DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This is a Final Action on the Merits. Claims 1-20 are currently pending and are addressed below.
Response to Amendments
The amendment filed on March 30th, 2026 has been considered and entered. Accordingly, claims 1, 9, and 16 have been amended.
Response to Arguments
The applicant’s arguments with respect to claims 1-20 have been considered but are moot in view of the newly formulated grounds of rejections necessitated by the applicant’s amendments.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 4, 7, 9, 11-12, 15-16, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Kreiling (US 20210043085 A1) (“Kreiling”) in view of Hoffman (US 20200348628 A1) (“Hoffman”) (Hoffman) in view of Suzuki (US 20200224384 A1) (“Suzuki”).
With respect to claim 1, Kreiling teaches a method comprising:
applying, by an autonomous off-road vehicle (AOV), a machine-learned model to a first state of a portion of an AOV and a desired state of the portion of the AOV, the machine-learned model configured to produce a set of control signals to actuate and adjust the portion of the AOV to move the portion of the AOV to the desired state (See at least Kreiling Paragraphs 43-48 “In the example of FIG. 1, the hydraulically actuated boom assembly 32 includes an aft bracket 34 affixed to the tractor chassis 24, a forward bracket 36 to which the FEL bale spear attachment 28 is pivotally attached, and an intermediate or mid bracket 38 situated between the brackets 34, 36. Twin upper loader arms 40 (one of which can be seen in FIG. 1) pivotally attach the aft bracket 34 to the mid bracket 38, which is, in turn, attached to the forward bracket 36 by twin lower loader arms 42 (again only one of which can be seen). Twin hydraulic lift cylinders 44 are further mounted between the aft bracket 34 and the mid bracket 38, while twin hydraulic bucket cylinders 46 are mounted between the mid bracket 38 and the forward bracket 36. Non-illustrated hydraulic lines of the boom assembly 32 are further present and fluidly connected to a pressurized hydraulic fluid supply on the loader 20 in a manner permitting an operator seated within the operator station 26 to control the hydraulic cylinders 44, 46. An operator can command the boom assembly 32 to lift the FEL bale spear attachment 28 from the illustrated home orientation (that is, the non-tilted, lowered position) by controlling the hydraulic lift cylinders 44 to extend in a desired manner. As the hydraulic lift cylinders 44 extend, the FEL bale spear attachment 28 lifts from the lowered home orientation shown in FIG. 1, travels through an intermediate or mast level position, and is ultimately raised to a full height position located above the operator station 26. Similarly, as the hydraulic bucket cylinders 46 retract in response to operator commands, the boom assembly 32 tilts the FEL bale spear attachment 28 from forward-facing angular orientation shown in FIG. 1 toward an increasingly upright orientation; that is, such that the bale spears included in the FEL bale spear attachment 28 rotate upwardly toward the front hood or windshield of the loader 20. Conversely, from the full height position, the operator can control the boom assembly 32 to stroke the hydraulic cylinders 44, 46 in an opposing to return the FEL bale spear attachment 28 to the lowered, non-tilted, lowered position shown in FIG. 1. The operator may control the cylinders 44, 46 to extend and retract, as desired, through movement of a suitable control interface (e.g., a joystick) located within the operator station 26 of the loader 20 … As appearing herein, the term “implement data source” refers broadly to any device, system, or sensor providing data relating to a work implement mounted to a work vehicle. The implement tracking data may include, for example, information pertaining to the present or predicted movement of a work vehicle chassis, as well as the present or predicted movement of a work implement when movable relative to a work vehicle chassis. Thus, utilizing the FEL bale spear attachment 28 mounted to the loader 20 (FIG. 1) as an example, the implement data sources 54 can include the operator input controls 66 utilized to control movement of the tractor chassis 24, such as the below-described steering wheel 88 (see FIGS. 3-5). Additionally, the implement data sources 54 may include operator input controls 66 utilized to control movement of the boom assembly 32, such as the below-described joystick 90 (see again FIGS. 3-5) … In more complex embodiments, the controller 48 may consider the present motion state of the work implement in establishing the projected trajectory of the work vehicle implement …” | Paragraph 117 “In one example, the controller 48 a may be comprised of one or more of software and/or hardware in any proportion. In such an example, controller 48 a may reside on a computer-based platform such as, for example, a server or set of servers. Any such server or servers may be a physical server(s) or a virtual machine(s) executing on another hardware platform or platforms. Any server, or for that matter any computer-based system, systems or elements described herein, will be generally characterized by one or more control units and associated processing elements and storage devices communicatively interconnected to one another by one or more busses or other communication mechanism for communicating information or data. In one example, storage within such devices may include a main memory such as, for example, a random access memory (RAM) or other dynamic storage devices, for storing information and instructions to be executed by the control unit(s) and for storing temporary variables or other intermediate information during the use of the control unit described herein.” | Paragraph 123 “Unless specifically stated otherwise or as apparent from the description herein, it is appreciated that throughout the present disclosure, discussions utilizing terms such as … other conjugation forms of these terms and like terms, refer to the actions and processes of a control unit, computer system or computing element (or portion thereof) such as, but not limited to, one or more or some combination of: a visual organizer system, a request generator, an Internet coupled computing device, a computer server, etc. In one example, the control unit, computer system and/or the computing element may manipulate and transform information and/or data represented as physical (electronic) quantities within the control unit, computer system's and/or computing element's processor(s), register(s), and/or memory(ies) into other data similarly represented as physical quantities within the control unit, computer system's and/or computing element's memory(ies), register(s) and/or other such information storage, processing, transmission, and/or display components of the computer system(s), computing element(s) and/or other electronic computing device(s). Under the direction of computer-readable instructions, the control unit, computer system(s) and/or computing element(s) may carry out operations of one or more of the processes, methods and/or functionalities of the present disclosure.”);
executing, by the AOV, the set of control signals to configure the portion of the AOV to a second state of the portion of the AOV (See at least Kreiling Paragraph 48 “In more complex embodiments, the controller 48 may consider the present motion state of the work implement in establishing the projected trajectory of the work vehicle implement …” | Paragraph 117 “In one example, the controller 48 a may be comprised of one or more of software and/or hardware in any proportion. In such an example, controller 48 a may reside on a computer-based platform such as, for example, a server or set of servers. Any such server or servers may be a physical server(s) or a virtual machine(s) executing on another hardware platform or platforms. Any server, or for that matter any computer-based system, systems or elements described herein, will be generally characterized by one or more control units and associated processing elements and storage devices communicatively interconnected to one another by one or more busses or other communication mechanism for communicating information or data. In one example, storage within such devices may include a main memory such as, for example, a random access memory (RAM) or other dynamic storage devices, for storing information and instructions to be executed by the control unit(s) and for storing temporary variables or other intermediate information during the use of the control unit described herein.”); and
Kreiling fails to explicitly disclose updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, 2) a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves, and 3) the set of control signals.
Hoffman teaches updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, and 3) the set of control signals (See at least Hoffman FIG. 4 and Paragraphs 122-124 “FIG. 4 is a flowchart of a method 400 for controlling a system as described herein. The method 400 includes detecting, during a first period of time, an output of a system (402). The method 400 additionally includes determining, based on the output detected during the first period of time, a first performance metric for the system (404). The method 400 additionally includes operating a first hybrid controller, based on the first performance metric, to generate a first hybrid controller output (406). The first hybrid controller includes a first constraint, a first dynamic system, a first learned system model, and a first learned system update module. The first learned system update module is configured to update the first learned system model based on at least one output detected from the system and to update the first learned system model according to at least one of a timing or a rate corresponding to a first learning parameter. The first dynamic system has a first dynamic parameter that corresponds to an overall responsiveness of the first dynamic system. Operating the first hybrid controller to generate the first hybrid controller output includes: (i) determining a first difference between the first performance metric and the first constraint; (ii) applying the determined first difference to the first dynamic system to generate a first dynamic system output; and (iii) applying the generated first dynamic output to the first learned system model to generate the first hybrid controller output. The method 400 additionally includes controlling the system, during a second period of time, according to the generated first hybrid controller output (408) and detecting, during a third period of time, the output of the system (410). The method 400 additionally includes determining, based on the output detected during the third period of time, a second performance metric for the system (412) and operating a second hybrid controller, based on the first performance metric and the second performance metric, to generate a first hybrid controller update (414). The first hybrid controller update includes at least one of an updated first constraint value, an updated first dynamic parameter, or an updated first learning parameter. The method 400 additionally includes updating the first hybrid controller according to the first hybrid controller update (416), operating the updated first hybrid controller, based on the second performance metric, to generate a second hybrid controller output (418), and controlling the system, during a fourth period of time, according to the generated second hybrid controller output (420).”).
It would have been obvious to one ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kreiling to include updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, , and 3) the set of control signals, as taught by Hoffman as disclosed above, in order to ensure accurate AOV movement with respect to a desired state (Hoffman Paragraph 3 “Such a hybrid controller may provide better outputs, with respect to controlling the output of the system or with respect to some other operational parameter of interest,”).
Kreiling in view of Hoffman fail to explicitly disclose updating the machine-learned model based on a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves.
Suzuki teaches determining a speed of the portion of the AOV relative to a body of the AOV (See at least Suzuki FIG. 9 and Paragraphs 90-91 “In FIG. 9, the target operating velocity generation section 710 generates first the target operating velocity Vt on the basis of the operation signal from the operation input amount sensor 33 b (Step S110), and the operating velocity detection section 740 and the posture detection section 750 generate the actual operating velocity Vr and the posture information on the basis of the detection result of any of the IMU sensors 20S, 21S, 22S, and 30S (Steps S120, S130). Next, the control intervention determination section 810 determines whether the difference between the target operating velocity Vt and the actual operating velocity Vr is larger than a preset threshold (Step S140), the operating velocity estimation section 760 computes the estimated operating velocity Ve in a case in which a determination result is YES (Step S150), and the first center-of-gravity position prediction section 780 calculates the ZMP using the estimated operating velocity Ve in a case in which the front work implement is suddenly stopped (Step S160), and calculates the ZMP using the estimated operating velocity Ve in a case in which the front work implement is slowly stopped (Step S170).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kreiling in view of Hoffman to include determining a speed of the portion of the AOV relative to a body of the AOV, as taught by Suzuki as disclosed above, such that the machine-learned model is updated based on a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves, in order to ensure accurate vehicle control (Suzuki Paragraph 10 “The present invention has been achieved in the light of the above respects, and an object of the present invention is to provide a work machine that can appropriately carry out limiting on operating velocities of a front work implement and slow deceleration of the front work implement and that can suppress reductions in workability and operability, a deterioration in a ride quality, and the like even in a case of work involving an abrupt change in disturbance and a change in a lever operation amount within minute time.”).
With respect to claim 4, and similarly claims 12 and 19, Kreiling in view of Hoffman in view of Suzuki teach that the one or more control signals cause the AOV to adjust an angle of a portion of the AOV below a ground surface, wherein the adjustment of the angle of the portion of the AOV maintains a desired speed of the portion of the AOV (See at least Kreiling Paragraph 32 “The projection of the work implement trajectory may thus be effected by an assessment of only its motion (in terms of one or both of its spatial position and orientational attitude) relative to the work vehicle chassis, or this combined with an assessment of the heading of the work vehicle. The motion of the work implement may be a single degree of freedom motion such as a change of only its spatial position or its attitude relative to the work vehicle chassis (e.g., only a pivotal motion such as a bucket tilt), or it may be a multiple degree of freedom, compound motion affecting both its spatial position and attitude (e.g., raising/lowering on loader arms and tilting a bucket or extending/retracting, swinging and tilting a bucket on a boom linkage). In other contexts, such compound motion may include additional degrees of freedom. In the case of the saw head of a feller buncher, for example, this could include rotation about a fore-aft axis generally in the travel direction of the work vehicle.” | Paragraphs 81-82 “Furthermore, in certain embodiments, the field of view of one or more imaging devices (e.g., camera) mounted to the work vehicle 202 may encompass the range of motion of the work vehicle and/or its implements, such as the boom 204 shown in FIG. 10. In such cases, the controller 48 a may further perform image analysis of video feed(s) provided by such imaging devices to the present orientation of the implement (e.g., the boom 204) at a given juncture in time. Information regarding past and present orientations of the boom 204 (or another independently movable implement) may also be tracked, stored in the memory 52 a, and then recalled from memory 52 a by controller 48 a as desired … ”) (See at least Wei Paragraph 21 “n any of the examples described herein, machine locations, speeds, headings, orientations, and/or other parameters determined by the respective location sensors 130 may be used by the system controller 122 and/or other components of the system 100 to coordinate activities of the digging machines 102, loading machines 104, hauling machines 106, and/or other components of the system 100. Further, in any of the examples described herein, machine locations, speeds, headings, orientations, and/or other parameters determined by the respective location sensors 130 may be used by the system controller 122 and/or other components of the system 100 to move portions of the pile 118 of material 119 throughout the worksite 112 as described herein.” | Paragraph 45 “Loading of the material 119 from the undesired-shaped pile 118 may become more difficult and far less efficient due to lack of resistance forces provided by a convex-shaped pile 118 of material 119. Obtaining and/or maintaining the convex-shaped pile 118 during a loading operation of the loading machine 104 may provide for the largest resistance forces against the loading machine 104 which may facilitate the most material 119 to enter the work tool 140 of the loading machine 104. Further, using the above-described primitive methods, such loading machines 104 may also complete loading instances where only partial-loads of the material 119 may be obtained as there may not be enough material 119, in a significant enough aggregation to constitute a full load of the work tool 140. Users of the loading machines 104 may desire to have the semi-autonomous or autonomous loading machines 104 function similar to the manner in which a human operator would operate the loading machine. Human operators, with their experience in considering the shapes of piles 118 of various materials 119 can effectively scoop the material 119 from the pile 118, in an orderly fashion such that in a first phase, material indicated by curve 220-1 is obtained, and, thereafter in a second phase, material indicated by a dashed curve 220-2 is obtained as depicted in FIG. 2. In this manner, the volume of material 119 within the work tool 140 of the loading machine 104 may be maximized for each material 119 scooping attempt while minimizing energy spent on final cleanup of any loose or unaggregated material 119”).
With respect to claim 7, and similarly claim 15, Kreiling in view of Hoffman in view of Suzuki teach that updating the machine-learned model comprises using online learning techniques to retrain the machine-learned model based on the second state of the portion of the AO (See at least Kreiling Paragraph 47 “. In such cases, the controller 48 may further perform image analysis of video feed(s) provided by such imaging devices to the present orientation of a work implement (e.g., the FEL bale spear attachment 28) at a given juncture in time. Information regarding past and present orientations of the FEL bale spear attachment 28 (or another independently-movable work implement) may also be tracked, stored in the memory 52, and then recalled from memory 52 by controller 48 as desired.” | Paragraph 81 “Furthermore, in certain embodiments, the field of view of one or more imaging devices (e.g., camera) mounted to the work vehicle 202 may encompass the range of motion of the work vehicle and/or its implements, such as the boom 204 shown in FIG. 10. In such cases, the controller 48 a may further perform image analysis of video feed(s) provided by such imaging devices to the present orientation of the implement (e.g., the boom 204) at a given juncture in time. Information regarding past and present orientations of the boom 204 (or another independently movable implement) may also be tracked, stored in the memory 52 a, and then recalled from memory 52 a by controller 48 a as desired.” | Paragraph 123 “other conjugation forms of these terms and like terms, refer to the actions and processes of a control unit, computer system or computing element (or portion thereof) such as, but not limited to, one or more or some combination of: a visual organizer system, a request generator, an Internet coupled computing device, a computer server, etc.”).
With respect to claim 9, Kreiling teaches a non-transitory computer-readable storage medium storing executable instructions that, when executed by a hardware processor, cause the hardware processor to perform steps comprising:
applying, by an autonomous off-road vehicle (AOV), a machine-learned model to a first state of a portion of an AOV and a desired state of the portion of the AOV, the machine-learned model configured to produce a set of control signals to actuate and adjust the portion of the AOV to move the portion of the AOV to the desired state (See at least Kreiling Paragraphs 43-48 “In the example of FIG. 1, the hydraulically actuated boom assembly 32 includes an aft bracket 34 affixed to the tractor chassis 24, a forward bracket 36 to which the FEL bale spear attachment 28 is pivotally attached, and an intermediate or mid bracket 38 situated between the brackets 34, 36. Twin upper loader arms 40 (one of which can be seen in FIG. 1) pivotally attach the aft bracket 34 to the mid bracket 38, which is, in turn, attached to the forward bracket 36 by twin lower loader arms 42 (again only one of which can be seen). Twin hydraulic lift cylinders 44 are further mounted between the aft bracket 34 and the mid bracket 38, while twin hydraulic bucket cylinders 46 are mounted between the mid bracket 38 and the forward bracket 36. Non-illustrated hydraulic lines of the boom assembly 32 are further present and fluidly connected to a pressurized hydraulic fluid supply on the loader 20 in a manner permitting an operator seated within the operator station 26 to control the hydraulic cylinders 44, 46. An operator can command the boom assembly 32 to lift the FEL bale spear attachment 28 from the illustrated home orientation (that is, the non-tilted, lowered position) by controlling the hydraulic lift cylinders 44 to extend in a desired manner. As the hydraulic lift cylinders 44 extend, the FEL bale spear attachment 28 lifts from the lowered home orientation shown in FIG. 1, travels through an intermediate or mast level position, and is ultimately raised to a full height position located above the operator station 26. Similarly, as the hydraulic bucket cylinders 46 retract in response to operator commands, the boom assembly 32 tilts the FEL bale spear attachment 28 from forward-facing angular orientation shown in FIG. 1 toward an increasingly upright orientation; that is, such that the bale spears included in the FEL bale spear attachment 28 rotate upwardly toward the front hood or windshield of the loader 20. Conversely, from the full height position, the operator can control the boom assembly 32 to stroke the hydraulic cylinders 44, 46 in an opposing to return the FEL bale spear attachment 28 to the lowered, non-tilted, lowered position shown in FIG. 1. The operator may control the cylinders 44, 46 to extend and retract, as desired, through movement of a suitable control interface (e.g., a joystick) located within the operator station 26 of the loader 20 … As appearing herein, the term “implement data source” refers broadly to any device, system, or sensor providing data relating to a work implement mounted to a work vehicle. The implement tracking data may include, for example, information pertaining to the present or predicted movement of a work vehicle chassis, as well as the present or predicted movement of a work implement when movable relative to a work vehicle chassis. Thus, utilizing the FEL bale spear attachment 28 mounted to the loader 20 (FIG. 1) as an example, the implement data sources 54 can include the operator input controls 66 utilized to control movement of the tractor chassis 24, such as the below-described steering wheel 88 (see FIGS. 3-5). Additionally, the implement data sources 54 may include operator input controls 66 utilized to control movement of the boom assembly 32, such as the below-described joystick 90 (see again FIGS. 3-5) … In more complex embodiments, the controller 48 may consider the present motion state of the work implement in establishing the projected trajectory of the work vehicle implement …” | Paragraph 117 “In one example, the controller 48 a may be comprised of one or more of software and/or hardware in any proportion. In such an example, controller 48 a may reside on a computer-based platform such as, for example, a server or set of servers. Any such server or servers may be a physical server(s) or a virtual machine(s) executing on another hardware platform or platforms. Any server, or for that matter any computer-based system, systems or elements described herein, will be generally characterized by one or more control units and associated processing elements and storage devices communicatively interconnected to one another by one or more busses or other communication mechanism for communicating information or data. In one example, storage within such devices may include a main memory such as, for example, a random access memory (RAM) or other dynamic storage devices, for storing information and instructions to be executed by the control unit(s) and for storing temporary variables or other intermediate information during the use of the control unit described herein.” | Paragraph 123 “Unless specifically stated otherwise or as apparent from the description herein, it is appreciated that throughout the present disclosure, discussions utilizing terms such as … other conjugation forms of these terms and like terms, refer to the actions and processes of a control unit, computer system or computing element (or portion thereof) such as, but not limited to, one or more or some combination of: a visual organizer system, a request generator, an Internet coupled computing device, a computer server, etc. In one example, the control unit, computer system and/or the computing element may manipulate and transform information and/or data represented as physical (electronic) quantities within the control unit, computer system's and/or computing element's processor(s), register(s), and/or memory(ies) into other data similarly represented as physical quantities within the control unit, computer system's and/or computing element's memory(ies), register(s) and/or other such information storage, processing, transmission, and/or display components of the computer system(s), computing element(s) and/or other electronic computing device(s). Under the direction of computer-readable instructions, the control unit, computer system(s) and/or computing element(s) may carry out operations of one or more of the processes, methods and/or functionalities of the present disclosure.”);
executing, by the AOV, the set of control signals to configure the portion of the AOV to a second state of the portion of the AOV (See at least Kreiling Paragraph 48 “In more complex embodiments, the controller 48 may consider the present motion state of the work implement in establishing the projected trajectory of the work vehicle implement …” | Paragraph 117 “In one example, the controller 48 a may be comprised of one or more of software and/or hardware in any proportion. In such an example, controller 48 a may reside on a computer-based platform such as, for example, a server or set of servers. Any such server or servers may be a physical server(s) or a virtual machine(s) executing on another hardware platform or platforms. Any server, or for that matter any computer-based system, systems or elements described herein, will be generally characterized by one or more control units and associated processing elements and storage devices communicatively interconnected to one another by one or more busses or other communication mechanism for communicating information or data. In one example, storage within such devices may include a main memory such as, for example, a random access memory (RAM) or other dynamic storage devices, for storing information and instructions to be executed by the control unit(s) and for storing temporary variables or other intermediate information during the use of the control unit described herein.”); and
Kreiling fails to explicitly disclose updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, 2) a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves, and 3) the set of control signals.
Hoffman teaches updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, and 3) the set of control signals (See at least Hoffman FIG. 4 and Paragraphs 122-124 “FIG. 4 is a flowchart of a method 400 for controlling a system as described herein. The method 400 includes detecting, during a first period of time, an output of a system (402). The method 400 additionally includes determining, based on the output detected during the first period of time, a first performance metric for the system (404). The method 400 additionally includes operating a first hybrid controller, based on the first performance metric, to generate a first hybrid controller output (406). The first hybrid controller includes a first constraint, a first dynamic system, a first learned system model, and a first learned system update module. The first learned system update module is configured to update the first learned system model based on at least one output detected from the system and to update the first learned system model according to at least one of a timing or a rate corresponding to a first learning parameter. The first dynamic system has a first dynamic parameter that corresponds to an overall responsiveness of the first dynamic system. Operating the first hybrid controller to generate the first hybrid controller output includes: (i) determining a first difference between the first performance metric and the first constraint; (ii) applying the determined first difference to the first dynamic system to generate a first dynamic system output; and (iii) applying the generated first dynamic output to the first learned system model to generate the first hybrid controller output. The method 400 additionally includes controlling the system, during a second period of time, according to the generated first hybrid controller output (408) and detecting, during a third period of time, the output of the system (410). The method 400 additionally includes determining, based on the output detected during the third period of time, a second performance metric for the system (412) and operating a second hybrid controller, based on the first performance metric and the second performance metric, to generate a first hybrid controller update (414). The first hybrid controller update includes at least one of an updated first constraint value, an updated first dynamic parameter, or an updated first learning parameter. The method 400 additionally includes updating the first hybrid controller according to the first hybrid controller update (416), operating the updated first hybrid controller, based on the second performance metric, to generate a second hybrid controller output (418), and controlling the system, during a fourth period of time, according to the generated second hybrid controller output (420).”).
It would have been obvious to one ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kreiling to include updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, , and 3) the set of control signals, as taught by Hoffman as disclosed above, in order to ensure accurate AOV movement with respect to a desired state (Hoffman Paragraph 3 “Such a hybrid controller may provide better outputs, with respect to controlling the output of the system or with respect to some other operational parameter of interest,”).
Kreiling in view of Hoffman fail to explicitly disclose updating the machine-learned model based on a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves.
Suzuki teaches determining a speed of the portion of the AOV relative to a body of the AOV (See at least Suzuki FIG. 9 and Paragraphs 90-91 “In FIG. 9, the target operating velocity generation section 710 generates first the target operating velocity Vt on the basis of the operation signal from the operation input amount sensor 33 b (Step S110), and the operating velocity detection section 740 and the posture detection section 750 generate the actual operating velocity Vr and the posture information on the basis of the detection result of any of the IMU sensors 20S, 21S, 22S, and 30S (Steps S120, S130). Next, the control intervention determination section 810 determines whether the difference between the target operating velocity Vt and the actual operating velocity Vr is larger than a preset threshold (Step S140), the operating velocity estimation section 760 computes the estimated operating velocity Ve in a case in which a determination result is YES (Step S150), and the first center-of-gravity position prediction section 780 calculates the ZMP using the estimated operating velocity Ve in a case in which the front work implement is suddenly stopped (Step S160), and calculates the ZMP using the estimated operating velocity Ve in a case in which the front work implement is slowly stopped (Step S170).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kreiling in view of Hoffman to include determining a speed of the portion of the AOV relative to a body of the AOV, as taught by Suzuki as disclosed above, such that the machine-learned model is updated based on a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves, in order to ensure accurate vehicle control (Suzuki Paragraph 10 “The present invention has been achieved in the light of the above respects, and an object of the present invention is to provide a work machine that can appropriately carry out limiting on operating velocities of a front work implement and slow deceleration of the front work implement and that can suppress reductions in workability and operability, a deterioration in a ride quality, and the like even in a case of work involving an abrupt change in disturbance and a change in a lever operation amount within minute time.”).
With respect to claim 11, and similarly claim 18, Kreiling in view of Hoffman in view of Suzuki teach that the machine-learned model is trained based on baseline training data and online training data, the online training data generated based on previous actions taken by the AOV (See at least Kreiling Paragraph 47 “ The sensors 68 can assume the proximity sensors, displacement sensors (e.g., for measuring hydraulic piston stroke), or any other devices capable of providing data from which the present orientation of a work implement relative to the work vehicle chassis (e.g., the tractor chassis 24) can be ascertained. Furthermore, in certain embodiments, the FOV of one or more imaging devices mounted to the loader 20 may encompass the range of motion of a work implement, such as the FEL bale spear attachment 28 shown in FIG. 1. In such cases, the controller 48 may further perform image analysis of video feed(s) provided by such imaging devices to the present orientation of a work implement (e.g., the FEL bale spear attachment 28) at a given juncture in time. Information regarding past and present orientations of the FEL bale spear attachment 28 (or another independently-movable work implement) may also be tracked, stored in the memory 52, and then recalled from memory 52 by controller 48 as desired.” | Paragraph 81 “ In such cases, the controller 48 a may further perform image analysis of video feed(s) provided by such imaging devices to the present orientation of the implement (e.g., the boom 204) at a given juncture in time. Information regarding past and present orientations of the boom 204 (or another independently movable implement) may also be tracked, stored in the memory 52 a, and then recalled from memory 52 a by controller 48 a as desired.” | Paragraph 123 “Unless specifically stated otherwise or as apparent from the description herein, it is appreciated that throughout the present disclosure, discussions utilizing terms such as … other conjugation forms of these terms and like terms, refer to the actions and processes of a control unit, computer system or computing element (or portion thereof) such as, but not limited to, one or more or some combination of: a visual organizer system, a request generator, an Internet coupled computing device, a computer server, etc. In one example, the control unit, computer system and/or the computing element may manipulate and transform information and/or data represented as physical (electronic) quantities within the control unit, computer system's and/or computing element's processor(s), register(s), and/or memory(ies) into other data similarly represented as physical quantities within the control unit, computer system's and/or computing element's memory(ies), register(s) and/or other such information storage, processing, transmission, and/or display components of the computer system(s), computing element(s) and/or other electronic computing device(s). Under the direction of computer-readable instructions, the control unit, computer system(s) and/or computing element(s) may carry out operations of one or more of the processes, methods and/or functionalities of the present disclosure.”).
With respect to claim 16, Kreiling teaches an autonomous off-road vehicle (AOV) comprising a hardware processor and a non-computer readable storage medium storing executable instructions that, when executed by the hardware processor, cause the AOV to perform steps comprising:
applying, by an autonomous off-road vehicle (AOV), a machine-learned model to a first state of a portion of an AOV and a desired state of the portion of the AOV, the machine-learned model configured to produce a set of control signals to actuate and adjust the portion of the AOV to move the portion of the AOV to the desired state (See at least Kreiling Paragraphs 43-48 “In the example of FIG. 1, the hydraulically actuated boom assembly 32 includes an aft bracket 34 affixed to the tractor chassis 24, a forward bracket 36 to which the FEL bale spear attachment 28 is pivotally attached, and an intermediate or mid bracket 38 situated between the brackets 34, 36. Twin upper loader arms 40 (one of which can be seen in FIG. 1) pivotally attach the aft bracket 34 to the mid bracket 38, which is, in turn, attached to the forward bracket 36 by twin lower loader arms 42 (again only one of which can be seen). Twin hydraulic lift cylinders 44 are further mounted between the aft bracket 34 and the mid bracket 38, while twin hydraulic bucket cylinders 46 are mounted between the mid bracket 38 and the forward bracket 36. Non-illustrated hydraulic lines of the boom assembly 32 are further present and fluidly connected to a pressurized hydraulic fluid supply on the loader 20 in a manner permitting an operator seated within the operator station 26 to control the hydraulic cylinders 44, 46. An operator can command the boom assembly 32 to lift the FEL bale spear attachment 28 from the illustrated home orientation (that is, the non-tilted, lowered position) by controlling the hydraulic lift cylinders 44 to extend in a desired manner. As the hydraulic lift cylinders 44 extend, the FEL bale spear attachment 28 lifts from the lowered home orientation shown in FIG. 1, travels through an intermediate or mast level position, and is ultimately raised to a full height position located above the operator station 26. Similarly, as the hydraulic bucket cylinders 46 retract in response to operator commands, the boom assembly 32 tilts the FEL bale spear attachment 28 from forward-facing angular orientation shown in FIG. 1 toward an increasingly upright orientation; that is, such that the bale spears included in the FEL bale spear attachment 28 rotate upwardly toward the front hood or windshield of the loader 20. Conversely, from the full height position, the operator can control the boom assembly 32 to stroke the hydraulic cylinders 44, 46 in an opposing to return the FEL bale spear attachment 28 to the lowered, non-tilted, lowered position shown in FIG. 1. The operator may control the cylinders 44, 46 to extend and retract, as desired, through movement of a suitable control interface (e.g., a joystick) located within the operator station 26 of the loader 20 … As appearing herein, the term “implement data source” refers broadly to any device, system, or sensor providing data relating to a work implement mounted to a work vehicle. The implement tracking data may include, for example, information pertaining to the present or predicted movement of a work vehicle chassis, as well as the present or predicted movement of a work implement when movable relative to a work vehicle chassis. Thus, utilizing the FEL bale spear attachment 28 mounted to the loader 20 (FIG. 1) as an example, the implement data sources 54 can include the operator input controls 66 utilized to control movement of the tractor chassis 24, such as the below-described steering wheel 88 (see FIGS. 3-5). Additionally, the implement data sources 54 may include operator input controls 66 utilized to control movement of the boom assembly 32, such as the below-described joystick 90 (see again FIGS. 3-5) … In more complex embodiments, the controller 48 may consider the present motion state of the work implement in establishing the projected trajectory of the work vehicle implement …” | Paragraph 117 “In one example, the controller 48 a may be comprised of one or more of software and/or hardware in any proportion. In such an example, controller 48 a may reside on a computer-based platform such as, for example, a server or set of servers. Any such server or servers may be a physical server(s) or a virtual machine(s) executing on another hardware platform or platforms. Any server, or for that matter any computer-based system, systems or elements described herein, will be generally characterized by one or more control units and associated processing elements and storage devices communicatively interconnected to one another by one or more busses or other communication mechanism for communicating information or data. In one example, storage within such devices may include a main memory such as, for example, a random access memory (RAM) or other dynamic storage devices, for storing information and instructions to be executed by the control unit(s) and for storing temporary variables or other intermediate information during the use of the control unit described herein.” | Paragraph 123 “Unless specifically stated otherwise or as apparent from the description herein, it is appreciated that throughout the present disclosure, discussions utilizing terms such as … other conjugation forms of these terms and like terms, refer to the actions and processes of a control unit, computer system or computing element (or portion thereof) such as, but not limited to, one or more or some combination of: a visual organizer system, a request generator, an Internet coupled computing device, a computer server, etc. In one example, the control unit, computer system and/or the computing element may manipulate and transform information and/or data represented as physical (electronic) quantities within the control unit, computer system's and/or computing element's processor(s), register(s), and/or memory(ies) into other data similarly represented as physical quantities within the control unit, computer system's and/or computing element's memory(ies), register(s) and/or other such information storage, processing, transmission, and/or display components of the computer system(s), computing element(s) and/or other electronic computing device(s). Under the direction of computer-readable instructions, the control unit, computer system(s) and/or computing element(s) may carry out operations of one or more of the processes, methods and/or functionalities of the present disclosure.”);
executing, by the AOV, the set of control signals to configure the portion of the AOV to a second state of the portion of the AOV (See at least Kreiling Paragraph 48 “In more complex embodiments, the controller 48 may consider the present motion state of the work implement in establishing the projected trajectory of the work vehicle implement …” | Paragraph 117 “In one example, the controller 48 a may be comprised of one or more of software and/or hardware in any proportion. In such an example, controller 48 a may reside on a computer-based platform such as, for example, a server or set of servers. Any such server or servers may be a physical server(s) or a virtual machine(s) executing on another hardware platform or platforms. Any server, or for that matter any computer-based system, systems or elements described herein, will be generally characterized by one or more control units and associated processing elements and storage devices communicatively interconnected to one another by one or more busses or other communication mechanism for communicating information or data. In one example, storage within such devices may include a main memory such as, for example, a random access memory (RAM) or other dynamic storage devices, for storing information and instructions to be executed by the control unit(s) and for storing temporary variables or other intermediate information during the use of the control unit described herein.”); and
Kreiling fails to explicitly disclose updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, 2) a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves, and 3) the set of control signals.
Hoffman teaches updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, and 3) the set of control signals (See at least Hoffman FIG. 4 and Paragraphs 122-124 “FIG. 4 is a flowchart of a method 400 for controlling a system as described herein. The method 400 includes detecting, during a first period of time, an output of a system (402). The method 400 additionally includes determining, based on the output detected during the first period of time, a first performance metric for the system (404). The method 400 additionally includes operating a first hybrid controller, based on the first performance metric, to generate a first hybrid controller output (406). The first hybrid controller includes a first constraint, a first dynamic system, a first learned system model, and a first learned system update module. The first learned system update module is configured to update the first learned system model based on at least one output detected from the system and to update the first learned system model according to at least one of a timing or a rate corresponding to a first learning parameter. The first dynamic system has a first dynamic parameter that corresponds to an overall responsiveness of the first dynamic system. Operating the first hybrid controller to generate the first hybrid controller output includes: (i) determining a first difference between the first performance metric and the first constraint; (ii) applying the determined first difference to the first dynamic system to generate a first dynamic system output; and (iii) applying the generated first dynamic output to the first learned system model to generate the first hybrid controller output. The method 400 additionally includes controlling the system, during a second period of time, according to the generated first hybrid controller output (408) and detecting, during a third period of time, the output of the system (410). The method 400 additionally includes determining, based on the output detected during the third period of time, a second performance metric for the system (412) and operating a second hybrid controller, based on the first performance metric and the second performance metric, to generate a first hybrid controller update (414). The first hybrid controller update includes at least one of an updated first constraint value, an updated first dynamic parameter, or an updated first learning parameter. The method 400 additionally includes updating the first hybrid controller according to the first hybrid controller update (416), operating the updated first hybrid controller, based on the second performance metric, to generate a second hybrid controller output (418), and controlling the system, during a fourth period of time, according to the generated second hybrid controller output (420).”).
It would have been obvious to one ordinary skill in the art before the effective filing date of the claimed invention to have modified the apparatus of Kreiling to include updating the machine-learned model based on 1) a comparison of the second state and the desired state of the portion of the AOV, , and 3) the set of control signals, as taught by Hoffman as disclosed above, in order to ensure accurate AOV movement with respect to a desired state (Hoffman Paragraph 3 “Such a hybrid controller may provide better outputs, with respect to controlling the output of the system or with respect to some other operational parameter of interest,”).
Kreiling in view of Hoffman fail to explicitly disclose updating the machine-learned model based on a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves.
Suzuki teaches determining a speed of the portion of the AOV relative to a body of the AOV (See at least Suzuki FIG. 9 and Paragraphs 90-91 “In FIG. 9, the target operating velocity generation section 710 generates first the target operating velocity Vt on the basis of the operation signal from the operation input amount sensor 33 b (Step S110), and the operating velocity detection section 740 and the posture detection section 750 generate the actual operating velocity Vr and the posture information on the basis of the detection result of any of the IMU sensors 20S, 21S, 22S, and 30S (Steps S120, S130). Next, the control intervention determination section 810 determines whether the difference between the target operating velocity Vt and the actual operating velocity Vr is larger than a preset threshold (Step S140), the operating velocity estimation section 760 computes the estimated operating velocity Ve in a case in which a determination result is YES (Step S150), and the first center-of-gravity position prediction section 780 calculates the ZMP using the estimated operating velocity Ve in a case in which the front work implement is suddenly stopped (Step S160), and calculates the ZMP using the estimated operating velocity Ve in a case in which the front work implement is slowly stopped (Step S170).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the apparatus of Kreiling in view of Hoffman to include determining a speed of the portion of the AOV relative to a body of the AOV, as taught by Suzuki as disclosed above, such that the machine-learned model is updated based on a speed of the portion of the AOV relative to a body of the AOV as the portion of the AOV moves, in order to ensure accurate vehicle control (Suzuki Paragraph 10 “The present invention has been achieved in the light of the above respects, and an object of the present invention is to provide a work machine that can appropriately carry out limiting on operating velocities of a front work implement and slow deceleration of the front work implement and that can suppress reductions in workability and operability, a deterioration in a ride quality, and the like even in a case of work involving an abrupt change in disturbance and a change in a lever operation amount within minute time.”).
Claims 2-3, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Kreiling (US 20210043085 A1) (“Kreiling”) in view of Hoffman (US 20200348628 A1) (“Hoffman”) (Hoffman) in view of Suzuki (US 20200224384 A1) (“Suzuki”)further in view of Wei (US 20210124359 A1) (“Wei”).
With respect to claim 2, and similarly claims 10 and 17, Kreiling in view of Hoffman in view of Suzuki fails to explicitly disclose that the machine-learned model uses a separately trained calibration model for the AOV.
Wei teaches that the machine-learned model uses a separately trained calibration model for the AOV (See at least Wei Paragraph 52 “A mathematical model may be built by the system controller 122 and/or the controller 136 of the loading machine 104 based on training data obtained from, for example, sensed operation of the loading machine 104 by a human operator. This training data may serve as a basis for the system controller 122 and/or the controller 136 of the loading machine 104 to determine how to predict or decide to move the loading machine 104 without being explicitly programmed to perform the task of moving the material 119 from the pile 118.”).
It would have been obvious to one ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kreiling in view of Hoffman in view of Suzuki to include that the machine-learned model uses a separately trained calibration model for the AOV as taught by Wei as disclosed above, in order to ensure accurate AOV movement with respect to a desired state (Wei Paragraph 1 “The present disclosure relates to systems and methods for movement of material. More specifically, the present disclosure relates to systems and methods for loading at least partially-autonomous machines with material from a pile in an efficient manner”).
With respect to claim 3, Kreiling in view of Hoffman in view of Suzuki in view of Wei teach that the machine-learned model is trained based on baseline training data and online training data, the online training data generated based on previous actions taken by the AOV (See at least Kreiling Paragraph 47 “ The sensors 68 can assume the proximity sensors, displacement sensors (e.g., for measuring hydraulic piston stroke), or any other devices capable of providing data from which the present orientation of a work implement relative to the work vehicle chassis (e.g., the tractor chassis 24) can be ascertained. Furthermore, in certain embodiments, the FOV of one or more imaging devices mounted to the loader 20 may encompass the range of motion of a work implement, such as the FEL bale spear attachment 28 shown in FIG. 1. In such cases, the controller 48 may further perform image analysis of video feed(s) provided by such imaging devices to the present orientation of a work implement (e.g., the FEL bale spear attachment 28) at a given juncture in time. Information regarding past and present orientations of the FEL bale spear attachment 28 (or another independently-movable work implement) may also be tracked, stored in the memory 52, and then recalled from memory 52 by controller 48 as desired.” | Paragraph 81 “ In such cases, the controller 48 a may further perform image analysis of video feed(s) provided by such imaging devices to the present orientation of the implement (e.g., the boom 204) at a given juncture in time. Information regarding past and present orientations of the boom 204 (or another independently movable implement) may also be tracked, stored in the memory 52 a, and then recalled from memory 52 a by controller 48 a as desired.” | Paragraph 123 “Unless specifically stated otherwise or as apparent from the description herein, it is appreciated that throughout the present disclosure, discussions utilizing terms such as … other conjugation forms of these terms and like terms, refer to the actions and processes of a control unit, computer system or computing element (or portion thereof) such as, but not limited to, one or more or some combination of: a visual organizer system, a request generator, an Internet coupled computing device, a computer server, etc. In one example, the control unit, computer system and/or the computing element may manipulate and transform information and/or data represented as physical (electronic) quantities within the control unit, computer system's and/or computing element's processor(s), register(s), and/or memory(ies) into other data similarly represented as physical quantities within the control unit, computer system's and/or computing element's memory(ies), register(s) and/or other such information storage, processing, transmission, and/or display components of the computer system(s), computing element(s) and/or other electronic computing device(s). Under the direction of computer-readable instructions, the control unit, computer system(s) and/or computing element(s) may carry out operations of one or more of the processes, methods and/or functionalities of the present disclosure.”).
Claims 5, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kreiling (US 20210043085 A1) (“Kreiling”) in view of Hoffman (US 20200348628 A1) (“Hoffman”) (Hoffman) in view of Suzuki (US 20200224384 A1) (“Suzuki”) further in view of Tsuji (US 20180135273 A1) (“Tsuji”).
With respect to claim 5, and similarly claims 13 and 20, Kreiling in view of Hoffman in view of Suzuki fail to explicitly disclose that the angle of the portion of the AOV is adjusted based on soil parameter data or a deviation of a speed of the portion of the AOV from an expected speed.
Tsuji teaches that the angle of the portion of the AOV is adjusted based on soil parameter data or a deviation of a speed of the portion of the AOV from an expected speed (See at least Tsuji Paragraphs 97-98 “In the present embodiment, an excavation operation is controlled based on information on a soil property of an excavation object. Specifically, when an excavation object has a gravelly soil property, an excavation operation in a shallow excavation pattern can be more efficient than in a deep excavation pattern. A penetration resistance is higher as a grain size is larger. Therefore, in penetration with bucket 7, drive force for running a vehicle more than in an example where a grain size is small is required and sufficient drive force (lift force) for raising the work implement is also required. An excavation object large in grain size is large in angle of repose. Therefore, even in the shallow excavation pattern in which penetration is not deep, an amount of flow into bucket 7 is larger than in an example of an excavation object small in grain size. In contrast, when an excavation object has a sandy soil property, an excavation operation in the deep excavation pattern is more efficient than in the shallow excavation pattern. A penetration resistance is lower as a grain size is smaller. Therefore, in penetration with bucket 7, drive force for running the vehicle can be reduced as compared with an example where a grain size is large, and drive force (lift force) for raising the work implement can also be reduced. An excavation object small in grain size is small in angle of repose. Therefore, deep penetration is required in order to ensure an amount of flow into bucket 7.” | Paragraphs 115-117 “Though soil property information is classified in accordance with a grain size and an excavation operation in an excavation attitude in accordance with the soil property information is performed in the present example, soil property information can further be classified based not only on a grain size but also on a type of a grain so that an excavation operation in an excavation attitude in accordance with the soil property information can also be performed … Though soil property information obtaining unit 100 obtains information on a soil property (a grain size) of an excavation object based on image data obtained from camera 40 in the first embodiment, limitation thereto is not intended and an amount of moisture can also be estimated as soil property information.” | Paragraph 124 “Moisture amount estimation unit 101 obtains environmental data obtained from environmental sensor 42 and estimates an amount of moisture in an excavation object. Specifically, the moisture amount estimation unit estimates an amount of moisture in the excavation object based on environmental data (at least one of a temperature and a humidity) obtained from environmental sensor 42.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kreiling in view of Hoffman in view of Suzuki to include that the angle of the portion of the AOV is adjusted based on soil parameter data or a deviation of a speed of the portion of the AOV from an expected speed, as taught by Tsuji as disclosed above, in order to ensure accurate AOV states in various environments (Tsuji Paragraph 9 “The present invention was made to solve the problems above, and an object is to provide a wheel loader capable of performing an efficient excavation operation in an excavation attitude in accordance with an excavation object.”).
Claims 6, 8, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Kreiling (US 20210043085 A1) (“Kreiling”) in view of Hoffman (US 20200348628 A1) (“Hoffman”) (Hoffman) in view of Suzuki (US 20200224384 A1) (“Suzuki”) further in view of Naber (US 10337631 B1) (“Naber”).
With respect to claim 6, and similarly claim 14, Kreiling in view of Hoffman in view of Suzuki teach selecting a set of control signals for moving the portion of the AOV to the desired state (See at least Kreiling Paragraphs 43-48).
Kreiling in view of Hoffman in view of Luo fail to explicitly disclose preventing a loss of hydraulic power.
Naber teaches preventing a loss of hydraulic power (See at least Naber Col. 2 “A second embodiment is directed to a system for providing a flow of a hydraulic fluid having a fluid pressure to a hydraulic tool, the system configured to prevent excessive loss of the hydraulic fluid when the fluid pressure decreases in the system, the system comprising a first valve configured to direct the hydraulic fluid to a return when the fluid pressure is below a first threshold, a second valve configured to direct the hydraulic fluid to a return when the fluid pressure is below a first threshold, and a third valve configured to direct the hydraulic fluid to the first valve when the fluid pressure is above a second threshold, wherein when the fluid pressure is above the second threshold the first valve is configured to direct the hydraulic fluid to a source coupler and the second valve is configured to direct the fluid from a return coupler to the return.”).
It would have been obvious of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kreiling in view of Hoffman in view of Suzuki to include preventing a loss of hydraulic power, as taught by Naber as disclosed above, such that the selected control signals for moving the portion of the AOV to the desired state prevent a loss of hydraulic power, in order to ensure efficient movement of the AOV (Naber “ Further, what is needed is a hydraulic system, or hydraulic circuit, that prevents the loss, or release, of hydraulic fluid from the hydraulic system in the event of a breach or damage to the system components.”).
With respect to claim 8, Kreiling in view of Hoffman in view of Suzuki in view of Naber teaches that updating the machine-learned model comprises measuring a result of the set of control signals using one or more sensors of the AOV (See at least Kreiling Wei Paragraph 52 “A mathematical model may be built by the system controller 122 and/or the controller 136 of the loading machine 104 based on training data obtained from, for example, sensed operation of the loading machine 104 by a human operator. This training data may serve as a basis for the system controller 122 and/or the controller 136 of the loading machine 104 to determine how to predict or decide to move the loading machine 104 without being explicitly programmed to perform the task of moving the material 119 from the pile 118.”).
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 nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IBRAHIM ABDOALATIF ALSOMAIRY whose telephone number is (571)272-5653. The examiner can normally be reached M-F 7:30-5:30.
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, Faris Almatrahi can be reached at 313-446-4821. 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.
/IBRAHIM ABDOALATIF ALSOMAIRY/ Examiner, Art Unit 3667 /KENNETH J MALKOWSKI/Primary Examiner, Art Unit 3667
Prosecution Insights