DETAILEC 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 .
Claim Objections
Claims 1, 12, 14-15, and 19-20 objected to because of the following informalities:
In claim 1, 12, 15, and 19 “subject intending at least one predetermined posture” should read “subject intending to perform at least one predetermined posture.”
In claim 14 and 20, “the neural activity of the subject's brain when the subject intends each of the plurality of postures” should read “the neural activity of the subject's brain when the subject intends to perform each of the plurality of postures.”
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Each of Claims 1-20 has been analyzed to determine whether it is directed to any judicial exceptions.
Step 2A, Prong 1
Each of Claims 1-20 recites at least one step or instruction for receiving neural signals which controls a prosthetic device, which is grouped as a mental process under the 2019 PEG or a certain method of organizing human activity under the 2019 PEG. Accordingly, each of Claims 1-20 recites an abstract idea.
Specifically, Claims 1 and 15 recite:
Claim 1 | “A system comprising:
a plurality of electrodes, each configured to detect a neural signal within a nervous system of a subject (Observation);
a controllable device configured to perform a plurality of actions based on a plurality of native touch and/or gesture commands (Judgement); and
a brain machine interface (BMI) device in communication with the plurality of electrodes and the controllable device, the BMI device comprising:
a non-transitory memory configured to store instructions (Observation) and a Posture Profile comprising a plurality of previously calibrated neural activity patterns of the subject, each of the plurality of previously calibrated neural activity patterns is related to the subject intending at least one predetermined posture, wherein each of the at least one predetermined posture replaces at least one of the plurality of native touch and/or gesture commands of the controllable device; and
a processor configured to implement the instructions to: receive the neural signals from the plurality of electrodes; preprocess the neural signals; scan the preprocessed neural signals to detect a neural activity pattern; determine whether the neural activity pattern is indicative of the subject intending at least one predetermined posture by probabilistically matching the neural activity pattern to at least one previously calibrated neural activity pattern of the subject intending at least one predetermined posture of the plurality of previously calibrated neural activity patterns related to the subject intending the at least one predetermined posture (Evaluation/Opinion); and
when the neural activity pattern is indicative of the subject intending the at least one predetermined posture: determine a command to be input into the controllable device based on the at least one predetermined posture and the Posture Profile of the subject for the controllable device; and send the command to the controllable device to perform an action of the plurality of actions based on the subject intending the at least one predetermined posture (Judgement), wherein the controllable device performs the action upon receiving the command, and wherein the action is not the at least one predetermined posture.”
Claim 15 | “A method comprising:
receiving, by a Brain Machine Interface (BMI) device comprising a processor, neural signals from a plurality of electrodes, wherein each of the plurality of electrodes are configured to detect the neural signals from a nervous system of a subject and to communicate with the BMI device (Observation);
preprocessing, by the BMI device, the neural signals;
scanning, by the BMI device, the preprocessed neural signals to detect a neural activity pattern of the subject (Observation);
determining, by the BMI device, whether the neural activity pattern is indicative of the subject intending at least one predetermined posture by probabilistically matching the neural activity pattern to at least one previously calibrated neural activity pattern of the subject intending at least one predetermined posture of a plurality of previously calibrated neural activity patterns related to the subject intending at least one predetermined posture, wherein the plurality of previously calibrated neural activity patterns are stored in a Posture Profile and each replace at least one of a plurality of native touch and/or gesture commands of a controllable device configured to perform a plurality of actions based on the plurality of native touch and/or gesture commands (Evaluation/Opinion); and
when the neural activity pattern is indicative of the subject intending the at least one predetermined posture:
determining, by the BMI device, a command to be input into the controllable device based on the at least one predetermined posture and the Posture Profile, and
sending, by the BMI device, the command to the controllable device to perform an action of the plurality of actions based on the subject intending the at least one predetermined posture, wherein the controllable device performs the action upon receiving the command, and wherein the action is not the at least one predetermined posture (Evaluation/Opinion).”
Regarding the dependent claims, the following dependent claims are directed to steps that are also abstract or organizing human activity:
These are a few examples, all applications will contain different bullets
Claim 4 contain additional elements.
Claims 7, 8, and 18 include steps that are also abstract as a mental process through additional data gathering or analysis
Claims 2-3, 5, 16, and 17 regard the predetermined posture and electrode placement on the user.
Claims 9, 10, include steps that are also abstract as a mathematical concept.
Claims 11-14, 19, and 20 include steps that are also abstract because a generic computer is executing a set of instructions.
Although the dependent claims are further limiting, they do not recite significantly more than the abstract idea. A narrowing idea is still an abstract idea and an abstract idea with additional well-known equipment/functions are not significantly more than the abstract idea.
Accordingly, as indicated above, each of the above-identified claims recites an abstract idea.
Step 2A, Prong 2
Regarding Claims 1 and 15 (and their respective dependent claims) meets Step 2A, Prong 2 because the above-identified abstract idea in each of independent claims are not integrated into a practical application. The above-identified abstract ideas do not improve the following: function of a particular machine, manufacture or other technology; treatment or prophylaxis for a disease or medical condition; or transforming or reducing of a particular article to a different state or thing (MPEP 2106.04(d)).
Step 2B
Lastly, the claims as a whole are analyzed to determine whether any elements, or in combination, to ensure that they amount to significantly more than the judicial exception itself. However, these claims do not appear to recite additional elements that amount to significantly more than the judicial exception.
The recited additional elements, more specifically plurality of electrodes and brain machine interface (BMI) device, are not significantly more because US Reference 20170265927 A1 provides evidence within paragraph 0003 that they are well-known, routine, and conventional.
The above-identified additional elements, more specifically the controllable device, computer, tablet, mobile device, non-transitory memory, a processor, and display, are generically claimed computer components which enable the above-identified abstract idea(s) to be conducted by performing the basic functions of automating mental tasks. The courts have recognized such computer functions as well understood, routine, and conventional functions when claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. See, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); and OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93.
Therefore, none of the Claims 1-20 amounts to significantly more than the abstract idea itself. Accordingly, Claims 1-20 are not patent eligible and rejected under 35 U.S.C. 101.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4, and 6-20 are rejected under 35 U.S.C. 103 as being unpatentable over Digiovanna et al. (US 20100137734 A1) in view of Principe et al. (US 20160242690 A1), Contreras et al. (US 20150012111 A1) and Patel et al. (US 20190314600 A1).
Regarding Claim 1 Digiovanna a system (BMI system – element 100) comprising:
a plurality of electrodes (micro-electrode array – element 120), each configured to detect a neural signal within a nervous system of a subject (Paragraph 0027, a micro-electrode array 120 electro-chemically coupled to a neural structure of a subject to capture neural activity in the neural structure);
a controllable device (prosthetic device – element 130) configured to perform a plurality of actions (actions – element 115); and
a brain machine interface (BMI) device (BMI agent – element 110) in communication with the plurality of electrodes and the controllable device (Paragraph 0027), the BMI device comprising:
a non-transitory memory (Paragraph 0012) configured to store instructions and a Posture Profile comprising a plurality of previously calibrated neural activity patterns of the subject (Digiovanna | Paragraphs 0027-0029, 0031, 0040; [Examiner’s note, the Posture Profile is the mapping between neural signals and control action. Additionally, the reinforcement learning within the BMI agent, where it associates one or more states of the neural activity with a control action for the prosthetic device]), each of the plurality of previously calibrated neural activity patterns is related to the subject intending at least one predetermined posture (Digiovanna | Paragraphs 0027-0029, 0031, 0040; [Examiner’s note, the Posture Profile is the mapping between neural signals and control action. Additionally, the reinforcement learning within the BMI agent, where it associates one or more states of the neural activity with a control action for the prosthetic device]), wherein each of the at least one predetermined posture replaces at least one of the plurality of native touch and or gesture commands of the controllable device (Digiovanna | Paragraph 0009, 0025-0030; [Examiner’s note, a native gesture commander of the controllable device occurs when a patient who has mobility within their fingers to interact with a touch screen to move a prosthetic arm to move left or right. Within this art, they are replacing the native gesture command through neural signals from the BMI device (110). The BMI device utilizes reinforcement learning to perform the predetermined postures by the prosthetic arm]); and
a processor configured to implement the instructions to (BMI agent – element 110; Paragraph 0012; [Examiner’s note, the processor is found within the BMI agent]):
receive the neural signals from the plurality of electrodes (feedback - element 125; Paragraph 0027);
determine whether the neural activity pattern is indicative of the subject intending at least one predetermined posture by the neural activity pattern to at least one previously calibrated neural activity pattern of the subject intending at least one predetermined posture of the plurality of previously calibrated neural activity patterns related to the subject intending the at least one predetermined posture (Paragraphs 0009, 0041); and
when the neural activity pattern is indicative of the subject intending the at least one predetermined posture (control action – 115; Step 303 of Figure 3; Paragraph 0039):
determine a command to be input into the controllable device based on the at least one predetermined posture and the Posture Profile of the subject for the controllable device (feedback – element 125; Paragraph 0027); and
send the command to the controllable device to perform an action of the plurality of actions based on the subject intending the at least one predetermined posture (control action – 115; Step 303 of Figure 3; Paragraph 0039), wherein the controllable device performs the action upon receiving the command (Step 303 of Figure 3; Paragraph 0039, At step 303, the BMI applies the control action 115 to the prosthetic device in accordance with the learning to control the prosthetic device for a targeted behavior).
Digiovanna is silent in teaching the controllable device’s action is based on a plurality of native touch and/or gesture commands; preprocess the neural signals; scan the preprocessed neural signals to detect a neural activity pattern; probabilistically matching; wherein the action is not the at least one predetermined posture;
Principe teaches preprocess the neural signals (Principe | Figure 3; Paragraph 0074); scan the preprocessed neural signals to detect a neural activity pattern (Principe | Paragraph 0045, 0122, 0126; [Examiner’s note, a spatiotemporal is a neural activity pattern. Preprocessing neural signals are used for extracting the local field potentials (LFPs), then the LFPs are used to create the spatiotemporal patterns (neural activity pattern).]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna to incorporating the teachings of preprocessing from Principe because preprocessing neural signals collected from the BMI device removes any noise from the raw data, and allows the machine learning models to recognize meaningful spatiotemporal patterns. As a result, the spatiotemporal model can clearly illustrate the user’s neural responses within the brain (Principe | Paragraph 0305).
Contreras teaches probabilistic matching (Contreras | Paragraphs 0044, 0046; [Examiner’s note, the exoskeleton and prosthetic limb are used interchangeably]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the system of Digiovanna in view of Principe to incorporate the teachings of probabilistic matching from Contreras because this process strengthens the correlation between the user's intended task and the exoskeleton's execution. As the system learns from past data, such as walking movements, it improves its ability to execute that task more effectively in the future (Contreras | Paragraph 0046, The result obtained from the GMM evaluation in real-time are the probabilities of the current feature vector belonging to the classes (or type of exoskeleton motion such as walk, stop, sit, stand, turns, etc.). The class which has the maximum probability is then selected as the command that is to be transmitted to the exoskeleton to execute that type of motion, hence allowing the user to command the exoskeleton in the BMI framework).
Lastly, Patel teaches controllable device’s action is based on a plurality of native touch and/or gesture commands (Patel | cursor control device – element 114; Paragraph 0040); wherein the action is not the at least one predetermined posture (Patel | input device – element 112; Paragraph 0040; [Examiner’s note, the action is inputted to the controllable device. The action is the command that operates the prosthetic or robotic arm.]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the system of Digiovanna in view of Principe and Contreras to incorporate the teachings of the system from Patel. Doing so will allow for the system to map the neural signals to the desired control for the controllable device (i.e. picking up an item with the prosthetic arm) (Patel | Abstract, Paragraphs 0010, 0064).
Regarding Claim 2, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1, wherein the at least one predetermined posture is a fixed position of at least one body part in space at a time (Digiovanna | Figure 4; Paragraph 0030).
Regarding Claim 3, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1, wherein the at least one predetermined posture comprises at least one specific intended position of a body, a limb (Digiovanna | Paragraph 0030), one or more extremities, one or more appendages, or a part of a face of the subject [Examiner’s note, the claim only requires one out of the group].
Regarding Claim 4, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1. Digiovanna in view of Principe and Contreras does not explicitly teach the controllable device is at least one of a computer, a tablet, a mobile device, or an environmental control element;
Patel teaches the controllable device is at least one of a computer, a tablet, a mobile device, an environmental control element (Patel | cursor control device – element 114; Paragraph 0040; [Examiner’s note, the environmental control element may be a mouse, a track-ball, a track-pad, an optical tracking device, or a touch screen.]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the system of Digiovanna in view of Principe and Contreras to incorporate the teachings of the controllable device from Patel. Doing so will allow for the system to map the neural signals to the desired control for the prosthetic based on the input from the environmental control element (Patel | Abstract, Paragraphs 0010, 0064).
Regarding Claim 6, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1, wherein the plurality of electrodes are each configured to be positioned on and/or implanted into the left precentral gyrus (Digiovanna | Paragraph 0012, The neural structure can be within the motor-cortex; Paragraph 0030, The micro-electrode 120 can be placed on a neural structure (e.g. brain tissue) of the patient to record neural signals which are sent to the BMI agent 110; Paragraph 0034; [Examiner’s note, the left precentral gyrus is located within the motor cortex of the brain.]) of the brain of the subject (Digiovanna | Paragraph 0039, The exemplary method can start in a state wherein a subject (e.g. animal) is fitted with a microelectrode implant connected to a BMI agent and a prosthetic device).
Digiovanna in view of Principe and Patel does not explicitly state the plurality of electrodes are positioned on the left precentral gyrus;
PNG
media_image1.png
433
734
media_image1.png
Greyscale
Contreras teaches the plurality of electrodes are positioned on the left precentral gyrus (Contreras | Figure 8; [Examiner’s note, refer to annotated figure 1 for further clarification.]).
Annotated Figure 1 | Circled electrode (C1) in Figure 8 is the location of the left precentral gyrus. In Table 3 from the “Variability of EEG electrode positions and their underlying brain regions: visualizing gel artifacts from a simultaneous EEG‐fMRI dataset,” discusses the electrode placed on C1 detect neural signals from the left precentral gyrus.
One having an ordinary skill in the art the time the invention was filed would have found it obvious to the system of Digiovanna in view of Principe and Patel to incorporate the teachings of electrode placement on the left precentral gyrus from Contreras because the placement of the electrode on the left precentral gyrus directly targets the primary motor cortex, which is responsible for controlling voluntary movements of the of the body. This enables the most direct and intuitive control of a prosthetic limb via a BMI. Thus, allowing the device to move inordinance with the patient’s desired activity (Contreras | Paragraph 0046).
Regarding Claim 7, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1, wherein the plurality of electrodes comprises at least one multi- channel intracortical microelectrode array (Digiovanna | micro-electrode array – element 120).
Digiovanna in view of Principe and Patel does not explicitly teach the electrode to detect the neural signals from at least a portion of a brain of the subject;
Contreras teaches the electrode to detect the neural signals from at least a portion of a brain of the subject (Contreras | Figure 8; [Examiner’s note, the electrode are place on the left precentral gyrus of the user’s brain and detects neural signals. Refer to annotated figure 1 for further clarification.]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to the system of Digiovanna in view of Principe and Patel to incorporate the teachings of electrode placement from Contreras because the placement of the electrode on the specific portions of the brain will measure specific types neural signals. For example, the electrode placement on the left precentral gyrus directly targets the primary motor cortex, which is responsible for controlling voluntary movements of the of the body. This enables the most direct and intuitive control of a prosthetic limb via a BMI. Thus, allowing the device to move inordinance with the patient’s desired activity (Contreras | Paragraph 0046).
Regarding Claim 8, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1.
Digiovanna in view of Contreras and Patel is silent in teaching wherein the neural signals comprise action potential features, local field potential features;
Principe teaches wherein the neural signals comprise action potential features, local field potential features (Principe | Paragraph 0061), or one or more features derived from the neural signal. One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna in view of Contreras and Patel to incorporate the action potential and local field potential features from Principe because those features aid in the differentiation of normal and abnormal brain states responding to a stimulus (Principe | Paragraph 0047).
Regarding Claim 9, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1.
Digiovanna in view of Contreras and Patel is silent in teaching wherein the probabilistic matching further comprises using a machine learning based multi-state decoder model;
Principe teaches wherein the probabilistic matching further comprises using a machine learning based multi-state decoder model (Principe | Paragraph 0110, 0347, 0361; [Examiner’s note, the multi-state decoder model comprises a linear discriminant analysis combined with a hidden Markov model]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna in view of Contreras and Patel to incorporate machine learning based multi-state decoder model from Principe because doing so allows for more accurately decoding a user's intent; the output from the system becomes more responsive and intuitive. Thus, reducing the user’s frustration and mental effort, as the system better anticipates and responds to their commands (Principe | Paragraph 0110).
Regarding Claim 10, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 9.
Digiovanna in view of Contreras and Patel is silent in teaching the machine learning based multi-state decoder model comprises a linear discriminant analysis combined with a hidden Markov model;
Principe teaches wherein the machine learning based multi-state decoder model comprises a linear discriminant analysis (Principe | Paragraph 0347, 0361) combined with a hidden Markov model (Principe | Paragraph 0110, After training, the state-space models provide a means to explore the temporal evolution and variability of neural responses during single trials. The low-dimensional or discrete state variables, as in hidden Markov models (HMMs), can be visually depicted to track the dynamics of the neural response have shown how a combination of both temporal dynamics and a discrete state can efficiently capture the dynamics in a neural response; [Examiner’s note, both linear discriminant analysis (LDA) and hidden Markov model (HMM) are used to further analysis the training data set.]) or a recurrent neural network. One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna in view of Contreras and Patel to incorporate machine learning based multi-state decoder model from Principe because doing so allows for more accurately decoding a user's intent; the output from the system becomes more responsive and intuitive. Thus, reducing the user’s frustration and mental effort, as the system better anticipates and responds to their commands (Principe | Paragraph 0110).
Regarding Claim 11, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1, wherein the processor further executes the instructions to create a Posture Profile of the subject for the controllable device (Digiovanna | Paragraphs 0027-0029, 0031, 0040; [Examiner’s note, the Posture Profile is the mapping between neural signals and control action]).
Regarding Claim 12, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 11, wherein creating the Posture Profile comprises: linking each of the stored plurality of previously calibrated neural activity patterns of the subject intending at least one predetermined posture with a specific command for the controllable device to perform a specific action (Digiovanna | Paragraphs 0027-0029, 0031, 0040; [Examiner’s note, the Posture Profile is the mapping between neural signals and control action. Additionally, the reinforcement learning within the BMI agent, where it associates one or more states of the neural activity with a control action for the prosthetic device]).
Regarding Claim 13, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 1, wherein the processor further executes the instructions to calibrate the BMI device (Digiovanna | Figure 6; Paragraph 0008, 0042; [Examiner’s note, calibrating the BMI device with machine learning (reinforcement learning) involves using algorithms to learn and correct for measurement inaccuracies based on reference data, as shown in Figure 6. Therefore, the BMI device is calibrated through the reinforcement learning).
Regarding Claim 14, Digiovanna in view of Principe, Contreras, and Patel teaches the system of claim 13, wherein calibration of the BMI device comprises: a plurality of postures (Digiovanna | Figure 4); detecting and recording, via the plurality of electrodes (Digiovanna | micro-electrode array – element 120), the neural activity of the subject when the subject intends each of the plurality of postures as each of the plurality of postures (Digiovanna | Paragraph 0030, The BMI agent 110 can send control actions to the robot appendage to control a movement of the prosthetic limb in accordance with the neural signals. The control actions can be a relative movement of the prosthetic limb in a three-dimensional coordinate space (e.g. up, down, left, right). The patient can observe the prosthetic limb movement and attempt to direct the prosthetic limb to perform a target behavior, such as moving to a specific location).
Digiovanna in view of Patel is silent in teaching displaying, on a display associated with the system; Principe teaches displaying (Principe | brain state display – element 118; Figure 1; Paragraph 0048, 0056), on a display associated with the system (Principe | Paragraph 0056). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna in view of Patel to incorporate the teachings of displaying from Principe because it allows for the user or physician to see the past and current brain states of the user (Principe | Paragraph 0048, The past and current brain state can be displayed on a portable device in 118, or watch-form factor, in conjunction with the landmark points as part of a brain state advisory system).
Additionally, Contreras teaches displaying the plurality of postures (Paragraph 0038, Robotic devices that provide feedback to the user, harness user intent, and provide assist-as-needed functionality (e.g., undesirable gait motion is resisted and assistance is provided toward desired motion) may also enhance motor learning and therefore neurological rehabilitation; Paragraph 0050, feedback is provided to the user by means of a visual display (e.g, smartphone, or small screen/display attached to the exoskeleton or the user's glasses)). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI device of Digiovanna in view of Principe and Patel to incorporate the teachings of displaying the postures from Contreras because the display of postures provides insight to the user real-time support for the patient’s neurological rehabilitation (Contreras | Paragraph 0038, Robotic devices that provide feedback to the user, harness user intent, and provide assist-as-needed functionality (e.g., undesirable gait motion is resisted and assistance is provided toward desired motion) may also enhance motor learning and therefore neurological rehabilitation; Paragraph 0046, The result obtained from the GMM evaluation in real-time are the probabilities of the current feature vector belonging to the classes (or type of exoskeleton motion such as walk, stop, sit, stand, turns, etc.). The class which has the maximum probability is then selected as the command that is to be transmitted to the exoskeleton to execute that type of motion, hence allowing the user to command the exoskeleton in the BMI framework).
Regarding Claim 15, Digiovanna discloses a method comprising:
receiving, by a Brain Machine Interface (BMI) device (BMI agent – element 110) comprising a processor (BMI agent – element 110; Figure 4; Paragraph 0012; [Examiner’s note, the processor is within the BMI agent]), neural signals from a plurality of electrodes (micro-electrode array – element 120), wherein each of the plurality of electrodes are configured to detect the neural signals from a nervous system of a subject and to communicate with the BMI device (Paragraph 0027);
by the BMI device (BMI system – element 100), the neural signals (micro-electrode array – element 120; Paragraph 0027);
scanning, by the BMI device, the neural signals to detect a neural activity pattern of the subject (Paragraph 0032; [Examiner’s note, a spatio-temporal activation of brain states is the neural activity patterns.]);
determining, by the BMI device, whether the neural activity pattern is indicative of the subject intending at least one predetermined posture by the neural activity pattern to at least one previously calibrated neural activity pattern of the subject intending at least one predetermined posture of a plurality of previously calibrated neural activity patterns related to the subject intending at least one predetermined posture ((Paragraph 0009, The neural network can use the one or more rewards to update (learn) the functional mapping, wherein the reward is provided responsive to a prior controlled movement of the prosthetic device, and the state is a spatio-temporal neural firing pattern; Paragraph 0041, The neural network 400 combines the gamma memory with a multi layer perceptron (MLP) to provide spatio-temporal segmentation. As an example, the neural network 400 can contain H nonlinearities and linear output processing elements (PE) associated with control actions (e.g. up, down, left, right movement). The neural network can implement various weight update techniques such as those that use a minimum square error criterion with back-propagation to update the weights during learning; Paragraph 0041, 0043),
wherein the plurality of previously calibrated neural activity patterns are stored in a Posture Profile (Paragraphs 0009, 0041)and each replace at least one of a plurality of native touch and/or gesture commands of a controllable device configured to perform a plurality of actions based on the plurality of native touch and/or gesture commands (Paragraphs 0027-0029, 0031, 0040; [Examiner’s note, the Posture Profile is the mapping between neural signals and control action. Additionally, the reinforcement learning within the BMI agent, where it associates one or more states of the neural activity with a control action for the prosthetic device]); and
when the neural activity pattern is indicative of the subject intending the at least one predetermined posture, sending, by the BMI device, a command to a controllable device to perform an action based on the subject intending the at least one predetermined posture (control action – 115; Step 303 of Figure 3; Paragraph 0039):
determining, by the BMI device, a command to be input into the controllable device based on the at least one predetermined posture and the Posture Profile (feedback – element 125; Paragraph 0027), and
sending, by the BMI device, the command to the controllable device to perform an action of the plurality of actions based on the subject intending the at least one predetermined posture (control action – 115; Step 303 of Figure 3; Paragraph 0039), wherein the controllable device performs the action upon receiving the command (Step 303 of Figure 3; Paragraph 0039, At step 303, the BMI applies the control action 115 to the prosthetic device in accordance with the learning to control the prosthetic device for a targeted behavior).
Digiovanna is silent in teaching preprocessing of neural signals, scan the preprocessed neural signals to detect a neural activity pattern, and probabilistic matching; the action is not the at least one predetermined posture;
Principe teaches preprocess the neural signals (Principe | Figure 3; Paragraph 0074); scan the preprocessed neural signals to detect a neural activity pattern (Principe | Paragraph 0045, 0122, 0126; [Examiner’s note, a spatiotemporal is a neural activity pattern. Preprocessing neural signals are used for extracting the local field potentials (LFPs), then the LFPs are used to create the spatiotemporal patterns (neural activity pattern).]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna to incorporating the teachings of preprocessing from Principe because preprocessing neural signals collected from the BMI device removes any noise from the raw data, and allows the machine learning models to recognize meaningful spatiotemporal patterns. As a result, the spatiotemporal model can clearly illustrate the user’s neural responses within the brain (Principe | Paragraph 0305).
Additionally, Contreras teaches probabilistic matching (Contreras | Paragraphs 0044, 0046; [Examiner’s note, the exoskeleton and prosthetic limb are used interchangeably]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the system of Digiovanna in view of Principe to incorporate the teachings of probabilistic matching from Contreras because this process strengthens the correlation between the user's intended task and the exoskeleton's execution. As the system learns from past data, such as walking movements, it improves its ability to execute that task more effectively in the future (Contreras | Paragraph 0046, The result obtained from the GMM evaluation in real-time are the probabilities of the current feature vector belonging to the classes (or type of exoskeleton motion such as walk, stop, sit, stand, turns, etc.). The class which has the maximum probability is then selected as the command that is to be transmitted to the exoskeleton to execute that type of motion, hence allowing the user to command the exoskeleton in the BMI framework).
Lastly, Patel teaches the action is not the at least one predetermined posture (Patel | input device – element 112; Paragraph 0040; [Examiner’s note, the action is inputted to the controllable device. The action is the command that operates the prosthetic or robotic arm.]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the system of Digiovanna in view of Principe and Contreras to incorporate the teachings of the system from Patel. Doing so will allow for the system to map the neural signals to the desired control for the controllable device (i.e. picking up an item with the prosthetic arm) (Patel | Abstract, Paragraphs 0010, 0064).
Regarding Claim 16, Digiovanna in view of Principe, Contreras, and Patel teaches method of claim 15, wherein the at least one predetermined posture comprises a fixed position of at least one body part of the subject in space at a time (Digiovanna | Figure 4; Paragraph 0030).
Regarding Claim 17, Digiovanna in view of Principe, Contreras, and Patel teaches the method of claim 15, wherein the at least one predetermined posture comprises at least one specific intended position of a body, a limb (Digiovanna | Paragraph 0030), one or more extremities, one or more appendages, or a face of the subject [Examiner’s note, the claim only requires one out of the group].
Regarding Claim 18, Digiovanna in view of Principe, Contreras, and Patel teaches the method of claim 15.
Digiovanna in view of Contreras and Patel is silent in teaching wherein the probabilistic matching further comprises using a machine learning based multi-state decoder model;
Principe teaches wherein the probabilistic matching further comprises using a machine learning based multi-state decoder model (Principe | Paragraph 0110, 0347, 0361; [Examiner’s note, the multi-state decoder model comprises a linear discriminant analysis combined with a hidden Markov model]). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna in view of Contreras and Patel to incorporate machine learning based multi-state decoder model from Principe because doing so allows for more accurately decoding a user's intent; the output from the system becomes more responsive and intuitive. Thus, reducing the user’s frustration and mental effort, as the system better anticipates and responds to their commands (Principe | Paragraph 0110).
Regarding Claim 19, Digiovanna in view of Principe, Contreras, and Patel teaches the method of claim 15, further comprising: creating, by the BMI device, the Posture Profile for the subject for the controllable device (Digiovanna | Paragraphs 0027-0029, 0031, 0040; [Examiner’s note, the Posture Profile is the mapping between neural signals and control action]), wherein the Posture Profile comprises: the plurality of previously calibrated neural activity patterns of the subject intending at least one predetermined posture; and a specific command for the controllable device to perform a specific action matched with each of the plurality of previously calibrated neural activity patterns of the subject intending the at least one predetermined posture (Digiovanna | Digiovanna | Paragraphs 0027-0029, 0031, 0040; [Examiner’s note, the Posture Profile is the mapping between neural signals and control action. Additionally, the reinforcement learning within the BMI agent, where it associates one or more states of the neural activity with a control action for the prosthetic device]).
Regarding Claim 20, Digiovanna in view of Principe, Contreras, and Patel teaches the method of claim 19, further comprising calibrating the BMI device by: a plurality of postures (Digiovanna | Figure 4); detecting and recording, via the plurality of electrodes (Digiovanna | micro-electrode array – element 120), the neural activity of the subject's brain when the subject intends each of the plurality of postures as each of the plurality of postures (Digiovanna | Paragraph 0030, The BMI agent 110 can send control actions to the robot appendage to control a movement of the prosthetic limb in accordance with the neural signals. The control actions can be a relative movement of the prosthetic limb in a three-dimensional coordinate space (e.g. up, down, left, right). The patient can observe the prosthetic limb movement and attempt to direct the prosthetic limb to perform a target behavior, such as moving to a specific location).
Digiovanna is silent in teaching displaying, on a display associated with the system; Principe teaches displaying (Principe | brain state display – element 118; Figure 1; Paragraph 0048, 0056), on a display associated with the system (Principe | Paragraph 0056). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI system of Digiovanna to incorporate the teachings of displaying from Principe because it allows for the user or physician to see the past and current brain states of the user (Principe | Paragraph 0048, The past and current brain state can be displayed on a portable device in 118, or watch-form factor, in conjunction with the landmark points as part of a brain state advisory system).
Additionally, Contreras teaches displaying the plurality of postures (Paragraph 0038, Robotic devices that provide feedback to the user, harness user intent, and provide assist-as-needed functionality (e.g., undesirable gait motion is resisted and assistance is provided toward desired motion) may also enhance motor learning and therefore neurological rehabilitation; Paragraph 0050, feedback is provided to the user by means of a visual display (e.g, smartphone, or small screen/display attached to the exoskeleton or the user's glasses)). One having an ordinary skill in the art the time the invention was filed would have found it obvious to modify the BMI device of Digiovanna in view of Principe to incorporate the teachings of displaying the postures from Contreras because the display of postures provides insight to the user real-time support for the patient’s neurological rehabilitation (Contreras | Paragraph 0038, Robotic devices that provide feedback to the user, harness user intent, and provide assist-as-needed functionality (e.g., undesirable gait motion is resisted and assistance is provided toward desired motion) may also enhance motor learning and therefore neurological rehabilitation; Paragraph 0046, The result obtained from the GMM evaluation in real-time are the probabilities of the current feature vector belonging to the classes (or type of exoskeleton motion such as walk, stop, sit, stand, turns, etc.). The class which has the maximum probability is then selected as the command that is to be transmitted to the exoskeleton to execute that type of motion, hence allowing the user to command the exoskeleton in the BMI framework).
Response to Arguments
Applicant’s arguments and amendments filed 12/04/2025 have been fully considered and they are not entirely persuasive.
The applicant’s argument and amendments have overcome the Claim Objection and the 35 U.S.C. 112b Rejection.
Regarding the 35 U.S.C 101 Rejection, the amendments to the claims do not overcome the rejection because the claims meet Step 2A Prong 1, Step 2B Prong 2, and Step 2B. The amended claims meet Step 2A Prong 1 because the claims discuss instructions to receive neural signals and execute a prosthetic device; the claims are read as a mental process. The amended claims meet Step 2A Prong 2 because the abstract idea in each of independent claims are not integrated into a practical application, refer to Step 2A, Prong 2 for further clarification. Lastly, the amended claims meet Step 2B because the additional elements of plurality of electrodes and brain machine interface are well-known, routine, and conventional as taught in US Reference 20170265927 A1; the additional elements of controllable device, computer, tablet, mobile device, non-transitory memory, a processor, and display are generically claimed computer components.
Regarding the 35 U.S.C. 103 Rejection, the examiner agrees that Digiovanna in view of Principe and Contreras does not teach the claim limitations found in the amended claims. Due to the scope changes from the amended claims, further search and consideration was required. New references, Patel et al. (US 20190314600 A1), are used to modify the system of Digiovanna in view of Principe and Contreras. Please refer to the 35 U.S.C 103 Rejection for further clarification.
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 SRISTI DIVINA GOMES whose telephone number is (571)272-1356. The examiner can normally be reached Monday-Friday: 9AM to 5PM EST.
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, Robert Chen can be reached at 571-272-3672. 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.
/SRISTI DIVINA GOMES/Examiner, Art Unit 3791
/DANIEL L CERIONI/Primary Examiner, Art Unit 3791
Prosecution Insights