DETAILED ACTION
Claims 1-9, 11, 13, 15, 17, 21, 23, 25-26, and 28 are currently pending and have been examined in this application. Claims 10, 12, 14, 16, 18-20, 22, 24, and 27 are canceled.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is in response to the “request for continued examination” filed 03/03/2026.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-2, 5-6, 8-9, 13, 26, 28 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (CN110411766) in view of Li (CN111523180) further in view of Van der Heiden (DE102017205973).
Claim 1:
Zheng explicitly teaches:
A computer-implemented method of assessing lateral stability of a moving vehicle in a real or simulated driving scenario, the method comprising: determining a time-varying lateral position signal for the moving vehicle [based on a lateral displacement between a reference line that denotes a direction of travel of the moving vehicle and a reference point of the moving vehicle];
(Zheng) – “The application relates to a method and device for detecting the serpentine instability of a train bogie, a system and a storage medium. The method for detecting the serpentine instability of the train bogie comprises the steps of conducting characteristic analysis on real-time collected lateral vibration data of the bogie, and inputting obtained characteristic data into an instability classification model to obtain an instability detection result. Statistical mining and modeling analysis are conducted on the lateral vibration data of the train bogie on the basis of two dimensions of the time domain and the frequency domain, the data characteristics for characterizing the serpentine instability of the bogie and the distribution condition of the data characteristics can be extracted from different angles, and therefore diagnosis and judgment can be conducted through the instability classification model. The classification model obtained based on historical data training is adopted for instability judgment, the detection standards of the method are more objective, the influence of human subjective factors can be reduced, and the accuracy of instability judgment is increased. On this basis, whether or not the serpentine instability phenomenon happens to the train bogie can be monitored and analyzed in real time, and a driver is timely reminded to take measures such as speed reduction to ensure safe running of a train.” (Abstract)
Examiner Note: Bracketed text not explicitly taught by primary reference, but is taught by non-primary reference later in the rejection.
computing an evolving frequency spectrum of the time-varying lateral position signal [over a moving window] across the time-varying lateral position signal; and
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
Examiner Note: Bracketed text not explicitly taught by primary reference, but is taught by non-primary reference later in the rejection.
analysing the evolving frequency spectrum to extract a lateral stability signal that indicates an extent to which the moving vehicle is maintaining a stable lateral position.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
Zheng does not explicitly teach:
based on a lateral displacement between a reference line that denotes a direction of travel of the moving vehicle and a reference point of the moving vehicle … over a moving window
Li, in the same field of endeavor of signal processing, teaches:
over a moving window
(Li) – “The invention provides a construction method for an acceleration test spectrum of vehicle-mounted equipment, and the method comprises the steps: obtaining the actual measurement vibration data of the vehicle-mounted equipment, and carrying out the primary selection of an actual measurement vibration data sample; performing data preprocessing such as singular point elimination, trend term elimination and the like on the preliminarily selected actually measured vibration data, performing data inspection, and judging whether the vibration process of the vehicle-mounted equipment meets the stability and each state duration or not; carrying out window processing on the finally determined actually measured vibration data, carrying out power spectral density estimation, and drawing a power spectral density curve graph of the vibration amplitude to the frequency when each actually measured speed is researched to form an actually measured spectrum; and determining an acceleration test acceleration factor, constructing an acceleration test spectrum of the vehicle-mounted equipment, and obtaining an acceleration test spectrum of the vehicle-mounted equipment. The vehicle-mounted equipment acceleration test spectrum constructed by the method is mainly suitable for determining vehicle-mounted electronic components such as a vehicle-mounted servo controller, a filling controller and the like, and an accurate and brand-new test spectrum construction method is provided for a vehicle-mounted equipment vibration test.” (Abstract)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the test spectrum construction method of Li. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, for the purpose of providing “an accurate and brand-new test spectrum construction method” (Li Abstract)
Li does not explicitly teach:
based on a lateral displacement between a reference line that denotes a direction of travel of the moving vehicle and a reference point of the moving vehicle
Van der Heiden, in the same field of endeavor of vehicle control, teaches:
based on a lateral displacement between a reference line that denotes a direction of travel of the moving vehicle and a reference point of the moving vehicle
(Van der Heiden) – “The invention provides a method for determining an offset or offset contained in a measured yaw rate signal of a yaw rate sensor of a motor vehicle. The offset can be determined during a journey of the motor vehicle along a road. On the basis of sensor data or environmental data of at least one environmental sensor of the motor vehicle, a relative lateral position of the motor vehicle with respect to at least one vehicle-external stationary object is determined. The position is determined repeatedly or continuously over time, resulting in a position signal. As an environment sensor for detecting the lateral position, for example, a camera may be provided. The lateral position represents a transverse distance, which is measured to the right or to the left transversely, for example, to the direction of travel with respect to the at least one object. For the distance measurement can be defined in the motor vehicle, a reference point, for example, the vehicle center of gravity or the center of the rear axle. By projecting the reference point in the transverse direction onto an object, a projection point can be defined on the object. The distance between the reference point and the projection point then represents the relative lateral position. If the at least one object is not right or left "next to" the motor vehicle and the reference point can not be projected directly transversely onto the at least object, the reference point of the Motor vehicle initially be projected virtually along, for example, the vehicle longitudinal axis to the front or rear of the at least one object in order to then define the lateral position with respect to the object in the manner described. In this way, one lateral position can become one beside or arranged on the road object, such as a tree can be determined.” (Para 0011)
“Fig. 2 exemplifies, as the designed as a camera environment sensor 13 on a windshield WIN can be arranged. Shown is a look through the windscreen WIN in a forward direction 16 road ahead 17 with two lanes 18 and a lane marker 19 , Through a longitudinal course or a longitudinal extension of the road 17 results in a coordinate system 20 with an X-axis along the length of the road 17 and a Y-axis transverse to the longitudinal course.” (Para 0033)
“Furthermore, there is still a transverse distance 23 illustrates the motor vehicle to a lane edge or roadside 24 , For example, to an edge mark, may have. Due to the transverse distance 23 can be considered a relative lateral position Dy of the motor vehicle 10 concerning the street 17 , eg with respect to the roadside, be defined. Based on the environment data 21 can through the control device 11 this lateral position Dy along the Y-direction transverse to the longitudinal course or to the longitudinal extent of the road (X-direction) are determined.” (Para 0035)
“Fig. 2 further shows a course of a desired trajectory 22 along which the motor vehicle 10 For example, by a control device of a driver assistance system (not shown) by an automated lateral guidance (steering) and / or longitudinal guidance (acceleration and braking) to be performed. The target trajectory 22 can be predetermined in a conventional manner by a Trajektorienplaner who the motor vehicle 10 to lead to a goal. ” (Para 0036)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the test spectrum construction method of Li. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, because “The pose of the vehicle can thereby be more accurately determined, since the yaw rate signal is determined without offset. Odometry thus determines the pose via the yaw rate and enters this in a coordinate system. This coordinate system is used for the path control. The accuracy of the pose calculated by odometry is of central importance. Deviations of the calculated pose from the real pose initially lead to an error in the controlled variable and thus to target deviations. In order to drive safely minimal deviations from the target are required.” (Van der Heiden Para 0056)
Claim 2:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
wherein said analysing comprises applying peak detection to the evolving frequency spectrum, the lateral stability signal determined based on an amplitude of any detected peak(s).
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
Claim 5:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
wherein the scenario is simulated, and the lateral position signal is dependent on a vehicle dynamics model.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“In the field of rail transit, there is no uniform evaluation standard for the stability of train lateral motion. Most researches on bogie-shaped instability of bogies are carried out through simulation and experiment” (Pg. 3)
Claim 6:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
wherein the lateral stability signal is a numerical signal that quantifies the extent to which the moving vehicle is maintaining a stable lateral position.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
Claim 8:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
comprising: applying a threshold to the lateral stability signal at multiple time steps of the scenario, in order to assess compliance with a lateral stability requirement at each of the multiple time steps.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“Conventional techniques use a pre-set instability threshold and prompt when real-time data exceeds the instability threshold. Compared with the conventional technology, after performing feature data extraction on the real-time data of the bogie, the embodiment of the present application uses the instability classification model based on the historical data training to detect the feature data, and then obtains the instability detection result; The historical data and the classification model are used to detect whether the bogie is in the form of serpentine instability.” (Pg. 4)
Claim 9:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
wherein the time-varying lateral position signal is a digital signal, wherein a sample rate of the digital time-varying lateral position signal is set based on a response time of the moving vehicle.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“Conventional techniques use a pre-set instability threshold and prompt when real-time data exceeds the instability threshold. Compared with the conventional technology, after performing feature data extraction on the real-time data of the bogie, the embodiment of the present application uses the instability classification model based on the historical data training to detect the feature data, and then obtains the instability detection result; The historical data and the classification model are used to detect whether the bogie is in the form of serpentine instability.” (Pg. 4)
“Specifically, the lateral vibration data of the bogie is collected in real time and data filtering is performed. Vibration data measurement and acquisition transmission during train operation will be interfered by various external conditions, and there are many kinds of equipment on the bogie of the train, such as wheel sets, motors, gear boxes, etc., vibration will occur during operation, vibration in different directions The signals are superimposed to affect the accuracy of the bogie stability judgment. Therefore, the data obtained by the sampling needs to be filtered to eliminate the sampling value deviation caused by accidental factors or pulse interference, and reduce the noise generated by the data during the acquisition and transmission process. Improve data quality and improve model accuracy.” (Pg. 7)
Examiner Note: With regard to a “response time,” no definition is given as to what the vehicle is responding to or in what way the time is determined. As such this may correspond with any form of response including computational response. Given this, a sampling rate will necessarily be based on the computational response of the system.
Claim 13:
Zheng in combination with the references relied upon in Claim 9 teach those respective limitations. Zheng further teaches:
wherein the evolving frequency spectrum is re-computed at a rate less than the [[a]] sample rate of the time- varying lateral position signal.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“Conventional techniques use a pre-set instability threshold and prompt when real-time data exceeds the instability threshold. Compared with the conventional technology, after performing feature data extraction on the real-time data of the bogie, the embodiment of the present application uses the instability classification model based on the historical data training to detect the feature data, and then obtains the instability detection result; The historical data and the classification model are used to detect whether the bogie is in the form of serpentine instability.” (Pg. 4)
“Specifically, the lateral vibration data of the bogie is collected in real time and data filtering is performed. Vibration data measurement and acquisition transmission during train operation will be interfered by various external conditions, and there are many kinds of equipment on the bogie of the train, such as wheel sets, motors, gear boxes, etc., vibration will occur during operation, vibration in different directions The signals are superimposed to affect the accuracy of the bogie stability judgment. Therefore, the data obtained by the sampling needs to be filtered to eliminate the sampling value deviation caused by accidental factors or pulse interference, and reduce the noise generated by the data during the acquisition and transmission process. Improve data quality and improve model accuracy.” (Pg. 7)
Claim 14: Canceled
Claim 26:
Zheng explicitly teaches:
Non-transitory media embodying computer-readable instructions, the computer-readable instructions configured upon execution on one or more hardware processors to assess lateral stability of a moving vehicle in a real or simulated driving scenario by operations comprising
(Zheng) – “The application relates to a method and device for detecting the serpentine instability of a train bogie, a system and a storage medium. The method for detecting the serpentine instability of the train bogie comprises the steps of conducting characteristic analysis on real-time collected lateral vibration data of the bogie, and inputting obtained characteristic data into an instability classification model to obtain an instability detection result. Statistical mining and modeling analysis are conducted on the lateral vibration data of the train bogie on the basis of two dimensions of the time domain and the frequency domain, the data characteristics for characterizing the serpentine instability of the bogie and the distribution condition of the data characteristics can be extracted from different angles, and therefore diagnosis and judgment can be conducted through the instability classification model. The classification model obtained based on historical data training is adopted for instability judgment, the detection standards of the method are more objective, the influence of human subjective factors can be reduced, and the accuracy of instability judgment is increased. On this basis, whether or not the serpentine instability phenomenon happens to the train bogie can be monitored and analyzed in real time, and a driver is timely reminded to take measures such as speed reduction to ensure safe running of a train.” (Abstract)
“In one embodiment, a system is provided that includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the system further including a bogie coupled to the processor.” (Pg. 8)
Remainder of Claim rejected based on the same rationale as Claim 1
Claim 28:
Zheng explicitly teaches:
A computer system for assessing lateral stability of a moving vehicle in a real or simulated driving scenario, the computer system comprising: non-transitory media embodying computer-readable instructions; and one or more hardware processors coupled to the non-transitory media and configured to execute the computer-readable instructions, which upon execution cause the one or more hardware processors to perform operations comprising:
(Zheng) – “The application relates to a method and device for detecting the serpentine instability of a train bogie, a system and a storage medium. The method for detecting the serpentine instability of the train bogie comprises the steps of conducting characteristic analysis on real-time collected lateral vibration data of the bogie, and inputting obtained characteristic data into an instability classification model to obtain an instability detection result. Statistical mining and modeling analysis are conducted on the lateral vibration data of the train bogie on the basis of two dimensions of the time domain and the frequency domain, the data characteristics for characterizing the serpentine instability of the bogie and the distribution condition of the data characteristics can be extracted from different angles, and therefore diagnosis and judgment can be conducted through the instability classification model. The classification model obtained based on historical data training is adopted for instability judgment, the detection standards of the method are more objective, the influence of human subjective factors can be reduced, and the accuracy of instability judgment is increased. On this basis, whether or not the serpentine instability phenomenon happens to the train bogie can be monitored and analyzed in real time, and a driver is timely reminded to take measures such as speed reduction to ensure safe running of a train.” (Abstract)
“In one embodiment, a system is provided that includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the system further including a bogie coupled to the processor.” (Pg. 8)
Remainder of Claim rejected based on the same rationale as Claim 1
Claim(s) 3-4, 7, 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (CN110411766) in view of Li (CN111523180) further in view of Van der Heiden (DE102017205973) further in view of Subasingha (US20190926).
Claim 3:
Zheng in combination with the references relied upon in Claim 2 teach those respective limitations. Zheng further teaches:
wherein said analysing comprises [detecting a noise floor] of the evolving frequency spectrum, the lateral stability signal determined based on the amplitude of any detected peak(s) [above the noise floor].
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
Zheng does not explicitly teach:
detecting a noise floor…above the noise floor
Subasingha, in the same field of endeavor of signal processing, teaches::
detecting a noise floor…above the noise floor
(Subasingha) – “A device can accurately discriminate an active pulse from noise by setting a dynamic noise floor that adjusts according to environmental conditions.” (Abstract)
“In some examples, the techniques may include identifying, as an active pulse, samples of the received signal that are associated with magnitudes that exceed the dynamic noise floor.” (Para 0026)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the dynamic noise floor of Subasingha. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, in order “to accurately ascertain a time at which a return signal is received” (Subasingha Para 0020)
Claim 4:
Zheng in combination with the references relied upon in Claim 3 teach those respective limitations. Zheng does not explicitly teach the following limitations in full. Subasingha further teaches:
wherein the noise floor is determined based on a noise portion of the spectrum above a frequency threshold.
(Subasingha) – “A device can accurately discriminate an active pulse from noise by setting a dynamic noise floor that adjusts according to environmental conditions.” (Abstract)
“In some examples, the multiple detectors may include additional detectors that may determine a TDOA, discriminate an active signal from noise, or other properties of the signal using a variety of techniques. For example, the multiple detectors may include a cross-correlation detector, a front edge detector, a deconvolution detector, a frequency domain analysis detector, etc.” (Para 0025)
“In some examples, the techniques may include identifying, as an active pulse, samples of the received signal that are associated with magnitudes that exceed the dynamic noise floor.” (Para 0026)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the dynamic noise floor of Subasingha. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, in order “to accurately ascertain a time at which a return signal is received” (Subasingha Para 0020)
Claim 7:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
wherein said analysing comprises [detecting a noise floor] of the evolving frequency spectrum, the lateral stability signal determined based on an amplitude of any detected peak(s) [above the noise floor], wherein the lateral position signal is determined as a sum of the amplitude of each peak [above the noise floor].
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
Zheng does not explicitly teach:
detecting a noise floor…above the noise floor… above the noise floor
Subasingha, in the same field of endeavor of signal processing, teaches::
detecting a noise floor…above the noise floor… above the noise floor
(Subasingha) – “A device can accurately discriminate an active pulse from noise by setting a dynamic noise floor that adjusts according to environmental conditions.” (Abstract)
“In some examples, the techniques may include identifying, as an active pulse, samples of the received signal that are associated with magnitudes that exceed the dynamic noise floor.” (Para 0026)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the dynamic noise floor of Subasingha. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, in order “to accurately ascertain a time at which a return signal is received” (Subasingha Para 0020)
Claim 21:
Zheng in combination with the references relied upon in Claim 3 teach those respective limitations. Zheng does not explicitly teach the following limitations in full. Subasingha further teaches:
wherein peaks are detected above a multiple of the noise floor, wherein the multiple is optionally a configurable parameter.
(Subasingha) – “A device can accurately discriminate an active pulse from noise by setting a dynamic noise floor that adjusts according to environmental conditions.” (Abstract)
“In some examples, the multiple detectors may include additional detectors that may determine a TDOA, discriminate an active signal from noise, or other properties of the signal using a variety of techniques. For example, the multiple detectors may include a cross-correlation detector, a front edge detector, a deconvolution detector, a frequency domain analysis detector, etc.” (Para 0025)
“In some examples, the techniques may include identifying, as an active pulse, samples of the received signal that are associated with magnitudes that exceed the dynamic noise floor.” (Para 0026)
Examiner Note: “a multiple” is recited with a high degree of generality. Any number may be a multiple of the noise floor including the noise floor itself as that would be equivalent to the noise floor multiplied by 1. The optionality of the “configurable parameter” means the prior art need not teach this feature.
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the dynamic noise floor of Subasingha. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, in order “to accurately ascertain a time at which a return signal is received” (Subasingha Para 0020)
Claim(s) 11, 23, 25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (CN110411766) in view of Li (CN111523180) further in view of Van der Heiden (DE102017205973) further in view of Zhu (US20190317516).
Claim 11:
Zheng in combination with the references relied upon in Claim 9 teach those respective limitations. Zheng does not explicitly teach the following in full. Zhu, in the same field of endeavor of trajectory tracking further teaches:
wherein the scenario is simulated, and the lateral position signal is dependent on a vehicle dynamics model, wherein the response time is determined by the vehicle dynamics model.
(Zhu) – “In order to effectively cope with the nonlinear and time-varying nature of car-like ground vehicle motion control, conventional systems may use what is known as a Model Predictive Control (MPC) technique. MPC runs a simulation of the vehicle motion over a finite future time interval with currently computed controller gains. MPC then modifies the vehicle model based on the simulation results, performs an on-line optimal control design to obtain a new set of gains, uses these gains to control the vehicle to the next decision time step, and repeats the process at every control decision step, typically between 50 and 100 times per second.” (Para 0005)
“Strictly speaking, vehicle dynamics may refer to the physical properties of the vehicle, represented by Eqns. 2 and 4, which result from the mass of the vehicle, and the distribution of that mass in the vehicle. Vehicle kinematics, represented by Eqns. 1 and 3, are geometric properties of the vehicle that constrain the dynamics of the vehicle. Together, Eqns. 1-4 are known as the Equations of Motion, which may be categorically referred to as the vehicle dynamics, and are accounted for by the vehicle dynamics module 332.” (Para 0073)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the trajectory tracking control of Zhu. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, because “there is a need for improved methods, systems, and computer program products for controlling autonomous driving cars.” (Zhu Para 0006)
Claim 12: Canceled
Claim 23:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
[applied to test at least part of an autonomous vehicle stack in control of the moving vehicle], the method comprising: using the lateral stability signal to identify and mitigate a performance issue [in said at least part of the autonomous vehicle stack].
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“Conventional techniques use a pre-set instability threshold and prompt when real-time data exceeds the instability threshold. Compared with the conventional technology, after performing feature data extraction on the real-time data of the bogie, the embodiment of the present application uses the instability classification model based on the historical data training to detect the feature data, and then obtains the instability detection result; The historical data and the classification model are used to detect whether the bogie is in the form of serpentine instability.” (Pg. 4)
“Specifically, the lateral vibration data of the bogie is collected in real time and data filtering is performed. Vibration data measurement and acquisition transmission during train operation will be interfered by various external conditions, and there are many kinds of equipment on the bogie of the train, such as wheel sets, motors, gear boxes, etc., vibration will occur during operation, vibration in different directions The signals are superimposed to affect the accuracy of the bogie stability judgment. Therefore, the data obtained by the sampling needs to be filtered to eliminate the sampling value deviation caused by accidental factors or pulse interference, and reduce the noise generated by the data during the acquisition and transmission process. Improve data quality and improve model accuracy.” (Pg. 7)
Zheng does not explicitly teach:
applied to test at least part of an autonomous vehicle stack in control of the moving vehicle…in said at least part of the autonomous vehicle stack
Zhu, in the same field of endeavor of trajectory tracking, teaches:
applied to test at least part of an autonomous vehicle stack in control of the moving vehicle…in said at least part of the autonomous vehicle stack
(Zhu) – “Systems, methods, and computer program products for autonomous car-like ground vehicle guidance and trajectory tracking control. A multi-loop 3DOF trajectory linearization controller provides guidance to a vehicle having nonlinear rigid-body dynamics with nonlinear tire traction force, nonlinear drag forces and actuator dynamics. The controller may be based on a closed-loop PD-eigenvalue assignment and a singular perturbation (time-scale separation) theory for exponential stability, and controls the longitudinal velocity and steering angle simultaneously to follow a feasible guidance trajectory. A line-of-sight based pure-pursuit guidance controller may generate a 3DOF spatial trajectory that is provided to the 3DOF controller to enable target pursuit and path-following/trajectory-tracking. The resulting combination may provide a 3DOF motion control system with integrated simultaneous steering and speed control for automobile and car-like mobile robot target pursuit and trajectory-tracking.” (Abstract)
“In order to effectively cope with the nonlinear and time-varying nature of car-like ground vehicle motion control, conventional systems may use what is known as a Model Predictive Control (MPC) technique. MPC runs a simulation of the vehicle motion over a finite future time interval with currently computed controller gains. MPC then modifies the vehicle model based on the simulation results, performs an on-line optimal control design to obtain a new set of gains, uses these gains to control the vehicle to the next decision time step, and repeats the process at every control decision step, typically between 50 and 100 times per second.” (Para 0005)
“Strictly speaking, vehicle dynamics may refer to the physical properties of the vehicle, represented by Eqns. 2 and 4, which result from the mass of the vehicle, and the distribution of that mass in the vehicle. Vehicle kinematics, represented by Eqns. 1 and 3, are geometric properties of the vehicle that constrain the dynamics of the vehicle. Together, Eqns. 1-4 are known as the Equations of Motion, which may be categorically referred to as the vehicle dynamics, and are accounted for by the vehicle dynamics module 332.” (Para 0073)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the trajectory tracking control of Zhu. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, because “there is a need for improved methods, systems, and computer program products for controlling autonomous driving cars.” (Zhu Para 0006)
Claim 25:
Zheng in combination with the references relied upon in Claim 1 teach those respective limitations. Zheng further teaches:
[applied to test at least part of an autonomous vehicle stack in control of the moving vehicle], the method comprising: providing an output for assessing performance [of said at least part of the autonomous vehicle stack] with respect to a lateral stability requirement.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“Conventional techniques use a pre-set instability threshold and prompt when real-time data exceeds the instability threshold. Compared with the conventional technology, after performing feature data extraction on the real-time data of the bogie, the embodiment of the present application uses the instability classification model based on the historical data training to detect the feature data, and then obtains the instability detection result; The historical data and the classification model are used to detect whether the bogie is in the form of serpentine instability.” (Pg. 4)
“Specifically, the lateral vibration data of the bogie is collected in real time and data filtering is performed. Vibration data measurement and acquisition transmission during train operation will be interfered by various external conditions, and there are many kinds of equipment on the bogie of the train, such as wheel sets, motors, gear boxes, etc., vibration will occur during operation, vibration in different directions The signals are superimposed to affect the accuracy of the bogie stability judgment. Therefore, the data obtained by the sampling needs to be filtered to eliminate the sampling value deviation caused by accidental factors or pulse interference, and reduce the noise generated by the data during the acquisition and transmission process. Improve data quality and improve model accuracy.” (Pg. 7)
Zheng does not explicitly teach:
applied to test at least part of an autonomous vehicle stack in control of the moving vehicle…of said at least part of the autonomous vehicle stack
Zhu, in the same field of endeavor of trajectory tracking, teaches:
applied to test at least part of an autonomous vehicle stack in control of the moving vehicle…of said at least part of the autonomous vehicle stack
(Zhu) – “Systems, methods, and computer program products for autonomous car-like ground vehicle guidance and trajectory tracking control. A multi-loop 3DOF trajectory linearization controller provides guidance to a vehicle having nonlinear rigid-body dynamics with nonlinear tire traction force, nonlinear drag forces and actuator dynamics. The controller may be based on a closed-loop PD-eigenvalue assignment and a singular perturbation (time-scale separation) theory for exponential stability, and controls the longitudinal velocity and steering angle simultaneously to follow a feasible guidance trajectory. A line-of-sight based pure-pursuit guidance controller may generate a 3DOF spatial trajectory that is provided to the 3DOF controller to enable target pursuit and path-following/trajectory-tracking. The resulting combination may provide a 3DOF motion control system with integrated simultaneous steering and speed control for automobile and car-like mobile robot target pursuit and trajectory-tracking.” (Abstract)
“In order to effectively cope with the nonlinear and time-varying nature of car-like ground vehicle motion control, conventional systems may use what is known as a Model Predictive Control (MPC) technique. MPC runs a simulation of the vehicle motion over a finite future time interval with currently computed controller gains. MPC then modifies the vehicle model based on the simulation results, performs an on-line optimal control design to obtain a new set of gains, uses these gains to control the vehicle to the next decision time step, and repeats the process at every control decision step, typically between 50 and 100 times per second.” (Para 0005)
“Strictly speaking, vehicle dynamics may refer to the physical properties of the vehicle, represented by Eqns. 2 and 4, which result from the mass of the vehicle, and the distribution of that mass in the vehicle. Vehicle kinematics, represented by Eqns. 1 and 3, are geometric properties of the vehicle that constrain the dynamics of the vehicle. Together, Eqns. 1-4 are known as the Equations of Motion, which may be categorically referred to as the vehicle dynamics, and are accounted for by the vehicle dynamics module 332.” (Para 0073)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the trajectory tracking control of Zhu. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, because “there is a need for improved methods, systems, and computer program products for controlling autonomous driving cars.” (Zhu Para 0006)
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (CN110411766) in view of Li (CN111523180) further in view of Van der Heiden (DE102017205973) further in view of Palanisamy (US20200142421).
Claim 15:
Zheng in combination with the references relied upon in Claim 9 teach those respective limitations. Zheng further teaches:
wherein a [zero-padded] raw lateral stability signal is computed from the evolving frequency spectrum, [[the]] and a final [zero-padded] raw lateral stability signal computed by filtering the [zero-padded] raw lateral stability signal.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“Conventional techniques use a pre-set instability threshold and prompt when real-time data exceeds the instability threshold. Compared with the conventional technology, after performing feature data extraction on the real-time data of the bogie, the embodiment of the present application uses the instability classification model based on the historical data training to detect the feature data, and then obtains the instability detection result; The historical data and the classification model are used to detect whether the bogie is in the form of serpentine instability.” (Pg. 4)
“Specifically, the lateral vibration data of the bogie is collected in real time and data filtering is performed. Vibration data measurement and acquisition transmission during train operation will be interfered by various external conditions, and there are many kinds of equipment on the bogie of the train, such as wheel sets, motors, gear boxes, etc., vibration will occur during operation, vibration in different directions The signals are superimposed to affect the accuracy of the bogie stability judgment. Therefore, the data obtained by the sampling needs to be filtered to eliminate the sampling value deviation caused by accidental factors or pulse interference, and reduce the noise generated by the data during the acquisition and transmission process. Improve data quality and improve model accuracy.” (Pg. 7)
Examiner Note: See 112 rejection.
Zheng does not explicitly teach:
zero-padded… zero-padded… zero-padded
Palanisamy, in the same field of endeavor of signal processing, teaches::
zero-padded… zero-padded… zero-padded
(Palanisamy) - “Sometimes it is convenient to pad the input with zeros on the border of the input volume. The size of this padding is a third hyperparameter. Padding provides control of the output volume spatial size. In particular, sometimes it is desirable to exactly preserve the spatial size of the input volume.” (Para 0092)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the end-to-end learning of commands for controlling an autonomous vehicle of Palanisamy. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, because “it is desirable to provide learning systems and methods that take advantage of prior knowledge, that take advantage of past information that the learning system has learned, and that are capable of learning more complex driving behaviors, while also being reliable, easy to train, and easy to validate.” (Palanisamy Para 0006)
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (CN110411766) in view of Li (CN111523180) further in view of Van der Heiden (DE102017205973) further in view of Palanisamy (US20200142421) further in view of Jorgensen (US20040230391).
Claim 17:
Zheng in combination with the references relied upon in Claim 15 teach those respective limitations. Zheng further teaches:
wherein the time-varying lateral position signal is computed by [downsampling a higher-fidelity] lateral position signal, wherein the sample rate of the [zero-padded] raw lateral stability signal matches the [downsampled] time-varying lateral position signal, and the lateral stability signal is [upsampled to match the sample rate of the higher-fidelity] lateral position signal.
(Zheng) – “A method for detecting a serpentine instability of a train bogie, characterized in that it comprises: Performing feature analysis on the lateral vibration data of the bogie obtained in real time to obtain feature data of the lateral vibration data; the feature analysis is time domain analysis and/or frequency domain analysis, and the feature data is time domain feature data and / or frequency domain feature data; Inputting the feature data into a preset instability classification model, and acquiring an instability detection result output by the instability classification model; the instability classification model is obtained by training based on historical feature data of the bogie, the history The feature data is obtained by performing time domain analysis and/or frequency domain analysis on the historical data of the bogie.” (Claim 1)
“performing frequency domain analysis on the filtered historical data to obtain eigenvalues of the spectral distribution; wherein, the characteristics of the data dispersion degree The value includes at least one of a peak, a peak value, and a variance of the lateral acceleration; the characteristic value of the spectral distribution includes at least one of a frequency, a magnitude, and an energy; Based on the eigenvalues of the data dispersion degree and/or the eigenvalues of the spectrum distribution, the acceleration variation law and distribution of the train during normal operation are analyzed, and the instability classification model is constructed.” (Claim 2)
“Conventional techniques use a pre-set instability threshold and prompt when real-time data exceeds the instability threshold. Compared with the conventional technology, after performing feature data extraction on the real-time data of the bogie, the embodiment of the present application uses the instability classification model based on the historical data training to detect the feature data, and then obtains the instability detection result; The historical data and the classification model are used to detect whether the bogie is in the form of serpentine instability.” (Pg. 4)
“Specifically, the lateral vibration data of the bogie is collected in real time and data filtering is performed. Vibration data measurement and acquisition transmission during train operation will be interfered by various external conditions, and there are many kinds of equipment on the bogie of the train, such as wheel sets, motors, gear boxes, etc., vibration will occur during operation, vibration in different directions The signals are superimposed to affect the accuracy of the bogie stability judgment. Therefore, the data obtained by the sampling needs to be filtered to eliminate the sampling value deviation caused by accidental factors or pulse interference, and reduce the noise generated by the data during the acquisition and transmission process. Improve data quality and improve model accuracy.” (Pg. 7)
Zheng does not explicitly teach:
downsampling a higher-fidelity…zero-padded…downsampled…upsampled to match the sample rate of the higher-fidelity
Palanisamy, in the same field of endeavor of signal processing, teaches:
zero-padded
(Palanisamy) - “Sometimes it is convenient to pad the input with zeros on the border of the input volume. The size of this padding is a third hyperparameter. Padding provides control of the output volume spatial size. In particular, sometimes it is desirable to exactly preserve the spatial size of the input volume.” (Para 0092)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the end-to-end learning of commands for controlling an autonomous vehicle of Palanisamy. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, because “it is desirable to provide learning systems and methods that take advantage of prior knowledge, that take advantage of past information that the learning system has learned, and that are capable of learning more complex driving behaviors, while also being reliable, easy to train, and easy to validate.” (Palanisamy Para 0006)
Palanisamy does not explicitly teach:
downsampling a higher-fidelity… downsampled…upsampled to match the sample rate of the higher-fidelity
Jorgensen, in the same field of endeavor of signal processing, teaches:
downsampling a higher-fidelity… downsampled…upsampled to match the sample rate of the higher-fidelity
(Jorgensen) - “The present invention provides a methodology, apparatus and system for resampling digital data utilizing a Fourier series based interpolation engine 104. A quick means to up-sample or down-sample data is provided without requiring computationally intensive processing. This is accomplished by utilizing low order coefficients of terms of a complete Fourier series expansion for a continuous signal. The summation of the expansion is limited to input samples immediately adjacent in time to the desired output. Generally speaking, the output is normally required to be a constant sampling rate, therefore, the input and output rates are related by an integer ratio. This ratio can be greater or smaller than one, providing up-sampling or down-sampling as appropriate. By employing the present invention, a DSP engine can be constructed that is adjustable to any ratio of sampling rates in a computationally efficient manner with low RMS error while preserving convolution through the resampling process.” (Abstract)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method for detecting a serpentine instability of Zheng with the end-to-end learning of commands for controlling an autonomous vehicle of Palanisamy. One of ordinary skill in the art would have been motivated to make these modifications, with a reasonable expectation of success, so that “a DSP engine can be constructed that is adjustable to any ratio of sampling rates in a computationally efficient manner with low RMS error while preserving convolution through the resampling process” (Jorgensen Abstract)
Response to Arguments
The 35 U.S.C. 112 rejections mailed 12/03/2025 has been withdrawn because the “amendment” and “remarks” filed 03/03/2026 satisfactorily overcome these rejection.
Applicant's arguments with respect to the 35 U.S.C. 103 rejection mailed12/03/2025 have been fully considered but they are not persuasive. Rejection has been updated to reflect amended language.
Specifically, all claims are now rejected further in view of Van der Heiden as necessitated by amendment. Examiner maintains that Van der Heiden resolves any alleged deficiency of the prior art rejection as evidenced in the above rejection rationale.
For at least the above reasons, all remaining claims remain rejected over 35 U.S.C. 103.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Minoiu-Enache (EP3344506) teaches detecting vehicle position using references.
Piantino (EP0051338) teaches measuring the position of a railway track based on reference points.
Tanaka (JP2016071438) teaches calculating a separation distance to a vehicle body from a reference line.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID RUBEN PEDERSEN whose telephone number is (571)272-9696. The examiner can normally be reached M-Th: 07:00 -16:00 Eastern.
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.
/DAVID RUBEN PEDERSEN/Examiner, Art Unit 3658