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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Drawings
The drawings are objected to because Figs. 6, 8, and 9 are not legible due to either the blurry text or the text on gray stippling background. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claims 1 and 17 are objected to because of the following informalities:
As per claim 1, the phrase “end-effector (390)” on the second to last line of the claim should be amended to read “end-effector
As per claim 17, the phrase “a teat cleaning unit” should be amended to “a teat cleaning unit,” to separate the list with a comma (,).
As per claim 17, the phrase “end-effector (390)” on the second line of the claim should be amended to read “end-effector.
Appropriate correction is required.
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.
Claim 16 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
As per claim 16, the limitation “the respective control current” lacks antecedent basis. It is unclear whether the claim should be dependent on claim 14 as claimed or dependent upon claim 15 in which a respective control current is defined. For the purposes of examination, the claim will be interpreted to be dependent upon claim 15.
As per claim 16, the phrase “presumably” renders the claim indefinite since the resulting claim does not clearly set for the metes and bounds of the patent protection desired.
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 (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.
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) 1-3, 5, 10, 12, and 18-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP2014006566A) in view of Wong (US 2018/0268289).
As per claim 1, 18, and 19, Sato teaches a controller for controlling a milking robot to move an end-effector in at least one dimension to a desired position (see at least pg. 16, ln. 58-60 for robot with hand and moving in three-dimensional space; claim does not differentiate the structure of a milking robot from any generic robot with an effector) according to a desired velocity profile, the controller comprising:
a feedforward module configured to obtain a set vector specifying the desired velocity profile, and based on the set vector produce at least one predicted control signal (see at least pg. 5, ln. 59 to pg. 6, ln. 6 for FF-NN unit 120 has input of displacement r, velocity s, and acceleration s2 and output of manipulated variable UNN);
a closed-loop controller configured to obtain a modified position and based thereon produce at least one primary control signal for controlling the end-effector to the desired position (see at least pg. 6, ln. 17-23 for displacement error signal input into FB-FN unit 130; see at least pg. 12, ln. 13 for output of UFN);
a first summation module configured to derive at least one modified control signal based on the at least one primary control signal and the at least one predicted control signal, which at least one modified control signal is adapted to be fed to the milking robot for controlling the end-effector to the desired position according to the desired velocity profile (see at least Fig. 4 below for right-most summation module with UNN and UFN as input and outputting U);
PNG
media_image1.png
485
1032
media_image1.png
Greyscale
);
a second summation module configured to derive the modified position based on the desired position and at least one output signal from the milking robot, which at least one output signal reflects a registered position of the end-effector (see at least Fig. 4 above for left-most summation module with displacement r and robot output signal y as inputs and displacement error ep as output),
wherein the feedforward module comprises a trained artificial neural network (see at least pg. 6, ln. 9 for FB-FN unit 130 with neural network), ANN, which comprises:
an input layer configured to obtain the set vector (see at least Fig. 9A below and pg. 6, ln. 4-5 for displacement r, velocity s (dr / dt) and acceleration s2 (d2 r / dt2) are input to the input layer
PNG
media_image2.png
571
1123
media_image2.png
Greyscale
),
an output layer configured to provide the at least one predicted control signal (see at least Fig. 9A above and pg. 6, ln. 6 for output value is UNN), and
a number of hidden layers interconnecting the input layer and the output layer, each of the input, output and hidden layers comprising a respective set of nodes connected to nodes to the respective of neighboring layers (see at least Fig. 9A for input, output, and hidden layers; see at least pg. 9, ln. 50-57 for learning by backpropagation wherein the input of the signal from the plant to be controlled is subtracted from the estimated value of the plant input calculated from the neural network).
Wong teaches that backpropagation training is used to adjust weights between the nodes in a neural network (see at least para. 1)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the device of Sato with the features of Wong because doing so would train the neural network to provide an actual output that is closer to an expected output.
As per claim 2, Wong further teaches wherein the weights of the trained ANN have been determined iteratively via a backpropagation training process comprising: comparing training data that express the registered control signals with the at least one predicted control signal produced by an ANN under training, which ANN under training represents the trained ANN after the training process has been completed (see at least para. 1 for backpropagation training wherein the actual response of the trained neural network is compared with an expected response and then adjustments to the neurons are made to make an actual output that is closer to an expected output).
As per claim 3, Sato teaches wherein the number of hidden layers is between two and six (see at least Fig. 9A above for FB-NN unit 120 uses one hidden layer; see at least Fig. 12A below for FB-FN uses 2 hidden layers
PNG
media_image3.png
704
775
media_image3.png
Greyscale
).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the FB-NN unit 120 of Sato to utilize more than one hidden layer for the neural network if necessary as involves only routine skill in the art to discover optimum or working ranges where general conditions of the claim are disclosed in the prior art.
As per claim 5, Sato further teaches wherein the desired position and the set vector respectively further describe a trajectory to be followed by for the end-effector (see at least pg. 5, ln. 59 to pg. 6, ln. 6 for FF-NN unit 120 has input of displacement r, velocity s, and acceleration s2 and output of manipulated variable UNN; see at least pg. 7, ln. 37 for target trajectory signal and pg. 9, ln. 38 for target trajectory).
As per claim 10, Sato further teaches wherein the trained ANN is implemented by a computer program run on at least one processing unit (see at least pg 5, ln. 13-15 for ICS unit 10 is a computer; see at least pg. 5, ln 49-50 for ICS unit 10 includes FF-NN unit 120).
As per claim 12, Sato futher teaches wherein the closed-loop controller is configured to operate according to a proportional-integral-derivative regulation principle (see at least pg. 10, ln. 33-34 for FB-FN unit 130 is a fuzzy PID controller).
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP2014006566A) in view of Wong (US 2018/0268289) and further in view of Lu (US 2022/0172812).
As per claim 4, Sato teaches wherein the backpropagation training process comprises 20000 epochs (see at least pg. 10, ln. 11-12) instead of the 400 to 1600 epochs as claimed.
However, Lu teaches multiple epochs, including 1000 epochs, may be used for backpropagation training.
It would have been one of ordinary skill in the art before the effective filing date of the invention to modify the controller of modified Sato with the features of Lu because it provides adjustability to the number of epochs that may be selected to arrive at the desired weights/factors and reduce underfitting and overfitting.
Claim(s) 6-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP2014006566A) in view of Wong (US 2018/0268289) and further in view of Tian (US 2013/0307459).
As per claim 6, Tian teaches wherein the set vector describes a velocity for the end-effector, which velocity varies from a start position to the desired position (see at least Fig. 6 for velocity graph depicting constant velocity after acceleration and before deceleration).
It would have been one of ordinary skill in the art before the effective filing date of the invention to modify the controller of modified Sato with the features of Tian because it enables generation of smooth, accurate, and stable point-to-point motion by preventing the robot from abruptly jumping from zero to maximum velocity and controlling velocity changes at a steady, maximum safe rate during ramping phases to avoid jerky motion.
As per claim 7, Tian further teaches wherein the set vector describes the velocity for the end-effector such that the end-effector accelerates during a first period from the start position and decelerates towards the desired position during a second period (see at least Fig. 6 for velocity graph depicting constant velocity after acceleration and before deceleration).
As per claim 8, Tian further teaches wherein the set vector describes a constant velocity for the end-effector between an expiry of the first period and before a beginning of the second period (see at least Fig. 6 for velocity graph depicting constant velocity after acceleration and before deceleration).
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP2014006566A) in view of Wong (US 2018/0268289) and further in view of Khan (US 5,606,646)
As per claim 9, modified Sato is silent regarding what type of trained ANN is used in the fuzzy neural network.
Khan teaches wherein the trained ANN is a recurrent neural network (see at least col. 3, ln. 27-30 for recurrent neural network-based fuzzy logic system).
It would have been one of ordinary skill in the art before the effective filing date of the invention to modify the controller of modified Sato with the features of Khan because no recurrent information is embedded in a feed-forward system and implementing a recurrent neural network with fuzzy logic provides for faster and more accurate system operation since knowledge of prior system states is used during a recall operation.
Claim(s) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP2014006566A) in view of Wong (US 2018/0268289) and further in view of Timofejevs (US 2021/0406664).
As per claim 11, Sato is silent regarding wherein the trained ANN is implemented on at least one neuromorphic circuit.
However, Timofejevs teaches using neuromorphic circuity to realize trained neural networks (see at least para. 10 for neuromorphic integrated circuit that is equivalent to a feed-forward or recurrent neural network)).
It would have been one of ordinary skill in the art before the effective filing date of the invention to modify the controller of modified Sato with the features of Timofejevs because utilizing a neuromorphic circuit can provide improved performance per watt, parallelism, and neuromorphism over conventional systems.
Claim(s) 13-14 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP2014006566A) in view of Wong (US 2018/0268289) and further in view of Andersson (US 2013/0074775).
As per claim 13, Andersson teaches wherein the at least one modified control signal is adapted to control a robotic arm comprising at least three controllable joints comprised in the milking robot (see at least claim 1 for controlling first, second, and third joint actuators of milking robot).
It would have been one of ordinary skill in the art before the effective filing date of the invention to modify the controller of modified Sato with the features of Andersson because it provides for controlling a robot in multiple degrees of freedom for better articulation while performing the task of milking an animal.
As per claim 14, Andersson further teaches wherein the at least one modified control signal is adapted to control at least one electric motor, at least one electro-hydraulic actuator and/or at least one electropneumatic actuator of a robotic arm comprised in the milking robot, such that the at least one electric motor (see at least claim 1 for controlling first, second, and third joint actuators of milking robot; see at least para. 69 for the actuators may be electric actuator; see at least claim 1 for rotation of joints acted on by an actuator).
As per claim 17, Andersson teaches wherein the end-effector comprises at least one of:
a teatcup gripper (see at least para. 16 for gripper configured to grip teatcup),
a teat cleaning unit (see at least para. 36 for robot holding the cleaning cup and attaching the cleaning up to a teat),
a camera unit (see at least para. 40 for sensor 16 is a video camera).
It would have been one of ordinary skill in the art before the effective filing date of the invention to modify the controller of modified Sato with the features of Andersson because it provides for control of tools necessary for a robot to autonomously perform the task of milking an animal.
Claim(s) 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sato (JP2014006566A) in view of Van Berkel (US 2018/0268289) and in view of Andersson (US 2013/0074775) and further in view of Labonville (US 2018/0185105).
As per claim 15, Andersson teaches (see at least para. 69 for the actuators may be electric actuator; see at least claim 1 for rotation of joints acted on by an actuator).
Labonville teaches wherein the at least one modified control signal is adapted to cause a respective control current and/or voltage to be produced, which respective control current and/or voltage is modulated in such a manner that the respective control current and/or voltage operates the at least one electric motor (see at least para. 32 for pulse-width modulated voltage control; see at least para. 36 for pulse-width modulated current control).
It would have been one of ordinary skill in the art before the effective filing date of the invention to modify the controller of modified Sato with the features of Labonville because it was well-known that using pulse width modulation allows for precise motor control by changing the duty cycle and is also more energy efficient by switching between fully on or fully off compared to scaling down continuous current or voltage.
As per claim 16, Andersson further teaches wherein the robotic arm is presumed to comprise at least two controllable joints, and the at least one modified control signal is configured to cause the respective control current to be fed to the at least one electric motor, the at least one electro-hydraulic actuator and/or the electro-pneumatic actuator of the robotic arm such that each of the at least two controllable joints is controlled separately (see at least claim 1 for controlling first, second, and third joint actuators of milking robot; see at least para. 69 for the actuators may be electric actuator; see at least claim 1 for rotation of joints acted on by an actuator).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROBERT NGUYEN whose telephone number is (571)272-4838. The examiner can normally be reached M-F 8AM - 4PM ET.
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, ANNA MOMPER can be reached at (571) 270-5788. 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.
/ROBERT T NGUYEN/PRIMARY EXAMINER, Art Unit 3619
Prosecution Insights