, the threshold value is in a range of 50% to 100%. In some other examples, a threshold value of less than 5% may be used. Further, the threshold value may be tuned based on false negative and/or false positive results.”); Regarding claim 5 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 3, wherein the pre-selected region is based on boundaries of an airport runway, boundaries of a taxiway system associated with the airport runway, and boundaries of a runway safety area associated with the airport runway. (Osipychev [0022] reads “In some examples, the trajectories are further modeled based upon a map 120 of an airport. For example, the trajectory of the intruder vehicle 106 may be based upon constraints prescribed by the map 120, such as locations where ground vehicles can turn and distances between a ground vehicle to intersections and runway thresholds. In this manner, the map 120 may guide the determination of the trajectory of the intruder vehicle 106.”); Regarding claim 6 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 5, wherein the airport runway comprises: one of a defined area for the landing and takeoff of the aircraft, taxiways for ground movement of the aircraft, blast pads, and overrun areas, a water surface, a strip for aircraft landing training that is adjacent to the defined area, a vertiport, or a heliport. (Osipychev [0022] reads “In some examples, the trajectories are further modeled based upon a map 120 of an airport. For example, the trajectory of the intruder vehicle 106 may be based upon constraints prescribed by the map 120, such as locations where ground vehicles can turn and distances between a ground vehicle to intersections and runway thresholds. In this manner, the map 120 may guide the determination of the trajectory of the intruder vehicle 106.” It would be appreciated by one with ordinary skill in the art that the given map of the airport would include any other common and well understood physical features of the given airport or location. ); 07-21-aia AIA Claim(s ) 4 is /are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev/Kanagarajan/Schonefeld , in further view of Blackman ( NPL, Design and analysis of modern tracking systems, 1999 ), in further view of Chuyin (CN 117519248 A). Re garding claim 4 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 3, wherein the auction algorithm is configured to assign using a distance between the non-cooperative objects, (Osipychev [0011] reads “In some examples, an airplane is not allowed to take off or land until all other aircraft and ground vehicles are clear of its designated runway. This ensures that aircraft maintain an appropriate separation distance to other aircraft and ground vehicles.” It would be appreciated by one with ordinary skill in the art that the calculated or estimated distances between objects would be an important factor and quantity in the sensing and determination of potentially colliding vehicles.); Osipychev/Kanagarajan/Schonefeld does not teach further comprising: assigning the detection to the non-cooperative objects using statistical gating and an auction algorithm, wherein the statistical gating includes a rectangular gate based on a state covariance to filter the detection considered for assignment, and wherein the detection that is not used to maintain an existing track is assigned to a new probationary track. Blackman in analogous art, teaches further comprising: assigning the detection to the non-cooperative objects using statistical gating (Blackman page 334-335 reads “Gating is a technique for eliminating unlikely observation-to-track pairings. — As discussed in Chapter 1, a gate is formed about the predicted measurement and all observations that satisfy the gating relationship (fall within the gate) are considered for track update. The manner in which the observations are actually chosen to update the track depends on the data association method but most data association methods utilize gating in order to reduce later computation.” It would be appreciated by one with ordinary skill in the art that this form of statistical method would be used and likewise adapted to this application.); And wherein the statistical gating includes a rectangular gate based on a state covariance to filter the detection considered for assignment, (Blackman 335 reads “e actual gating process is typically a progression of operations with in-creasing complexity. One computationally efficient approach to first use a coarse form of gating, such as binning. Using the binning approach, the measurement space is divided into a grid of cells (or bins). Then, a track is only com- pared with observations in its bin and in adjacent bins. Bin size can be chosen adaptively based on track quality and available computational resources. Efficient techniques for the implementation of coarse gating are presented in [13-15].” It would be appreciated by one with ordinary skill in the art that this form of statistical method would be used and likewise adapted to this application.); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan/Schonefeld with that of Blackman to include a method for filtering the large amount of data that is being imputed to the system. This would then to provide the system with a modern method of updating the track of an object. (Blackman page 334 and 335 reads “Gating is a technique for eliminating unlikely observation-to-track pairings. — As discussed in Chapter 1, a gate is formed about the predicted measurement and all observations that satisfy the gating relationship (fall within the gate) are considered for track update”); Osipychev/Kanagarajan/Schonefeld/Blackman does not teach and an auction algorithm, and wherein the detection that is not used to maintain an existing track is assigned to a new probationary track. Chuyin in analogous art, teaches and an auction algorithm, (Chuyin page 3 paragraph 2 reads “The existing task planning method comprises the following steps: an intelligent optimization method of biological elicitation, a task planning method of reinforcement learning and a method based on a market auction mechanism;”); and wherein the detection that is not used to maintain an existing track is assigned to a new probationary track. (Chuyin page 4 paragraph 24 reads “judging the global optimal inspection task Is of unmanned aerial vehicle a * Newly allocated patrol Checking whether a line segment consisting of the positions of the tasks is associated with the candidate unmanned plane b * If the line segments formed by the positions of any two adjacent inspection tasks intersect, the step S4.3 is performed, and if the line segments do not intersect, the global optimal inspection task is added>Assigned to unmanned plane a * Step S5 is carried out afterwards;” It would be appreciated by one with ordinary skill in the art that in the case where vehicles are not going to collide that the resources are consumed to preform that task would be re allocated.) It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan/Schonefeld/Blackman with that of Chuyin to include a method for prioritizing which objects to be tracked. This would allow for an improved and more efficient system for task allocation and planning of aerial vehicles. (Chuyin page 3 paragraph 1 reads “at the moment, an efficient task planning scheme is required to be adopted to reduce the unnecessary navigation distance of the unmanned aerial vehicles, so that the unmanned aerial vehicles can complete the electric power inspection task more quickly.”); 07-21-aia AIA Claim (s) 7-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev/Kanagarajan/Schonefeld, in further view of Durand (US 20140142838 A1) . Regarding claim 7 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 3. Osipychev/Kanagarajan/Schonefeld does not teach wherein the pre-selected false negative threshold includes a pre-selected maximum allowed value of a false negative, and wherein the pre-selected false positive threshold includes a maximum cumulative probability of a false positive. Durand in analogous art, teaches wherein the pre-selected false negative threshold includes a pre-selected maximum allowed value of a false negative, and wherein the pre-selected false positive threshold includes a maximum cumulative probability of a false positive. (Durand [0030] reads “The threshold may also be selected so that a possibility of false positive collision forecasting is reduced or minimized.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan/Schonefeld with that of Durand to include a process that would allow for the system to understand false positive and negative results. This would allow the system to be more aware of aircraft on the ground. (Durand [0003] reads “Aircraft are required to operate in two different environments, on the ground and in the air. While on the ground (e.g., while at an airport) aircraft need to be moved around to position them for takeoff as well as for other reasons such as maintenance, storage, passenger loading/unloading and the like. However, aircraft are designed, primarily, to optimize their flight, not their ground based operations. This can lead to cases on the ground, especially with wide body aircraft, where the aircraft crews have poor situational awareness of the aircraft and its dimensions due to limited visibility. Thus, the crew is limited in their ability to judge clearance of the aircraft with respect to obstacles on the ground, which may be numerous at unimproved airports in some countries.”); Regarding claim 8 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 3, further comprising: declaring the runway incursion when a ratio of the number of scans to the number of updates reaches a threshold (Osipychev [0004] reads “The instructions are executable by the processor to receive run-time position data for an intruder vehicle and to receive run-time position data for an aircraft. A trajectory of the intruder vehicle is modeled based at least on the run-time position data for the intruder vehicle.” And [0033 – 0034] reads “In this manner, the trajectory prediction is scaled based upon the predicted behavior of the intruder vehicle to accurately estimate collision risk posed by the intruder vehicle. In other examples, when the intersection probability value and the behavior probability value are correlated, the collision probability value is found using the conditional probability rule. The recommended collision avoidance action is output in some examples based at least on a determination that the collision probability value is greater than a threshold value.” It would be appreciated by one with ordinary skill in the art that an vehicle that is being monitored by a collision avoidance system would have it run-time data continuously updated such that it is accurate at the current run time.); Osipychev/Kanagarajan/Schonefeld does not teach based on the pre-selected false negative threshold and the pre-selected false positive threshold. Durand in analogous art, teaches based on the pre-selected false negative threshold and the pre-selected false positive threshold. (Durand [0030] reads “The threshold may also be selected so that a possibility of false positive collision forecasting is reduced or minimized.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan/Schonefeld with that of Durand to include a process that would allow for the system to understand false positive and negative results. This would allow the system to be more aware of aircraft on the ground. (Durand [0003] reads “Aircraft are required to operate in two different environments, on the ground and in the air. While on the ground (e.g., while at an airport) aircraft need to be moved around to position them for takeoff as well as for other reasons such as maintenance, storage, passenger loading/unloading and the like. However, aircraft are designed, primarily, to optimize their flight, not their ground based operations. This can lead to cases on the ground, especially with wide body aircraft, where the aircraft crews have poor situational awareness of the aircraft and its dimensions due to limited visibility. Thus, the crew is limited in their ability to judge clearance of the aircraft with respect to obstacles on the ground, which may be numerous at unimproved airports in some countries.”); 07-21-aia AIA Claim (s) 9-13 is/are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev/Kanagarajan/Schonefeld in further view of Pearson (US 20240395154 A1), in further view of Yufeng (US 20210350715 A1); Regarding claim 9 Osipychev/Kanagarajan/Schonefeld teaches The method of claim 3. Osipychev/Kanagarajan/Schonefeld does not teach further comprising: filtering tracks of non-cooperating objects based on track history, sensor measurements, and trajectory previews generated by the dynamic model, the filtering including: estimating the trajectory previews of the non-cooperating objects by providing the track history to a first Kalman filter; estimating acceleration of the non-cooperating objects by providing the trajectory previews and the sensor measurements to a second Kalman filter; and smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process. Pearson in analogous art, teaches the filtering including: estimating the trajectory previews of the non-cooperating objects by providing the track history to a first Kalman filter; estimating acceleration of the non-cooperating objects by providing the trajectory previews and the sensor measurements to a second Kalman filter; (Pearson [0071] reads “In some embodiments, determining the third state estimate and the third state estimate confidence metric comprises using an Extended Kalman Filter. In some embodiments, the second state estimate, the second state estimate confidence metric, the gyroscopic data, the accelerometer data, the altitude data, the magnetic field data and the GNSS data are inputs of the Extended Kalman Filter.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan/Schonefeld with that of Pearson to provide a safer takeoff and landing environment for aircraft in high density situations. (Pearson [0002] reads “Aerial vehicles, such as manned vertical take-off and landing (VTOL) aerial vehicles, can collide with objects such as birds, walls, buildings or other aerial vehicles during flight. Collision with an object can cause damage to the aerial vehicle, particularly when the aerial vehicle is traveling at a high speed. Furthermore, collisions can be dangerous to people or objects nearby that can be hit by debris or the aerial vehicle itself. This can be a particularly large issue when high density airspace is considered.); Osipychev/Kanagarajan/Schonefeld/Pearson does not teach further comprising: filtering tracks of non-cooperating objects based on track history, sensor measurements, and trajectory previews generated by the dynamic model, and smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process. Yufeng in analogous art, teaches further comprising: filtering tracks of non-cooperating objects based on track history, sensor measurements, and trajectory previews generated by the dynamic model, (Yufeng [0018] reads “FIG. 7 is diagram that illustrates position filtering when projecting a measured position onto a guidance line while making maneuver path predictions, in accordance with some embodiments;”); and smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process. (Yufeng [0018] reads “FIG. 7 is diagram that illustrates position filtering when projecting a measured position onto a guidance line while making maneuver path predictions, in accordance with some embodiments;” It would be appreciated by one with ordinary skill in the art that filtering of a projection would include reducing the noise in the data and further smoothing that data.); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan/Schonefeld/Pearson with that of Yufeng to provide a system that would allow a pilot to have a better sense of their surrounding and to avoid wing tip collisions. (Yufeng [0002] reads “It can be very difficult for a pilot to see the wingtips of its aircraft while taxiing the aircraft on an airport surface and judge the clearance between its aircraft and obstructions such as buildings, other aircraft, ground vehicles, and poles etc. Collisions with such obstructions have occurred every year for many years and the frequency of collisions have increased with air traffic growth. Aircraft collisions with any obstruction can not only damage the aircraft, but can also put the aircraft out of service, and may impact an airlines' reputation.”); Regarding claim 10 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng teaches The method of claim 9, further comprising: receiving the sensor measurements; sensor measurements associated with the possible new and existing object tracks, (Kanagarajan [0022] reads “Processing circuitry 110 may be configured to predict potential collisions based on data received by receiver 120 and/or data stored by memory 122. For example, receiver 120 may include a radar sensor that is configured to receive reflected signals indicating the locations and velocities of vehicle 140 and object 150. Additionally or alternatively, receiver 120 may be configured to receive a surveillance message from vehicle 140 or object 150 indicating the location and velocity of vehicle 140 or object 150. Other potential data sources for processing circuitry 110 to predict potential collisions include traffic controller clearances, images of vehicle 140 or object 150, and Global Navigation Satellite System (GNSS) data.”); estimating acceleration of the possible new and existing objects; (Osipychev [0023] reads “In some examples, the trajectory prediction module 116 comprises a deterministic model. For example, the trajectory of the aircraft 104 may be a predetermined function of a ground speed and a heading of the aircraft 104. In other examples, the trajectory prediction module 118 comprises a machine learning model trained to output the trajectory of the intruder vehicle and/or the trajectory of the aircraft.” It would be appreciated by one with ordinary skill in the art that a trajectory of an aircraft would include acceleration especially when in relation to an airport where aircraft are normally expected to accelerate in order to take off and land.); determining the trajectory previews based on the estimated acceleration; (Osipychev [0022] “With reference again to FIG. 2, the computing system 102 further comprises a trajectory prediction module 118 configured to model a trajectory of the intruder vehicle 106 based at least on the run-time position data 110 for the intruder vehicle.”); and generating a predicted state and a covariance estimate of object trajectories. (Osipychev [0013] reads “Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); Regarding claim 11 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng teaches The method of claim 10, wherein estimating acceleration of the possible new and existing objects comprises: using a modified Kalman filter to determine the trajectory previews. (Pearson [0071] reads “In some embodiments, determining the third state estimate and the third state estimate confidence metric comprises using an Extended Kalman Filter. In some embodiments, the second state estimate, the second state estimate confidence metric, the gyroscopic data, the accelerometer data, the altitude data, the magnetic field data and the GNSS data are inputs of the Extended Kalman Filter.”); Regarding claim 12 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng teaches The method of claim 11, further comprising: smoothing the object trajectories; and obtaining an inference. (Yufeng [0018] reads “FIG. 7 is diagram that illustrates position filtering when projecting a measured position onto a guidance line while making maneuver path predictions, in accordance with some embodiments;” It would be appreciated by one with ordinary skill in the art that filtering of a projection would include reducing the noise in the data and further smoothing that data.); Regarding claim 13 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng teaches The method of claim 12, wherein smoothing the object trajectories comprises: feeding the object trajectories, the sensor measurements, and the trajectory previews into a Gaussian Process. (Osipychev [0004] reads “The computing system is further configured to determine an intersection probability value that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft. A behavior probability value that comprises a confidence level of a predicted behavior classification for the intruder vehicle is determined based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft. Based at least on the intersection probability value and the behavior probability value, the computing system is configured to output a recommended collision avoidance action.” It would be appreciated by one with ordinary skill in the art that the computing system would be configured to use any sort of commonly known mathematical expression to predict the trajectory of future objects); 07-21-aia AIA Claim (s) 14 - 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng, in further view of Barfoot ( NPL | Batch Continuous-Time Trajectory Estimation as Exactly Sparse Gaussian Process Regression | 2014 ) . Regarding claim 14 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng teaches The method of claim 13. Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng does not teach wherein for the Gaussian Process: a linear time varying stochastic differential equation is PNG media_image2.png 178 298 media_image2.png Greyscale PNG media_image3.png 426 289 media_image3.png Greyscale PNG media_image4.png 615 419 media_image4.png Greyscale PNG media_image5.png 42 291 media_image5.png Greyscale Barfoot in analogous art, teaches wherein for the Gaussian Process: a linear time varying stochastic differential equation is PNG media_image2.png 178 298 media_image2.png Greyscale PNG media_image3.png 426 289 media_image3.png Greyscale PNG media_image4.png 615 419 media_image4.png Greyscale PNG media_image5.png 42 291 media_image5.png Greyscale (Barfoot end of page 1 and beginning of page 2 reads “In this paper, we consider a particular class of GPs (generated by linear, time-varying (LTV) stochastic differential equations (SDE) driven by white noise) whereupon the inverse kernel matrix is exactly sparse (block-tridiagonal) and can be derived in closed form. Concentrating on this class of covariance functions results in only a minor loss of generality, because many commonly used covariance functions such the Matérn class and the squared exponential covariance function can be exactly or approximately represented as linear SDES [17, 37, 41]. We provide an example of this relationship at the end of this paper. The resulting sparsity allows the approach of Tong et al. [45, 46] to be implemented very efficiently.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng with that of Barfoot to include complex differential and Gaussian expressions. This would allow for the system to have improved model of predicted trajectories. (Barfoot abstract reads “Abstract--In this paper, we revisit batch state estimation through the lens of Gaussian process (GP) regression. We consider continuous-discrete estimation problems wherein a trajectory is viewed as a one-dimensional GP, with time as the independent variable. Our continuous-time prior can be defined by any linear, time-varying stochastic differential equation driven by white noise; this allows the possibility of smoothing our trajectory estimates using a variety of vehicle dynamics models (e.g. 'constant-velocity'). We show that this class of prior results in an inverse kernel matrix (i.e., covariance matrix between all pairs of measurement times) that is exactly sparse (block-tridiagonal) and that this can be exploited to carry out GP regression (and interpolation) very efficiently.”); Regarding claim 15 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng/Barfoot teaches The method of claim 14, wherein the trajectory previews are generated by the dynamic model comprising PNG media_image6.png 161 407 media_image6.png Greyscale (Barfoot page 2 paragraph 2 reads “The result is that we derive a principled method to construct trajectory-smoothing terms for batch optimization (or factors inafactor-graph representation) based on a class of useful motion models; this paves the way to incorporate vehicle dynamics models, including exogenous inputs, to help with trajectory estimation.”); ); Regarding claim 16 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng/Barfoot teaches The method of claim 15, wherein the predicted state and the covariance estimate of each of the object trajectories comprise PNG media_image7.png 446 540 media_image7.png Greyscale PNG media_image8.png 176 496 media_image8.png Greyscale (Barfoot page 2 paragraph 3 reads “Therefore, our main contribution is to emphasize the strong connection between classical estimation theory and machine learning via GP regression. We use the fact that the inverse kernel matrix is sparse for a class of useful GP priors [28, 37] in a new way to efficiently implement nonlinear, GP regression for batch, continuous-time trajectory estimation. We also show that this naturally leads to a subtle generalization of SLAM that we call simultaneous trajectory estimation and mapping (STEAM), with the difference being that chains of discrete poses are replaced with Markovian trajectories in order to incorporate continuous-time motion priors in an efficient way. Finally, by using this GP paradigm, we are able to exploit the classic GP interpolation approach to query the trajectory at any time of interest in an efficient manner.”); Regarding claim 17 Osipychev/Kanagarajan/Schonefeld/Pearson/Yufeng/Barfoot teaches The method of claim 16, further comprising: feeding an accelerate estimate, PNG media_image9.png 17 17 media_image9.png Greyscale into the dynamic model to obtain the previews. (Barfoot page 5 paragraph 7 reads “Alternatively, since these parameters have physical meaning. they can be computed directly from the training data. In our experiments, we obtained Qe by modelling it as a diagonal matrix, and fitting Gaussians to the state accelerations. The measurement noise properties were determined from the training data in a similar manner.”); 07-21-aia AIA Claim (s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev (US 20240242618 A1), in further view of Durand (US 20140142838 A1), in further view of Schonefeld (Runway incursion prevention systems: A review of runway incursion avoidance and alerting system approaches | NPL | 2012) . Regarding claim 18 Osipychev teaches A computer system for determining a probability of runway incursion during aircraft landing, the computer system comprising: a hardware processor; and a non-volatile storage medium storing instructions that when executed by the hardware processor perform operations comprising: detecting and tracking non-cooperative objects in a pre-selected region during the aircraft landing; (Osipychev abstract reads “the computing system is further configured to determine an intersection probability value that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect. A behavior probability value that comprises a confidence level of a predicted behavior classification for the intruder vehicle is determined based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft. Based at least on the intersection probability value and the behavior probability value, the computing system is configured to output a recommended collision avoidance action.”); and determining the probability of the runway incursion based on vision detection probabilities, a number of scans of the pre-selected region associated with the aircraft landing, a number of updates to the detected existing and new tracks of objects, (Osipychev [0013] reads “Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); and the third outcome including that the runway incursion is ongoing indicating at least one of the detected new and existing object tracks is predicted to be within the runway safety area when an aircraft touches down. (Osipychev [0057] reads “As indicated at 522, in some examples, the recommended collision avoidance action is output at a “sweet spot” in a landing approach. The term “sweet spot” refers to a predetermined location (e.g. a predetermined time and/or geographic location, or predetermined range of times and/or range of geographic locations) in a landing approach. For example, the computing system 102 may be configured to determine, based upon historical landing information or modeled landing information, a predetermined time and/or a predetermined location at which there is adequate time to redirect the aircraft 104 or to instruct the aircraft 104 to continue the landing approach.”); Osipychev does not teach and determining a first outcome, a second outcome, or a third outcome based on the probability of the runway incursion based on the predicted future object motion, the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria, a pre-selected false negative threshold, and a pre-selected false positive threshold. Duran in analogous art, teaches a pre-selected false negative threshold, and a pre-selected false positive threshold. (Durand [0030] reads “The threshold may also be selected so that a possibility of false positive collision forecasting is reduced or minimized.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev with that of Durand to include a process that would allow for the system to understand false positive and negative results. This would allow the system to be more aware of aircraft on the ground. (Durand [0003] reads “Aircraft are required to operate in two different environments, on the ground and in the air. While on the ground (e.g., while at an airport) aircraft need to be moved around to position them for takeoff as well as for other reasons such as maintenance, storage, passenger loading/unloading and the like. However, aircraft are designed, primarily, to optimize their flight, not their ground based operations. This can lead to cases on the ground, especially with wide body aircraft, where the aircraft crews have poor situational awareness of the aircraft and its dimensions due to limited visibility. Thus, the crew is limited in their ability to judge clearance of the aircraft with respect to obstacles on the ground, which may be numerous at unimproved airports in some countries.”); Osipychev/Durand does not teach and determining a first outcome, a second outcome, or a third outcome based on the probability of the runway incursion based on the predicted future object motion, the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria. Schonefeld in analogous art, teaches and determining a first outcome, a second outcome, or a third outcome based on the probability of the runway incursion based on the predicted future object motion, the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, (Schonefeld section 2.2 reads “False or insufficient information (in gray) leads to poor decisions (such as crossing a closed hold line), which result in dangerous operations. RIPAS attempts to provide reliable information that is sufficient for good decisions (such as showing the status of a hold line by signals). The remaining poor decisions should be detected by RIPAS, and a warning should be issued to prevent dangerous operations. If dangerous operations occur anyway, then the system shall issue an alert so that the operation can be cancelled and a status of safe operation can be obtained.”); the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria, (Schonefeld section 3.1.3.2. reads “Surface Movement Radar (SMR): A global and usually non-cooperative sensor that detects vehicles over the whole airport area. Its update rate is usually approximately 1 Hz. Its capabilities for locating smaller vehicles and pedestrians are limited. Even high performance systems such as Airport Surface Detection Equipment Model 3(ASDE-3) radar and Airport Surface Detection Equipment-Model X (ASDE-X) radar suffer from Multipath reflections that can lead to false target reports”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan with that of Schonefeld to include a system for better dealing with edge cases in a runway incursion system. This improvement would allow for improved safety around airports with regards to runway incursions. (Schonefeld introduction reads “Runway incursions are occurrences at an aerodrome that involve the incorrect presence of an aircraft, a ground vehicle, or a person on the protected area designated for the landing and take-off of aircraft. The growing traffic volume has kept avoiding runway incursions on the National Transportation Safety Board (NTSB) “Most Wanted” list for safety improvements for over a decade [1]. In the past, runway incursions have led to accidents with significant loss of life.”); 07-21-aia AIA Claim (s) 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev/Duran/Schonefeld, in further view of Pearson (US 20240395154 A1), in further view of Yufeng (US 20210350715 A1); Regarding claim 19 Osipychev/Duran/Schonefeld teaches The computer system of claim 18, further comprising: filtering tracks of non-cooperating objects based on track history, sensor measurements, and trajectory previews generated by a dynamic model, (Osipychev abstract reads “the computing system is further configured to determine an intersection probability value that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect. A behavior probability value that comprises a confidence level of a predicted behavior classification for the intruder vehicle is determined based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft. Based at least on the intersection probability value and the behavior probability value, the computing system is configured to output a recommended collision avoidance action.”); integrating the object detections over time by detecting possible new and existing object tracks, assigning the object detections to the object tracks, and filtering the object detections; (Osipychev [0013] reads “A trajectory of the aircraft is modeled based at least on the run-time position data for the aircraft. Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.” It would be appreciated by one with ordinary skill in the art that the constant use of current run time data would result in the ability to track objects through time.); estimating an object state based on the integrated detection; predicting future object motion and trajectory previews based on the estimated object state, the dynamic model, and the track history; (Osipychev [0022] “With reference again to FIG. 2, the computing system 102 further comprises a trajectory prediction module 118 configured to model a trajectory of the intruder vehicle 106 based at least on the run-time position data 110 for the intruder vehicle. The trajectory prediction module 118 also models a trajectory of the aircraft 104 based at least on the run-time position data 112 for the aircraft 104. In some examples, the trajectories are further modeled based upon a map 120 of an airport. For example, the trajectory of the intruder vehicle 106 may be based upon constraints prescribed by the map 120, such as locations where ground vehicles can turn and distances between a ground vehicle to intersections and runway thresholds. In this manner, the map 120 may guide the determination of the trajectory of the intruder vehicle 106.”); determining the probability of the runway incursion based on the predicted future object motion; and adapting the detection over time to new environments based on accuracy of the probability. (Osipychev [0013] reads “Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); Osipychev/Duran/Schonefeld does not teach the filtering including: estimating the trajectory previews of the non-cooperating objects by providing the track history to a first Kalman filter; estimating acceleration of the non-cooperating objects by providing the trajectory previews and the sensor measurements to a second Kalman filter; smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process; Pearson in analogous art, teaches the filtering including: estimating the trajectory previews of the non-cooperating objects by providing the track history to a first Kalman filter; estimating acceleration of the non-cooperating objects by providing the trajectory previews and the sensor measurements to a second Kalman filter; (Pearson [0071] reads “In some embodiments, determining the third state estimate and the third state estimate confidence metric comprises using an Extended Kalman Filter. In some embodiments, the second state estimate, the second state estimate confidence metric, the gyroscopic data, the accelerometer data, the altitude data, the magnetic field data and the GNSS data are inputs of the Extended Kalman Filter.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Duran/Schonefeld with that of Pearson to provide a safer takeoff and landing environment for aircraft in high density situations. (Pearson [0002] reads “Aerial vehicles, such as manned vertical take-off and landing (VTOL) aerial vehicles, can collide with objects such as birds, walls, buildings or other aerial vehicles during flight. Collision with an object can cause damage to the aerial vehicle, particularly when the aerial vehicle is traveling at a high speed. Furthermore, collisions can be dangerous to people or objects nearby that can be hit by debris or the aerial vehicle itself. This can be a particularly large issue when high density airspace is considered.); Osipychev/Duran/Schonefeld/Pearson does not teach smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process; Yufeng in analogous art, teaches smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process; (Yufeng [0018] reads “FIG. 7 is diagram that illustrates position filtering when projecting a measured position onto a guidance line while making maneuver path predictions, in accordance with some embodiments;” It would be appreciated by one with ordinary skill in the art that filtering of a projection would include reducing the noise in the data and further smoothing that data.); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Duran/Schonefeld/Pearson with that of Yufeng to provide a system that would allow a pilot to have a better sense of their surrounding and to avoid wing tip collisions. (Yufeng [0002] reads “It can be very difficult for a pilot to see the wingtips of its aircraft while taxiing the aircraft on an airport surface and judge the clearance between its aircraft and obstructions such as buildings, other aircraft, ground vehicles, and poles etc. Collisions with such obstructions have occurred every year for many years and the frequency of collisions have increased with air traffic growth. Aircraft collisions with any obstruction can not only damage the aircraft, but can also put the aircraft out of service, and may impact an airlines' reputation.”); 07-21-aia AIA Claim (s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over as applied to Osipychev (US 20240242618 A1), in further view of Pearson US 20240395154 A1 in further view of Yufeng (US 20210350715 A1), in further view of Schonefeld (Runway incursion prevention systems: A review of runway incursion avoidance and alerting system approaches | NPL | 2012) . Regarding claim 20 Osipychev teaches A computer program product for determining a probability of runway incursion during aircraft landing, the computer program product comprising a non- volatile computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to perform operations comprising: detecting and tracking non-cooperative objects in a pre-selected region during the aircraft landing; (Osipychev abstract reads “the computing system is further configured to determine an intersection probability value that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect. A behavior probability value that comprises a confidence level of a predicted behavior classification for the intruder vehicle is determined based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft. Based at least on the intersection probability value and the behavior probability value, the computing system is configured to output a recommended collision avoidance action.”); determining the probability of the runway incursion based on vision detection probabilities, (Osipychev [0019] reads “For example, image data of an airport may be obtained from a camera located on the aircraft. The image data may be input into the convolutional model to thereby cause the convolutional model to output the run-time position data for one or more vehicles located at the airport. In this manner, the computing system may obtain position data for any vehicles that lack a transponder compatible with the position data receiver.”); a number of scans of the pre-selected region associated with the aircraft landing, a number of updates to the detected existing and new tracks of objects, (Osipychev [0013] reads “Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); a pre-selected false negative threshold, and a pre-selected false positive threshold, (Osipychev [0034] reads “The recommended collision avoidance action is output in some examples based at least on a determination that the collision probability value is greater than a threshold value. In some examples, the threshold value is in a range of 5% to 100%. In other examples, the threshold value is in a range of 20% to 100%. In yet other examples, the threshold value is in a range of 50% to 100%. In some other examples, a threshold value of less than 5% may be used. Further, the threshold value may be tuned based on false negative and/or false positive results.”); filtering tracks of non-cooperating objects based on track history, sensor measurements, and trajectory previews generated by a dynamic model, (Osipychev abstract reads “the computing system is further configured to determine an intersection probability value that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect. A behavior probability value that comprises a confidence level of a predicted behavior classification for the intruder vehicle is determined based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft. Based at least on the intersection probability value and the behavior probability value, the computing system is configured to output a recommended collision avoidance action.”); integrating [[the]] object detections of objects possibly within a runway safety area over time by detecting possible new and existing object tracks of the objects, assigning the object detections to the object tracks, and filtering the object detections of the objects to smooth the tracks; estimating an object state based on the integrated detection; predicting future object motion of the objects and trajectory previews of the detected new and existing object tracks based on the estimated object state, a dynamic model, and a track history; (Osipychev [0022] “With reference again to FIG. 2, the computing system 102 further comprises a trajectory prediction module 118 configured to model a trajectory of the intruder vehicle 106 based at least on the run-time position data 110 for the intruder vehicle. The trajectory prediction module 118 also models a trajectory of the aircraft 104 based at least on the run-time position data 112 for the aircraft 104. In some examples, the trajectories are further modeled based upon a map 120 of an airport. For example, the trajectory of the intruder vehicle 106 may be based upon constraints prescribed by the map 120, such as locations where ground vehicles can turn and distances between a ground vehicle to intersections and runway thresholds. In this manner, the map 120 may guide the determination of the trajectory of the intruder vehicle 106.”); determining a first outcome, a second outcome, or a third outcome based on the probability of the runway incursion based on the predicted future object motion, (Osipychev [0013] reads “Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); and the third outcome including that the runway incursion is ongoing indicating at least one of the detected new and existing object tracks is predicted to be within the runway safety area when an aircraft touches down; (Osipychev [0057] reads “As indicated at 522, in some examples, the recommended collision avoidance action is output at a “sweet spot” in a landing approach. The term “sweet spot” refers to a predetermined location (e.g. a predetermined time and/or geographic location, or predetermined range of times and/or range of geographic locations) in a landing approach. For example, the computing system 102 may be configured to determine, based upon historical landing information or modeled landing information, a predetermined time and/or a predetermined location at which there is adequate time to redirect the aircraft 104 or to instruct the aircraft 104 to continue the landing approach.”); and adapting the detection over time to new environments based on accuracy of the probability. (Osipychev [0013] reads “Based at least on the run-time position data for the intruder vehicle and the run-time position data for the aircraft, an intersection probability value is determined that represents a probability that the trajectory of the intruder vehicle and the trajectory of the aircraft intersect.”); Osipychev does not teach the filtering including: estimating the trajectory previews of the non-cooperating objects by providing the track history to a first Kalman filter; estimating acceleration of the non-cooperating objects by providing the trajectory previews and the sensor measurements to a second Kalman filter; smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process; the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria. Pearson in analogous art, teaches the filtering including: estimating the trajectory previews of the non-cooperating objects by providing the track history to a first Kalman filter; (Pearson [0071] reads “In some embodiments, determining the third state estimate and the third state estimate confidence metric comprises using an Extended Kalman Filter. In some embodiments, the second state estimate, the second state estimate confidence metric, the gyroscopic data, the accelerometer data, the altitude data, the magnetic field data and the GNSS data are inputs of the Extended Kalman Filter.”); estimating acceleration of the non-cooperating objects by providing the trajectory previews and the sensor measurements to a second Kalman filter; (Pearson [0208] reads “In some embodiments, the first state estimation may rely on an extended Kalman filter, separate from the extended Kalman filter used for the third state estimation.”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev with that of Pearson to provide a safer takeoff and landing environment for aircraft in high density situations. (Pearson [0002] reads “Aerial vehicles, such as manned vertical take-off and landing (VTOL) aerial vehicles, can collide with objects such as birds, walls, buildings or other aerial vehicles during flight. Collision with an object can cause damage to the aerial vehicle, particularly when the aerial vehicle is traveling at a high speed. Furthermore, collisions can be dangerous to people or objects nearby that can be hit by debris or the aerial vehicle itself. This can be a particularly large issue when high density airspace is considered.); Osipychev/Pearson does not teach smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process; the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria. Yufeng in analogous art, teaches smoothing the tracks of the non-cooperating objects based on providing the track history, the sensor measurements, and the estimated acceleration to a Gaussian process; (Yufeng [0018] reads “FIG. 7 is diagram that illustrates position filtering when projecting a measured position onto a guidance line while making maneuver path predictions, in accordance with some embodiments;” It would be appreciated by one with ordinary skill in the art that filtering of a projection would include reducing the noise in the data and further smoothing that data.); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Pearson with that of Yufeng to provide a system that would allow a pilot to have a better sense of their surrounding and to avoid wing tip collisions. (Yufeng [0002] reads “It can be very difficult for a pilot to see the wingtips of its aircraft while taxiing the aircraft on an airport surface and judge the clearance between its aircraft and obstructions such as buildings, other aircraft, ground vehicles, and poles etc. Collisions with such obstructions have occurred every year for many years and the frequency of collisions have increased with air traffic growth. Aircraft collisions with any obstruction can not only damage the aircraft, but can also put the aircraft out of service, and may impact an airlines' reputation.”); Osipychev/Pearson/Yufeng does not teach the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria. Schonefeld in analogous art, teaches the first outcome including insufficient evidence indicating that not enough of the object detections have been integrated to meeting probability criteria, or that not enough of the runway safety area has been encompassed to meet false negative criteria, or a track inside the runway safety area does not have a high enough scan-to-track updates ratio to meet false positive criteria, (Schonefeld section 2.2 reads “False or insufficient information (in gray) leads to poor decisions (such as crossing a closed hold line), which result in dangerous operations. RIPAS attempts to provide reliable information that is sufficient for good decisions (such as showing the status of a hold line by signals). The remaining poor decisions should be detected by RIPAS, and a warning should be issued to prevent dangerous operations. If dangerous operations occur anyway, then the system shall issue an alert so that the operation can be cancelled and a status of safe operation can be obtained.”); the second outcome including that none of the detected new and existing object tracks falls within a runway safety area and the runway safety area has been scanned a pre-selected number of times to meet the false negative criteria, (Schonefeld section 3.1.3.2. reads “Surface Movement Radar (SMR): A global and usually non-cooperative sensor that detects vehicles over the whole airport area. Its update rate is usually approximately 1 Hz. Its capabilities for locating smaller vehicles and pedestrians are limited. Even high performance systems such as Airport Surface Detection Equipment Model 3(ASDE-3) radar and Airport Surface Detection Equipment-Model X (ASDE-X) radar suffer from Multipath reflections that can lead to false target reports”); It would have been obvious to one with ordinary skill in the art, before the effective filing date of the claimed invention to have modified the teachings of Osipychev/Kanagarajan with that of Schonefeld to include a system for better dealing with edge cases in a runway incursion system. This improvement would allow for improved safety around airports with regards to runway incursions. (Schonefeld introduction reads “Runway incursions are occurrences at an aerodrome that involve the incorrect presence of an aircraft, a ground vehicle, or a person on the protected area designated for the landing and take-off of aircraft. The growing traffic volume has kept avoiding runway incursions on the National Transportation Safety Board (NTSB) “Most Wanted” list for safety improvements for over a decade [1]. In the past, runway incursions have led to accidents with significant loss of life.”); Response to arguments Applicant argues < Applicant's claimed integrating object detections of objects possibly within a runway safety area over time is not an obvious step from Osipychev's invention because Osipychev does not include any description of integrating their object detections of objects within a runway safety area. Further, Osipychev is limited to providing recommended actions to the aircraft operator to avoid a collision with a single object. Applicant, on the contrary, determines possible outcomes based on the status of collected data. The aircraft operator may make intelligent conclusions based on the reported outcome.> [Arguments page 16 second and third paragraphs]. The examiner respectfully disagrees. The current broadest reasonable interpretation of the current invention does not encompass the limited scope of determining possible future outcomes as argued by the applicant. The claims as currently written recite “predicted future object motion” of a given vehicle. Similarly, the claims recite little to none about presenting or displaying this given information to an aircraft operator and further, the “outcomes” as argued before have little to do with possible motion or paths that the aircraft may take and instead are broadest reasonable interpretated as situations about how much data is being collected by the system. Therefore, the combination teaches the claimed invention. Applicant argues < Importantly, Kanagarajan is focused on ground-based collisions, not Applicant's claimed determining a probability of runway incursion during aircraft landing. Kanagarajan is concerned with wingtip collisions while the aircraft are taxiing around the airport. Such a system is not analogous to Applicant's claimed runway incursion during aircraft landing because Kanagarajan is expecting a final result to be a light shining on a collision area, but if such an action were taken by any of Applicant's claimed objects, or the landing aircraft, because of the speed of a landing aircraft in comparison with the speed of a taxiing aircraft, the landing aircraft would have flown past the light or collided with the object long before such light show would be useful.> [Arguments page 17 second paragraph]. The examiner respectfully disagrees. Kanagarajan is found by the examiner to be in analogous art, because it is in the same field of invention as the currently claimed invention. Furthermore, Kanagarajan is not relied upon for teaching the output of the system as argued above. Kanagarajan is only used to teach that the monitoring systems of aircraft can be changed in real time based on what is happening in a given scene. Therefore, the combination teaches the claimed invention. Applicant argues < With respect to (2), Durand describes a system for avoiding collisions between an aircraft on the ground and an obstacle on the ground (Durand, paragraph 22). The method of use of Durand's system includes the flight crew's identifying an obstacle, the pilot's slowing the taxiing aircraft down and monitoring the obstacle using Durand's system, Durand's system's predicting a collision between the slow-moving aircraft and a possibly stationary object, Durand's system's issuing an alert, and the pilot's stopping the aircraft. No matter how slow a landing aircraft can fly, it is unlikely that Durand's system could issue an alert in time for the pilot to respond by stopping the aircraft. Durand's system would have to be considerably upgraded to accommodate Applicant's claimed aircraft landing. Further, Durand simply provides to the pilot a collision alert. On the contrary, Applicant determines data-based outcomes about the objects in the runway safety area, thus providing information that may be used to avoid a collision.> [Arguments page 22 spanning paragraph]. The examiner respectfully disagrees. Durand is found to be in analogous art, of the claimed invention because it similarly teaches the detection and monitoring of potential collisions of vehicles at airports. Furthermore, the office does not rely upon Durand to physically monitor and determine the path of given vehicles at an airport and not to give any sort of alert to a pilot or operator. Durand is only relied upon to teach the understanding of the amount of false negative detection results in the given system. Therefore, the combination teaches the claimed invention. Applicant argues < Pearson does not disclose or suggest that multiple data-based outcomes could be determined as Applicant claims because Pearson's system by-passes the pilot altogether. Pearson's method includes generating a depth map and region point cloud, determining state estimates and confidences of the position, velocity, etc. of the aircraft and the object in the region, generating a repulsion vector, determining a collision avoidance velocity vector, determining a control vector, and controlling a propulsion system so that the aircraft avoids the object (Pearson, paragraph 81). Pearson may alert the pilot (Pearson, paragraph 272), but does not determine Applicant's claimed outcomes because they are unnecessary in Pearson's system. Pearson's invention is described to avoid collisions that may be caused by pilot error or slow pilot reaction time (Pearson, paragraph 3). Thus, Pearson's system would not need to include Applicant's claimed outcomes. > [Arguments page 27 first paragraph]. The examiner respectfully disagrees. The “Outcomes” as currently presented in the amended claims at not intended to be taught by Pearson. Pearson is relied upon in the current rejection of record to teach the use of a Kalman filter that uses acceleration data. Pearson is not used to teach any form of alerting the pilot as the was argued by the applicant. Therefore, the combination teaches the claimed invention. Applicant argues < With respect to (3), Yufeng (Liu) describes a system in which collisions between an aircraft taxiing on the ground and another object are detected and avoided. Yufeng (Liu) does not address aircraft landing and collision avoidance during that time, and Yufeng (Liu)'s system cannot be retrofitted to accommodate aircraft landing because the speeds between ground-based taxiing aircraft and landing aircraft are too different. Yufeng (Liu)'s process for collision avoidance includes determining a position of the aircraft, the potential ground path of dynamic obstacles that are moving in the vicinity of the aircraft, filtering the position data, determining the aircraft's position relative to a guidance line and correcting the position accordingly, generating an aircraft protection zone around the corrected position, making maneuver path predictions for the aircraft and the object, performing a collision risk assessment, and generating a collision alert when the aircraft and the object will overlap (Yufeng (Liu)), paragraphs 41-65). Not only does Yufeng (Liu) not determine Applicant's claimed outcomes, but Yufeng (Liu) is limited to assessing a single object at a time relative to the aircraft, at ground speeds.> [arguments Page 27 spanning paragraph]. The examiner respectfully disagrees. Yufeng is not relied upon by the current rejection of record to determine the new amended outcomes of the claimed invention. These outcomes are taught by a combination of Osipychev and Schonefeld as shown earlier in the rejection. Similarly, Yufeng is not relied upon to teach sections regarding the process of landing a given aircraft safely. Yufeng is relied upon to teach to process of filtering and smoothing the expected path of a given aircraft. This process as taught by Yufeng could easily be done by one with ordinary skill in the art. Therefore, the combination teaches the claimed invention. Other references not Cited Throughout examination other references were found that could read onto the prior art. Though these references were not used in this examination they could be used in future examination and could read on the contents of the current disclosure. These references are, Gupta (US 11854418 B2); Claudel (US 20240203272 A1); Ray (US 20220051576 A1). Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN MARTIN O'MALLEY whose telephone number is (571)272-6228. The examiner can normally be reached Mon - Fri 9 am - 5 pm. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ramon Mercado can be reached at (571) 270 - 5744. 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. /JOHN MARTIN O'MALLEY/Examiner, Art Unit 3658 /Ramon A. Mercado/Supervisory Patent Examiner, Art Unit 3658 Application/Control Number: 18/815,421 Page 2 Art Unit: 3658 Application/Control Number: 18/815,421 Page 3 Art Unit: 3658 Application/Control Number: 18/815,421 Page 4 Art Unit: 3658 Application/Control Number: 18/815,421 Page 5 Art Unit: 3658 Application/Control Number: 18/815,421 Page 6 Art Unit: 3658 Application/Control Number: 18/815,421 Page 7 Art Unit: 3658 Application/Control Number: 18/815,421 Page 8 Art Unit: 3658 Application/Control Number: 18/815,421 Page 9 Art Unit: 3658 Application/Control Number: 18/815,421 Page 10 Art Unit: 3658 Application/Control Number: 18/815,421 Page 11 Art Unit: 3658 Application/Control Number: 18/815,421 Page 12 Art Unit: 3658 Application/Control Number: 18/815,421 Page 13 Art Unit: 3658 Application/Control Number: 18/815,421 Page 14 Art Unit: 3658 Application/Control Number: 18/815,421 Page 15 Art Unit: 3658 Application/Control Number: 18/815,421 Page 16 Art Unit: 3658 Application/Control Number: 18/815,421 Page 17 Art Unit: 3658 Application/Control Number: 18/815,421 Page 18 Art Unit: 3658 Application/Control Number: 18/815,421 Page 19 Art Unit: 3658 Application/Control Number: 18/815,421 Page 20 Art Unit: 3658 Application/Control Number: 18/815,421 Page 21 Art Unit: 3658 Application/Control Number: 18/815,421 Page 22 Art Unit: 3658 Application/Control Number: 18/815,421 Page 23 Art Unit: 3658 Application/Control Number: 18/815,421 Page 24 Art Unit: 3658 Application/Control Number: 18/815,421 Page 25 Art Unit: 3658 Application/Control Number: 18/815,421 Page 26 Art Unit: 3658 Application/Control Number: 18/815,421 Page 27 Art Unit: 3658 Application/Control Number: 18/815,421 Page 28 Art Unit: 3658 Application/Control Number: 18/815,421 Page 29 Art Unit: 3658 Application/Control Number: 18/815,421 Page 30 Art Unit: 3658 Application/Control Number: 18/815,421 Page 31 Art Unit: 3658 Application/Control Number: 18/815,421 Page 32 Art Unit: 3658 Application/Control Number: 18/815,421 Page 33 Art Unit: 3658 Application/Control Number: 18/815,421 Page 34 Art Unit: 3658 Application/Control Number: 18/815,421 Page 35 Art Unit: 3658 Application/Control Number: 18/815,421 Page 36 Art Unit: 3658 Application/Control Number: 18/815,421 Page 37 Art Unit: 3658 Application/Control Number: 18/815,421 Page 38 Art Unit: 3658 Application/Control Number: 18/815,421 Page 39 Art Unit: 3658 Application/Control Number: 18/815,421 Page 40 Art Unit: 3658 Application/Control Number: 18/815,421 Page 41 Art Unit: 3658
Prosecution Insights