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 (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) 1-2, 5, 7, 10-12, 15, 17, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US Pub No.: 2018/0177619) in view of Chestek (US Pub No.: 2016/0143751).
Regarding claim 1, Zhang (US Pub No.: 2018/0177619) discloses a system for operating a robotic prosthetic limb (prosthetic with control signals and arrays in the abstract), comprising: a brain machine interface (BMI) configured to sense neuron activity of a user evaluation of a brain in [0004] with a brain machine interface in [0111]) and generate a signal indicating the sensed neuron activity (shown in figure 9 as per [0016]); and a robotic prosthetic limb (robotic prosthesis in [0004]) configured to wirelessly communicate with the BMI (wireless communication in [0232]), the robotic prosthetic limb including: one or more motors connected configured to actuate the robotic prosthetic limb (motors in [0033]); a processor (in [0055]); and a memory (in [0061] and [0068]), including instructions stored thereon (in [0070]-[0071]), which when executed by the processor cause the system to: communicate a signal from the BMI to the robotic prosthetic limb (communicating instructions to an output device in [0070]-[0071]. BMI details in [0109]-[0111]), the signal including neuron activity of the user (in [0023]-[0025], signals derived from the motor cortex is disclosed with EEG signals also present); input the neuron activity into four machine learning ([0071] with machine learning per se in [0074]. As a plural of algorithms are disclosed in [0074], four machine learning algorithms are provided for) models configured to generate individual predictions of a movement of the robotic prosthetic limb (predictive models in [0068]); generate a motor control signal (generating a signal in [0055] and [0064]), for each of the one or more motors by averaging the individual predictions ([0152]-[0155] teaches a driving of a prosthesis); and actuate the robotic prosthetic limb in response to the generated motor control signals (in [0152]-[0155]).
Additionally, Chestek (US Pub No.: 2016/0143751) teaches or more motors connected configured to actuate the robotic prosthetic limb (motors in [0048]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the actuators of Chestek to actuate a prosthetic limb as presented in Zhang in order to allow for an individual control of appendages of a prosthetic device, as presented in [0048] and [0053].
Regarding claim 2, Zhang in view of Chestek teach the system of claim 1, wherein Zhang teaches that the BMI includes:a plurality of electrodes are configured to be implanted into the brain of a user and configured to read one or more neural signals generated by the user (implanted electrode in [0041] and [0048]); a processor configured to digitize the neural signal read by the plurality of electrodes (an analogue to digital converter is present in [0049], where the digital signal is used in a signal processor in [0052]); and a first wireless transceiver configured to wirelessly communicate the digitized signal with the robotic prosthetic limb (wireless transceiver in [0232]).
Regarding claim 5, Zhang in view of Chestek teach the system of claim 2, wherein Zhang teaches that the robotic prosthetic limb further includes a second wireless transceiver configured to wirelessly communicate with the first wireless transceiver (as communication may be between multiple devices in a wireless manner in [0232], providing for multiple wireless transceivers are provided for in Zhang).
Regarding claim 7, Zhang in view of Chestek teach the system of claim 6, wherein Zhang teaches that the instructions when executed by the processor further cause the system to: generate a sensory feedback signal (via the feedback controller in [0066]-[0067]), the sensory feedback signal configured to provide training data for the machine learning models ([0066]-[0067]); and train the machine learning models based on the sensory feedback signal (training a machine learning algorithm in [0074]).
Regarding claim 10, Zhang in view of Chestek teach the system of claim 1, wherein Zhang teaches that the four machine learning models use unsupervised learning (as Zhang does not disclose a labeling of data before a machine learning, Zhang is taken to teach unsupervised learning).
Regarding claim 11, Zhang discloses a processor-implemented method for operating a robotic prosthetic limb (prosthetic with control signals and arrays in the abstract, processor detailed in [0052]-[0053]), the method comprising: communicating a signal from a brain machine interface (BMI) to the robotic prosthetic limb, the signal including neuron activity of a user, the (BMI) configured to sense neuron activity of the user (evaluation of a brain in [0004] with a brain machine interface in [0111]) and generate the signal indicating the sensed neuron activity (shown in figure 9 as per [0016]); inputting the neuron activity (in [0023]-[0025], signals derived from the motor cortex is disclosed with EEG signals also present) into four machine learning models configured to generate individual predictions of a movement of a robotic prosthetic limb ([0071] with machine learning per se in [0074] for control of a device. As a plural of algorithms are disclosed in [0074], four machine learning algorithms are provided for), the robotic prosthetic limb configured to wirelessly communicate with the BMI (wireless communication in [0232]), wherein the robotic prosthetic limb includes one or more motors connected configured to actuate the robotic prosthetic limb (motors in [0033]); generating a motor control signal (generating a signal in [0055] and [0064]), for each of the one or more motors by averaging the individual predictions ([0152]-[0155] teaches a driving of a prosthesis); and actuating the robotic prosthetic limb in response to the generated motor control signals (in [0152]-[0155]).
Additionally, Chestek (US Pub No.: 2016/0143751) teaches or more motors connected configured to actuate the robotic prosthetic limb (motors in [0048]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the actuators of Chestek to actuate a prosthetic limb as presented in Zhang in order to allow for an individual control of appendages of a prosthetic device, as presented in [0048] and [0053].
Regarding claim 12, Zhang in view of Chestek teach the processor-implemented method of claim 11, wherein Zhang teaches that the BMI includes:a plurality of electrodes are configured to be implanted into the brain of a user and configured to read one or more neural signals generated by the user (implanted electrode in [0041] and [0048]); a processor configured to digitize the neural signal read by the plurality of electrodes (an analogue to digital converter is present in [0049], where the digital signal is used in a signal processor in [0052]); and a first wireless transceiver configured to wirelessly communicate the digitized signal with the robotic prosthetic limb (wireless transceiver in [0232]).
Regarding claim 15, Zhang in view of Chestek teach the processor-implemented method of claim 12, wherein Zhang teaches that the robotic prosthetic limb further includes a second wireless transceiver configured to wirelessly communicate with the first wireless transceiver (as communication may be between multiple devices in a wireless manner in [0232], providing for multiple wireless transceivers are provided for in Zhang).
Regarding claim 17, Zhang in view of Chestek teach the processor-implemented method of claim 16, with Zhang further comprising: generating a sensory feedback signal, the sensory feedback signal configured to provide training data for the machine learning models; and training the machine learning models based on the sensory feedback signal (feedback details in [0059] and [0066]-[0067]. Machine learning algorithms, as disclosed in [0074], are also seen as requiring a feedback means to create a learning).
Regarding claim 20, Zhang discloses a non-transitory computer readable medium storing a processor-implemented method for operating a robotic prosthetic limb (prosthetic with control signals and arrays in the abstract), the method comprising: communicating a signal from a brain machine interface (BMI) to the robotic prosthetic limb (evaluation of a brain in [0004] with a brain machine interface in [0111], wireless communication in [0232]), the signal including neuron activity of a user (neuron activity sensing implied with the brain evaluation of [0004] and [0023]), the (BMI) configured to sense neuron activity of the user and generate a signal indicating the sensed neuron activity (shown in figure 9 as per [0016]); inputting the neuron activity into four machine learning models ([0071] with machine learning per se in [0074]. As a plural of algorithms are disclosed in [0074], four machine learning algorithms are provided for) configured to generate individual predictions of a movement of a robotic prosthetic limb (predictive models in [0068]), the robotic prosthetic limb configured to wirelessly communicate with the BMI (wireless transceiver in [0232]), wherein the robotic prosthetic limb includes one or more motors connected configured to actuate the robotic prosthetic limb (motors in [0033]); generating a motor control signal (generating a signal in [0055] and [0064]), for each of the one or more motors by averaging the individual predictions ([0152]-[0155] teaches a driving of a prosthesis), for each of the one or more motors by averaging the individual predictions; and actuating the robotic prosthetic limb in response to the generated motor control signals (in [0152]-[0155]).
Additionally, Chestek (US Pub No.: 2016/0143751) teaches non-transitory computer readable medium storing a processor-implemented method for operating a robotic prosthetic limb (in [0109]) one or more motors connected configured to actuate the robotic prosthetic limb (motors in [0048]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the actuators of Chestek to actuate a prosthetic limb as presented in Zhang in order to allow for an individual control of appendages of a prosthetic device, as presented in [0048] and [0053].
Claim(s) 3-4, 6, 14, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US Pub No.: 2018/0177619) in view of Chestek (US Pub No.: 2016/0143751) in further view of Bendett (US Pub No.: 2010/0114190).
Regarding claim 3, Zhang in view of Chestek teach the system of claim 2. However, Zhang does not teach wherein the plurality of electrodes include a flexible, biocompatible coating.
Instead, Bendett (US Pub No.: 2010/0114190) teach wherein the plurality of electrodes include a flexible, biocompatible coating (electrodes for sensing in [0087]-[0088] with a silicone coat in [0054]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the electrodes with the silicone coating applied to them for the purpose of providing an insulation to said electrode (as per [0054]).
Regarding claim 4, Zhang in view of Chestek and Bendett teach the system of claim 3, wherein Bendett teaches that the flexible, biocompatible coating includes silicone (in [0054]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the electrodes with the silicone coating applied to them for the purpose of providing an insulation to said electrode (as per [0054]).
Regarding claim 6, Zhang in view of Chestek teach the system of claim 1. However, Zhang does not teach wherein the robotic prosthetic limb further includes a sensor configured to sense the movement of the robotic prosthetic limb, and wherein the instructions when executed by the processor further cause the system to: access the sensor signal indicating the movement; and compare the sensed movement to the predicted movement.
Instead, Bendett teaches wherein the robotic prosthetic limb further includes a sensor configured to sense the movement of the robotic prosthetic limb (motion sensing system for a prosthesis user in [0027]), and wherein the instructions when executed by the processor further cause the system to: access the sensor signal indicating the movement; and compare the sensed movement to the predicted movement (in [0028], neural signals are cross-correlated with parameters of a model movement, with motion sensing also in [0027]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the comparison of motion to a model for the purpose of allowing for a control of an external device that allow for “better device control” as per [0028] of Bendett.
Regarding claim 14, Zhang in view of Chestek teach the processor-implemented method of claim 13. However, Zhang does not teach wherein the plurality of electrodes include a flexible, biocompatible coating, and wherein the flexible, biocompatible coating includes silicone.
Instead, Bendett teaches wherein the plurality of electrodes include a flexible, biocompatible coating, and wherein the flexible, biocompatible coating includes silicone (electrodes for sensing in [0087]-[0088] with a silicone coat in [0054]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the electrodes with the silicone coating applied to them as presented in Bendett for the purpose of providing an insulation to said electrode (as per [0054]).
Regarding claim 16, Zhang in view of Chestek teach the processor-implemented method of claim 11. However, Zhang does not teach wherein the robotic prosthetic limb further includes a sensor configured to sense the movement of the robotic prosthetic limb, and wherein the method further comprises: accessing the sensor signal indicating the movement; and comparing the sensed movement to the predicted movement.
Instead, Bendett teaches wherein the robotic prosthetic limb further includes a sensor configured to sense the movement of the robotic prosthetic limb (motion sensing system for a prosthesis user in [0027]), and wherein the method further comprises: accessing the sensor signal indicating the movement; and comparing the sensed movement to the predicted movement (in [0028], neural signals are cross-correlated with parameters of a model movement, with motion sensing also in [0027]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the comparison of motion to a model for the purpose of allowing for a control of an external device that allow for “better device control” as per [0028] of Bendett.
Claim(s) 8, 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US Pub No.: 2018/0177619) in view of Chestek (US Pub No.: 2016/0143751) in further view of Ayyad (US Pub No.: 2020/0187841).
Regarding claim 8, Zhang in view of Chestek teach the system of claim 1, wherein generating the prediction of the movement includes: generating a direction and speed prediction for the prosthetic limb by each of the four machine learning models (prediction of an intended movement in [0066], neural network in [0062], machine learning in [0074]).
However, Zhang does not teach averaging each of the direction predictions and the speed predictions of the four machine learning models to generate the motor control signal.
Instead, Ayyad (US Pub No.: 2020/0187841) does teach averaging each of the direction predictions and the speed predictions of the four machine learning models to generate the motor control signal (in [0044] with a control of a prosthesis in [0242]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the machine learning details of Ayyad into Zhang for the purpose of providing a machine learning algorithm that averages signal forces in [0044] in order to find an evoked response in [0085] of Ayyad, which is beneficial as the system of Ayyad allows for an averaging of a large amount of data (in [0086]) that creates a baseline model (in [0087]) that can be used in a device control (in [0242]).
Regarding claim 18, Zhang in view of Chestek teach the processor-implemented method of claim 11. wherein Zhang teaches that generating the prediction of the movement includes: generating a direction and speed prediction for the prosthetic limb by each of the four machine learning models (prediction of an intended movement in [0066], neural network in [0062], machine learning in [0074]).
However, Zhang does not teach averaging each of the direction predictions and the speed predictions of the four machine learning models to generate the motor control signal.
Instead, Ayyad (US Pub No.: 2020/0187841) does teach wherein generating the prediction of the movement includes: generating a direction and speed prediction for the prosthetic limb by each of the four machine learning models; and averaging each of the direction predictions and the speed predictions of the four machine learning models to generate the motor control signal (in [0044] with a control of a prosthesis in [0242]).
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US Pub No.: 2018/0177619) in view of Chestek (US Pub No.: 2016/0143751) in further view of Nazari (US Pub No.: 2024/0225861).
Regarding claim 9, Zhang in view of Chestek teach 9 the system of claim 1, wherein at least one machine learning model of the four machine learning models is a convolutional neural network (neural network in [0054]-[0055] and [0062]).
However, Zhang does not explicitly teach that the neural network is a convolutional neural network. Instead Nazari (US Pub 2024/0225861) teaches a convolutional neural network in the abstract. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the convolutional neural network of Naziri into Zhang for the purpose of providing a neural network with convolutional layers (in [0016]) with the ability to produce a feature map (as per [0062]-[0063]).
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US Pub No.: 2018/0177619) in view of Chestek (US Pub No.: 2016/0143751) in further view of Hewage (US Pub No.: 2021/0365144).
Regarding claim 13, Zhang in view of Chestek teach the processor-implemented method of claim 12, further comprising selecting each of the four machine learning models based on an energy used by each of the four machine learning models and further based on an accuracy of the four machine learning models being within a predetermined threshold.
Instead, Hewage (US Pub No.: 2021/0365144) teaches a further comprising of a selecting of each of the four machine learning models based on an energy used by each of the four machine learning models (selecting of a machine learning technique in [0082]. Power in [0519]) and further based on an accuracy of the four machine learning models being within a predetermined threshold (being performed by the cost function evaluation that evaluates the learning models (ML techniques) based on an error threshold in [0442]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the machine learning selection of Hewage into the combination involving Zhang for the purpose of providing a means to select and evaluate the performance of a machine learning technique, as disclosed in [0082].
Claim(s) 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (US Pub No.: 2018/0177619) in view of Chestek (US Pub No.: 2016/0143751) in further view of Bendett (US Pub No.: 2010/0114190) and Nazari (US Pub No.: 2024/0225861).
Regarding claim 19, Regarding claim 16, Zhang in view of Chestek and Bendett teach the processor-implemented method of claim 11, wherein Zhang discloses at least one machine learning model of the four machine learning models is a convolutional neural network (neural network in [0054]-[0055] and [0062]).
However, Zhang does not explicitly teach that the neural network is a convolutional neural network. Instead Nazari (US Pub No.: 2024/0225861) teaches a convolutional neural network in the abstract. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the convolutional neural network of Naziri into Zhang for the purpose of providing a neural network with convolutional layers (in [0016]) with the ability to produce a feature map (as per [0062]-[0063])
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Do (US Pub No.: 2025/0281750) considered for a brain controlled implantable device in the abstract with a prosthesis shown in figure 1A. Shepherd (US Pub No.: 2019/0056248) considered for soft actuated prosthetic devices in [0007].
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AREN PATEL whose telephone number is (571)272-0144. The examiner can normally be reached 7:00 - 4:30 M-Th.
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, Jerrah C. Edwards can be reached at (408) 918-7557. 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.
/AREN PATEL/Examiner, Art Unit 3774
/JERRAH EDWARDS/Supervisory Patent Examiner, Art Unit 3774