Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Applicant’s amendment filed on April 6, 2026 amends independent claims 1 and 4-20. Claims 1-20 are pending.
Response to Arguments
Applicant's arguments filed on April 6, 2026 regarding the newly presented claim limitations have been fully considered and are unpersuasive and/or moot as shown in the rejections that follow. The newly presented independent claims are taught by the combination of Yanke and Weston as shown in the rejections that follow. Examiner disagrees with Applicant’s remarks that Yanke fails to teach the newly presented limitations in the amended independent claims. In an effort to persuade the Examiner, the Applicant cites various embodiments of Yanke which do not correspond to the newly presented limitations. Yanke and Weston, in combination, teaches the newly presented claim limitations of the amended independent claims, in light of the new ground of rejection, as shown in detail in the rejections under 35 U.S.C. 103.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 10 and 16 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Each of claims 10 and 16 recites “wherein the [sic] dynamically adjusts the header comprises a positional adjustment of the header, a spatial orientation adjustment of the header, or both”. There appears to be a number of missing word(s) that precede the word “dynamically”. As a result, the metes and bounds of the claims is undefined, and it is unclear what the claim is directed to. Since the Examiner is unable to determine what each of claims 10 and 16 is directed to, an examination of the merits of this claim will need to be performed at a future date after appropriate amendments are made.
Appropriate amendments are required to correct the foregoing issues. Applicant is requested to provide support from the specification for any amendments made. No new matter should be added.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-7, 11, 14-15, 17, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Yanke et al. (US 12,022,772) in view of Weston et al. (US 2023/0410528).
Regarding claim 1, Yanke teaches an impact detection system of a header of an agricultural system, the impact detection system comprising: (see Yanke at col. 1 lines 34-37 which discloses that a second aspect of the present disclosure is directed to an apparatus for controlling an agricultural header based on movement of crop material at the agricultural header during harvesting; Yanke at col. 1 lines 26-29 which discloses that method may include analyzing one or more images containing at least a portion of the agricultural header to detect crop material present in the one or more images; see Yanke at col. 4 lines 48-50 which discloses that in some implementations, the corn header 108 includes impact sensors that detect a force or sound of EHP interacting (e.g., impacting) with the header 108. Examiner maps apparatus for controlling an agricultural header to the impact detection system for a header of an agricultural system.)
a first camera coupled to the agricultural system capturing imagery of at least one row unit of the header; (see Yanke at col. 4 lines 41-44 which discloses that the harvester control system 112 includes one or more sensors 114 that sense the presence of a crop material, such as EHP (ears, heads, or pods), relative to the header 108 and that in some implementations, the region sensors 114 are image sensors that capture images; see Yanke at col.6 lines 11-13 which discloses region sensors, such as region sensors 114 or 206, include image sensors, such as a camera (e.g., mono camera and stereo camera); also see Yanke at col. 5 lines 24-26 which discloses that one or more of the sensors 114 captures images of crop material moving through the row units. Examiner notes that capturing images of crop material moving through the row units corresponds to capturing imagery of at least one row unit of the header.)
wherein the agricultural system comprises a first sensor positioned in a rearward end portion of a deck plate of the header, and wherein a first vibration signal is generated by the first sensor indicative of a first vibration associated with an initial contact of a portion of a crop with the deck plate (see at least Yanke at col. 3 lines 57-67 which discloses that the present disclosure is directed to control of an agricultural header based on crop material movement relative to a portion of the header or a position of a type of crop material in relation to a position of another type of crop material at a location proximate to the agricultural header. Yanke further discloses that the present disclosure describes detecting the presence or movement of crop material, such as a crop material representing grain (e.g., ears, heads, or pods of crops ("EHP")), relative to the harvester header or a portion of the harvester header; further, see Yanke at col. 4 lines 46-50 which discloses that the combine harvester 100, the corn header 108, or both may include other sensors and that for example, in some implementations, the corn header 108 includes impact sensors that detect a force or sound of EHP interacting (e.g., impacting) 50 with the header 108. See Yanke at least col. 4 lines 55 to 65 which discloses that the sensors 114 are interchangeably referred to as region sensors as the sensors 114 capture images of a region, such as a region proximate to a header, that other types of sensors that are operable to obtain images of crop material at locations relative to a header are also encompassed by the present disclosure, that further, different types of image sensors may be used in combination with each other, and each sensor is operable to transmit sensed data to the harvester control system 112 for analysis, as described in more detail later, and that the sensed data are transmitted over a wired or wireless connection to the harvester control system 112. See at least Yanke at col. 6 lines 1-29, for example, which discloses that region sensor 206 may be located on a header, such as header 108 shown in Fig. 1, … in order to capture images of a region relative to the header; further, see Yanke at col. 22 lines 4-31 which at least discloses the deck plates of a header. Examiner maps one of the impact sensors to the first sensor and notes that each sensor transmits sensed data, corresponding to the recited first vibration signal, to the harvester control system for analysis 112. Examiner notes that a region sensor being located on a header corresponds to at least a first sensor positioned in a rearward end portion of a deck plate of the header since Yanke at least teaches a header comprising a deck plate. Examiner notes that EHP stands for ears, heads, or pods of crops. Thus, EHP maps to the recited portion of a crop. Examiner has shown a teaching based on a broadest reasonable interpretation of the claimed language.)
Yanke further teaches and a controller performing a process that comprises: executing a machine learning (ML) algorithm and between the portion of a crop in the imagery and a location of the initial contact of the portion of the crop with the deck plate in the imagery (see Yanke at col. 6 lines 27-29 which discloses that the one or more region sensors 206 are in communication with the controller 200 and transmit the image data to the controller 200; see Yanke at cols. 9-10 which discloses that example image analysis techniques are not exclusive and that other types of image analysis techniques may be employed to detect the presence of crop material within an image and movement of the crop material between images, that further, in some implementations, classification approaches using machine learning algorithms are also used to identify features, such as different types of crop material or features of a header, and movement of detected objects between images and that example machine learning algorithms include, but are not limited to, supervised learning algorithms, unsupervised learning algorithms, semi-supervised learning algorithms, and reinforcement learning algorithms; see Yanke at col. 10 lines 12-19 which discloses that in some implementations, neural networks, including neural networks using deep learning, may also be used to identify and classify crop material present in the image data, that example neural networks include perception neural networks, that feed-forward neural networks, convolutional neural networks, recurrent neural networks, and autoencoders, to name only a few and that other types of neural networks are also within the scope of the present disclosure. Further, see Yanke at col. 10 lines 20-32 which discloses that the image analyzer identifies a location of the identified crop material within the images, and that for example, the image analyzer is operable to detect whether the identified crop material is attached to a crop plant; located on a surface, such as a surface of a header; in the air; or on the ground; see Yanke at col. 22 lines 4-31 which at least discloses at least the deck plates of a header.)
Yanke does not expressly disclose that generates an output based on a computer vision technique of digitally counting pixels, which in a related art, Weston teaches (see Weston at [0115] which discloses that the image analyzer circuitry 208 identifies the first vertical position and/or first angular position relative to the features 806A, 806B, that for example, the image analyzer circuitry 208 can identify a vertical position (e.g., a ride height, etc.) of the vehicle 100 and/or individual ones of the suspension components 104A, 104B, 104C, 104D relative to the features 806A, 806B. In some examples, the vertical position can determine the vertical position and/or angular position via pixel counting and/or pixel scaling. Examiner maps the determination of vertical position via pixel counting to generating an output based on a computer vision technique of digitally counting pixels. Examiner shows a teaching based on a broadest reasonable interpretation of the claimed language.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yanke to include generating an output based on a computer vision technique of digitally counting pixels, as taught by Weston.
One would have been motivated to make such a modification to determine vertical or angular position, as suggested by Weston at [0115].
The modified Yanke further teaches and based on the first vibration signal; generating at least one control signal based on the generated ML algorithm output; and controlling an actuator with the at least one control signal that dynamically adjusts the header (see Yanke at col. 4 lines 64-65 which discloses that the sensed data are transmitted over a wired or wireless connection to the harvester control system 112; Examiner had mapped one of the impact sensors to the first sensor. Examiner notes that the sensed data includes sensed data provided by the impact sensors which detect force or impact or vibration to the impact sensors. Further, see Yanke at col. 7 lines 50-52 which discloses that the controller 200 generates one or more control signals that are used to actuate one or more actuators of the header. Also, see Yanke at col. 20 line 47 to col. 21 line 15, for example, which discloses the analysis of undesirable crop harvesting performance based on data from a plurality of rows of a header and over a selected period of time using numerical analysis, rules, one or more neural networks, machine learning algorithms, either alone or in combination with each other and that in some implementations, the mitigation actions represent changes to the header, e.g., changes to one or more settings of one or more components. Thus, based on the foregoing, Examiner has shown a teaching based on a broadest reasonable interpretation of the claimed language.)
Regarding claim 2, the modified Yanke teaches the impact detection system of claim 1, wherein the portion of the crop comprises an ear of corn (see Yanke at col. 3 lines 62-65 which discloses that the present disclosure describes detecting the presence or movement of crop material, such as a crop material representing grain (e.g., ears, heads, or pods of crops ("EHP")); see Yanke at col. 10 lines 40-42 which disclose that the image analyzer has identified an ear of corn.)
Regarding claim 3, the modified Yanke teaches the impact detection system of claim 1, wherein the first camera is coupled to the header or to a cab portion of the agricultural system (see Yanke at col. 4 lines 41-44 which discloses that the harvester control system 112 includes one or more sensors 114 that sense the presence of a crop material, such as EHP (ears, heads, or pods), relative to the header 108 and that in some implementations, the region sensors 114 are image sensors that capture images; also see Yanke at col. 4 lines 53-55 which discloses that the sensor includes, for example, an optical sensor (e.g., camera, a stereo camera). Examiner notes that image sensors which sense the presence of crop material relative to the header corresponds to the first camera coupled to the header; also, see Yanke at col. 6 lines 5-7 which discloses that a region sensor 206 may be located on a header, such as header 108 shown in Fig. 1. Alternatively, the region sensor or camera being located on a header corresponds to a camera coupled to the header. Examiner has shown a teaching based on a broadest reasonable interpretation of the claimed language.)
Regarding claim 4, the modified Yanke teaches the impact detection system of claim 1, comprising a second camera coupled to the agricultural system capturing additional imagery of at least one additional row unit of the header, the captured additional imagery comprising an additional location of a respective initial contact of an additional portion of an additional crop with the deck plate, and wherein the controller further performs the process with the additional imagery (see Yanke at col. 5 lines 24-28 which discloses that for example, in some instances, one or more of the sensors 114 captures images of crop material moving through the row units 110, within a trough of a cross-auger of the corn header 108, or at one or more locations contained within the confines of the corn header 108; see Yanke at col. 20 lines 36-40 which also discloses that the performance of each row unit is monitored, and each row unit is adjustable independently based on the monitored performance. Examiner maps another of the one or more sensors to the second camera. Examiner maps another of the row units to the at least one additional row unit of the header.)
Regarding claim 5, the modified Yanke teaches the impact detection system of claim 1, wherein the ML algorithm generates the output based on the computer vision technique of digitally counting pixels and the first vibration signal, as associated with various time metrics comprising an initial time corresponding to the initial contact of the portion of the crop with the deck plate, a time associated with a peak in the first vibration signal, and over a time period; and wherein the controller further generates the at least one control signal based on the generated ML output as associated with the various time metrics and a combined impact location, the combined impact location being based on an average or a median of the location of the initial contact of the portion of the crop with the deck plate and an additional location of a respective initial contact of an addition portion of an additional crop with the deck plate (see Yanke at col. 7 lines 50-52 which discloses that the controller 200 generates one or more control signals that are used to actuate one or more actuators of the header; see Yanke at col. 8 lines 39-45 which further discloses that the harvester control system 112 includes or is communicably coupled to actuators 240 and that the actuators 240 are associated with a header to alter a state or parameter of the header, or the actuators 240 are associated with a combine harvester or other agricultural vehicle coupled to a header and similarly function to alter a state or parameter of the header. Also, see Yanke at col. 10 lines 1-12, for example, which discloses that image analysis techniques may be employed to detect the presence of crop material within an image and movement of the crop material between images and that in some implementations, classification approaches using machine learning algorithms are also used to identify features, such as different types of crop material or features of a header, and movement of detected objects between images. Examiner notes that the detection, identification, and the application of image analysis techniques to the movement of detected objects occurs over a period of time over different objects, and that the period of time includes an initial time, a time associated with a peak of the first vibration signal, and over a time period which corresponds to various time metrics and a combined impact location, the combined impact location being based on an average or a median of the location of the initial contact of the portion of the crop with the deck plate and an additional location of a respective initial contact of an addition portion of an additional crop with the deck plate. Also, see Yanke at col. 10 lines 20-38 which discloses: Additionally, the image analyzer identifies a location of the identified crop material within the images. For example, the image analyzer is operable to detect whether the identified crop material is attached to a crop plant; located on a surface, such as a surface of a header; in the air; or on the ground. Further, the image analyzer is operable to determine whether the crop material was present on the ground prior to harvesting or traveled to the ground as a result of harvesting. This functionality is described in greater detail below. The image analyzer also determines a position (e.g., position vector), movement (e.g., a movement vector), or both of the crop material within an image, between multiple images, or a combination thereof. A movement vector (an example of which is shown in FIG. 18) encompasses a speed and direction of movement and is determinable, for example, within an image using, for example, motion blur of an object; between multiple images using, for example, a change in position between images; or using a combination of these techniques. Also, see Yanke at Fig. 18 which depicts movement of the vector as a function of time T1 and T2. Examiner notes that using a movement vector that encompasses a speed and direction of movement of the crop material while encompassing change in position between images over time corresponds to calculating a combined impact location based on an average or a median of the location of the initial contact of the portion of the crop at the header and the additional locations of the respective initial contacts of the additional portions of the additional crops at the header. Examiner has shown a teaching based on a broadest reasonable interpretation in light of what is written in the specification.)
Regarding claim 6, the modified Yanke teaches the impact detection system of claim 5, wherein the controller further generates the at least one control signal in response to the combined impact location being outside of a target impact region; and wherein the at least one control signal further comprises one or more alarms (see Yanke at Fig. 3 element 312 which discloses adjusting a setting of the header when the measured distribution data fails to satisfy the target distribution data; see Yanke at col. 17 lines 55-67 which discloses that at 312 one or more settings of a header are altered when a measured distribution value of the measured distribution data does not satisfy criteria contained in the target distribution data, that for example, when a measured distribution value for a parameter meets or exceeds the defined threshold, a change is applied to a component or system of the header or agricultural vehicle coupled to the header, and thus, when a measured distribution for a parameter contained in the measured distribution data fails to satisfy the corresponding criteria in the target distribution data, the controller, such as controller 200, generates a signal, for example, to cause a change in position of an actuator to alter a setting of the header. Further, see Yanke at col. 21 lines 16-20 which discloses that in some implementations, the mitigation actions are automatically implemented, that in some instances, a user, such as a remote or local operator, is notified about mitigation actions that are automatically implemented and that the user may be notified visually, audibly, or haptically. Examiner maps visual, audible, or haptic notification to the one or more alarms.)
Regarding claim 7, the modified Yanke teaches the impact detection system of claim 1, wherein the agricultural system further comprises: a second sensor positioned in a forward end portion of the deck plate, the second sensor generating a second vibration signal indicative of a second vibration associated with the initial contact of the portion of the crop with the deck plate, and wherein the deck plate comprises a first deck plate of a pair of deck plates (see Yanke at col. 4 which discloses that the harvester control system 112 is computer implemented device that receives information, such as in the form of sensor data, and that in some implementations, the corn header 108 includes impact sensors that detect a force or sound of EHP interacting (e.g., impacting) with the header 108. Examiner maps a second of the impact sensors to the second sensor. See at least Yanke at col. 6 lines 1-29, for example, which discloses that region sensor 206 may be located on a header, such as header 108 shown in Fig. 1, … in order to capture images of a region relative to the header; further, see Yanke at col. 22 lines 4-31 which at least discloses deck plates of a header and separation of the deck plates. Examiner notes that a region sensor being located on a header corresponds to at least a second sensor positioned in a forward end portion of a first deck plate of the at least pair of deck plates.)
Regarding claim 11, the modified Yanke teaches the impact detection system of claim 1, wherein the deck plate comprises a first deck plate of a pair of deck plates (see Yanke at col. 22 lines 4-31 which at least discloses deck plates of a header and separation of the deck plates. Examiner notes that one of the pair of deck plates corresponds to a first deck plate.)
Claim 14 is directed toward a header that performs the steps recited in the system of claim 1. The cited portions of the reference(s) used in the rejection of claim 1 teaches the steps recited in the header of claim 14. Additionally, Yanke at col. 4 lines 16-20 teaches a plurality of row units distributed across a width of the header (see Yanke at col. 4 lines 16-20 in conjunction with Fig. 1 which discloses that the combine harvester 100 includes a corn header 108 that includes a plurality of row units 110, with each row unit 110 aligning with a particular row 106 to harvest the crops contained in that row 106.).
Claim 15 is directed toward an agricultural system that performs the steps recited in the system of claim 4. The cited portions of the reference(s) used in the rejection of claim 4 teach the steps recited in the header of claim 15. Therefore, claim 15 is rejected under the same rationale used in the rejection of claim 4.
Claim 17 is directed toward a header that performs the steps recited in the system of claim 7. The cited portions of the reference(s) used in the rejection of claim 7 teach the steps recited in the header of claim 17. Therefore, claim 17 is rejected under the same rationale used in the rejection of claim 7.
Independent claim 19 recites a method that performs the steps recited in the impact detection system of claim 1. The cited portions of the prior art used in the rejection of claim 1 teach the corresponding limitations recited in the method of claim 19. Therefore, claim 19 is rejected for the same reasons as stated for claim 1 above.
Claims 8-9, 12-13, 18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yanke et al. (US 12,022,772) in view of Weston et al. (US 2023/0410528) and further in view of Merrill et al. (US 12052943).
Regarding claim 8, the modified Yanke does not expressly disclose the impact detection system of claim 1, wherein the controller further performs a training of the ML algorithm with a training process comprising supervised learning via iterative optimization of an objective function which in a related art Merrill teaches (see Merrill at col. 4 in conjunction with Fig. 1 which discloses an agricultural apparatus 111 comprising a controller area network (CAN) and an application controller 114 in communication with machine learning system instructions; see at least Merrill at col. 30 which discloses that in supervised training, training data is used by a supervised training algorithm to train a machine learning model, that the training data includes input and a "known" output, as described above and that in an embodiment, the supervised training algorithm is an iterative procedure … and that an error or variance between the predicated output and the known output is calculated using an objective function and that in effect, the output of the objective function indicates the accuracy of the machine learning model based on the particular state of the model artifact in the iteration.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yanke to include wherein the controller further performs a training of the ML algorithm with a training process comprising supervised learning via iterative optimization of an objective function, as taught by Merrill.
One would have been motivated to make such a modification to improve the training of machine learning models, as suggested by Merrill at the Abstract.
Regarding claim 9, the modified Yanke teaches based on the first vibration signal, the second vibration signal, or both; and an image-based training process via the computer vision technique of digitally counting pixels of a digital distance in one or more frames in the imagery between the location of the initial contact of the portion of the crop with the deck plate and a reference feature positioned in association with the header (see Yanke at col. 4 lines 46-50 which discloses that the combine harvester 100, the corn header 108, or both may include other sensors and that for example, in some implementations, the corn header 108 includes impact sensors that detect a force or sound of EHP interacting (e.g., impacting) 50 with the header 108. Examiner mapped impact sensors to first and second sensors producing first and second vibration signals, respectively. Also, see Weston at [0115] which discloses that the image analyzer circuitry 208 identifies the first vertical position and/or first angular position relative to the features 806A, 806B, that for example, the image analyzer circuitry 208 can identify a vertical position (e.g., a ride height, etc.) of the vehicle 100 and/or individual ones of the suspension components 104A, 104B, 104C, 104D relative to the features 806A, 806B. In some examples, the vertical position can determine the vertical position and/or angular position via pixel counting and/or pixel scaling. Examiner maps the determination of vertical position via pixel counting to generating an output based on a computer vision technique of digitally counting pixels. Further, see Yanke at col. 10 lines 20-32 which discloses that the image analyzer identifies a location of the identified crop material within the images, and that for example, the image analyzer is operable to detect whether the identified crop material is attached to a crop plant; located on a surface, such as a surface of a header; in the air; or on the ground; See Yanke at col. 11 lines 37-53 which discloses that the image analyzer also identifies a reference location 406 corresponding to a part or feature of the header 408, that in this example, the reference location 406 is a static location corresponding to a discernable feature, such as a tip 410 of a row unit cover 412 of the header 408; see Yanke at col. 22 lines 4-31 which at least discloses at least the deck plates of a header.)
The modified Yanke does not expressly disclose the impact detection system of claim 7, wherein the controller further performs a training of the ML algorithm with a training process, the training process comprising: a feedback training process via reinforcement learning with signal analytics [based on the first vibration signal, the second vibration signal, or both; and an image-based training process via the computer vision technique of digitally counting pixels of a digital distance in one or more frames in the imagery between the location of the initial contact of the portion of the crop with the deck plate and a reference feature positioned in association with the header], which in a related art, Merrill teaches (see Merrill at col. 19 which discloses argonomic dataset evaluation logic as a feedback loop; see Merrill at col. 32 which discloses positive and negative reinforcement learning with signal analytics. In addition, see Merrill at col. 35 which discloses RNN (recurrent neural network) model training that may use backpropagation through time, which is a technique that may achieve higher accuracy for an RNN model than with ordinary backpropagation.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yanke to include wherein the controller further performs a training of the ML algorithm with a training process, the training process comprising: a feedback training process via reinforcement learning with signal analytics, as taught by Merrill.
One would have been motivated to make such a modification to improve the training of machine learning models, as suggested Merrill at the Abstract.
Regarding claim 12, the modified Yanke teaches impact detection system of claim 9, wherein the reference feature comprises a patterned cover on a hood positioned between adjacent row units of the header (see Yanke at col. 9 lines 60-66 which discloses that the image analyzer may use one or more of the following image analysis techniques: two-dimensional (2D) object recognition, three-dimensional (3D) object recognition, image segmentation, motion detection (e.g., single particle tracking), video tracking, optical flow, 3D pose estimation, pattern recognition, and object recognition, to name a few. Yanke at col. 11 lines 45-53 further discloses that other marker types may be used to identify the reference location 406 in a presented image, that example markers include markers having different shapes, colors, patterns, symbols, and characters and that in some instances, text or objects are used as a marker type to identify the reference location 406 on a display and, still further, text or objects with varying intensity are used as a marker type to identify the reference location 406 on a display. Examiner notes that a reference location corresponding to a part or feature of a header maps to a patterned cover on a hood positioned between adjacent row units of the header. Examiner has shown a teaching based on a broadest reasonable interpretation of the claimed language in light of the specification, at [0041], which states that FIG. 5 is a perspective side view of an embodiment of the hood 218 that may be employed within the header 200 of FIG. 2.).
Regarding claim 13, the modified Yanke teaches a header (see Yanke at the Abstract which discloses systems and methods for controlling agricultural headers; see Yanke at Fig. 1 which illustratively depicts corn header 108; see Yanke at col. 4 which discloses that the present disclosure encompasses self-propelled forage harvester, windrow traction vehicles, cotton harvesters, or other agricultural vehicles that carry or otherwise transport a header and other types of headers, such as a draper header, to harvest crops. Examiner notes that headers require the use of bolts for it to be secured onto a combine harvester.)
The modified Yanke further teaches the impact detection system of claim 9, wherein the reference feature comprises one or more bolts [on the header], one or more ribs on a hood of the header, one or more grooves on the hood, a cover for the hood, or any combination thereof (see Weston at [0028] which discloses that in some examples, machine-learning algorithms can be used to refine vehicle calibration over time to account for wear of the suspension components and similar effects and that in some examples disclosed herein, visually identifiable suspension features (e.g., spring seats, Panhard bolts, etc.) can be used as reference points.)
Regarding claim 18, the modified Yanke does not expressly disclose the agricultural system of claim 14, wherein the controller further performs a training of the ML algorithm with a training process comprising supervised learning via iterative optimization of an objective function which in a related art Merrill teaches (see Merrill at col. 4 in conjunction with Fig. 1 which discloses an agricultural apparatus 111 comprising a controller area network (CAN) and an application controller 114 in communication with machine learning system instructions; see at least Merrill at col. 30 which discloses that in supervised training, training data is used by a supervised training algorithm to train a machine learning model, that the training data includes input and a "known" output, as described above and that in an embodiment, the supervised training algorithm is an iterative procedure … and that an error or variance between the predicated output and the known output is calculated using an objective function and that in effect, the output of the objective function indicates the accuracy of the machine learning model based on the particular state of the model artifact in the iteration.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yanke to include wherein the controller further performs a training of the ML algorithm with a training process comprising supervised learning via iterative optimization of an objective function, as taught by Merrill.
One would have been motivated to make such a modification to improve the training of machine learning models, as suggested Merrill at the Abstract.
Regarding claim 20, the modified Yanke teaches and wherein the deck plate comprises a first deck plate of a pair of deck plates (see Yanke at col. 22 lines 4-31 which at least discloses deck plates of a header and separation of the deck plates. Examiner notes that one of the pair of deck plates corresponds to a first deck plate.).
The modified Yanke does not expressly disclose the method of claim 19, further comprising: training the ML algorithm with a training process comprising supervised learning via iterative optimization of an objective function, which in a related art, Merrill teaches (see Merrill at col. 4 in conjunction with Fig. 1 which discloses an agricultural apparatus 111 comprising a controller area network (CAN) and an application controller 114 in communication with machine learning system instructions; see at least Merrill at col. 30 which discloses that in supervised training, training data is used by a supervised training algorithm to train a machine learning model, that the training data includes input and a "known" output, as described above and that in an embodiment, the supervised training algorithm is an iterative procedure … and that an error or variance between the predicated output and the known output is calculated using an objective function and that in effect, the output of the objective function indicates the accuracy of the machine learning model based on the particular state of the model artifact in the iteration.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yanke to include wherein the controller further performs a training of the ML algorithm with a training process comprising supervised learning via iterative optimization of an objective function, as taught by Merrill.
One would have been motivated to make such a modification to improve the training of machine learning models, as suggested Merrill at the Abstract.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROY RHEE whose telephone number is 313-446-6593. The examiner can normally be reached M-F 8:30 am to 5:30 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 may contact the Examiner via telephone or 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, Kito Robinson, can be reached on 571-270-3921. 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, one may visit: https://patentcenter.uspto.gov. In addition, more information about Patent Center may be found at https://www.uspto.gov/patents/apply/patent-center. Should you have questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ROY RHEE/Primary Examiner, Art Unit 3664
Prosecution Insights