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 .
DETAILED ACTION
Claims 1-20 are pending. Claims 1-20 are rejected.
Amendments to the claims have been recorded.
Response to Amendment
Applicant’s arguments with respect to claims have been considered but are moot because the arguments do not apply to the new references being used in the current rejection.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims rejected as failing to define the invention in the manner required by 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
The claim(s) are narrative in form and replete with indefinite language. The structure which goes to make up the device must be clearly and positively specified. The structure must be organized and correlated in such a manner as to present a complete operative device. The claim(s) must be in one sentence form only. Note the format of the claims in the patent(s) cited.
The claims are generally narrative and indefinite, failing to conform with current U.S. practice. They appear to be a literal translation into English from a foreign document and are replete with grammatical and idiomatic errors.
Claim 20 recites “use one of vector quantization and entropy coding to further compress, using the first machine learning model,” The claim is unclear as to how the “vector quantization and entropy coding” is being used and whey its is being used? Is it being used just to be user? There is no clear limitation as to what function is associated with “use one of vector quantization and entropy coding to further compress, using the first machine learning model,”. As such the limitation seems to just be narrative and does not further limit the claim. It is noted that Applicant has amended to claims back to the original claim language that was rejected using the same rejection.
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 Huang US 2021015771 in view of Lue US 20250065894.
1. A method using a partitioned deep neural network with a constrained data cap, the method comprising:
receiving, at a first machine learning model, raw data from a controller of a steering system; 21; receive sensor data [sensor data is raw data]; Also 46; The encoding system can use the resulting estimated distribution to losslessly compress the raw sequential stream of symbols representing the nodes of the tree-based structure using an entropy coding algorithm such as arithmetic coding. Also; 27; can generate specific control signals for the autonomous vehicle (e.g., adjust steering, braking, velocity, and so on).
generating, using a first encoder of the first machine learning model, compressed code using the raw data; 5, using the contextual information [raw sensor data] as input to a machine-learned model, 18; the present disclosure is directed to systems and methods for generating a compressed and encoded representation of point cloud (e.g., LIDAR) data.
Also 21; receive sensor data about the environment, perceive objects [perceived objects are models and not the object themselves] within the vehicle's surrounding environment (e.g., other vehicles),
identifying, using the first machine learning model, values, of a plurality of values of the compressed code, that are outside of a value range; 127; Shannon's source coding theorem, the cross-entropy between q(x) and p(x) provides a tight lower bound on the bitrate achievable by arithmetic or range coding algorithms such that the better q(x) approximates p(x), the lower the true bitrate. The entropy model can be trained to minimize the cross-entropy loss between the models predicted distribution q and the distribution of training data. It is noted that anything outside the theorem is outside the range.
generating, using a first head of the first machine learning model, a prediction value for each identified value, the prediction value for each respective value of the identified values predicting whether a respective value indicates an anomaly in the raw data; 126; eight-bit symbols (e.g., representing a node) in a plurality of eight-bit symbols, entropy model can be to generate [at a first head node i.e. 404] an estimate distribution q(x.sub.n) for a particular symbol x.sub.n that minimizes the difference (or cross-extropy) [anomaly] with the actual distribution of symbols for the particular symbol p(x.sub.n)
further compressing, using the first machine learning model using vector quantization, portions of the compressed code associated with prediction values that are greater than a threshold, 129, where x.sub.an(i)={x.sub.pa(i), x.sub.pa(pa(i)), . . . , X.sub.pa( . . . (pa(i)))} with |x.sub.an(i)|≤K can be the set of ancestor nodes of a given node i, up to a given order K. [any value outside of x.sub.an(i) are greater than a threshold K] Also 56; to generating statistical data based on the feature data associated with nodes higher in the tree hierarchy. 62; fed through a linear layer [quantized] and softmax to output intensity probability values. In some examples, the intensity value is an 8-bit integer, so the resulting probability vector [quantized by layers] is 256-dimensional p(r.sub.i.sup.(t)|X.sup.(t)|P.sup.(t−1);w)).
wherein the portion of the compressed code are compressed from a continuous vector space to a discreet space; 63; The data encoding system can then encode the byte streams using the entropy model discussed above to produce a compressed bitstream. 66; The data encoding system can divide the three-dimensional space [continuous vector space] into eight sub-areas [discreet space].
communicating the portions of the compressed code to a second machine learning model; 67; the data encoding system [parent] can add a node representing the respective sub-area as a child node [second machine learning model] of the initial node in the tree-based data structure.
receiving, from a second head of the second machine learning model, diagnostics information responsive to the portions of the compressed code, wherein the first head [404; child consumes 404 and 408] Also; 124; contextual information has been calculated by the encoding system [compressing code] and first machine learning mode consume less space and compute cycles than the second head and the second machine learning model, and [402; parent consumes 402; 406; 404; 408]. Also see 2144.04(c.) design choice
controlling the steering system, using the controller of the steering system, based on the diagnostic information. 27; can generate specific control signals for the autonomous vehicle (e.g., adjust steering, braking, velocity, and so on).
Huang teaches all of the limitations of claim 1 but does not teach wherein the diagnostics information includes severity information and monitoring parameter information;
However, Luo teaches 424; method also includes comparing the error [parameter] to a threshold [judging severity to a threshold] and determining that a current path of the first vehicle is inappropriate for traversing the road segment.
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 for the purpose of controlling a vehicle such that the claimed invention as a whole would have been obvious. The combination is also considered obvious to try as stated in KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 415-421, 82 USPQ2d 1385, 1395-97 (2007).
2. The method of claim 1, further comprising, in response to receiving the diagnostics information,
initiating at least one corrective action procedure. 62; The data encoding system can leverage temporal correlations
3. The method of claim 1, wherein the diagnostics information further includes issue classification information. 205; training technique is backwards propagation of errors [issue classification information as error].
4. The method of claim 1, wherein the first machine learning model is disposed within a vehicle.Fig.1 #102
5. The method of claim 1, wherein the second machine learning model is disposed on a remote computing device. Fig.1 #106
6. The method of claim 5, wherein the remote computing device is associated with a cloud computing infrastructure. Associated with Fig.1 #108
7. Canceled
8. The method of claim 1, wherein the steering system includes an electronic power steering system. Intended use of electric power steering.
9. The method of claim 1, wherein further compressing,
using the first machine learning model, the portions of the compressed code associated with prediction values that are greater than the threshold further includes using vector quantization. 154 and 167; the data encoding system 606 can quantize and encode the point cloud data into an octree representation (e.g., via octree generated 610) where leaves represent the quantized points and intermediate nodes contain 8-bit symbols representing child occupancies. This feature can be fed through a linear layer and softmax to output intensity probability values. In some examples, the intensity value is an 8-bit integer, so the resulting probability vector is 256-dimensional p(r.sub.i.sup.(t)|X(t)|P.sup.(t−1);w)).
10. The method of claim 1, wherein further compressing,
using the first machine learning model, the portions of the compressed code associated with prediction values that are greater than the threshold further includes using entropy coding. 46; using an entropy coding algorithm.
11-16 are rejected using the same rejections as made to claims 1-6.
18. is rejected using the same rejection as made to claim 10. Intended use of will know method of vector quantization.
19. is rejected using the same rejection as made to claim 9.
20. is rejected using the same rejection as made to claim 1. Intended use of well-known method of vector quantization and entropy coding. Claim 20 is broader in scope then claim 1 based on Markush grouping.
Citation of Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Han US 20150120145 para 64; [0064] The steering system unit 10 is disposed at four wheels of a vehicle, controls steering of the wheels and collects and transmits the state information of the wheels. Further, when any one of steering systems in the steering system unit 10 breaks, the steering system transmits fault information to the control unit 20 and the steering systems without a fault receive corrected steering angles calculated by the control unit 20 and control the steering angle of their wheels.
Conclusion
THIS ACTION IS MADE FINAL. 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 SIHAR A KARWAN whose telephone number is (571)272-2747. The examiner can normally be reached on M-F 11am.-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
Prosecution Insights