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 .
This Action is FINAL and is in response to the claims filed September 16, 2026. Claims 1, 15-28, 30-33, and 35 are currently pending, of which claims 1, 16, 17, 19, 21, 25, 30, 31, 33, and 35 are currently amended. Claims 2-14, 29, and 34 were previously cancelled.
Response to Arguments
Specification
Applicant argues that the current title is already “descriptive and technically accurate with respect to the subject matter of the specification and the claims.” See Remarks 10. Examiner notes that the sensors just being arranged does not capture anything about the inventive concept. Nevertheless, in light of Applicant’s remarks, the previous objection has been withdrawn.
Claim Objections
Applicant has amended the claims at issue and the previous objections have therefore been withdrawn.
Rejections Under 35 USC §112
Applicant has amended the claims at issue and the previous rejections under 35 U.S.C. 112(b) have therefore been withdrawn.
Prior Art Rejections
Applicant’s arguments regarding the previously cited art have been fully considered. Specifically, Appolicant has amended the claims at issue and argues that these amendments regarding the configuration of sensors in the regions is not taught by Athreya or Park. See Remarks 13-14. These arguments are moot, as new reference Rublee has been introduced to teach the multiple area arrangement of sensors within a workspace. See Rublee Figs. 1 and 2 and paras. [0027-28] and [0033-34].
It is for at least these reasons and the reasons cited below that the claims remain ejected in this Action.
Examiner’s Note
The prior art rejections below cite particular paragraphs, columns, and/or line numbers in the references for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 15-26, 30-33, and 35 is/are rejected under 35 U.S.C. 103 as being unpatentable over Athreya et al. (W.O. 2021/158225; hereinafter “Athreya”) and further in view of Rublee et al. (U.S. Publication No. 2017/0144307; hereinafter, “Rublee”) and Park et al. (U.S. Publication No. 2021/0406560; hereinafter, “Park”).
As per claim 1, Athreya teaches a method of managing a sensor grid system, the method comprising:
applying an output from the one or more sensors associated with a region of the working space to a task model to perform a task associated with the working space (See Athreya Fig. 2 and paras. [0018], [0047-48] and [0068]: sensors for environment conditions, including their placement, that can be input into a selection model);
determining a task accuracy parameter corresponding to an accuracy with which the task model performs the task for the region (See Athreya paras. [0032-33]: target accuracy of model); and
in response to the task accuracy parameter being below a task accuracy parameter threshold: increasing the complexity of the task model (See Athreya paras. [0045] and [0060]: increasing machine learning model structure complexity if below threshold target accuracy).
However, while Athreya teaches configuring a plurality of sensors arranged in a working space to collect data within the working space (See Athreya Fig. 2 and paras. [0018], [0047-48] and [0068]), Athreya does not explicitly teach dividing a working space into regions for these sensors.
Rublee teaches the working space divided into one or more regions, each region associated with one or more sensors to the plurality of sensors (See Rublee Figs. 1 and 2 and paras. [0027-28] and [0033-34]: environment divided into a grid of areas, where each of the areas has a corresponding sensor).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine, with a reasonable expectation of success, the environmental sensors of Athreya with the sensor grid of Rublee. One would have been motivated to combine these references because both references disclose sensor arrangements in a workspace environment, and Rublee further enhances the sensor environment of Athreya by treating each area uniquely and thus allowing for efficient and safe movement across the workspace (See Rublee para. [0018]).
Furthermore, while Athreya/Rublee teaches increasing model complexity, Athreya does not explicitly teach increasing sensor resolution.
Park teaches increasing the resolution of the output from the one or more sensors associated with the region (See Park para. [0008]: “To further increase the accuracy and precision of the multi-sensor fusion network, one or more additional channels may be provided as input to the multi-sensor fusion network”).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine, with a reasonable expectation of success, the model complexity of Athreya/Rublee with the additional sensors of Park. One would have been motivated to combine these references because both references disclose machine learning control systems with autonomous robots, and Park further enhances the model accuracy of Athreya because “[b]y reducing noise and increasing the accuracy and precision of the multi-sensor fusion network, the downstream processes that rely on these outputs of the multi-sensor fusion network—representing locations, velocities, poses, appearances, etc. of static and dynamic objects or features in the environment—may also benefit from increased performance and effectiveness” (See Park para. [0009]).
As per claim 15, Athreya/Rublee/Park further teaches the method of claim 1, comprising using the resolution of the sensors and the complexity of the task model to perform the task using the data collected from the plurality of sensors (See Athreya paras. [0052-53]: based on inferencing results, can control vehicles and robots or perform other commands).
As per claim 16, the claim is directed to an apparatus that implements the same features of the method of claim 1 and is therefore rejected for at least the same reasons therein. Furthermore, Athreya teaches the apparatus comprising a processor and memory containing instructions executable by the processor to configure the apparatus to implement said method (See Athreya paras. [0054-55]).
As per claim 17, Athreya/Rublee/Park further teaches the apparatus of claim 16, wherein the task comprises:
detecting predetermined objects (See Athreya para. [0052]: object detection);
controlling automated devices (See Athreya par. [0062]: controlling robot and self-driving vehicles);
quality assurance of automated devices (See Athreya para. [0062]: reporting on parts detected on an assembly line); and
identifying security threats (See Athreya para. [0062]: identify person in security camera footage).
As per claim 18, Athreya/Rublee/Park teaches the apparatus of claim 16. However, while Athreya teaches increasing the complexity of the model, Athreya/Rublee does not explicitly teach repeating the increase of the sensor resolution.
Park teaches operative to increase the resolution of the output from the sensors again, following increasing the complexity of the task model (See Park para. [0008]: “To further increase the accuracy and precision of the multi-sensor fusion network, one or more additional channels may be provided as input to the multi-sensor fusion network – e.g., at each iteration”. Therefore, the iteration will continue until the targeted accuracy of Athreya is reached)
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine Athreya/Rublee with the teachings of Park for at least the same reasons as discussed above in claim 1.
As per claim 19, Athreya/Rublee/Park teaches the apparatus of claim 16. However, while Athreya teaches sensors, Athreya does not explicitly teach working space arrangements of the sensors.
Park teaches wherein the sensors are arranged to monitor respective regions of the working space and the task comprises detecting predetermined objects (See Park paras. [0071-72] and [0088]: environmental map data and sensors arranged and can be overlapped to determine and update an occupancy grid).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine Athreya/Rublee with the teachings of Park for at least the same reasons as discussed above in claim 1.
As per claim 20, Athreya/Rublee/Park further teaches the apparatus of claim 19, wherein the predetermined objects are persons and an output of the sensor grid is used to control automated devices within the working space (See Athreya para. [0007]: “navigation (e.g., navigating a robot or autonomous vehicle to a location while avoiding obstacles)”; para. [0052]: object detection as well, including person, that would affect control of a robot).
As per claim 21, Athreya/Rublee/Park further teaches the apparatus of claim 16. However, while Athreya teaches increasing model complexity, Athreya does not explicitly teach increasing sensor resolution.
Park teaches wherein the resolution of the output from the sensors is increased by tuning any one or more of the following parameters of the sensors: pixel resolution; sampling frequency; quantization; bandwidth; filtering; and the number of sensors. (See Park para. [0008]: “To further increase the accuracy and precision of the multi-sensor fusion network, one or more additional channels may be provided as input to the multi-sensor fusion network”; para. [0049]: up-sampling spatial resolution of DNN layers).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine Athreya/Rublee further with the teachings of Park for at least the same reasons as discussed above in claim 1.
As per claim 22, Athreya/Rublee/Park further teaches the apparatus of claim 16, wherein the task model is a pre-trained neural network (See Athreya para. [0031]: “a machine learning model or models may be selected from a set of pre-trained machine learning models”.
As per claim 23, Athreya/Rublee/Park further teaches the apparatus of claim 22, comprising a training module configured to generate the trained neural network by one or more of: training an untrained neural network using the output from the sensors; using transfer learning from another trained neural network trained using a different working space (See Athreya para. [0058]: pre-trained models vs machine learning trained by apparatus; see also Park para. [0185]: training can be performed by a variety of methods, includes transfer learning).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine Athreya/Rublee further with the teachings of Park for at least the same reasons as discussed above in claim 1.
As per claim 24, Athreya/Rublee/Park further teaches the apparatus of claim 22, wherein the memory contains a plurality of neural networks of different complexity (See Athreya paras. [0030] and [0032]: varying complexity of models based on sensor conditions. This includes image sensors associated with inference levels and some situations may require more complex inferencing when “the illumination condition is demanding”, for example).
As per claim 25, Athreya/Rublee/Park further teaches the apparatus of claim 22, wherein increasing the complexity of the task model comprises using another neural network having an increase in one or more of the following architectural parameters: input resolution; layer depth; and layer width (See Athreya paras. [0042] and [0045]: “each layer of the machine learning model structure may have a separate quantization. The quantization for a layer may depend on a factor or factors, such as weight distribution, layer depth, etc.” Furthermore, apparatus may increase complexity and/or quantization in a case that the confidence value is below a target accuracy based on the error feedback)
As per claim 26, Athreya/Rublee/Park further teaches the apparatus of claim 20, wherein the task model is a neural network trained using the output from the sensors together with person sensing data from the automated devices (See Athreya paras. [0018] and [0061-62]: inferencing can include detected person presence data; para. [0032]: trained based on facial recognition images).
As per claim 30, Athreya/Rublee/Park further further teaches the apparatus of claim 16, wherein the memory comprises the task model (See Athreya para. [0058]: memory may store machine learning model).
As per claim 31, the claim is directed to a system that implements the same features of the method of claim 1 and is therefore rejected for at least the same reasons therein. Furthermore, Athreya/Rublee/Park further teaches a sensor grid having a plurality of sensors; an apparatus, the apparatus comprising a processor and memory containing instructions executable by the processor to configure the apparatus to implement said method (See Athreya paras. [0054-55]).
As per claim 32, Athreya/Rublee/Park further teaches the system of claim 31, wherein the apparatus is further configured to configure the sensor grid (See Athreya para. [0018]: sensor placement in the environment; see also Park paras. [0071-72] and [0088]: environmental map data and sensors arranged and can be overlapped to determine and update an occupancy grid).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine Athreya/Rublee further with the teachings of Park for at least the same reasons as discussed above in claim 1.
As per claim 33, Athreya/Rublee/Park further teaches the system of claim 31, wherein the sensors comprise one or more of the following: thermometers; thermal imaging sensors; and cameras (See Athreya paras. [0020-22]: sensors such as cameras).
As per claim 35, the claim is directed to a storage media that implements the same features of the method of claim 1 and is therefore rejected for at least the same reasons therein. Furthermore, Athreya/Rublee/Park teaches a non-transitory computer readable storage media having stored thereon a computer program that, when executed, performs a method, the method comprising said method pf claim 1 (See Athreya paras. [0054-55]).
Claim(s) 27 and 28 is/are rejected under 35 U.S.C. 103 as being unpatentable over Athreya/Rublee/Park as applied above, and further in view of Stroman et al. (U.S. Publication No. 2019/0107408; hereinafter “Stroman”).
As per claim 27, Athreya further teaches the apparatus of claim 20, wherein the task accuracy parameter threshold corresponds to a collision avoidance limit between persons and automated devices (See Athreya para. [0007]: “navigation (e.g., navigating a robot or autonomous vehicle to a location while avoiding obstacles)”; para. [0052]: object detection as well, including person, the would affect control of a robot).
However, while Athreya teaches collision avoidance, Athreya does not explicitly teach minimizing energy use.
Stroman teaches a requirement to minimize energy use by the sensors and task model (See Stroman abstract and paras. [0041-43]: energy consumption taken into account when plotting paths, including identifying the “minimum energy or minimum fuel consumption path, called the global path”).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine, with a reasonable expectation of success, the vehicle and robotics controls of Athreya with the energy determinations of Stroman. One would have been motivated to combine these references because both references disclose vehicle obstacle avoidance, and Stroman further enhances the vehicle navigation of Athreya by ensuring efficient use of fuel and minimizing energy waste (See Stroman paras. [0008] and [0051]).
As per claim 28, Athreya/Rublee/Park/Stroman teaches the apparatus of claim 27. While Athreya increases the complexity in response to the task accuracy not being reached (See Athreya para. [0045]), Athreya does not do so with the number of sensors.
Park teaches adding more sensors to the sensor grid in response to the task accuracy parameter threshold not being reached (See Park para. [0008]: “To further increase the accuracy and precision of the multi-sensor fusion network, one or more additional channels may be provided as input to the multi-sensor fusion network – e.g., at each iteration”. Therefore, the iteration will continue until the targeted accuracy of Athreya is reached)
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to combine Athreya with the teachings of Park for at least the same reasons as discussed above in claim 1.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nicholas Klicos whose telephone number is (571)270-5889. The examiner can normally be reached Mon-Fri 9:00 AM-5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant 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, Scott Baderman can be reached at (571) 272-3644. 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.
/NICHOLAS KLICOS/Primary Examiner, Art Unit 2118
Prosecution Insights