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 .
Claims 1-19 are pending for examination. Claims 1, and 17-19 are independent.
Response to Amendment
The office action is responsive to the amendments filed on 05/08/2026. As
directed by the amendments claims 1-13, and 17-19 are amended.
Response to Arguments
Applicant's arguments filed 05/08/2026 have been fully considered.
Applicant arguments regarding 35 U.S.C. § 103:
Applicant’s arguments with respect to claim(s) have been considered but are moot because the new ground of rejection.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (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.
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.
Claim(s) 1-13, and 16-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Saur et al. (US 20220039883 A1, hereinafter "Saur") in view of Kolluri et al. (US 20210362327 A1, hereinafter "Kolluri").
Regarding Claim 1
Saur discloses: A medical arm control system, comprising:
circuitry configured to: ([Para 0050-0053 and Fig 3])
perform a first instance of supervised learning based on first input data and first training data; ([Para 0008-0010, 0042, 0055, and Fig 2] describes virtual surgical robot 32 simulating movements and actions of the moveable robot member 8 and with its kinematic and geometric characteristics by a virtual 3D model of the surgical robot 2. The virtual surgical robot 32 includes at least one of a robot arm, an endoscope, and a surgical tool 14. Examiner interprets the virtual 3D model as a control model, pre-surgical data as input data, and sensor data as training data.)
generate a reward model, for calculation of a reward, based on the to a movement of the medical arm ([Para 0015-0017, 0048-0050, 0055 and Fig 2] discloses calculating a reward model for the robot. Examiner interprets pre-surgical data as second input data used by the machine learning unit.)
execute the reward model based on third input data; calculate the reward based on the execution of the reward model; reinforce the autonomous movement control model based on the calculated reward. ([Para 0048-0050, 0055 and Fig 2] Examiner interprets simulated data as third input data used by the machine learning unit to perform reinforcement learning and control the robot.)
Saur does not explicitly disclose: perform a second instance of supervised learning based on second input data and second training data; generate a reward model, for calculation of a reward, based on the second instance of supervised learning, wherein the reward corresponds to a movement of the medical arm;
However, Kolluri discloses in the same field of endeavor: perform a first instance of supervised learning based on first input data and first training data; ([Para 0068-0074 and Fig 2A] describes trained neural networks (i.e. first instance of supervised learning).)
generate an autonomous movement control model, for autonomous control of a , based on the first instance of supervised learning; ([Para 0068, 0074, 0076 and Fig 2A] describes a control policy initialized/based on the neural networks. Para 0105 describes a robotic arm.)
perform a second instance of supervised learning based on second input data and second training data; ([Para 0068-0074 and Fig 2A] describes multiple neural networks and a training engine 240 with demonstrated action. Under broadest reasonable interpretation examiner interprets both second neural networks and demonstrated action model as a second instance of supervised learning.)
generate a reward model, for calculation of a reward, based on the second instance of supervised learning, wherein the reward corresponds to a movement of the medical arm ([Para 0085-0088 and Fig 2A] describes reinforcement learning subsystem 210 can generate a reward based on demonstrated action. Examiner also interprets the second neural network as a second instance to generating a reward.);
execute the reward model based on third input data; ([Para 0075, 0085-0088 and Fig 2A] describes parameter corrections or corrective actions (i.e. third inputs).)
calculate the reward based on the execution of the reward model; ([Para 0085-0088 and Fig 2A] describes reinforcement learning and reward calculation.) and
reinforce the autonomous movement control model based on the calculated reward. ([Para 0085-0088 and Fig 2A] describes reinforcement learning and reward calculation to control the robot.)
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the control policy disclose by Kolluri into the Surgical System disclose by Saur to disclose a second instance of supervised learning and further generating a reward model. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the control policy disclose by Kolluri as all the references are in the field of machine learning. A person of ordinary skill of the art would have been motivated to perform the combination for being able to train and adjust a reinforcement learning algorithm.
Regarding Claim 2
Saur in view of Kolluri discloses: The medical arm control system according to claim 1, wherein the medical arm is configured to support a medical observation device. ([Para 0008, 0042 and Fig 1] Saur discloses a robot arm with a surgical tool.).
Regarding Claim 3
Saur in view of Kolluri discloses: The medical arm control system according to claim 2, wherein the medical observation device comprises an endoscope. ([Para 0008, 0042 and Fig 1] Saur discloses a robot arm with endoscope.).
Regarding Claim 4
Saur in view of Kolluri discloses: The medical arm control system according to claim 1, wherein the medical arm is configured to support a medical instrument. ([Para 0008, 0042 and Fig 1] Saur discloses a robot arm with a surgical tool.).
Regarding Claim 5
Saur in view of Kolluri discloses: The medical arm control system according to claim 1, wherein the first input data includes information regarding at least one of a position of the medical arm an attitude of the medical arm, a position of a medical instrument, an attitude of the_medical instrument, surgical site information, patient information, or an image of a surgical site. ([Para 0010, 0041, and Fig 2] Saur descries pre-surgical data of a patient.)
Regarding Claim 6
Saur in view of Kolluri discloses: The medical arm control system according to claim 5, wherein each of the first input data and the first training data [[are]]comprises at least one of clinical data, simulated clinical data, or virtual clinical data. ([Para 0008-0010, 0042, 0055, and Fig 2] Saur describes a virtual 3D model of the surgical robot 2. Examiner interprets the virtual 3D model as with pre-surgical data as input data, and sensor data as training data.
Regarding Claim 7
Saur in view of Kolluri discloses: The medical arm control system according to claim 5, wherein the first training data includes information regarding at least one of the position of the medical arm, the attitude of the medical arm, [[and]]or image information of the image of the surgical site. ([Para 0009 and 0042] Saur describes kinematic and geometric characteristics by a virtual 3D model of the surgical robot 2.)
Regarding Claim 8
Saur in view of Kolluri discloses: The medical arm control system according to claim 7, wherein the autonomous movement control model is configured to output outputs information regarding at least one of the position of the medical arm, the attitude of the medical arm, a speed of the medical arm, [[and ]]an acceleration of the medical arm, [[and]]or an imaging condition of the image of the surgical site. ([Para 0042] Saur describes actuator 6 moves the moveable robot member 8 to 6D poses in the surgical field, which means that there are three directions of translational movement and three directions of rotational movement. The actuator 6 changes the position as well as the orientation of the robot member 8. )
Regarding Claim 9
Saur in view of Kolluri discloses: The medical arm control system according to claim 5, wherein the second input data includes at least one of the patient information [[and]]or the image of the surgical site. ([Para 0010, 0041, and Fig 2] Saur descries pre-surgical data of a patient.)
Regarding Claim 10
Saur in view of Kolluri discloses: The medical arm control system according to claim 9, wherein the second input data further includes at least of one of clinical data, simulated clinical data, or virtual clinical data. ([Para 0010, 0041, and Fig 2] Saur descries pre-surgical data of a patient that’s simulated.)
Regarding Claim 11
Saur in view of Kolluri discloses: The medical arm control system according to claim 5, wherein the patient information includes information regarding at least one of a heart rate of a patient, a pulse rate of the patient, a blood pressure of the patient, a blood flow oxygen concentration of the patient,one or more brain waves of the patient, respiration of the patient, sweating of the patient, myoelectric potential associated with the patient, a skin temperature of the patient, [[and]]or a skin electrical resistance of the [[a ]]patient. ([Para 00012-0013, 0044-0045], Saur describes data like blood pressure.)
Regarding Claim 12
Saur in view of Kolluri discloses: The medical arm control system according to claim 5, wherein the surgical site information includes information regarding at least one of a type of an organ of a patient, a position of the organ of the patient, [[and ]]an attitude of [[an ]]the organ of the patient, [[and]]or a positional relationship between the medical instrument and the organ of the patient. ([Para 0006, 0009-0010, 0038-0045], Saur describes surgical field information for changing the robot member's position and/or orientation.)
Regarding Claim 13
Saur in view of Kolluri discloses: The medical arm control system according to claim 1, wherein the circuitry is further configured to control comprising a control unit that controls the medical arm according to based on the reinforced autonomous movement control model. ([Para 0016-0018, 0048-0057, and Fig 1-3] Saur describes controlling surgical robot based on machine learning an (i.e. reinforcement learning).)
Regarding Claim 16
Saur in view of Kolluri discloses: The medical arm control system according to claim 1, wherein the third input data is virtual clinical data. ([Para 0048-0050, 0055 and Fig 2], Saur describes simulated data as third input data used by the machine learning unit.)
Regarding Claim 17
Saur discloses: A medical arm device, comprising:
circuitry configured to: ([Para 0050-0053 and Fig 3])
obtain a reward from a reward model, wherein the reward model is configured to calculate the reward corresponding to a movement of a medical arm; ([Para 0015-0017, 0048-0050, 0055 and Fig 2] discloses calculating a reward model for the robot arm movement.)
reinforce, based on the reward, an autonomous movement control model for autonomous control of the medical arm; ([Para 0015-0017, 0048-0050, 0055 and Fig 2] discloses reinforcement learning for calculating a reward model for the robot arm.) and
store the autonomous movement control model, wherein
the autonomous movement control model is generated based on a first instance of supervised learning, the first instance of supervised learning is based on first input data and first training data, ([Para 0008-0010, 0042, 0055, and Fig 2] describes virtual surgical robot 32 simulating movements and actions of the moveable robot member 8 and with its kinematic and geometric characteristics by a virtual 3D model of the surgical robot 2. The virtual surgical robot 32 includes at least one of a robot arm, an endoscope, and a surgical tool 14. Examiner interprets the virtual 3D model as a control model, pre-surgical data as input data, and sensor data as training data.)
Saur does not explicitly disclose: the reward model is generated based on a second instance of supervised learning, and the second instance of supervised learning is based on second input data and second training data.
However, Kolluri discloses in the same field of endeavor: obtain a reward from a reward model, wherein the reward model is configured to calculate the reward corresponding to a movement of a ([Para 0085-0088 and Fig 2A] describes reinforcement learning subsystem 210 can generate a reward based on movement of the robot arm.); reinforce, based on the reward, an autonomous movement control model for autonomous control of the ([Para 0085-0088 and Fig 2A] describes reinforcement learning subsystem 210 can generate a reward based on movement of the robot arm.); store the autonomous movement control model, wherein the autonomous movement control model is generated based on a first instance of supervised learning, the first instance of supervised learning is based on first input data and first training data, ([Para 0068, 0074, 0076 and Fig 2A] describes a control policy initialized/based on the neural networks. Para 0105 describes a robotic arm.) the reward model is generated based on a second instance of supervised learning, and the second instance of supervised learning is based on second input data and second training data. ([Para 0085-0088 and Fig 2A] describes reinforcement learning subsystem 210 can generate a reward based on demonstrated action. Examiner also interprets the second neural network as a second instance to generating a reward.)
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the control policy disclose by Kolluri into the Surgical System disclose by Saur to disclose a second instance of supervised learning and further generating a reward model. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the control policy disclose by Kolluri as all the references are in the field of machine learning. A person of ordinary skill of the art would have been motivated to perform the combination for being able to train and adjust a reinforcement learning algorithm.
Regarding Claim 18
Saur discloses: A medical arm control method for a medical arm control system, the medical arm control method comprising: ([Para 0050-0053 and Fig 3])
obtaining a reward from a reward model, wherein the reward model is configured to calculate the reward corresponding to a movement of a medical arm; ([Para 0015-0017, 0048-0050, 0055 and Fig 2] discloses calculating a reward model for the robot arm movement.)
reinforcing, based on the reward, an autonomous movement control model forautonomous control of the medical arm, ([Para 0015-0017, 0048-0050, 0055 and Fig 2] discloses reinforcement learning for calculating a reward model for the robot arm.) wherein
the autonomous movement control model is generated based on a first instance of supervised learning, the first instance of supervised learning is based on first input data and first training data, ([Para 0008-0010, 0042, 0055, and Fig 2] describes virtual surgical robot 32 simulating movements and actions of the moveable robot member 8 and with its kinematic and geometric characteristics by a virtual 3D model of the surgical robot 2. The virtual surgical robot 32 includes at least one of a robot arm, an endoscope, and a surgical tool 14. Examiner interprets the virtual 3D model as a control model, pre-surgical data as input data, and sensor data as training data.)
Saur does not explicitly disclose: the reward model is generated based on a second instance of supervised learning, and the second instance of supervised learning is based on second input data and second training data; and controlling the medical arm based on the reinforced autonomous movement control model.
However, Kolluri discloses in the same field of endeavor: obtaining a reward from a reward model, wherein the reward model is configured to calculate the reward corresponding to a movement of a ([Para 0085-0088 and Fig 2A] describes reinforcement learning subsystem 210 can generate a reward based on movement of the robot arm.); reinforcing, based on the reward, an autonomous movement control model forautonomous control of the medical arm [Para 0085-0088 and Fig 2A] describes reinforcement learning subsystem 210 can generate a reward based on movement of the robot arm.), wherein the autonomous movement control model is generated based on a first instance of supervised learning, the first instance of supervised learning is based on first input data and first training data, ([Para 0068, 0074, 0076 and Fig 2A] describes a control policy initialized/based on the neural networks. Para 0105 describes a robotic arm.)
the reward model is generated based on a second instance of supervised learning, and the second instance of supervised learning is based on second input data and second training data; ([Para 0085-0088 and Fig 2A] describes reinforcement learning subsystem 210 can generate a reward based on demonstrated action. Examiner also interprets the second neural network as a second instance to generating a reward.) and controlling the medical arm based on the reinforced autonomous movement control model. ([Para 0085-0088 and Fig 2A] the reinforcement learning 210 described can control the robot.)
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the control policy disclose by Kolluri into the Surgical System disclose by Saur to disclose a second instance of supervised learning and further generating a reward model. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the control policy disclose by Kolluri as all the references are in the field of machine learning. A person of ordinary skill of the art would have been motivated to perform the combination for being able to train and adjust a reinforcement learning algorithm.
Regarding Claim 19
Saur in view of Kolluri discloses: A non-transitory computer readable medium having stored thereon, computer executable instructions, which when executed by a computer, cause the computer to execute operations ([Para 0176, Claim 15, and Fig 1], Kolluri discloses non-transitory computer readable medium.), the operations comprising: (Claim 19 is a program claim that corresponds to claim 1 and the rest of the limitations are rejected on the same ground)
Claim(s) 14 -15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Saur in view of Kolluri and Lendvay et al. (US 20170116873 A1, hereinafter "Lendvay").
Regarding Claim 14
Saur in view of Kolluri discloses: The medical arm control system according to claim 1, wherein the second training data includes
Saur in view of Kolluri does not explicitly disclose: an evaluation score;
However, Lendvay discloses in the same field of endeavor: wherein the second training data includes an evaluation score of a state of the medical ([Para 0047-0052, 0133, 0156, 0165, Fig 4, and Fig 10-12] describes a rating for robotic surgery.)
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of rating robotic surgeries disclosed by Lendvay into the Control method disclosed by Kolluri and the surgical system disclosed by Saur to provide an evaluation score. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of rating robotic surgeries disclosed by Lendvay as all the references are in the field of robotics. A person of ordinary skill of the art would have been motivated to perform the combination for being able to assess the performance of robotic operations to further improve future operations.
Regarding Claim 15
Saur in view of Kolluri and Lendvay discloses: The medical arm control system according to claim 14, wherein the evaluation score is a subjective evaluation score by a doctor. ([Para 0047-0052, 0133, 0156, 0165, Fig 4, and Fig 10-12] Lendvay describes a rating for robotic surgery can be from an expert reviewer (i.e. surgeon).)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Leviney et al. ("End-to-End Training of Deep Visuomotor Policies") describes a supervised learning and reinforcement learning model for controlling a robotic arm.
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TEWODROS E MENGISTU whose telephone number is (571)270-7714. The examiner can normally be reached Mon-Fri 9:30-5:30.
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, ABDULLAH KAWSAR can be reached at (571)270-3169. 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.
/TEWODROS E MENGISTU/ Examiner, Art Unit 2127
Prosecution Insights