DETAILED ACTION
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 Remarks
General Note
In the interest of compact prosecution and timely examination, Examiner respectfully requests that Applicant point out the support for any claim amendments which are considered to have changed the scope of a claim in accordance with the guidance of MPEP 2163. Lack thereof may be considered as an indication that Applicant does not find the claim scope to have changed or may establish a prima facie case for a rejection under 35 USC § 112(a). MPEP 2163 relates.
Priority
Applicant’s arguments found in Applicant’s Remarks filed 03/12/2026 (hereafter typically referred to as Applicant’s remarks, arguments, or similar) filed in response to the Office Action dated 12/18/2025 (hereafter typically referred to as the prior or previous Office Action) have been fully considered but are found unpersuasive.
General Note: Applicant has chosen to label the two documents (Document 1 and Document 2) opposite that of the Examiner. For continuity, Examiner maintains the labelling established in the prior Office Action in this Office Action.
Per MPEP 2163(II)(A)(3)(b) which is directed towards “New Claims, Amended Claims, or Claims Asserting Entitlement to the Benefit of an Earlier Priority Date or Filing Date under 35 U.S.C. 119, 120, 365, or 386” (emphasis added), “To comply with the written description requirement of 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, or to be entitled to an earlier priority date or filing date under 35 U.S.C. 119, 120, 365, or 386, each claim limitation must be expressly, implicitly, or inherently supported in the originally filed disclosure. When an explicit limitation in a claim “is not present in the written description whose benefit is sought it must be shown that a person of ordinary skill would have understood, at the time the patent application was filed, that the description requires that limitation.” Hyatt v. Boone, 146 F.3d 1348, 1353, 47 USPQ2d 1128, 1131 (Fed. Cir. 1998)” (emphasis added).
None of Applicant’s specifically pointed out support appears to explicitly support the limitations or features embodied thereby. Furthermore, Applicant does not appear to otherwise show that the limitation/feature is implicitly or inherently disclosed, or “that a person of ordinary skill would have understood, at the time the patent application was filed, that the description requires that limitation”. Finally, those portions referred to as part of the specific recitations are large and widely encompassing, e.g. “Section II-III” or “p. 6-7”. These documents appear to be pre-publication research papers and make frequent reference to other published references which are typically if not always prior art. Such broad referencing if anything appears to indicate that one or more of these included cited references discloses the limitation/feature and consequently that they lack novelty. As is repeated throughout MPEP 2163 “Applicant should ... specifically point out the support for any amendments made to the disclosure” (emphasis added).
More particularly:
With respect to cited support of Claim 1, the recited portion merely recites “geometric paths”. There is no explicit recitation of the limitations at issue. Furthermore, with respect to any implicit or inherent disclosure that Applicant may consider self-evident and thus not pointed out to the phrase “geometric paths”, see the following. The definition of “geometric” that appears appropriate to the disclosure/context is “of, relating to, or according to the methods or principles of geometry” where the definition of “geometry” that appears appropriate to the disclosure/context is “a branch of mathematics that deals with the measurement, properties, and relationships of points, lines, angles, surfaces, and solids”. Therefore, there is no clear inherent or implicit disclosure requiring “an output representing a plurality of points along a path”, especially wherein the points are used to “generate … control signals” in relation to “a policy”.
With respect to Claim 2, wherein a portion of the limitation is now found in Claim 1, the recited support merely recites “we might learn a policy over a give fabric, for instance using RL”. This would appear to disclose what it states, learning a policy using RL (Reinforcement Learning). It does not recite “the reinforcement learning-based model is updated … based … on the policy”. More specifically, the exact nature of learning the policy is not stated as being based on the policy, and instead simply that RL might be used to learn a policy. Consequently, no explicit supporting disclosure appears in the recited portion. As noted previously, Applicant does not otherwise appear to show that the limitation/feature is implicitly or inherently disclosed, or “that a person of ordinary skill would have understood, at the time the patent application was filed, that the description requires that limitation”.
With respect to Claim 3, the recited support makes no mention of poses. At most it discloses a goal and a navigation policy. Even more generally, a search for the word “pose” does not return any results in Document 1 (again, as labelled by Examiner). Consequently, no explicit supporting disclosure appears in the recited portion. As noted previously, Applicant does not otherwise appear to show that the limitation/feature is implicitly or inherently disclosed, or “that a person of ordinary skill would have understood, at the time the patent application was filed, that the description requires that limitation”.
With respect to Claim 4, the recited support makes no mention of poses or more particularly an intermediate pose. At most it discloses a goal and a navigation policy. Even more generally, a search for the word “pose” does not return any results in Document 1 (again, as labelled by Examiner). Consequently, no explicit supporting disclosure appears in the recited portion. As noted previously, Applicant does not otherwise appear to show that the limitation/feature is implicitly or inherently disclosed, or “that a person of ordinary skill would have understood, at the time the patent application was filed, that the description requires that limitation”.
With respect to Claim 6, the recited support makes no mention of a “type” or types “of maneuvers”. The separate documents appear to individually disclose a fingertip contact operation. Consequently, no explicit supporting disclosure appears in the recited portion. As noted previously, Applicant does not otherwise appear to show that the limitation/feature is implicitly or inherently disclosed, or “that a person of ordinary skill would have understood, at the time the patent application was filed, that the description requires that limitation”.
With respect to Claim 7, no specific recited appear is provided. A review of the portions provided appears to only disclose training different policy “seeds” with FGP and Dextreme, seemingly for the purpose of comparing performance between the disclosed method and a prior method (Dextreme). There is no indication of a coexistence of a “plurality of models” from which a particular model is determined and apparently selected. It furthermore indicates the use of prior art reference disclosure for some of what is disclosed. Consequently, no explicit supporting disclosure appears in the recited portion. As noted previously, Applicant does not otherwise appear to show that the limitation/feature is implicitly or inherently disclosed, or “that a person of ordinary skill would have understood, at the time the patent application was filed, that the description requires that limitation”.
With respect to Claim 10, Applicant is wholly unresponsive. No attempted showing of support appears provided and Claim 10 remains un-amended and un-cancelled.
Claim Objections
The objections to the claims provided in the previous Office Action are withdrawn in light of Applicant’s amendments to the claim filed 03/12/2026 (hereafter typically referred to as Applicant’s amendments).
Claim Rejections - 35 USC § 102
Applicant’s arguments have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Xie et al. further in view of Li et al. as demonstrated with at least Claim 2. See the updated 35 USC § 103 rejection below.
Claim Rejections - 35 USC § 103
Applicant provides no arguments with respect to the combination of Xie et al. further in view of Li et al. or any other combination of references presented in the previous Office Action. There is therefore nothing to respond to with respect to 35 USC § 103.
Furthermore, Applicant requests reconsideration of Claims 2 and 12 which have been cancelled in Applicant’s amendments to the claims.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed application, Application No. 63/537,452, fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application.
At the present time, it is believed that it is at least likely that the provisional application does not support any of the presently filed claims, and furthermore that the provisional application does not support at least one of the presently filed claims (see discussions of Claim 4, 6, 7, and 10 below). The disclosure of the provisional application appears to consist of the following two documents:
Document 1 titled “Fabrics: A Foundationally Stable Medium for Encoding Prior Experience”
Document 2 titled “Geometric Fabrics: a Safe Guiding Medium for Policy Learning”
Specifically, a non-exhaustive list of features which appear to not be disclosed in Applicant’s provisional application are of:
Claim 1 “an output representing a plurality of points along a path”, especially wherein the points are used to “generate … control signals” in combination with “a policy”. For example, the word “point” or “points” does not appear in the context of point or points of a path explicitly anywhere in either document.
Claim 1, “provide an input indicative of a goal pose for a robot to a reinforcement learning-based model”. The closest support found was in Section III, B. of Document 2, which still does not appear to disclose the feature and appears to rely on reference document [8], which itself relies on other references, names different authors to the inventorship, and would appear to be prior art if the true support for this feature.
Claim 3, “an initial pose” and “a pose of one or more objects”. These items do not appear explicitly disclosed anywhere in either document.
Claim 4, “an intermediate pose”. This item does not appear explicitly disclosed anywhere in either document. Furthermore, “a second output” or “updated set of control signals” based/caused thereon.
Claim 6, no discussion of “types of maneuver” appears present in any form anywhere in either document.
Claim 7, no discussion of a “plurality of models”, let alone a determination of a particular model therefrom appears present in any form anywhere in either document.
Claim 10, most if not all of the listed types of systems are not disclosed. The disclosure of both documents appears highly general and do not appear to get particular with such a broad spectrum of systems in which to apply the disclosure.
Claims 5, 8 – 9, 11, and 13 – 22 either depend from a claim which does not appear to have sufficient support within the provisional application, or otherwise effectively recite the same limitations as those above.
Accordingly, all of the claims (Claims 1, 3 – 11, and 12 – 22) are not entitled to the benefit of the prior application.
Examiner notes in particular that support for at least some of the believed missing features might be disclosed in Documents 1 and/or 2, particularly based on the other documents referred to therein, or based on the generally extremely broad nature of the claim construction presently provided. However, said referred documents are typically prior art themselves and/or refer to the prior art cited or even applied in this Office Action. Furthermore, if support is reliant on the presently particularly broad nature of construction of the claims, support may readily be lost under any narrowing amendment.
Finally, and furthermore, Examiner notes that Document 2 provides as author, Arthur Allshire, who is presently not listed as an inventor on this or the provisional application.
Claim Interpretation
The term “geometric fabric” first recited in Claim 1 has been interpreted as a specific term of art. The meaning of the term has been interpreted in line with the definition provided by Xie et al. (Xie, Mandy, et al. "Geometric fabrics for the acceleration-based design of robotic motion." arXiv preprint arXiv:2010.14750 (2020).) which appears to be one of the earliest, if not the earliest, publications describing and defining the term.
Xie describes geometric fabrics as:
“the most concrete incarnation of a new mathematical formulation for reactive behavior called optimization fabrics. Fabrics generalize recent work on Riemannian Motion Policies (RMPs); they add provable stability guarantees and improve design consistency while promoting the intuitive acceleration-based principles of modular design that make RMPs successful”.
Fabrics are contrasted from RMPs on Page 1, Section I which states “Fabrics, on the other hand, are fundamentally unbiased in a rigorous sense (see Section III of supplemental paper [16]), meaning practically that the underlying fabric does not prevent the system from achieving task goals”
Furthermore, geometric fabrics are described on Page 1, Section I as a specific type of fabric and specific subtype of “optimization fabric”, “Geometric fabrics are a special type of fabric that expresses its unbiased nominal behavior as a generalized nonlinear geometry in the robot’s configuration space; they constitute the most concrete incarnation of optimization fabric”.
Applicant makes frequent use of “to” and “for” in a manner which might be interpreted as merely indicating intended purpose or use. These have instead been interpreted as meaning “configured to” or similar. Examples include “circuits to” of Claim 1, “model to” of Claim 1, “robot to” of Claim 1, “one or more circuits are to” of Claims 3, 4, 6, 7, and 9, and “system for” of Claim 10.
The claims do not appear to claim with any particularity what comprises or otherwise constitutes a “control signal” or the nature of any corresponding controller or similar. As such, what might be considered a “control signal” is particularly broad. For example, there be little or even no distinction between “a control signal” and an “output” which “represents” “a path” or “a plurality of points” along said path.
Claim Rejections - 35 USC § 112(a)
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 3 – 11, and 13 – 22 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding Claims 1 and 11, the claims recite the limitation “provide the output to a geometric fabric configured to adjust the output to be compliant with a policy corresponding to one or more criteria for operation of the robot” (Claim 1) or equivalent (Claim 11) and then “generate one or more control signals for the operation of the robot based at least on the adjusted output” (Claim 1) or equivalent (Claim 11). As best understood by the examiner, the disclosure appears to only disclose one “adjustment” to be “compliant” with “a geometric fabric” as part of the control signal generation, as found in Claims 4 and 14. See at least [0006], [0029], [0050], and [0065]. Applicant does point out support for this amendment within their claims, or alternatively if it is the same as that pointed out with respect to the issue of priority, it is at minimum not found there as evidenced in the Response to Arguments section. Examiner was unable to identify support in a review of the lengthy specification.
The issue appears to further compound with Claims 4 and 14 which introduce the perceived supported second/adjusted output.
Therefore, the claim contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding Claims 21 and 22, the claims recite the limitations “wherein the one or more criteria represented by the policy is based on a metric-weighted acceleration term, a curvature corresponding to the geometric fabric, and an acceleration term corresponding to the plurality of points”. Examiner was unable to identify support for these limitations within Applicant’s originally filed disclosure. Furthermore, Applicant does point out support for this amendment within their claims.
For example, the term “metric” or “metric-weighted” were not found in Examiner’s search of the disclosure. The term “weight” was provided with what appears to be generic and effectively unrelated disclosure. The term “curvature” was not found in Examiner’s search of the disclosure. Examiner was unable to find any “acceleration term” holding correspondence with “the plurality of points”.
In the interest of compact prosecution, Examiner furthermore notes that Applicant incorporates by reference U.S. Provisional Application No. 63/537,452. While it is not believed that this reference discloses these limitations in accordance with the written description of 35 USC § 112(a) either, it is furthermore noted that even if supported in said reference the incorporation of essential material in the specification by reference to an unpublished U.S. application, foreign application or patent, or to a publication is improper. Applicant would be required to amend the disclosure to include the material incorporated by reference, if the material is relied upon to overcome any objection, rejection, or other requirement imposed by the Office. The amendment must be accompanied by a statement executed by the applicant, or a practitioner representing the applicant, stating that the material being inserted is the material previously incorporated by reference and that the amendment contains no new matter. 37 CFR 1.57(g).
Regarding Claims 3 – 10 and 13 – 20, the claims depend from claim(s) rejected above and inherit the deficiencies of said claim(s) as described above. Therefore, Claims 3 – 10 and 13 – 20 are rejected under the same logic presented above.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 3 – 5, 8 – 11, 13 – 15, 18 – 22 are rejected under 35 U.S.C. 103 as being unpatentable over Xie et al. (Xie, Mandy, et al. "Geometric fabrics for the acceleration-based design of robotic motion." arXiv preprint arXiv:2010.14750 (2020)) further in view of Li et al. (Li, Anqi, et al. "RMP2: A structured composable policy class for robot learning." arXiv preprint arXiv:2103.05922 (2021)).
Regarding Claim 1, Xie teaches:
One or more processors comprising:
one or more circuits to (Examiner notes that this and the processor limitation appear inherent to the disclosure; the disclosure clearly utilizes a controller, computer, or similar which inherently have these components):
provide an input indicative of a goal pose for a robot (See at least Page 1, Section I, “The task is the optimization problem characterizing the end-effector’s target as its local minimum”) to a … model (See at least Page 2, Section II, “use policies as trajectory generators”) to cause the model to generate an output, the output representing a plurality of points along a path for movement of the robot to the goal pose (See at least Page 3, Section III, A., “the HD2 property ensures the differential equation is more than just a collection of trajectories (its integral curves); it additionally has a path consistency property whereby every integral curve … will follow the same path” and Figure 3);
provide the output to a geometric fabric configured to adjust the output to be compliant with a policy corresponding to one or more criteria for operation of the robot (A plurality of fabrics are used at times. Geometric fabrics can be summed, or in other words feed into one another. See at least Page 5, Section VII, “When geometric fabrics are summed …” and Figure 4 or alternatively see at least layers of geometric fabric, for example in Section IX, A “Behavioral Layers”, in particular Section 3), the “Cubby Collision” layer, and Section IV “Above we showed that because geometric equations define collections of path, independent of speed, we can energize them to conserve a given measure of Finsler energy (which in turn endows them with a priority metric and can be viewed as bending the corresponding Finsler geometry into the shape of the given arbitrary geometric equation)”)
generate one or more control signals for operation of the robot based at least on the plurality of points along the path and a policy corresponding to one or more criteria for the operation of the robot (See at least Section IX, A. 1), “This behavior controls robot posture and resolves manipulator redundancy”); and
provide the one or more control signals to the robot to cause the robot to move toward the goal pose (See at least Figure 3 or 5).
Xie does not teach, but in combination with Li teaches:
…
reinforcement learning-based [model] (See at least Page 6, Section IV(B), “In reinforcement learning (RL) applications, one can choose whether to differentiate through the RMP2 algorithm: one can either choose RMP2 as part of the policy, or as a component of the environment dynamics”)
…
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the claimed invention to utilize reinforcement learning as disclosed in Li in the system of Xie with a reasonable expectation of success. The use of neural networks is routine and commonplace, including reinforcement learning, for the purpose of refining models and systems, eliminating the need for hand-crafted systems for every situation, and other reasons. Furthermore, the concept of using such neural networks, including the suggestion to use reinforcement learning, in combination with geometric fabrics is well documented in the prior art. See Page 8, Section X “Conclusions” of Xie et al., “Interestingly, the strong generalization observed in our experiments suggests geometric fabrics may additionally represent a well-informed and flexible inductive bias for policy learning”; Page 8, Section VIII of Van Wyk, Karl, et al. "Geometric fabrics: Generalizing classical mechanics to capture the physics of behavior." IEEE Robotics and Automation Letters 7.2 (2022): 3202-3209, “Many existing techniques in the literature can naturally leverage fabrics (e.g., reinforcement learning as in [21], imitation learning, planning), and it is a point of future work to explore many of these areas” wherein [21] is reference Li above; and Xie, Mandy, et al. "Neural geometric fabrics: Efficiently learning high-dimensional policies from demonstration." Conference on Robot Learning. PMLR, 2022. (see title).
Regarding Claim 3, the combination of Xie and Li teaches:
The one or more processors of claim 1,
Xie further teaches:
wherein, when providing the input indicative of the goal pose for the robot to the model, the one or more circuits are to:
provide an initial pose of the robot relative to an environment (See at least Page 3, Section II, A, “starting from a given position x0”), the goal pose for the robot relative to the environment (See at least Page 1, Section I, “The task is the optimization problem characterizing the end-effector’s target as its local minimum”), and a pose of one or more objects relative to the environment in which the robot is operating (See at least Section VIII, Circular Object Repulsion which goes into detail in mathematical terms) to the model to cause the model to generate the output.
Regarding Claim 4, the combination of Xie and Li teaches:
The one or more processors of claim 3,
Xie further teaches:
wherein, when generating the one or more control signals for operation of the robot, the one or more circuits are to:
determine a set of control signals to move the robot between a first pose and at least one intermediate pose along the path based at least on the output of the model (See intermediate positions between start and end in Figures 3 or 5), and
provide the set of control signals to cause a second output to be generated based at least on the policy, the second output comprising an updated set of control signals representing an updated path that is compliant with the geometric fabric (See at least layers of geometric fabric, for example in Section IX, A “Behavioral Layers”, in particular Section 3), the “Cubby Collision” layer, and Section IV “Above we showed that because geometric equations define collections of path, independent of speed, we can energize them to conserve a given measure of Finsler energy (which in turn endows them with a priority metric and can be viewed as bending the corresponding Finsler geometry into the shape of the given arbitrary geometric equation)”).
Regarding Claim 5, the combination of Xie and Li teaches:
The one or more processors of claim 4,
Xie further teaches:
wherein each control signal of the set of control signals is configured to cause at least one actuator associated with a corresponding joint of the robot to move at least a portion of the robot from the first pose to a second pose of the at least one intermediate pose (See at least Figures 3 or 5).
Regarding Claim 8, the combination of Xie and Li teaches:
The one or more processors of claim 1,
Xie further teaches:
wherein the one or more criteria represented by the policy comprises at least one criteria based at least on a second-order differential equation (See at least Page 2, Section II, “Geometric fabrics build on the theory of spectral semisprays (specs), which generalize the idea of modular secondorder differential equations first derived and used as Riemannian Motion Policies (RMPs) in [15, 2]”).
Regarding Claim 9, the combination of Xie and Li teaches:
The one or more processors of claim 1,
Xie further teaches:
wherein the one or more circuits that provide the one or more control signals to the robot to cause the robot to move toward the goal pose: simulate operation of the robot in a simulated environment (See at least Page 10, Section A, C, “behavior is simulated” and Figure 5), and
provide the one or more control signals to the robot while operating in the simulated environment to cause the robot to move in the simulated environment (See again Figure 5).
Regarding Claim 10, the combination of Xie and Li teaches:
The one or more processors of claim 1,
Xie further teaches:
wherein the one or more processors are comprised in at least one of:
a control system for an autonomous or semi-autonomous machine (See at least Page 7, Section IX, “wherein a robot must autonomously interact with cubbies (bins)”);
a perception system for an autonomous or semi-autonomous machine;
a system for performing simulation operations;
a system for performing digital twin operations;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets;
a system for performing deep learning operations;
a system for generating or presenting at least one of augmented reality content, virtual reality content, or mixed reality content;
a system for hosting one or more real-time streaming applications;
a system for implementing large language models (LLMs);
a system for implementing vision language models (VLMs);
a system implemented using an edge device;
a system implemented using a robot;
a system for performing conversational AI operations;
a system for performing generative AI operations;
a system for generating synthetic data;
a system incorporating one or more virtual machines (VMs);
a system implemented at least partially in a data center; or
a system implemented at least partially using cloud computing resources
Regarding Claim 21, the combination of Xie and Li teaches:
The one or more processors of claim 1, wherein the one or more criteria represented by the policy is based on a metric-weighted acceleration term (See at least Page 4, Section IV, “priority matrix on that behavior Me defining how it combines with other policies as a metric-weighted average of parts” and Page 4, Section IV, “A forced geometric fabric is a collection of fabric terms defined as pairs … of a Finsler energy … and an acceleration policy”, wherein note the equation form of acceleration policy and Page 5, Section VII(B), “It is often most intuitive to design a geometric fabrics’
forcing potential as a forcing spec”), a curvature corresponding to the geometric fabric (See at least Page 3, Section III(B), “In geometric fabrics, the energy tensor defines the policy’s
priority metric and the curvature terms fe are used for stability … in policy
form so it’s treated intuitively as another acceleration policy averaged into the final metric weighted average” (equations generally omitted, see original reference for clear display thereof), and an acceleration term corresponding to (The nature of the correspondence is not claimed) the plurality of points (See again recitations with respect to “a metric-weighted acceleration term”).
Regarding Claims 11, 13 – 15, 18 – 20, and 22 the claims are directed to effectively the same subject matter as the claims above with respect to the application of prior art. The claims are therefore rejected under the same logic as the claims above.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 6 – 7 and 16 – 17 are rejected under 35 U.S.C. 103 as being unpatentable over Xie et al. in view of Li et al. further in view of Lewis (US 20210174245 A1).
Regarding Claim 6, the combination Xie and Li teaches:
The one or more processors of claim 1,
Xie does not teach, but in combination with Lewis teaches:
wherein the one or more circuits are to:
determine a type of maneuver associated with the input to the model,
wherein, when providing the input to the model, the one or more circuits are to:
provide the input to the model based at least on the type of maneuver associated with the path (See at least [0041] “The processor 102 may execute the instructions 208 to apply a selected candidate model of the accessed candidate models 142 on the accessed data to determine a predicted action of the identified actor 120. The processor 102 may select one of the accessed candidate models 142 to apply on the accessed data based on, for instance, which of accessed candidate models 142 most closely matches the accessed data”).
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the claimed invention to utilize a plurality of models which are identified and used as most appropriate based on the input as disclosed in Lewis in the system of Xie or Xie in combination with Li with a reasonable expectation of success. Doing so would allow for a most appropriate model to be applied for any given situation.
Regarding Claim 7, the combination Xie and Li teaches:
The one or more processors of claim 1,
Xie does not teach, but in combination with Lewis teaches:
wherein, when providing the input to the model, the one or more circuits are to:
determine the model from among a plurality of models, the model associated with the robot; and
provide the input to the model based at least on determining the model (See at least [0041] “The processor 102 may execute the instructions 208 to apply a selected candidate model of the accessed candidate models 142 on the accessed data to determine a predicted action of the identified actor 120. The processor 102 may select one of the accessed candidate models 142 to apply on the accessed data based on, for instance, which of accessed candidate models 142 most closely matches the accessed data”).
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the claimed invention to utilize a plurality of models which are identified and used as most appropriate based on the input as disclosed in Lewis in the system of Xie or Xie in combination with Li with a reasonable expectation of success. Doing so would allow for a most appropriate model to be applied for any given situation.
Regarding Claims 16 and 17, the claims are directed to effectively the same subject matter as the claims above with respect to the application of prior art. The claims are therefore rejected under the same logic as the claims above.
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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Ratliff et al. (US 20220371184 A1).
Van Wyk, Karl, et al. "Geometric fabrics: Generalizing classical mechanics to capture the physics of behavior." IEEE Robotics and Automation Letters 7.2 (2022): 3202-3209.
Xie, Mandy, et al. "Neural geometric fabrics: Efficiently learning high-dimensional policies from demonstration." Conference on Robot Learning. PMLR, 2022.
Aljalbout, Elie, et al. "Learning vision-based reactive policies for obstacle avoidance." Conference on Robot Learning. PMLR, 2021.
Ratliff, Nathan D., et al. "Generalized nonlinear and finsler geometry for robotics." 2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021.
Cheng, Ching-An, et al. "Rmpflow: A geometric framework for generation of multitask motion policies." IEEE Transactions on Automation Science and Engineering 18.3 (2021): 968-987.
Ratliff, Nathan D., et al. "Optimization fabrics." arXiv preprint arXiv:2008.02399 (2020).
Handa, Ankur, et al. "DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality." arXiv preprint arXiv:2210.13702 (2022).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW C GAMMON whose telephone number is (571)272-4919. The examiner can normally be reached M - F 10:00 - 6:00.
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, ADAM MOTT can be reached on (571) 270-5376. 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.
/MATTHEW C GAMMON/Examiner, Art Unit 3657
/ADAM R MOTT/Supervisory Patent Examiner, Art Unit 3657
Prosecution Insights