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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submissions, filed on January 23rd, 2026, have been entered.
Status of Claims
Claims 1-2 and 4-20 are pending, claims 1, 12 and 17 have has been amended, claim 3 is cancelled. Claims 1-2 and 4-20 remains rejected.
Response to Argument(s)
In view of the Amendments to independent claims 1, 12 and 17 the previously applied prior art rejections are withdrawn. Applicants’ arguments are rendered moot in view of the new grounds of rejection set forth below.
Regarding the Applicants’ argument on the 101 rejection:
In pages 7-12 of the remarks, the Applicants centrally argue that the claims, the independent claims 1, 12 and 17 provides a solution to a practical application, and the independent claim 17 further is considered significantly more than abstract idea.
In support of the above arguments, the Applicants submits that the features of the claim 1 helps address the technical challenges of “How to reliably charge an unmanned aerial vehicle during an ongoing trip using the electric power lines, while preventing failed landings, mechanical overload of electric power lines, and electrical faults caused by incompatibility between the unmanned aerial vehicle and different types of power lines”, as disclosed in the specification’s [0048].
PNG
media_image1.png
456
630
media_image1.png
Greyscale
Regarding claim 12:
PNG
media_image2.png
360
626
media_image2.png
Greyscale
Regarding claim 17:
PNG
media_image3.png
296
626
media_image3.png
Greyscale
Therefore, claim 17 provides the inventive concept and has a practical application and considered to be significantly more.
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ argument and find them to be incommensurate with the scope of the claims. Importantly, the Applicants are reminded that the claims are interpreted under BRI (broadest reasonable interpretation) in light of the specification. Therefore, the direct teachings from the specification cannot be imported to be the instant scope of the claim. The claims need to clearly reflect the inventive concept the Applicants stated in their arguments. For example, the independent claim 1 does not recite that the data being obtained from the UAV being attributes of size, battery status, and the current location, but the claim simply recites “obtain a set of UAV attributes and location information associated with the UAV;” moreover, the examiner finds the main improvement of the invention provide the solution for, reflected in the Applicants’ argument, however, not currently reflected in the claim, being that “the system app[lied a trained first machine learning model to evaluate the feasibility and safety of charging at each candidate power line, the evaluation considered both UAV-specific information and power line characteristics, as well as environmental factor.” This idea being considered an inventive concept of a practical application, however, not reflected in the claim itself.
Regarding the independent claim 12, similar to the above reply, claim 12 does not reflect the inventive concept stated in the Applicants’ argument, such as, the claim does not recite any “the pre-trained machine learning model that evaluate whether the UAV can safely and effectively draw power from that specific power line by giving outputs a binary result of success or failure classification to decide that the chosen line is suitable for charging under the current conditions,” neither the claim recite any, “charging output may include which of the cables to land on and a time of landing.”
Similarly for the independent claim 17, the claim does not reflect the inventive concept asserted in the Applicants’ argument, such as, the claim does not recite “the system ingests labeled historical charging records, UAV characteristics being payload weight, battery sate, adapter type.”
Importantly, for the requirements of the 101 Step 2A prong 2 and Step 2B, there must be indication of additional elements that integrate the judicial exceptions into a practical application and/or the additional elements make the claim as a whole being considered as significantly more. Please see MPEP §2106.05.
The Applicants are recommended the amend the claims to reflect the inventive concepts as discussed.
Regarding the Applicants’ argument on the 102 rejection:
In pages 12-15 of the remarks, the Applicants argue that the proposed MingFeng art does not teach or suggest the features of the claims:
“electric power lines;
determine geographic data, power rating, cable design associated with the electric power lines.”
In support of the above argument, the Applicants assert that the Applicants is entitled to their own lexicographer and may rebut the presumption that claim terms are to be given their ordinary and customary meaning by clearly setting forth a definition of the term that is different from its ordinary and customary meaning(s) in the specification at the relevant time. Wherein the explicit specification provides the definition for the term “electric power line” in the instant specification’s [0036] refers to infrastructure used for the transmission and distribution of electrical power from generation or transmission units to consumers, the lines includes uninsulated cables, be suspended by towers or poles, and operate at high voltages ranging from 240V to 220kV. Therefore the proposed art MingFeng does not teach or suggest this definition and is different to the claimed invention.
Examiner’s reply:
Regarding the features of the claims, “determine geographic data, power rating, cable design associated with the electric power lines” is newly added features into the claims, hence, overcome the previous ground of rejection, new grounds of rejections are set forth below.
Regarding the argument to “electric power lines,” the examiner respectfully disagrees with the Applicants’ argument, importantly, the term “electric power lines” as asserted by the Applicants to be supported in the instant specification’s [0039] doesn’t meet the requirements of lexicographer’s entitlement of a term that the inventor may define specific terms used to describe invention, but must do so “with reasonable clarity, deliberateness, and precision,” if done, must “set out his uncommon definition in some manner within the patent disclosure” so as to give one of ordinary skill in the art notice of the change in meaning. Importantly, paragraph [0039] does not provide a precise and deliberate definition of the term “electric power lines,” but gives some examples of what the term can be of, that the “electric power line MAY refer to a power line….For example…..,” is in exemplary language and is open to other interpretations, moreover, “MAY REFER” is not precise and definite.
Moreover, the examiner finds the proposed MingFeng’s “charging station” to fall within the same scope of the recited term “electric power lines” since charging stations carry power for charging the UAV, moreover, therefore, include power lines, electrical lines.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-3, 5-6, 8-20 are rejected under 35 U.S.C. 101
Regarding Independent Claim 1 and its dependent claims 2-3, 5-6 and 8-11,
Step 1 Analysis: Claim 1 is directed to a system/device, which falls within one of the four statutory categories.
Step 2A Prong 1 Analysis: Claim 1 recites, in part, “identify one or more electric power lines from the plurality of electric power lines based on the set of UAV attributes, the set of electric power line attributes, a set of environmental attributes, and a trained first machine learning model, wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines; and direct the UAV to the identified one or more electric power lines for charging the UAV” The limitations as mentioned, as drafted, are processes that, under broadest reasonable interpretation, covers the performance of the limitation in the mind which falls within the “Mental Processes” and “certain method of organizing human activities” groupings of abstract ideas. The limitations of:
“identify one or more electric power lines from the plurality of electric power lines based on the set of UAV attributes, the set of electric power line attributes, a set of environmental attributes, and a trained first machine learning model” is a step of what a human mind can also perform through observation and evaluation, the human mind can identify power lines based on certain given information here being the UVA attributes, such as specified in the claim to includes some information and details (observable information by the human mind), the set of electric power line attributes, a set of environmental attributes and a trained first machine learning model, moreover, the machine learning model here being recited to be given no further performance of any particular processing but to simply be a model or an information for the identifying to be based on not directly recited to perform any function, hence, abstract idea;
“direct the UAV to the identified one or more electric power lines for charging the UAV” is a limitation abstract idea can be understood to be certain method of organizing human activities or following instructions such as instruction to direct the UVA to the identified electric power lines for charging the UAV, or it can be understood to be of an intended use wherein the identified power lines being used for charging the UAV, hence still abstract idea.
Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 Analysis: This judicial exception is not integrated into a practical application. particular, the claim recites the following additional element(s) –
A system for charging an unmanned aerial vehicle (UAV), the system comprising: a memory configured to store computer executable instructions; and one or more processors configured to execute the instructions to: obtain a set of UAV attributes and location information associated with the UAV;
the additional elements of “a system….,” “a memory configured to store …. instructions,” “a one or more processor configured to execute….” are recited at high generality of generic computer components performing generic functions such as a system here being part of a preamble can just be understood as a system of computing device, memory storing instructions or processor to execute the instructions. Moreover, the step of obtaining the set of UVA attributes… merely constitutes pre-solution activity involving data gathering of obtaining data. Such extra-solution activity does not integrate the abstract idea into a practical application. Please see MPEP §2106.05(g). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim as a whole is directed to an abstract idea. Please see MPEP §2106.04.(a)(2).III.C.
In view of the of the foregoing, the additional step does not integrate the abstract idea into a practical application.
Step 2B Analysis: there are no additional elements that amount to significantly more than the judicial exception. Moreover, the additional element as mentioned above does not amount to significantly more for the claim as a whole. Please see MPEP §2106.05. The claim is directed to an abstract idea.
For all of the foregoing reasons, claim 1 does not comply with the requirements of 35 USC 101.
Accordingly, the dependent claims 2-3, 5-6 and 8-11 do not provide elements that overcome the deficiencies of the independent claim 1. Moreover, claims 2-3, 5 and 10, each recites, wherein clauses of further specification of the limitation it depends on which being abstract idea, hence, further specification to abstract idea is still abstract idea of further specifying what the abstract idea is based on or wherein of without providing further limiting features or additional element that helps to indicate an integration into a practical application of being significantly more. Claim 6 recites, in part, “query a database for a functional class feature of each of labeled training information, unlabeled test information, or a combination thereof, as at least one of the set of features.” is a step of an additional element, under Step 2A Prong 2, to be insignificant extra-solution activity of data gathering. Claim 8 recites, in part, “receive a first set of images from the UAV; determine a set of image features relating to the first set of images, using a trained second machine learning model” being limitations of, under Step 2A Prong 2, additional elements of insignificant extra-solution activity of data gathering for the receiving step and the trained second machine learning model being a generic neural network recited at high-level of generality, hence, they do not indicate an integration into a practical application; “and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images” being a step of what the human mind can perform through observation and judgement such as, based on certain given information here being the image features, the human mind can label images with labels according to a certain condition such as recited in this limitation based on observing and judging the information and the image. Claim 9 recites, in part, “receive a set of labeled historic samples, the set of labeled historic samples comprising positive samples and negative samples associated with one or more electric power lines” being a limitation of an additional element, under Step 2A Prong 2, of an insignificant extra-solution activity of data gathering; “determine a set of sample features relating to the set of labeled historic samples” being a step that the human mind can also perform through observation and evaluation such as the human mind can determine a set of features relating to a set of labeled sampled according to given information; “and based on the set of labeled historic samples and the set of sample features, train the second machine learning model to label one or more unlabeled test samples with at least one of a positive label for presence of an electric power line or a negative label for absence of an electric power line, in the corresponding one or more unlabeled test samples” recites an additional element of the second machine learning model, however, still recited at high level of generality without limiting on how the output being accomplished but simply recited to output label and further specify that the labels being of such as positive label or negative such as recited in this limitation based on a given input of information without further limiting how the machine learning model works or perform to accomplish such outcome, hence, this additional element is not indicative of an integration into a practical application. Claim 11 recites, in part, “trigger the imaging source associated with the UAV to capture the first set of images based on at least one of the location information, timing information, and battery information, associated with the UAV” recites a step an additional element, under Step 2A Prong 2, to be insignificant extra-solution activity of capturing the image being data gathering, and the triggering to be a post-solution activity, hence is not indicative of an integration into a practical application.
Accordingly, the dependent claims 2-3, 5-6 and 8-11 are not patent eligible under 101.
Regarding Independent Claim 12 and its dependent claims 13-16,
Step 1 Analysis: Claim 12 is directed to a method/process, which falls within one of the four statutory categories.
Step 2A Prong 1 Analysis: Claim 12 recites, in part, “determining a classification label for charging of the UAV by the electric power line, using the set of features and a trained first machine learning model” The limitations as mentioned, as drafted, are processes that, under broadest reasonable interpretation, covers the performance of the limitation in the mind which falls within the “Mental Processes” grouping of abstract ideas. The limitations of:
“determining a classification label for charging of the UAV by the electric power line, using the set of features and a trained first machine learning model” is a step that the human mind can also perform, moreover, the human can determine label for charging of the UAV based on given information such as using the set of features and a trained machine learning model through observation and evaluation process, moreover, the “trained first machine learning model” is recited in this limitation as a given information without limiting how the machine learning model contributes to the process of determining, the limitation simply recites “determining….” using “…machine learning model” without having it directly being involved in the process, hence, the examiner reads the limitation, based on BRI (broadest reasonable interpretation) to just be a given information that the human mind can use to determine the label such as discussed.
Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 Analysis: This judicial exception is not integrated into a practical application. particular, the claim recites the following additional element(s) –
obtaining a set of features for charging of the UAV by an electric power line, the set of features comprising a set of UAV attributes and location information associated with the UAV and a set of electric power line attributes relating to the electric power line, wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines; and based on the classification label, generating a charging output associated with the UAV and the electric power line
The step of obtaining…. and generating…. merely constitutes pre-solution activities involving data gathering of obtaining data and generating data. Such extra-solution activity does not integrate the abstract idea into a practical application. Please see MPEP §2106.05(g). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim as a whole is directed to an abstract idea. Please see MPEP §2106.04.(a)(2).III.C.
In view of the of the foregoing, the additional step does not integrate the abstract idea into a practical application.
Step 2B Analysis: there are no additional elements that amount to significantly more than the judicial exception. Moreover, the additional element as mentioned above does not amount to significantly more for the claim as a whole. Please see MPEP §2106.05. The claim is directed to an abstract idea.
For all of the foregoing reasons, claim 1 does not comply with the requirements of 35 USC 101.
Accordingly, the dependent claims 13-16 do not provide elements that overcome the deficiencies of the independent claim 12. Moreover, claim 15, recites, a wherein clause of further specification of the limitation it depends on which being abstract idea, hence, further specification to abstract idea is still abstract idea of further specifying what the abstract idea is based on or wherein of without providing further limiting features or additional element that helps to indicate an integration into a practical application of being significantly more. Claim 13 recites, in part, “wherein the charging output comprising: when and where to charge the UAV on the electric power line, when the classification label corresponds to a successful label; and abort charging of the UAV from the electric power line when the classification label corresponds to an unsuccessful label” are steps of certain method of organizing human activities of following instructions abstract ideas. Claim 14 recites, in part, “receiving a first set of images from the UAV; determining a set of image features relating to the first set of images, using a trained second machine learning model” recite, under Step 2A Prong 2, additional elements of “receiving…” which is insignificant extra-solution activity of data gathering, the “trained second machine learning model” is recited at high level of generality without further limiting how and in what details that output or processing happens and accomplishes; “and based on the set of image features, labeling the first set of images with at least one of a positive label for presence of the electric power line or a negative label for absence of the electric power line, in the corresponding first set of images” is a step of what the human mind can also perform through observation and judgment, the human mind can observe judge for labeling something based on given information and according to certain condition such as recited in this limitation. Claim 16 recites, in part, “triggering the imaging source associated with the UAV to capture the first set of images based on at least one of the location information, timing information, and battery information associated with the UAV” recites a step an additional element, under Step 2A Prong 2, to be insignificant extra-solution activity of capturing the image being data gathering, and the triggering to be a post-solution activity, hence is not indicative of an integration into a practical application
Accordingly, the dependent claims 13-16 are not patent eligible under 101.
Regarding Independent Claim 17 and its dependent claims 18-20,
Step 1 Analysis: Claim 17 is directed to a product/device, which falls within one of the four statutory categories.
Step 2A Prong 1 Analysis: Claim 17 recites, in part, “determining a plurality of features corresponding to charging of the one or more UAVs on the one or more electric power lines, using the labeled training information” The limitations as mentioned, as drafted, are processes that, under broadest reasonable interpretation, covers the performance of the limitation in the mind which falls within the “Mental Processes” grouping of abstract ideas. The limitations of:
“determining a plurality of features corresponding to charging of the one or more UAVs on the one or more electric power lines, using the labeled training information” is a step that the human mind can also perform, moreover, the human can determine label for charging of the UAV based on given information such as using the set of features and a trained machine learning model through observation and evaluation process, moreover, the “trained first machine learning model” is recited in this limitation as a given information without limiting how the machine learning model contributes to the process of determining, the limitation simply recites “determining….” using “…machine learning model” without having it directly being involved in the process, hence, the examiner reads the limitation, based on BRI (broadest reasonable interpretation) to just be a given information that the human mind can use to determine the label such as discussed.
Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 Analysis: This judicial exception is not integrated into a practical application. particular, the claim recites the following additional element(s) –
A computer programmable product comprising a non-transitory computer readable medium having stored thereon computer executable instructions, which when executed by one or more processors, cause the one or more processors to carry out operations for processing event data, the operations comprising: receiving labeled training information relating to charging of one or more unmanned aerial vehicles (UAVs) on one or more electric power lines, the labeled training information including a set of UAV attributes relating to the one or more UAVs, a set of power line attributes relating to the one or more electric power lines, a set of environment attributes and a set of labels relating to classification of charging, wherein the set of electric power line attributes includes geographic data, power rating, cable state associated with the corresponding electric power line; and training a first machine learning model to label one or more unlabeled test information with a classification label for classification of charging, using the plurality of features and the set of labels.
The additional elements of “a product….,” “a non-transitory computer readable medium…,” “a one or more processor ….” are recited at high generality of generic computer components performing generic functions such as a system here being part of a preamble can just be understood as a system of computing device, non-transitory computer readable medium such as ROM or RAN storing instructions or processor to execute the instructions. the step of receiving… merely constitutes pre-solution activity involving data gathering of obtaining data. Such extra-solution activity does not integrate the abstract idea into a practical application. Moreover, the additional element of “training….machine learning model….” recites the step of a generic machine learning model receiving an input and outputting an output without further limiting how the output is accomplished, therefore, recited a high level of generality of well-known machine learning model. Please see MPEP §2106.05(g). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim as a whole is directed to an abstract idea. Please see MPEP §2106.04.(a)(2).III.C.
In view of the of the foregoing, the additional step does not integrate the abstract idea into a practical application.
Step 2B Analysis: there are no additional elements that amount to significantly more than the judicial exception. Moreover, the additional element as mentioned above does not amount to significantly more for the claim as a whole. Please see MPEP §2106.05. The claim is directed to an abstract idea.
For all of the foregoing reasons, claim 1 does not comply with the requirements of 35 USC 101.
Accordingly, the dependent claims 18-20 do not provide elements that overcome the deficiencies of the independent claim 17. Claim 18 recites, in part, “obtaining a set of features for charging of an UAV by an electric power line, the set of features comprising a set of UAV attributes and location information associated with the UAV and a set of electric power line attributes relating to the electric power line” is an additional element, under Step 2A Prong 2, of an insignificant extra-solution activity of data gathering; “determining a classification label for charging of the UAV by the electric power line, using the set of features and the trained first machine learning model” is a step that the human mind can also perform through observation and evaluation such as the human can observe and determine label for charging the UIAV based on certain condition and given information such as recited in the limitation; “and based on the classification label, generating a charging output associated with the UAV and the electric power line” is a step of an additional element, under Step 2A Prong 2, to be insignificant extra-solution activity of data gathering such as generating data based on certain given information. Claim 19 recites, in part, “receiving a set of labeled historic samples, the set of labeled historic samples comprising positive samples and negative samples associated with one or more electric power lines” is a step of an additional element, under Step 2A Prong 2, to be insignificant extra-solution activity of data gathering such as receiving data; “determining a set of sample features relating to the set of labeled historic samples” is a step that the human mind can also perform of an observation, evaluation such as the human mind can determine a set of features based on certain condition and given information such as recite in the limitation; “and based on the set of labeled historic samples and the set of sample features, training a second machine learning model to label one or more unlabeled test samples with at least one of a positive label for presence of an electric power line or a negative label for absence of an electric power line, in the corresponding one or more unlabeled test samples” recites the step of training a generic machine learning model receiving an input and outputting an output without further limiting how the output is accomplished, therefore, recited a high level of generality of well-known machine learning model. Claim 20 discloses, in part, “storing the trained first machine learning model, the trained second machine learning model along with the labeled training information and the labeled historic samples locally on the UAV” which is of storing information, data being an additional element, under Step 2A Prong 2, to be insignificant extra-solution activity of data gathering.
Accordingly, the dependent claims 18-20 are not patent eligible under 101.
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.
Claims 1-2, 4-7, 12-13 and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over MingFeng Fan et. al. (“Deep Reinforcement Learning for UVA Routing in the Presence of Multiple Charging Stations, May 2023, IEEE Transactions on Vehicular Technology, Vol. 72, No. 5” hereinafter as “Fan”) in view of Maxim Lu et. al. (“Wireless Charging Techniques for UAVs: A Review, Reconceptualization, and Extension, May 2018, IEEE Access, Vol. 6” hereinafter as “Lu”).
Regarding claim 1, Fan discloses a system for charging an unmanned aerial vehicle (UAV), the system comprising (title): a memory configured to store computer executable instructions; and one or more processors configured to execute the instructions to (abstract discloses the use of deep learning in the processing hence, can be understood to have the use of a computer which includes a memory and processor to perform the function as recited for the invention processing): obtain a set of UAV attributes and location information associated with the UAV (page 5735, 1st paragraph, discloses the URPMCS of the invention uses the information of the UAV’s information such as on-board energy, energy consumption per unit traveling distance and maximum flight range, these information can be understood as UAV attributes which being used for the mathematical formulation of URPMCS [UAV routing problem in the presence of multiple charging stations] of this invention; moreover, section III.A, 1st paragraph, discloses the URPMCS also takes into the information of the UAV’s depot which being starting location and destination of the UAV [2nd paragraph] which is analogous to the location information as claimed); identify a plurality of electric power lines in proximity of the UAV, based on the location information (page 5735, 2nd column, last paragraph, of section III.A, discloses minimizing the traveled distance for the UAV, and moreover, the UAV must fly to the nearby charging station [section III.A, 2nd paragraph], therefore, is analogous to identify plurality of electric power lines in proximity based on the location information as claimed, by BRI [broadest reasonable interpretation]); obtain a set of electric power line attributes for the plurality of electric power lines (page 5736, 2nd column, 4th paragraph, discloses extracting features includes vectors of query, key and value, wherein the query and the key being charging nodes and target nodes being the charging stations and the UAV, therefore, the features of the charging station here is analogous to the electric power line attributes as claimed, for the plurality of charging stations, by BRI, covers the scope of the claim); identify one or more electric power lines from the plurality of electric power lines based on the set of UAV attributes, a set of environment attributes, the set of electric power line attributes and a trained first machine learning model (the plurality of charging stations are identified, as discussed previously, based on the UAV attributes, the set of electric power line attributes and a trained machine learning model being trained [page 5733, 1st column, last paragraph]; moreover, section III.A discloses the identification of charging stations for the UAV to use also depends on the region of interest of the charging stations being located in [the environment] such as considering of nearby charging stations, the availability of the stations, the route to reach the station, the altitude of the charging station [all of these are analogous to a set of environment attributes as recited]; and direct the UAV to the identified one or more electric power lines for charging the UAV (when the charging stations are identified, the UAV are directed to the charging stations for charging such as shown in FIG. 1).
However, Fan does not explicitly disclose wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines.
In the same field of UVA charging station energy efficiency determine (title and abstract, Lu) Lu discloses wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines (similar to Fan, Lu determines the efficient way to charge a UAV, the routing of the UAV depends on the location, availability and accessibility of the charging stations at the area; moreover, Lu discloses the availability and locations of the charging stations such as in impassable and remote locations [abstract and page 29865, last par. of 1st col.], therefore, the attributes of the electric power line here being locations of the charging stations [impassable or remote areas] which is analogous to geographic data, moreover, including power rating and coil geometry of the power lines [page 29871, 2nd par.]; therefore, in this instance, the power attributes being the information regarding the location of the charging station, power rating and coil geometry of the charging stations for the charging of the UAV efficiency).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan to identify one or more electric power lines from the plurality of electric power lines based on the set of UAV attributes, the set of electric power line attributes, a set of environment attributes, and a trained first machine learning model, wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines as taught by Lu to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to charge UAV efficiently regardless of geography (abstract, Lu).
Regarding claim 2, Fan in view of Lu, wherein Fan discloses the system of claim 1, wherein the UAV is directed to the electric power lines which is nearest to an original route of the UAV (shown in FIG. 1 of the UVA being directed to the charging stations of nearby charging stations based on the depot of the UAV, it can be understood to visit the nearest to the original route of the UAV as claimed, by BRI such as disclosed in section III.A).
Regarding claim 4, Fan in view of Lu, wherein Fan discloses the system of claim 1, wherein to train the first machine learning model, the one or more processors are configured to: receive labeled training information relating to charging of one or more UAVs on one or more electric power lines, the labeled training information including a set of UAV attributes relating to the one or more UAVs (section IV.B discloses training of the model including training information comprising of batch of instances and total rewards, the batch of instances can be understood as the labeled training information including UAV attributes since the instances correspond to learning task being the charging of the UAV at the charging station such as discloses in section IV.C and algorithm 1; moreover, the instances include ablation study involving determining effectiveness of the learning based on investigation of the impact such as disclosed in page 5739, 2nd column, 1st 2 paragraphs, hence, the instances here can be understood to be labeled known training information), a set of power line attributes relating to the one or more electric power lines, and a set of labels relating to classification of charging (algorithm 1 as discussed previously, and the disclosure in section IV.C teaches that the learning task includes the charging of the UAV at the charging stations, the regarding information here includes the attributes relating to the charging stations, and the reward includes information about successful or unsuccessful charging such as disclosed in section V.B); determine a plurality of features corresponding to charging of the one or more UAVs on the one or more electric power lines, using the labeled training information (the rewards as disclosed in section V.B corresponds to the determination of information regarding the charging of the UAVs on the charging stations, this information can be understood as the plurality of features as recited in this limitation); and train the first machine learning model to label one or more unlabeled test information with a classification label for classification of charging, using the plurality of features and the set of labels (the model as discussed previously, is used to label unlabeled test information using the features determined such as shown and disclosed in FIG. 2, by BRI, covers the scope of the claim).
Regarding claim 5, Fan in view of Lu, wherein Fan discloses the system of claim 4, wherein the set of labels includes one or more ground truth labels including at least one of a successful charging and an unsuccessful charging (the ablation study as discussed above to determine the successful and unsuccessful charging which covers the claim’s limitation by BRI which can be understood to have ground truth labels or information).
Regarding claim 6, Fan in view of Lu, wherein Fan discloses the system of claim 1, wherein to obtain the set of features, the one or more processors are configured to query a database for a functional class feature of each of labeled training information, unlabeled test information, or a combination thereof, as at least one of the set of features (“or” indicates a selection, the examiner selects “at least one of the set of features” for mapping which is disclosed in section IV. A, 4th paragraph, wherein a query is conducted for the extracting features [set of features as claimed] wherein the query serves a function of model parameter calculation hence can be understood as a functional class feature, moreover, the query being stored a form of vector hence can be understood to be stored in a database for the querying, by BRI, covers the scope of the limitation).
Regarding claim 7, Fan in view of Lu, wherein Fan discloses the system of claim 4, wherein the trained first machine learning model along with the training information is stored locally on the UAV (abstract discloses the model is being used for the UAV hence, can be understood to be stored locally on the UAV, based on BRI).
Regarding claim 12, Fan discloses a method for charging an unmanned aerial vehicle (UAV), the method comprising (title): obtaining a set of features for charging of the UAV by an electric power line, the set of features comprising a set of UAV attributes and location information associated with the UAV and a set of electric power line attributes relating to the electric power line (page 5735, 1st paragraph, discloses the URPMCS of the invention uses the information of the UAV’s information such as on-board energy, energy consumption per unit traveling distance and maximum flight range, these information can be understood as UAV attributes which being used for the mathematical formulation of URPMCS [UAV routing problem in the presence of multiple charging stations] of this invention; moreover, section III.A, 1st paragraph, discloses the URPMCS also takes into the information of the UAV’s depot which being starting location and destination of the UAV [2nd paragraph] which is analogous to the location information as claimed; page 5735, 2nd column, last paragraph, of section III.A, discloses minimizing the traveled distance for the UAV, and moreover, the UAV must fly to the nearby charging station [section III.A, 2nd paragraph], therefore, is analogous to identify plurality of electric power lines in proximity based on the location information as claimed, by BRI [broadest reasonable interpretation]; page 5736, 2nd column, 4th paragraph, discloses extracting features includes vectors of query, key and value, wherein the query and the key being charging nodes and target nodes being the charging stations and the UAV, therefore, the features of the charging station here is analogous to the electric power line attributes as claimed, for the plurality of charging stations, by BRI, covers the scope of the claim, moreover, the query and key are determined compatibility); determining a classification label for charging of the UAV by the electric power line, using the set of features and a trained first machine learning model (section IV. 1st paragraph, discloses the output solution being permutation of nodes consisting of all targets, the depot and charging stations which can be understood as classification label for charging s claimed by BRI); and based on the classification label, generating a charging output associated with the UAV and the electric power line (the model as discussed previously, is used to label unlabeled test information using the features determined such as shown and disclosed in FIG. 2, by BRI, covers the scope of the claim).
However, Fan does not explicitly disclose wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines.
In the same field of UVA charging station energy efficiency determine (title and abstract, Lu) Lu discloses wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines (similar to Fan, Lu determines the efficient way to charge a UAV, the routing of the UAV depends on the location, availability and accessibility of the charging stations at the area; moreover, Lu discloses the availability and locations of the charging stations such as in impassable and remote locations [abstract and page 29865, last par. of 1st col.], therefore, the attributes of the electric power line here being locations of the charging stations [impassable or remote areas] which is analogous to geographic data, moreover, including power rating and coil geometry of the power lines [page 29871, 2nd par.]; therefore, in this instance, the power attributes being the information regarding the location of the charging station, power rating and coil geometry of the charging stations for the charging of the UAV efficiency).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan to identify one or more electric power lines from the plurality of electric power lines based on the set of UAV attributes, the set of electric power line attributes, a set of environment attributes, and a trained first machine learning model, wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines as taught by Lu to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to charge UAV efficiently regardless of geography (abstract, Lu).
Regarding claim 13, Fan in view of Lu, wherein Fan discloses the method of claim 12, wherein the charging output comprising: when and where to charge the UAV on the electric power line, when the classification label corresponds to a successful label; and abort charging of the UAV from the electric power line when the classification label corresponds to an unsuccessful label (algorithm 1 as discussed previously, and the disclosure in section IV.C teaches that the learning task includes the charging of the UAV at the charging stations, the regarding information here includes the attributes relating to the charging stations, and the reward includes information about successful or unsuccessful charging such as disclosed in section V.B; the rewards as disclosed in section V.B corresponds to the determination of information regarding the charging of the UAVs on the charging stations, this information can be understood as the plurality of features as recited in this limitation; the model as discussed previously, is used to label unlabeled test information using the features determined such as shown and disclosed in FIG. 2, by BRI, covers the scope of the claim; the ablation study as discussed above to determine the successful and unsuccessful charging which covers the claim’s limitation by BRI which can be understood to have ground truth labels or information; moreover, the parameters are updated based on the rewards which is based on successful or unsuccessful of the learning task, the updating can be understood as abortion as claimed, by BRI).
Regarding claim 17, Fan discloses a computer programmable product comprising a non-transitory computer readable medium having stored thereon computer executable instructions, which when executed by one or more processors, cause the one or more processors to carry out operations for processing event data, the operations comprising (abstract discloses the use of deep learning in the processing hence, can be understood to have the use of a computer which includes a memory and processor to perform the function as recited for the invention processing): receiving labeled training information relating to charging of one or more unmanned aerial vehicles (UAVs) on one or more electric power lines, the labeled training information including a set of UAV attributes relating to the one or more UAVs (section IV.B discloses training of the model including training information comprising of batch of instances and total rewards, the batch of instances can be understood as the labeled training information including UAV attributes since the instances correspond to learning task being the charging of the UAV at the charging station such as discloses in section IV.C and algorithm 1; moreover, the instances include ablation study involving determining effectiveness of the learning based on investigation of the impact such as disclosed in page 5739, 2nd column, 1st 2 paragraphs, hence, the instances here can be understood to be labeled known training information), a set of power line attributes relating to the one or more electric power lines, , a set of environment attributes, and a set of labels relating to classification of charging (algorithm 1 as discussed previously, and the disclosure in section IV.C teaches that the learning task includes the charging of the UAV at the charging stations, the regarding information here includes the attributes relating to the charging stations, and the reward includes information about successful or unsuccessful charging such as disclosed in section V.B; moreover, section III.A discloses the identification of charging stations for the UAV to use also depends on the region of interest of the charging stations being located in [the environment] such as considering of nearby charging stations, the availability of the stations, the route to reach the station, the altitude of the charging station [all of these are analogous to a set of environment attributes as recited]); determining a plurality of features corresponding to charging of the one or more UAVs on the one or more electric power lines, using the labeled training information (the rewards as disclosed in section V.B corresponds to the determination of information regarding the charging of the UAVs on the charging stations, this information can be understood as the plurality of features as recited in this limitation); and training a first machine learning model to label one or more unlabeled test information with a classification label for classification of charging, using the plurality of features and the set of labels (the model as discussed previously, is used to label unlabeled test information using the features determined such as shown and disclosed in FIG. 2, by BRI, covers the scope of the claim).
However, Fan does not explicitly disclose wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines.
In the same field of UVA charging station energy efficiency determine (title and abstract, Lu) Lu discloses wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines (similar to Fan, Lu determines the efficient way to charge a UAV, the routing of the UAV depends on the location, availability and accessibility of the charging stations at the area; moreover, Lu discloses the availability and locations of the charging stations such as in impassable and remote locations [abstract and page 29865, last par. of 1st col.], therefore, the attributes of the electric power line here being locations of the charging stations [impassable or remote areas] which is analogous to geographic data, moreover, including power rating and coil geometry of the power lines [page 29871, 2nd par.]; therefore, in this instance, the power attributes being the information regarding the location of the charging station, power rating and coil geometry of the charging stations for the charging of the UAV efficiency).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan to identify one or more electric power lines from the plurality of electric power lines based on the set of UAV attributes, the set of electric power line attributes, a set of environment attributes, and a trained first machine learning model, wherein the set of electric power line attributes includes geographic data, power rating, cable design associated with the corresponding electric power lines as taught by Lu to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to charge UAV efficiently regardless of geography (abstract, Lu).
Regarding claim 18, Fan in view of Lu, wherein Fan discloses the computer programmable product of claim 17, the operations further comprising: obtaining a set of features for charging of an UAV by an electric power line, the set of features comprising a set of UAV attributes and location information associated with the UAV and a set of electric power line attributes relating to the electric power line (page 5735, 1st paragraph, discloses the URPMCS of the invention uses the information of the UAV’s information such as on-board energy, energy consumption per unit traveling distance and maximum flight range, these information can be understood as UAV attributes which being used for the mathematical formulation of URPMCS [UAV routing problem in the presence of multiple charging stations] of this invention; moreover, section III.A, 1st paragraph, discloses the URPMCS also takes into the information of the UAV’s depot which being starting location and destination of the UAV [2nd paragraph] which is analogous to the location information as claimed; page 5735, 2nd column, last paragraph, of section III.A, discloses minimizing the traveled distance for the UAV, and moreover, the UAV must fly to the nearby charging station [section III.A, 2nd paragraph], therefore, is analogous to identify plurality of electric power lines in proximity based on the location information as claimed, by BRI [broadest reasonable interpretation]; page 5736, 2nd column, 4th paragraph, discloses extracting features includes vectors of query, key and value, wherein the query and the key being charging nodes and target nodes being the charging stations and the UAV, therefore, the features of the charging station here is analogous to the electric power line attributes as claimed, for the plurality of charging stations, by BRI, covers the scope of the claim, moreover, the query and key are determined compatibility); determining a classification label for charging of the UAV by the electric power line, using the set of features and the trained first machine learning model (section IV. 1st paragraph, discloses the output solution being permutation of nodes consisting of all targets, the depot and charging stations which can be understood as classification label for charging s claimed by BRI); and based on the classification label, generating a charging output associated with the UAV and the electric power line (the model as discussed previously, is used to label unlabeled test information using the features determined such as shown and disclosed in FIG. 2, by BRI, covers the scope of the claim).
Claims 8-11, 14-16 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over MingFeng Fan et. al. (“Deep Reinforcement Learning for UVA Routing in the Presence of Multiple Charging Stations, May 2023, IEEE Transactions on Vehicular Technology, Vol. 72, No. 5” hereinafter as “Fan”) in view of Maxim Lu et. al. (“Wireless Charging Techniques for UAVs: A Review, Reconceptualization, and Extension, May 2018, IEEE Access, Vol. 6” hereinafter as “Lu”) and Ziwen Jiang et. al. (“An Autonomous Landing and Charging System for Drones, 2019, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, MIT Libraries, DSpace@MIT, Graduate Theses” hereinafter as “Jiang”) and Phong Nguyen et. al. (“Lightdenseyolo: A fast and accurate marker tracker for autonomous uav landing by visible light camera sensor on drone, 2018, Sensors, 18(6):1703, 2018” hereinafter as “Nguyen”).
Regarding claim 8, Fan in view of Lu, wherein Fan discloses the system of claim 1, wherein the one or more processors are further configured to (as discussed above in claim 1).
However, Fan in view of Lu does not explicitly disclose receive a first set of images from the UAV; determine a set of image features relating to the first set of images, using a trained second machine learning model; and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images.
In the same field of Placement of Recharging Stations (title, Jiang), Jiang discloses receive a first set of images from the UAV (section 4.3, 1st paragraph, discloses collecting images from the drone); determine a set of image features relating to the first set of images (section 4.3, 1st paragraph, discloses determining features relating to the images such as marker locations); and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images (section 4.3, 1st paragraph, discloses based on the features, label with markers to determine if there is correct platform including the charging station or not which, by BRI, covers the limitation’s scope).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan in view of Lu to have a system to determine charging stations for UAVs and further receive a first set of images from the UAV and determine a set of image features relating to the first set of images and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images as taught by Jiang to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to detect charging and perform landing more correctly based on the captured images (abstract, Jiang).
However, Fan in view of Lu in view of Jiang does not explicitly disclose using a trained second machine learning model.
In the same field of landing UAV autonomously (title, Nguyen), Nguyen discloses using a trained second machine learning model (abstract discloses the landing of the UAV on the platform can be determined using a neural network [analogous to the second machine learning model as claimed], therefore, the model of Jiang can be understood to be performed by the neural network of Nguyen to cover the claimed limitation).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan in view of Lu in view of Jiang to have a system to determine charging stations for UAVs and further receive a first set of images from the UAV and determine a set of image features relating to the first set of images and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images, moreover, the determine a set of image features relating to the first set of images, using a trained second machine learning model as taught by Nguyen to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to perform imaging and locating and landing of the UAV more accurately (abstract, Nguyen).
Regarding claim 9, Fan in view of Lu in view of Jiang and Nguyen discloses the system of claim 8, wherein to train the second machine learning model, the one or more processors are further configured to: receive a set of labeled historic samples, the set of labeled historic samples comprising positive samples and negative samples associated with one or more electric power lines (Nguyen, page 10, last paragraph, discloses the training dataset includes ground truth result; moreover, page 18, 1st paragraph, discloses the ground truth results includes positive and negative samples hence, is analogous to the claimed invention; moreover, Nguyen teaches about positive and negative samples of marker detections which is applied to Jiang to indicate the samples being associated with the charging stations such as discussed above to teach the claimed limitation, by BRI); determine a set of sample features relating to the set of labeled historic samples (Nguyen, page 10, last paragraph, discloses the training dataset includes the sampled relating to the set of anchors can be understood as labeled historic sampled, by BRI); and based on the set of labeled historic samples and the set of sample features, train the second machine learning model to label one or more unlabeled test samples with at least one of a positive label for presence of an electric power line or a negative label for absence of an electric power line, in the corresponding one or more unlabeled test samples (as discussed previously, the training dataset is used for training the neural network model of Nguyen to label the unlabeled input to output corresponding positive and negative detections wherein page 18, 1st paragraph, discloses the positive finding corresponding to the presence of marker and the negative to the absence, moreover, the presence of marker as being in combined with Jiang teaches the presence of the charging station or the absence of the charging station, as discussed previously above, by BRI). The combination of arts remains the same as for claim 8 above.
Regarding claim 10, Fan in view of Lu and Jiang and Nguyen discloses the system of claim 8, wherein the first set of images is captured by an imaging source associated with the UAV during a travel (as discussed above, the image being captured in Jiang by the UAV during its travel). The combination of arts remains the same as for claim 8 above.
Regarding claim 11, Fan in view of Lu and Jiang and Nguyen discloses the system of claim 10, wherein the one or more processors are further configured to: trigger the imaging source associated with the UAV to capture the first set of images based on at least one of the location information, timing information, and battery information, associated with the UAV (“at least one of” indicates a selection, the examiner selects “location information” for mapping which is disclosed in Jiang, page 53, last paragraph, discloses the image is taken at the end of the positioning cycles which indicates location information).
Regarding claim 14, Fan in view of Lu discloses the method of claim 12, the method further comprising: (as discussed above in claim 11).
However, Fan in view of Lu does not explicitly disclose receiving a first set of images from the UAV; determining a set of image features relating to the first set of images, using a trained second machine learning model; and based on the set of image features, labeling the first set of images with at least one of a positive label for presence of the electric power line or a negative label for absence of the electric power line, in the corresponding first set of images.
In the same field of Placement of Recharging Stations (title, Jiang), Jiang discloses receiving a first set of images from the UAV (section 4.3, 1st paragraph, discloses collecting images from the drone); determine a set of image features relating to the first set of images (section 4.3, 1st paragraph, discloses determining features relating to the images such as marker locations); and based on the set of image features, labeling the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images (section 4.3, 1st paragraph, discloses based on the features, label with markers to determine if there is correct platform including the charging station or not which, by BRI, covers the limitation’s scope).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan in view of Lu to have a system to determine charging stations for UAVs and further receive a first set of images from the UAV and determine a set of image features relating to the first set of images and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images as taught by Jiang to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to detect charging and perform landing more correctly based on the captured images (abstract, Jiang).
However, Fan in view of Lu in view of Jiang does not explicitly disclose using a trained second machine learning model.
In the same field of landing UAV autonomously (title, Nguyen), Nguyen discloses using a trained second machine learning model (abstract discloses the landing of the UAV on the platform can be determined using a neural network [analogous to the second machine learning model as claimed], therefore, the model of Jiang can be understood to be performed by the neural network of Nguyen to cover the claimed limitation).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan in view of Lu in view of Jiang to have a system to determine charging stations for UAVs and further receive a first set of images from the UAV and determine a set of image features relating to the first set of images and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images, moreover, the determine a set of image features relating to the first set of images, using a trained second machine learning model as taught by Nguyen to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to perform imaging and locating and landing of the UAV more accurately (abstract, Nguyen).
Regarding claim 15 Fan in view of Lu in view of Jiang and Nguyen discloses the method of claim 14, wherein the first set of images is captured by an imaging source associated with the UAV during a travel (as discussed above, the image being captured in Jiang by the UAV during its travel). The combination of arts remains the same as for claim 8 above.
Regarding claim 16, Fan in view of Lu in view of Jiang and Nguyen discloses the method of claim 15, the method further comprising: triggering the imaging source associated with the UAV to capture the first set of images based on at least one of the location information, timing information, and battery information associated with the UAV (“at least one of” indicates a selection, the examiner selects “location information” for mapping which is disclosed in Jiang, page 53, last paragraph, discloses the image is taken at the end of the positioning cycles which indicates location information).
Regarding claim 19, Fan in view of Lu discloses the computer programmable product of claim 17, the operations further comprising: (as discussed above in claim 11).
However, Fan in view of Lu does not explicitly disclose receiving a first set of images from the UAV; determining a set of sample features relating to the set of labeled historic samples; and based on the set of labeled historic samples and the set of sample features, training a second machine learning model to label one or more unlabeled test samples with at least one of a positive label for presence of an electric power line or a negative label for absence of an electric power line, in the corresponding one or more unlabeled test samples.
In the same field of Placement of Recharging Stations (title, Jiang), Jiang discloses receiving a first set of images from the UAV (section 4.3, 1st paragraph, discloses collecting images from the drone); determining a set of sample features relating to the set of labeled historic samples (section 4.3, 1st paragraph, discloses determining features relating to the images such as marker locations); and based on the set of labeled historic samples and the set of sample features, training a second machine learning model to label one or more unlabeled test samples with at least one of a positive label for presence of an electric power line or a negative label for absence of an electric power line, in the corresponding one or more unlabeled test samples (section 4.3, 1st paragraph, discloses based on the features, label with markers to determine if there is correct platform including the charging station or not which, by BRI, covers the limitation’s scope).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan in view of Lu to have a system to determine charging stations for UAVs and further receive a first set of images from the UAV and determine a set of image features relating to the first set of images and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images as taught by Jiang to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to detect charging and perform landing more correctly based on the captured images (abstract, Jiang).
However, Fan in view of Lu in view of Jiang does not explicitly disclose using a trained second machine learning model.
In the same field of landing UAV autonomously (title, Nguyen), Nguyen discloses using a trained second machine learning model (abstract discloses the landing of the UAV on the platform can be determined using a neural network [analogous to the second machine learning model as claimed], therefore, the model of Jiang can be understood to be performed by the neural network of Nguyen to cover the claimed limitation).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Fan in view of Lu in view of Jiang to have a system to determine charging stations for UAVs and further receive a first set of images from the UAV and determine a set of image features relating to the first set of images and based on the set of image features, label the first set of images with at least one of a positive label for presence of the electric power line and a negative label for absence of the electric power line, in the corresponding first set of images, moreover, the determine a set of image features relating to the first set of images, using a trained second machine learning model as taught by Nguyen to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to perform imaging and locating and landing of the UAV more accurately (abstract, Nguyen).
Regarding claim 20, Fan in view of Lu in view of Jiang and Nguyen discloses the computer programmable product of claim 19, the operations further comprising: storing the trained first machine learning model (the trained model is being used for future detection, of Nguyen, hence can be understood to be stored), the trained second machine learning model along with the labeled training information and the labeled historic samples locally on the UAV (all the information as discussed above can be understood to be stored locally on the UAV, by BRI).
Pertinent Prior Art(s)
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Surajit Das Barman et. al., “Wireless Powering by Magnetic Resonant Coupling: Recent Trends in Wireless Power Transfer System and Its Applications, Nov. 2025, Renewable and Sustainable Energy Reviews, Vol. 51, Nov. 2015, pp. 1525-1552” discloses a UAV charging station composed of factors considering power level, coil geometry including size and weight, A-factor, and coupling parameters and operating frequency (page 1527, 2nd par.).
Stefan Smolenaers, “US 2022/0144117 A1” discloses electric vehicle charging station including controlling of power to supper energy to the source, at any power rating, up to its maximum power rating, and concerning power network and station ([0278]), and the vehicle including unmanned aircraft such as drones ([0135]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PHUONG HAU CAI whose telephone number is (571)272-9424. The examiner can normally be reached M-F 8:30 am - 5:00pm.
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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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.
/PHUONG HAU CAI/ Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673