Prosecution Insights
Last updated: April 19, 2026
Application No. 18/914,929

KERNEL-BASED ERGODIC SEARCH

Non-Final OA §103
Filed
Oct 14, 2024
Examiner
KARWAN, SIHAR A
Art Unit
3658
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Northwestern University
OA Round
1 (Non-Final)
56%
Grant Probability
Moderate
1-2
OA Rounds
3y 3m
To Grant
82%
With Interview

Examiner Intelligence

Grants 56% of resolved cases
56%
Career Allow Rate
215 granted / 385 resolved
+3.8% vs TC avg
Strong +26% interview lift
Without
With
+25.8%
Interview Lift
resolved cases with interview
Typical timeline
3y 3m
Avg Prosecution
41 currently pending
Career history
426
Total Applications
across all art units

Statute-Specific Performance

§101
11.2%
-28.8% vs TC avg
§103
27.8%
-12.2% vs TC avg
§102
33.4%
-6.6% vs TC avg
§112
16.4%
-23.6% vs TC avg
Black line = Tech Center average estimate • Based on career data from 385 resolved cases

Office Action

§103
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 . Claim Rejections - 35 USC § 103 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Baron US 10,140,249 in view of Ebrahimi US 20220026920. 1. Baron teaches a computer-implemented method for kernel-based ergodic search using a robot, comprising: receiving, via a processor, a target distribution indicative of a desired ergodic search coverage; C2L37; optimal Bayesian performance [Also known as Gaussian Kernal distribution or Gaussian distribution or Bell curve with a target center or Gaussian mean i.e. target distribution] for stationary ergodic. Also; C3L40; Fitting Gaussian models; used to fit a given data sequence [target] with a GM model, and the parameters can be learned using a modified expectation-maximization (EM) algorithm. generating, via a metric generator, a kernel-based ergodic metric based on the target distribution and a candidate trajectory; C3L37 Bayesian [Gaussian kernel; Radial Basis Function, Bell shaped weighted] generating, via a gradient generator, a kernel-based ergodic gradient based on the kernel-based ergodic metric; C15L10; The performance of the two AMP-UD implementations was compared to (i) the universal CS recovery algorithm SLA-MCMC; and (ii) the empirical Bayesian [Gaussian based ergodic kernal] message passing approaches EM-GM-AMP-MOS for i.i.d. inputs and turboGAMP for non-i.i.d. inputs. The results for other CS algorithms such as compressive sensing matching pursuit (CoSaMP), gradient projection for sparse reconstruction (GPSR) C17L4; AMP-UD is designed to reconstruct stationary ergodic signals. but does not teach generating, via a controller, a trajectory based on the kernel-based ergodic gradient; and implementing, via a trajectory controller, the trajectory for the robot. However; Ebrahimi teaches generating, via a controller, a trajectory based on the kernel-based ergodic gradient; and Ebrahimi 67; the motion planning functionality 112 may generate the motion plan 210 based at least in part on the trajectory 242 and provide the motion plan 210 to the motion control functionality 110, Also 86; a kernel function over the trajectories. Thus, SVGD may help ensure a diverse set of samples, while leveraging parallel gradient-based optimization. implementing, via a trajectory controller, the trajectory for the robot. Ebrahimi 67; the motion planning functionality 112 may generate the motion plan 210 based at least in part on the trajectory 242 and provide the motion plan 210 to the motion control functionality 110, Therefore, it was well known at the time the invention was filed and would have been obvious to one of ordinary skill in the art to combine the teachings with a reasonable expectation for the purpose of light weight and real time ALAM for robots such that the claimed invention as a whole would have been obvious. 2. The computer-implemented method for kernel-based ergodic search using the robot of claim 1, wherein the kernel-based ergodic metric is based on a delta kernel. C11L15; stationary ergodic signals with bounded components, the optimal estimation error [difference or delta] among all sliding-window denoising schemes despite not knowing the prior for the signal. When the error metric is square error, the optimal error is the MMSE [minimum mean square error expectation of gaussian i.e. Gaussian Kernel]. 3. The computer-implemented method for kernel-based ergodic search using the robot of claim 1, wherein the kernel-based ergodic metric is based on an L2 distance between the target distribution and a spatial empirical distribution of the candidate trajectory.C9L28; the initialization to examine the maximal distance between each symbol of the input data sequence and the current initialization of the μ.sub.s's ,distance is greater than 0.1σ.sub.q [L2 distance from Gaussian mean] then a Gaussian component whose mean is initialized as the value of the symbol being examined is added 4. The computer-implemented method for kernel-based ergodic search using the robot of claim 1, wherein the kernel-based ergodic metric includes an information maximization element and a uniform coverage element. Ebrahimi 510; vertices and generates plane equations associated with geometric primitive defined by vertices [areas to be covered i.e. coverage mask]; plane equations are transmitted to a coarse [maximization of element i.e. max coverage low resolution as opposed to fine elements min coverage high res] raster engine to generate coverage information (e.g., an x, y coverage mask for a tile) for primitive; 5. The computer-implemented method for kernel-based ergodic search using the robot of claim 1, wherein the kernel-based ergodic metric is formulated as a Gaussian kernel. C4L50 ergodic Gaussian kernel fomula i.e. E^(-(X-XI)^2)2O^2) 6. The computer-implemented method for kernel-based ergodic search using the robot of claim 1, comprising performing kernel parameter selection for the kernel-based ergodic metric based on a kernel parameter selection objective function by minimizing a derivative of one or more independent and identically distributed (IID) samples from the target distribution with respect to the kernel-based ergodic metric. Fig.1 and C4L10 with the GM-based [ergodic Gaussian kernel model] i.i.d. denoiser η.sub.iid,t(⋅). 7. The computer-implemented method for kernel-based ergodic search using the robot of claim 1, comprising generating the trajectory based on iteratively optimizing a descent direction of a kernel ergodic control objective associated with the kernel-based ergodic metric with a quadratic cost. Ebrahimi 76; The motion planning functionality 112 may modify the candidate distribution iteratively to obtain a set of candidate distributions (represented by a variable Q) and select, as the trajectory distribution, the candidate distribution associated with a minimum divergence [minimum quadratic cost]; 73; corresponds to the cumulative running cost and may be selected based on a domain (e.g., quadratic cost, obstacle cost, etc.) 8. The computer-implemented method for kernel-based ergodic search using the robot of claim 7, wherein the iteratively optimizing the descent direction is based on a linear-quadratic regulator (LQR). Ebrahimi 73; In Eq. 1 above, an expression c.sub.t(x.sub.t, u.sub.t; z) corresponds to the cumulative running cost and may be selected based on a domain (e.g., quadratic cost, obstacle cost, etc.). [Eq.1 is linear quadratic regulator as it is a summation and not exponential] Also 76; The motion planning functionality 112 may modify the candidate distribution iteratively to obtain a set of candidate distributions (represented by a variable Q) and select, as the trajectory distribution, the candidate distribution associated with a minimum divergence using Eq. 3 above 9. The computer-implemented method for kernel-based ergodic search using the robot of claim 1, wherein the kernel-based ergodic metric is generalized to a Lie group. C12L60 Lie group calculation [Lie group parameterized with Lo /l to derived a finite Lh] 10. The computer-implemented method for kernel-based ergodic search using the robot of claim 9, wherein the Lie group is a special orthogonal group SO(3) or a special Euclidean group SE(3). Ebrahimi 108-109; denotes the softmax function computed on Euclidean distances between all points. Claims 11-15 are rejected using the same rejections as made to claims 1-5 respectively. Claim 16 is rejected using the same rejections as made to claim 1. Claims 17-20 are rejected using the same rejections as made to claims 6-9 respectively. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to SIHAR A KARWAN whose telephone number is (571)272-2747. The examiner can normally be reached on M-F; 11-7pm. 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, Ramon Mercado can be reached on 571-270-5744. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /SIHAR A KARWAN/Examiner, Art Unit 3664
Read full office action

Prosecution Timeline

Oct 14, 2024
Application Filed
Feb 05, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12589502
CARGO-HANDLING APPARATUS, CONTROL DEVICE, CONTROL METHOD, AND STORAGE MEDIUM
2y 5m to grant Granted Mar 31, 2026
Patent 12589750
VEHICULAR CONTROL SYSTEM
2y 5m to grant Granted Mar 31, 2026
Patent 12589504
SYSTEM AND METHOD FOR COGNITIVE SURVEILLANCE ROBOT FOR SECURING INDOOR SPACES
2y 5m to grant Granted Mar 31, 2026
Patent 12583100
ROBOT TO WHICH DIRECT TEACHING IS APPLIED
2y 5m to grant Granted Mar 24, 2026
Patent 12576516
HUMAN SKILL BASED PATH GENERATION
2y 5m to grant Granted Mar 17, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
56%
Grant Probability
82%
With Interview (+25.8%)
3y 3m
Median Time to Grant
Low
PTA Risk
Based on 385 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month