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 . This action is made final.
This action is in response to the amendments filed on March 10, 2026.
Claims 1-3, and 5-8 have been amended.
Response to Amendment
The amendment filed March 10, 2026 has been entered. Claims 1-10 remain pending in the application.
Response to Arguments
Regarding the 103 Arguments
Applicant’s arguments with respect to claim(s) 1-10 have been considered but are moot because they were directed to teachings relied upon in the prior rejection for limitations that have since been amended and are not met in the present rejection by newly applied references.
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, and 5-10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Badu et al. (US 20240081938 A1, referred to as Badu), in view of Mungara et al. (US 20250093231 A1, referred to as Mungara), in view of Goldade et al. (US 20250072979 A1, referred to as Goldade), in view of Shelton et al. (US 20220233119 A1, referred to as Shelton), Roh et al. (US 20240398479 A1, referred to as Roh), Barral et al. (US 12367972 B1, referred to as Barral).
Regarding claim 1, Badu teaches (Currently Amended) A surgical robotic system for comprising:
a surgical robot with one or more robotic components including robotic arms coupled to surgical instruments at a patient console, and configured to perform surgical procedures at a surgical site (Badu [0028-0031]: Describes a surgical robotic system including robotic arms coupled to surgical instruments/end effectors and a surgeon console form which the robotic arms and instruments are controlled to perform a surgical procedure at the surgical site.).;
a sensor array coupled to the one or more robotic components, the sensor array configured to detect operational anomalies including microvibration signatures, positional deviations, thermal fluctuations, acoustic emissions, and environmental conditions, the sensor array producing operative data (Badu[0026-0031]: Describes a surgical robot comprising arms with multiple sensors and are integrated into the robotic joints and tools. These sensors provide position, load and other operational measurements. These are used to assist in surgeries and detect anomalies in the system.; [0092-0094]: Describes analyzing sensor measurements to detect anomalous operation of the surgical instrument, including detecting deviations between predicted and measured operational behavior to detect operational anomalies.);
an artificial intelligence (Al) engine coupled to the sensor array, the Al engine configured to provide one or more of: receive operational signature data; analyze the data using a predictive failure model trained to identify mechanical degradation, material fatigue, or impending failure (Badu [0026-0031]: Describes sensors feeding a processor comprising machine learning models and using the robotic instruments.; [0066-0068]: Describes analyzing sensor measurements received form the tool arrays, and uses a machine learned predictive model to predict expected operation and detect anomalies based on differences between predicted and measured operation.; [0073-0079]: Describes detecting abnormal conditions/impending failure of the robotic instrument.)
Although Badu teaches a sensor array operatively coupled to the one or more robotic components, the sensor array configured to detect operational anomalies, it does not include microvibration signatures, positional deviations, thermal fluctuations, acoustic emissions, and environmental conditions.
Mungara teaches, microvibration signatures, positional deviations, thermal fluctuations, acoustic emissions, and environmental conditions([0029-0034]: Describes capturing sound, and vibration data anomalies in a mechanical array component, to identify acute anomalies in the system and adjust based on those anomalies found.; [0038-0046]: Describes that a multi-modal sensor collects sound, vibration and temperature data for identifying anomalies in the mechanical components. The anomalies being detected are in view of the operation of the machine in its environmental environment.; [0052-0055]: Describes acquiring thermal fluctuations received to determine environmental condition shifts.; [0092]: Describes that a sensor can notify a user of a misalignment of a tool and direct the user to correct the issue.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined Badu’s surgical robotic sensor array with Mungara’s sensors detecting vibration, acoustic, thermal and environmental anomaly signatures. Doing so would have enabled the sensors to detect vast anomalies to enhance the systems sensing capabilities, ensuring a streamlined and accurate model.
Mungara also teaches, an artificial intelligence (Al) engine coupled to the sensor array, the Al engine configured to provide one or more of: receive operational signature data; analyze the data using a predictive failure model trained to identify mechanical degradation, material fatigue, or impending failure (Mungara [0003-0013]: Describes receiving operational signature data including sound, vibration and temperature from mechanical components in real time and employing one or more machine learning models to identify anomalies indicative of mechanical wear/degradation and emerging faults, enabling a proactive maintenance before they can worsen.)
Mungara further teaches, generate a predictive maintenance alert prior to substantial impact on surgical performance (Mungara, [0006-0012] and [0039-0042]: Describes generating alerts based on proactive identification of anomalies in mechanical components, wherein anomalies are detected prior to worsening or failure and alerts and recommendations are generated accordingly.)
Although Badu in view of Mungara teaches, microvibration signatures, positional deviations, thermal fluctuations, acoustic emissions, and environmental conditions, and generate a predictive maintenance alert prior to substantial impact on surgical performance. They do not teach, control a dynamic calibration module configured to automatically adjust operational parameters of the one or more robotic components during the surgical procedure based on the predictive maintenance alert without interrupting surgical workflow.
Shelton teaches control a dynamic calibration module configured to automatically adjust operational parameters of the one or more robotic components during the surgical procedure based on the predictive maintenance alert without interrupting surgical workflow (Shelton [0487-0493 Describes a surgical computing system that determines control feature(s)/operational parameter(s) for a surgical instrument and automatically communicates the control feature(s) to the surgical instrument, wherein the surgical instrument modifies its operation based on the control feature(s). The adjustments may occur during a surgical procedure and that operational parameters that may be adjusted include, power level, advancement speed, closure speed, loads, and wait times. The sensing systems, a surgical hub and surgical devices are communicably coupled to implement adjustments.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined Badu’s (surgical robotic anomaly-detection) with Mungara’s mechanical condition monitoring with Shelton’s automatic adjustable framework. Doing so would have enabled the system to detect mechanical failure of robotic components during operation, and adjust accordingly.
Shelton further teaches, a self-healing maintenance engine configured to autonomously initiate preprogrammed corrective mechanical adjustments or activate redundant system components prior to surgeon notification (Shelton [00488-00493]: Describes a system that autonomously determines and implements preprogrammed corrective operational adjustments for a surgical instrument based on sensed conditions, wherein control feature(s)/operational parameters are automatically communicated to the surgical instrument and the surgical instrument modifies its operation accordingly, without requiring surgeon intervention. These corrective adjustments are performed as part of the system operation and may occur prior to any surgeon notification.)
prior to surgeon notification (Shelton [0718], and [1962-1966]: Describes that, if operational parameters are not overridden, the surgical instrument modifies operation based on the determined operational parameters, and further describes predictive decision making in which system adjustments and control system may be preemptively adjusted as part of local response and notification determination, with predictive decision making also influencing notification to a user, thereby teaching corrective action occurring before or without waiting for surgeon notification.); and
to implement redundancy activation protocols including switching operational control to backup actuators (Shelton [0713-0718]: Describes a surgical computing system and/or surgical instrument may, in connection with determine operational parameters, enable pairing or utilization of an additional and/or alternative actuator (remote actuator) to operate the device in addition to or in place of the built-in actuator, and that additional and/or alternative controls may be selectively activated for the user. Communicating determined operational parameters to the surgical instrument, the surgical instrument receiving the indication, and, if the operational parameters are not overridden, modifying operation based upon the received indication of the determined operational parameters. Corresponding to implementing a redundancy activation protocol that includes switching operational control to backup actuators.)
Although Badu in view of Mungara, in view of Shelton teaches, control a dynamic calibration module configured to automatically adjust operational parameters of the one or more robotic components during the surgical procedure based on the predictive maintenance alert without interrupting surgical workflow, a self-healing maintenance engine configured to autonomously initiate preprogrammed corrective mechanical adjustments or activate redundant system components prior to surgeon notification, prior to surgeon notification, and to implement redundancy activation protocols including switching operational control to backup actuators. They do not teach, wherein the dynamic calibration module initiates staged dynamic recalibration of the operational parameters using a virtual twin simulation (digital twin simulation) prior to physical execution of the staged dynamic recalibration.
Roh teaches, wherein the dynamic calibration module initiates staged dynamic recalibration of the operational parameters using a virtual twin simulation (digital twin simulation) prior to physical execution of the staged dynamic recalibration (Roh US 20240398479 A1: [0036-0037, [0138], [0145], [0152-0154], [0168-0169]: Describes obtaining a digital anatomical model and generating an XR surgical simulation environment that includes the digital anatomical model, where a virtual model is used to simulate robotic/surgical steps and generate a plan based on the simulation. IT adjusts a workflow based on comparison to stored workflows and configuring the surgical robot with the adjusted workflow, as well as generating a virtual model, performing simulations using the virtual model to predict outcomes, determining a next step, and modifying the surgical plan based on the simulation before further execution.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined Badu, in view of Mungara, in view of Shelton’s framework, with Roh’s digital twin/XR surgical simulation techniques. Doing so would have enabled the system to improve planning, testing, monitoring, and maintenance of robotic surgical actions.
Roh further teaches, to validate, using the virtual twin simulation (digital twin simulation), at least one candidate corrective mechanical adjustment or candidate recalibration (Roh [0227-0228], and [0256-0261]: Describes creating a patient specific 3D digital twin and displaying the digital twin in an XR surgical simulation environment, where a user selects a tool, performs an action on the digital twin, saves the selected tool and action performed, and iteratively adds additional steps as needed, thereby evaluating candidate actions in the digital twin environment before real-world use. The digital twin serves as the digital counterpart for system simulation, integration, testing, monitoring, and maintenance, and that simulations may be used to generate, modify, select, and verify surgical plans and surgical robot configurations.)
and select a validated one of the at least one candidate corrective mechanical adjustment or the candidate recalibration prior to physical execution (Roh [0228-0231] [0256-0265]: Describes using simulations to generate, modify, and verify surgical plans, selecting a configuration of the surgical robot based on the simulations, and generating future robotic surgical actions for execution according to the intraoperative surgical plan.)
Although Badu in view of Mungara, in view of Shelton, in view of Roh teaches, wherein the dynamic calibration module initiates staged dynamic recalibration of the operational parameters using a virtual twin simulation (digital twin simulation) prior to physical execution of the staged dynamic recalibration, and, to validate, using the virtual twin simulation (digital twin simulation), at least one candidate corrective mechanical adjustment or candidate recalibration. They do not teach, responsive to the predictive maintenance alert.
Goldade teaches, responsive to the predictive maintenance alert (Goldade US 20250072979 [0022], [0029-0030], [0044-0047], and [0052-0055]: Describes a predictive maintenance module that applies one or more machine learning models to operational data and kinematics data to generate inferences relating to predictive maintenance, determines whether those inferences meet action criteria, and generates action data including notifications, API messages, and automated actions, such that subsequent maintenance/corrective actions are initiated in response to the predictive maintenance generated notification/action signal.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined Badu, in view of Mungara, in view of Shelton, in view of Roh’s framework, with Goldade’s predictive maintenance techniques. Doing so would have enabled the system to analyze operational and kinematics data to identify impending maintenance issues and automatically trigger responsive actions before substantial degradation or failure occurs.
Goldade further teaches, redundant sensors, or alternative motion pathways responsive to the predictive maintenance alert (Goldade US 20250072979 [0008], [0011], and [0024]: Describes implementing redundancy activation protocols responsive to the predictive maintenance alert in that the robotically assisted surgical system applies a machine learning model to operational data to determine predictive maintenance related inferences and, responsive to those inferences meeting an action threshold, determines and outputs action data indicative of a preventative maintenance action. The action data may include outputting a notification, outputting an API message to trigger an action, and/or initiating an automated remedial action associated with the robot, and teaches monitoring operation of the robot and generating inferences to facilitate predictive maintenance. Corresponding to a corrective/response actions that are implemented responsive to the predictive maintenance alert.)
Although Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade teaches, responsive to the predictive maintenance alert, and, redundant sensors, or alternative motion pathways responsive to the predictive maintenance alert. They do not teach, by simulating an expected response of the one or more robotic components.
Barral teaches, by simulating an expected response of the one or more robotic components (Barral Col 11 lines 64-67 cont. Col 12, lines 1-24, Col 15, lines 33-67 cont. Col 16 lines 1-11: Describes simulating an expected response of the one or more robotic components because the simulation component is configured to simulate configurations of the robotic arms, project future positions of the robotic arms, determine expected configurations, simulate the anticipated moves of the robotic arms, and determine an adjustment to the robotic arms at the present stage to resolve future complications. )
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined Badu, in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade’s framework with Barral’s expected configuration simulation techniques. Doing so would have enabled the system to simulate the expected future response of the robotic arms, compare present and expected configurations and determine present stage adjustment before a later complication occurs.
Regarding claim 5, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1.
Shelton further teaches, wherein the dynamic calibration module includes a surgeon override feature allowing manual intervention during recalibration operations (Shelton [0717-0718]: Describes a surgeon override feature in which one or more determined/adjusted operational parameters (i.e., adjustment operations) may be overridden by a healthcare professional, including via manual intervention, and the instrument/system may implement the adjusted operational parameters only if they are not overridden)
Roh further teaches, including approval, modification, or cancellation of the staged dynamic recalibration determined using the virtual twin simulation (digital twin simulation) prior to physical execution (Roh [0199], [0228-0231], and [0259-0261]: Describes that virtual simulations may be reviews by a physician to accepts or reject a recommended surgical plan and that the physician may modify the surgical plan pre-operatively or intraoperatively. The simulations may be used to plan future surgical steps and modify surgical plans, that intraoperative virtual simulation may be used to plan future surgical steps and modify surgical plans, and that a digital twin XR simulation environment is sued to perform, save, and add simulated actions prior to execution.).
Regarding claim 6, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1.
Mungara teaches, degradation risk scores, component condition metrics, and suggested maintenance strategies (Mungara [0088-0092]: Describes an interface that presents diagnostic metrics and alerts, including machine health scores, trend analyses, and fault diagnosis recommendations. These scores and analyses indicate the condition of the machinery, quantify anomaly severity/risk, and support maintenance recommendations and prioritization based on urgency/severity.)
Shelton teaches, an augmented reality interface configured to overlay (Shelton [0894-0897] : Describes a surgeon interface, a suggestion overlay, notifications displayed as an overlay, and a augmented reality (AR) or mixed reality overlay on the surgeon interface.)
Roh teaches, on a 3D rendering of the robotic system (Roh [0032], and [0153-0157]: Describes a XR surgical simulation environment including virtual models of the surgical robot and tools, and further teaches that the robotic surgical system generates a 3D rendering of objects/surfaces as a digital representation using computer graphics processing.) and to display predictive analytics generated using the virtual twin simulation (digital twin simulation), the predictive analytics including predicted effects of the staged dynamic recalibration prior to physical execution.
( [0145-0148], and [0168-0169]: Describes generating a virtual model and performing surgical simulations using the virtual model to predict outcomes, where the surgical plan may be modified based on the predicted outcomes of the simulation. The results, including visualizations of the data, may be displayed for viewing by the surgical team or user, and teaches generating predicted outcomes and simulations for physician review. The simulations are performed in an XR surgical simulation environment comprising a digital twin.)
Regarding claim 7, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1.
Mungara teaches, wherein the predictive maintenance alert includes a failure mode classification, confidence score, predicted impact on surgical task fidelity, urgency score, and recommended intervention strategy
(Mungara [0088-0090]: Describes that predictive maintenance alerts may include a failure mode classification for detected anomalies, along with associated confidence and severity/priority scores (e.g., machine health scores) and recommended intervention or maintenance strategies to address the detected condition.)
Although Mungara teaches wherein the predictive maintenance alert includes a failure mode classification, confidence score, urgency score, and recommended intervention strategy. It does not teach, predicted impact on surgical task fidelity.
Badu teaches, predicted impact on surgical task fidelity ([0048-0052]: Describes predicting deviations from expected operation of a surgical robotic instrument based on sensed operational data, which enables assessment of the predicted impact of a detected failure on surgical task execution and performance fidelity.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined Mungara’s classified fault outputs, confidence scores, and recommended intervention with Badu’s surgical robotic system. Doing so would prioritize responses and mitigate impacts on surgical task fidelity. Doing so would have enabled the system, to improve real-time situational awareness and facilitate timely maintenance actions.
Roh teaches, selected based on output of the virtual twin simulation (digital twin simulation) (Roh [0227-0228], and [0259-0261]: Describes that the recommended intervention strategy is selected based on output of a virtual twin simulation since the virtual simulations may be used to generate, modify, and/or verify surgical plans, and that a configuration of the surgical robot is selected based on the simulations. The digital XR surgical simulation environment in which a user performs actions on the digital twin, saves the selected tool and action, and adds additional steps as needed.)
Barral teaches, that simulates at least one of the corrective mechanical adjustments or the redundancy activation protocols prior to surgeon notification (Barral Col 11 lines 64-67 cont. Col 12, lines 1-24, and Col 15, lines 27-67, cont. Col 16, lines 1-12: Teaches that the virtual twin simulation simulates corrective mechanical adjustment since it determines expected configurations of robotic arms, simulating the anticipated moves of the robotic arms, and determining an adjustment to the robotic arms, simulating the anticipated moves of the robotic arms, and determining an adjustment to the robotic arms at the present stage to resolve future complications).
Regarding claim 8, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1.
Shelton teaches, wherein the dynamic calibration module modifies actuation force, motion trajectories, servo gains, torque profiles, damping coefficients, or thermal load distributions in real-time using a staged adjustment strategy to avoid mechanical perturbations (Shelton [0562-0574, and [1033-1035]: Describes that, based on detected or predicted complications, the computing system may generate control signals to alter surgical instrument operational parameters, including closure force, closure velocity, compression rate, load thresholds, tissue creep wait time, and firing speed, and further teaches communicating a determined control feature to the surgical instrument and having the instrument modify its operations based upon the received indication. It also shows dynamic switching between control modes based on monitored usage data during operation.)
Barral teaches, wherein the staged adjustment strategy is determined based on a simulated response of the one or more robotic components in the virtual twin simulation (digital twin simulation) prior to physical execution(Barral Col 11 lines 64-67 cont. Col 12, lines 1-24, and Col 15, lines 27-67, cont. Col 16, lines 1-12: teaches that the staged adjustment strategy is determined based on a simulated response of one or more robotic components prior to physical execution since the simulation component simulates configurations of robotic arms throughout the remainder of the procedure based on present configuration data, projects future positions of the robotic arms, compares present and expected future configurations, simulates anticipated moves of the robotic arms, and determines an adjustment to the robotic arms at the present stage to resolve future complications.)
Regarding claim 9, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1.
Mungara further teaches, wherein the sensor array comprises one or more of accelerometers, strain gauges, piezoelectric sensors, acoustic emission sensors, fiber optic sensors, thermal sensors, humidity sensors, or barometric pressure sensors (Mungara [0031-0032]: Describes that the sensor array may include acoustic sensors (microphone) and accelerometers for vibration capture, and thermal sensors (thermocouples or infrared).)
Regarding claim 10, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1, further comprising a data preprocessing module configured to clean sensor data prior to analysis by the artificial intelligence (AI) engine, the data preprocessing module comprising(Mungara [0008-0009], [0046-0047], and [0055]: Describe a pre-processor that preprocesses received sensor data (sound/vibration/temperature) to remove background noise and correct thermal shifting before feature extraction and anomaly detection/ML analysis.):
a noise reduction submodule configured to apply one or more signal processing techniques selected from the group consisting of low-pass filtering, wavelet denoising, and Kalman filtering (Mungara [0048-0049]: Describes a noise reduction submodule that applies signal processing including wavelet denoising and low-pass filtering to remove background noise form sensor data prior to anomaly/ML analysis.);
an outlier detection submodule configured to identify and exclude anomalous data points using one or more statistical or machine learning methods selected from the group consisting of z- score analysis, isolation forests, and clustering-based anomaly detection (Mungara [0068], and [0075-0077]: Describes identifying anomalies/outliers using statistical metrics and ML-based anomaly detection models such as statistical distribution metrics and adaptive thresholds responsive to real-time data, outlier-oriented statics including MAD and IQR and ML anomaly detection models such as autoencoders and isolation forest for detecting subtle deviations.);
a normalization submodule configured to standardize sensor input features across temporal and spatial dimensions to ensure consistency of AI-based inference (Badu [0099]: Describes normalizing and scaling input telemetry used by the ML model (including torque telemetry and encoder positions), and that the normalized data is used for training/inference processing.);
a missing data handling submodule configured to apply interpolation or imputation methods based on one or more of historical sensor data, real-time contextual cues, or model-based estimation (Shelton [1787]: Describes a missing data handling submodules configured to apply interpolation to data streams, where the system may interpolate data (e.g., measurement data over time) when processing sensor-derived information, which handles missing or incomplete data values prior to downstream analysis.); and
a synchronization submodule configured to temporally align data streams from the sensor array using timestamp correlation or cross-sensor temporal fusion algorithms (Shelton[2381], and [02385-2387]: Describes synchronization processing to temporally align multi-sensor data streams, including providing sensing systems with synchronized timestamps using a master time clock and performing data stream fusion using augmented timestamps and unified timing codes to synchronize asynchronous feeds.; [2422-2424]: Describes synchronization processing including network synchronized timestamps, master time clocks, data stream fusion/fixation, augmented timestamps, and tolerant/overlay timestamp matching, which corresponds to multiple senor data feeds in time.).
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Badu et al. (US 20240081938 A1, referred to as Badu), in view of Mungara et al. (US 20250093231 A1, referred to as Mungara), in view of Goldade et al. (US 20250072979 A1, referred to as Goldade), in view of Shelton et al. (US 20220233119 A1, referred to as Shelton), Roh et al. (US 20240398479 A1, referred to as Roh), Barral et al. (US 12367972 B1, referred to as Barral), in view of Millman et al. (US 8241271 B2, referred to as Millman).
Regarding claim 2, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches the system of claim 1.
Shelton teaches, wherein the self-healing maintenance engine comprises:
a corrective action library mapping specific degradation patterns to corresponding adjustments (Shelton [0825-0829], [1033-1035], and [1592-1594]: Describes storing threshold and action settings in a recovery threshold and event trigger database, which stores corrective action information associated with detected conditions/threshold events in a library. It uses a scoring rubric and corresponding configuration package/recommended setting information, which maps assessed conditions to selected corrective settings. Corresponding adjustments to instrument operating parameters, including energy level, compression rate, load thresholds, closure fore, closure velocity, tissue creep wait time, and firing speed. These corresponds to a corrective action library that maps detected degradation/event conditions to corresponding adjustments.);
redundancy activation protocols including switching operational control to backup actuators, redundant sensors, or alternative motion pathways (Shelton [0714-0718]: Describes that a surgical computing system and/or surgical instrument may enable pairing or utilization of an additional and/or alternative actuator to operate the device in addition to or in placer of the built-0in actuator, and that additional and/or alternative controls may be activated. It further details communicating determined operational parameters to the surgical instrument, the instrument receiving those parameters, and, if the operational parameters are not overridden, the instrument modifying operation based upon the received indication of the determined operational parameters.);
at least one corrective mechanical adjustment from the corrective action library (Shelton [0562-0564], [0825-0829], and [1033-1035]: Describes computing and storing threshold and action settings in a database, selecting corresponding configuration packages based on threshold/scoring output, and generating control signals to alter instrument operational parameters such as closure force, closure velocity, tissue creep wait time, firing speed, load thresholds, and energy level.),
prioritization logic based on urgency scores generated by the AI engine's risk assessment module ([1907-910], and [1917-1920]: Describes that data collection, analysis, and/or a risk model may prioritize incoming data streams, tank them in numerical order, and apply weights based on the prioritization, and that the risk model includes a risk assessment and may indicate a high risk based on the analysis and risk model.);
Roh teaches, a closed-loop feedback system to verify efficacy of corrective actions (Roh [0145], [0153-0154], and [0225]: Describes generating a virtual model and performing simulations using the virtual model to predict outcomes, and that inter-operative data can be computed to the predicted data, and when the difference exceeds a threshold, warnings can be generated and the procedure adjusted. Corresponding to a feedback system that verifies whether a corrective action was effective by comparing actual operative results to expected/predicted results and indicating when the corrective action is insufficient.); the closed-loop feedback system configured to compare post-adjustment operative data from the sensor array to expected outputs generated by the virtual twin simulation (digital twin simulation) for at least one of the corrective mechanical adjustments or the redundancy activation protocols (Roh [0145], [0153-0154], and [0225]: Describes a robotic surgical system that can generate a virtual model and perform simulations using the virtual model to predict outcomes, and that “inter-operative data can be compared to the predicted data” and when different exceed a threshold, warnings may be generated and the procedure adjusted, in a XR/simulated environment for performing such simulations. ; Barral further teaches simulating expected configurations and determine an adjustment to the robotic arms at the present stage to resolve future complications, thereby evidencing the corrective mechanical adjustment branch of the recited comparison.)
and responsive to the closed-loop feedback system indicating insufficient efficacy of the corrective mechanical adjustment (Roh [0145], and [0225]: describes generating a virtual model and performing simulations using the virtual model to predict outcomes, and that interoperative data can be compared to the predicted data and, when the difference exceeds a threshold, warning can be generated and the procedure adjusted.)
Goldade teaches, wherein the self-healing maintenance engine is configured to autonomously select, based on the predictive maintenance alert (Goldade [0008], [0011], and [0024]: Determines whether inferences meet action criteria, and outputs action data including notifications, API triggered actions, and automated remedial actions associated with the robot.),
Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches execute the selected corrective mechanical adjustment prior to surgeon notification… and, execute at least one of the redundancy activation protocols by switching operational control to the backup actuators, redundant sensors, or the alternative motion pathways (As taught above in claim 1)
Although Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, a corrective action library mapping specific degradation patterns to corresponding adjustments; redundancy activation protocols including switching operational control to backup actuators, redundant sensors, or alternative motion pathways; a closed-loop feedback system to verify efficacy of corrective actions; the closed-loop feedback system configured to compare post-adjustment operative data from the sensor array to expected outputs generated by the virtual twin simulation (digital twin simulation) for at least one of the corrective mechanical adjustments or the redundancy activation protocols; and prioritization logic based on urgency scores generated by the AI engine's risk assessment module; wherein the self-healing maintenance engine is configured to autonomously select, based on the predictive maintenance alert, at least one corrective mechanical adjustment from the corrective action library, execute the selected corrective mechanical adjustment prior to surgeon notification, and responsive to the closed-loop feedback system indicating insufficient efficacy of the corrective mechanical adjustment, execute at least one of the redundancy activation protocols by switching operational control to the backup actuators, redundant sensors, or the alternative motion pathways. They do not teach, wherein the robotic surgical instrument is configured to translate along an insertion axis and rotate about the insertion axis, wherein, as the robotic surgical instrument slides along or rotates about the insertion axis, a center point is relatively fixed with respect to the patient console, and one or more robotic arms are moved to maintain or reposition the robotic surgical instrument with respect to the center point.
Millman teaches, wherein the robotic surgical instrument is configured to translate along an insertion axis and rotate about the insertion axis, wherein, as the robotic surgical instrument slides along or rotates about the insertion axis, a center point is relatively fixed with respect to the patient console, and one or more robotic arms are moved to maintain or reposition the robotic surgical instrument with respect to the center point (Col 8 lines 4-39: Describes a robotic surgical instrument which is configured to translate along an insertion axis and rotate about the insertion axis, as it does so, along an insertion axis 215C, the robotic surgical tool may slide into and out from a surgical site and can also rotate about the insertion axis 215C. As the robotic surgical tool slides along or rotates about the insertion axis 215C, the center point 215 is relatively fixed, and that the entire robotic arm is generally moved in order to maintain or re-position back to the center point 215.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined Badu, in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade in view of Barral’s framework with Millman’s instrument configuration. Doing so would have improved stable endoscopic instrument positioning and manipulation about a fixed pivot during minimally invasive robotic surgery.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Badu et al. (US 20240081938 A1, referred to as Badu), in view of Mungara et al. (US 20250093231 A1, referred to as Mungara), in view of Goldade et al. (US 20250072979 A1, referred to as Goldade), in view of Shelton et al. (US 20220233119 A1, referred to as Shelton), Roh et al. (US 20240398479 A1, referred to as Roh), Barral et al. (US 12367972 B1, referred to as Barral), in view of Saget et al. (US 20190122330 A1, referred to as Saget).
Regarding claim 3, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1.
Roh teaches, wherein the simulated data comprises data generated by performing virtual robotic surgical procedures based on historical data describing previous surgical procedures, for training a machine learning model to direct the one or more robotic components during the surgical procedures, and wherein at least a portion of the simulated data is generated in a digital twin environment representing one or more of the robotic components and patient anatomy.
(Roh [0250], [0259-0261], [0272], and [0281-0285]: Describes an XR surgical simulation environment including virtual models of surgical tools, a virtual model of a surgical robot, and a a3D digital anatomical twin of a patient, where virtual surgical actions are performed and simulated in that environment. It adjusts a surgical workflow based on stored reference workflows and stored historical workflows, and uses the system for pre-operative training to simulate surgical steps and train ML systems, with an ML model trained to provide surgical workflows based on stored historical workflows and used by the surgical robot or AI to control the surgical robot.)
However, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches do not teach, wherein the Al engine utilizes a hybrid deep learning architecture comprising at least one of a recurrent neural network (RNN), convolutional neural network (CNN), or graph neural network (GNN) trained on historical, simulated, and real-time intraoperative data.
Saget teaches, wherein the Al engine utilizes a hybrid deep learning architecture comprising at least one of a recurrent neural network (RNN), convolutional neural network (CNN), or graph neural network (GNN) trained on historical, simulated, and real-time intraoperative data
(Saget [0076-0079]: Describes an AI enabled surgical guidance computing platform including one or more artificial intelligence engines used to analyze/interpret medical images and provide guidance.;[0091-0097], [0100-0105], and [0154-0157]: Describes the AI system as a multi-module deep learning platform using multiple trained predication engines/classifiers and weighted contributions. Deep learning approaches including convolutional neural networks for image classification and outcome prediction are used in the platform. Historical datasets are used to train the AI engines including medical image datasets with known outcomes, preoperative/postoperative image datasets, outcomes datasets, and literature/study datasets.; [0080-0085], [0101-0103], and [0158-0160]: Describes receiving and processing real-time intraoperative data, including intraoperative fluoroscopic images, intraoperative workflows and dynamically updated guidance indicators based on changing intraoperative images.)
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined the surgical architecture of Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches with the surgical robotic control of Saget. Doing so would have enabled the system to improve closed loop control robustness and reduce control error/instability during surgical manipulation.
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Badu et al. (US 20240081938 A1, referred to as Badu), in view of Mungara et al. (US 20250093231 A1, referred to as Mungara), in view of Goldade et al. (US 20250072979 A1, referred to as Goldade), in view of Shelton et al. (US 20220233119 A1, referred to as Shelton), Roh et al. (US 20240398479 A1, referred to as Roh), Barral et al. (US 12367972 B1, referred to as Barral), in view of Flanagan et al. (US 20220083911 A1, referred to as Flanagan).
Regarding claim 4, Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches, the system of claim 1.
However, they do not teach, wherein the predictive failure model is updated using federated and online learning across multiple robotic systems, with differential privacy applied to protect sensitive surgical data by sharing only model updates and not raw data.
Flanagan teaches, wherein the predictive failure model is updated using federated and online learning across multiple robotic systems, with differential privacy applied to protect sensitive surgical data by sharing only model updates and not raw data (Flanagan [0001-0003], and [0039-0043]: Describes updating a machine learning model using federated learning across multiple distributed devices/systems, where a master model is distributed to multiple client devices that compute local model updated and return those updated for aggregation.; [[0031-0034]: Describes that raw user data remains local on the client device and that the system shares only model updated (not raw data) with the backend server.; [0034-0036, and [0049]: Describes applying differential privacy to protect sensitive data by encoding the model updated on the client device (hashing/randomization) before transmission to the backend server.; [0010], [0044-0047], and [0050]: Describe that the backend server receives a plurality of differential privacy encoded model updates, aggregates them, and updated the master model, which is then redistributed and the process continues (continual/online-style updating).).
It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to have combined the surgical architecture of Badu in view of Mungara, in view of Shelton, in view of Roh, in view of Goldade, in view of Barral teaches with the machine learning techniques of Flanagan. Doing so would have enabled the system to share only differentially private model updates other than raw data, reducing privacy risk and permit collaborative model improvement across multiple sites.
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 DONALD T RODEN whose telephone number is (571)272-6441. The examiner can normally be reached Mon-Thur 8:00-5:00 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, Omar Fernandez Rivas can be reached at (571) 272-2589. 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.
/D.T.R./Examiner, Art Unit 2128
/OMAR F FERNANDEZ RIVAS/Supervisory Patent Examiner, Art Unit 2128