DETAILED ACTION
The amendments filed 4/22/2026 have been entered. Claims 1-18 are pending.
Claim Objections
Claim 11 is objected to because of the following informalities:
Claim 11, line 6: “one” should be deleted in “a location one or position of the joint”
Appropriate correction is required.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4, 7, 9, 10, 14, 18, and 19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Brisson (US Publication No. 2022/0175472).
Brisson teaches:
Re claim 1. A method for controlling a plurality of joints of a robot based on a desired joint state, the method comprising
obtaining information on the desired joint state (Step 900, Fig. 9; and paragraph [0079]: “In Step 900, a desired state is obtained. The desired state may be for one or multiple joints associated with one or more manipulator arm segments of the manipulator assembly, or for the entire manipulator assembly. The desired state may be a desired position, a desired velocity, a desired force, etc. Depending on the implementation of the method for reducing an energy buildup, the desired state may be provided in a Cartesian reference frame or in a joint reference frame.”);
obtaining information on a current joint state (Step 902, Fig. 9; and paragraph [0082]: “In Step 902, an actual state is obtained. The actual state may be an actual position, an actual velocity, an actual torque, an actual force, etc. In one or more embodiments, the actual state, used for the subsequent steps, is represented by a sensed state. The sensed state may be obtained from sensors, e.g., sensors in the joint actuators. Thus, the sensed state may be a measurement of the actual state. The sensed state may alternatively be an estimate of the actual state. For the purpose of the subsequent discussion, the sensed/estimated state and the actual state are treated as equivalents. Depending on the implementation of the method for reducing an energy buildup, the actual state may be provided in a Cartesian space or in a joint space.”);
filtering the desired joint state based on the information on the current joint state and based on state constraints of the robot to obtain information on a filtered desired joint state, wherein the filtered desired joint state complies to the state constraints (Step 904-906, Fig. 9; and paragraphs [0086-0087]: “the difference between the commanded state and the actual state is compared against an error threshold to determine whether the difference exceeds the error threshold.”; “The resulting difference between the commanded state and the actual state may be barely sufficient to reach the saturation limit of the associated actuator, based on the proportional control gain (KP) selected for the actuator, i.e., the commanded state may be set to the minimum distance (or a small multiple of the minimum distance) from the actual state required to obtain saturation. In other words, a barely sufficient difference between the commanded state and the actual state is a difference that drives the servo loop into saturation without the difference being significantly larger than necessary to reach the saturation limit. The updating of the commanded state may be performed in a single time instant or more gradually over time (e.g. over a fraction of a second or multiple seconds, etc.) in a single step or over multiple steps. A multi-step or more gradual updating may be more likely used with algorithms that check the commanded state for unexpected jumps (e.g. seemingly implausible jumps, such as jumps beyond what the system can achieve or an expected maximum for the operating condition). In such cases, a multi-step or more gradual updating would help avoid incorrectly triggering such algorithms.” Paragraphs [0059-0060] teach environmental constrains the robot must comply with. Paragraph [0066] teaches hardware limitations, such as a maximum motor current.); and
controlling the joints of the robot based on the information on the filtered desired joint states (Step 908, Fig. 9; and paragraph [0088]: “the commanded state is applied to control the actual state of the manipulator arm assembly.”).
Re claim 2. Wherein the filtering of the desired state is based on reducing a difference between the filtered desired state and the desired state considering the state constraints (paragraph [0087]: “The updating of the commanded state may be performed in a single time instant or more gradually over time (e.g. over a fraction of a second or multiple seconds, etc.) in a single step or over multiple steps. A multi-step or more gradual updating may be more likely used with algorithms that check the commanded state for unexpected jumps (e.g. seemingly implausible jumps, such as jumps beyond what the system can achieve or an expected maximum for the operating condition). In such cases, a multi-step or more gradual updating would help avoid incorrectly triggering such algorithms.”. As the actual state moves towards the commanded state, the commanded state and the updated commanded state will be closer together.).
Re claim 3. Wherein the filtering is based on minimizing a difference between the filtered desired state and the desired state considering the state constraints (paragraph [0087]: “The updating of the commanded state may be performed in a single time instant or more gradually over time (e.g. over a fraction of a second or multiple seconds, etc.) in a single step or over multiple steps. A multi-step or more gradual updating may be more likely used with algorithms that check the commanded state for unexpected jumps (e.g. seemingly implausible jumps, such as jumps beyond what the system can achieve or an expected maximum for the operating condition). In such cases, a multi-step or more gradual updating would help avoid incorrectly triggering such algorithms.”. As the actual state moves towards the commanded state, the commanded state and the updated commanded state will be closer together.).
Re claim 4. Wherein the difference is determined by a sum or a weighted sum of the differences between the desired joint state and the filtered desired joint state in terms one or more of location or position of the joint, a velocity of the joint, an acceleration of the joint, a jerk of the joint, and/or a higher order derivative of the location or position (step 904, Fig. 9; and paragraph [0085]).
Re claim 7. Wherein the filtering is further based on avoiding an ultimate infeasible state of the robot (paragraphs [0066 and 0073]).
Re claim 9. Wherein the filtering is further based on coupling effects between the joints of the robot and/or non-linear dynamics of the joints of the robot (paragraph [0074]: “the method may also be applied in a Cartesian reference frame, e.g., when applying a similar paradigm to an entire manipulator arm”; paragraph [0076]: “the method may be applied to position, velocity, or force signals, in joint space and/or in Cartesian space.”).
Re claim 10. Wherein the current, the desired and the filtered desired joint states comprise one or more of information on a location or position of the joint, a velocity of the joint, an acceleration of the joint, a jerk of the joint, and/or a higher order derivative of the location or position (paragraph [0076]: “the method may be applied to position, velocity, or force signals”).
Re claim 14. Wherein the filtering is based on state constraints, which are based on a number of multiple subsequent time intervals (paragraph [0108]).
Re claim 18. A non-transitory computer readable medium storing a computer program having program code for performing the method according to claim 1, when the computer program is executed on a computer, a processor, or a programmable hardware component (paragraphs [0061-0064], Fig. 7A and Fig. 9).
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.
Claims 5, 6, 8, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Brisson (US Publication No. 2022/0175472) as applied to claim 4 above, and further in view of Ichnowski et al. (US Publication No. 2021/0365032).
The teachings of Brisson have been discussed above. Brisson fails to specifically teach: (re claim 5) wherein the difference is a mean-square error or a weighted mean square error between the filtered desired state and the desired state considering the state constraints.
Ichnowski teaches, at the abstract and paragraph [0061], using a weighted sum of mean squared error for determining trajectories for an autonomous system while accounting for constraints of the system. This allows close matching of a desired trajectory to an output trajectory, while keeping the output trajectory kinematically and dynamically feasible.
In view of Ichnowski’s teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include, with the method as taught by Brisson, (re claim 5) wherein the difference is a mean-square error or a weighted mean square error between the filtered desired state and the desired state considering the state constraints, with a reasonable expectation of success, since Ichnowski teaches using a weighted sum of mean squared error for determining trajectories for an autonomous system while accounting for constraints of the system. This allows close matching of a desired trajectory to an output trajectory, while keeping the output trajectory kinematically and dynamically feasible.
Brisson further teaches:
Re claim 6. Wherein the filtering comprises determining filter rules for each of the plurality of joints separately (claim 30).
Brisson fails to specifically teach: (re claim 8) wherein the avoiding of the ultimate infeasible state is based on analyzing an effect of a filtered desired jerk on future states.
Ichnowski teaches, at paragraph [0073], enforcing jerk limits on robotic joints so as to reduce wear on the robot, leading to longer lifespans and reduced downtime, as well as reduce travel time, increase construction speed, reduce durations of surgical operations, and so on.
In view of Ichnowski’s teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include, with the method as taught by Brisson, (re claim 8) wherein the avoiding of the ultimate infeasible state is based on analyzing an effect of a filtered desired jerk on future states, with a reasonable expectation of success, since Ichnowski teaches enforcing jerk limits on robotic joints so as to reduce wear on the robot, leading to longer lifespans and reduced downtime, as well as reduce travel time, increase construction speed, reduce durations of surgical operations, and so on.
Brisson fails to specifically teach: (re claim 17) wherein the state constraints comprise kinematic and dynamic constraints of the joint.
Ichnowski teaches, at paragraph [0061], keeping an output trajectory kinematically and dynamically feasible. This ensure that any output may be physically achieved by the system.
In view of Ichnowski’s teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include, with the method as taught by Brisson, (re claim 17) wherein the state constraints comprise kinematic and dynamic constraints of the joint, with a reasonable expectation of success, since Ichnowski teaches, at paragraph [0061], keeping an output trajectory kinematically and dynamically feasible. This ensure that any output may be physically achieved by the system.
Claims 11 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Brisson (US Publication No. 2022/0175472) as applied to claim 4 above, and further in view of Dariush (US Publication No. 2007/0162164).
The teachings of Brisson have been discussed above. Brisson fails to specifically teach: (re claim 11) wherein the current and the filtered desired joint states comprise information on a location or position of the joint, a velocity of the joint, an acceleration of the joint and a jerk of the joint, and
wherein the desired joint state comprises three or less elements of the group of information on a location on or position of the joint, a velocity of the joint, an acceleration of the joint and a jerk of the joint, and
wherein the method further comprises predicting a desired joint state for a subsequent time interval based on the current and the desired joint state, wherein the desired joint state for the subsequent time interval comprises predicted information on one or more elements of the group of a location or position of the joint, a velocity of the joint, an acceleration of the joint and a jerk of the joint, and
wherein the filtering is based on the predicted desired joint state for the subsequent time interval.
Dariush teaches, at Fig. 3, and paragraphs [0053, 0073, and 0083], predicting joint variables q from prediction system 316 based on the fed back joint variables q, constraints 304, and computed task descriptors 312. These values comprise information on a location or position of the joint, a velocity of the joint, and acceleration of the joint and a jerk of the joint as the values may be integrated or derived to determine the further parameters, and thus the values contain information on these further parameters. Paragraph [0037] teaches this predictive capacity can be used to fill in time intervals in which data is not available, thus providing a more temporally complete set of joint variables.
In view of Dariush’s teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include, with the method as taught by Brisson, (re claim 11) wherein the current and the filtered desired joint states comprise information on a location or position of the joint, a velocity of the joint, an acceleration of the joint and a jerk of the joint, and wherein the desired joint state comprises three or less elements of the group of information on a location on or position of the joint, a velocity of the joint, an acceleration of the joint and a jerk of the joint, and wherein the method further comprises predicting a desired joint state for a subsequent time interval based on the current and the desired joint state, wherein the desired joint state for the subsequent time interval comprises predicted information on one or more elements of the group of a location or position of the joint, a velocity of the joint, an acceleration of the joint and a jerk of the joint, and wherein the filtering is based on the predicted desired joint state for the subsequent time interval, with a reasonable expectation of success, since Dariush teaches, at Fig. 3, and paragraphs [0053, 0073, and 0083], predicting joint variables q from prediction system 316 based on the fed back joint variables q, constraints 304, and computed task descriptors 312. These values comprise information on a location or position of the joint, a velocity of the joint, and acceleration of the joint and a jerk of the joint as the values may be integrated or derived to determine the further parameters, and thus the values contain information on these further parameters. Paragraph [0037] teaches this predictive capacity can be used to fill in time intervals in which data is not available, thus providing a more temporally complete set of joint variables.
Brisson fails to specifically teach: (re claim 12) wherein the predicting of the desired joint state for the subsequent time interval comprises using a parametric state estimation based on the desired joint state to obtain the predicted desired joint state for the subsequent time interval.
Dariush teaches, at paragraphs [0043 and 0077] and Figs. 3 and 6, the target system may be described by kinematic parameters or kinematic and dynamic parameters.
In view of Dariush’s teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include, with the method as taught by Brisson, (re claim 12) wherein the predicting of the desired joint state for the subsequent time interval comprises using a parametric state estimation based on the desired joint state to obtain the predicted desired joint state for the subsequent time interval, with a reasonable expectation of success, since Dariush teaches, at paragraphs [0043 and 0077] and Figs. 3 and 6, the target system may be described by kinematic parameters or kinematic and dynamic parameters. Paragraph [0037] teaches the predictive capacity of Dariush can be used to fill in time intervals in which data is not available, thus providing a more temporally complete set of joint variables.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Brisson (US Publication No. 2022/0175472) as modified by Dariush (US Publication No. 2007/0162164) as applied to claim 12 above, and further in view of Kumar et al. (Make Bipedal Robots Learn How to Imitate).
The teachings of Brisson have been discussed above. Brisson fails to specifically teach: (re claim 13) wherein the parametric state estimation uses a Savitzky-Golay algorithm.
Kumar teaches, at the abstract, determining desired joint angles of a robot within physical limits while using a Savitzky-Golay filter to smooth the data. This reduces noise in the dataset.
In view of Kumar’s teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include, with the method as taught by Brisson, (re claim 13) wherein the parametric state estimation uses a Savitzky-Golay algorithm, with a reasonable expectation of success, since Kumar teaches, at the abstract, determining desired joint angles of a robot within physical limits while using a Savitzky-Golay filter to smooth the data. This reduces noise in the dataset.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Brisson (US Publication No. 2022/0175472) as applied to claim 14 above, and further in view of Lalonde et al. (US Publication No. 2018/0172450).
The teachings of Brisson have been discussed above. Brisson fails to specifically teach: (re claim 15) wherein the number of subsequent intervals is configured to allow stopping a motion of a joint based on a maximum deceleration constraint of the joint.
Lalonde teaches, at paragraph [0216], applying a maximum deceleration to a motive source in a robot at the end of a stopping trajectory to ensure safety in the event of a failure to plan at a subsequent planning time interval.
In view of Lalonde’s teachings, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include, with the method as taught by Brisson, (re claim 15) wherein the number of subsequent intervals is configured to allow stopping a motion of a joint based on a maximum deceleration constraint of the joint, with a reasonable expectation of success, since Lalonde teaches, at paragraph [0216], applying a maximum deceleration to a motive source in a robot at the end of a stopping trajectory to ensure safety in the event of a failure to plan at a subsequent planning time interval.
Response to Arguments
Applicant’s arguments, see page 6, filed 4/22/2026, with respect to the objections to claims 11 and 19, the 35 USC § 112 rejection of claim 19, and the 35 USC § 101 rejection of claims 1-19 have been fully considered and are persuasive. The objections to claims 11 and 19, the 35 USC § 112 rejection of claim 19, and the 35 USC § 101 rejection of claims 1-19 have been withdrawn.
Applicant's arguments filed 4/22/2026 have been fully considered but they are not persuasive.
Applicant remarks, on page 7,
Independent claim 1 recites, in part, "...filtering the desired joint state based on the information on the current joint state and based on state constraints of the robot to obtain information on a filtered desired joint state, wherein the filtered desired joint state complies to the state constraints..."
It is respectfully submitted that Brisson fails to disclose this feature. Rather, Brisson describes a commanded state, which may be different than a desired state according to an offset, is compared to an actual state to determine a difference. The difference is compared to an error threshold. If the error exceeds the threshold, the commanded state is updated.
Accordingly, rather than filtering desired joint states to eliminate states that violate constraints, Brisson describes correcting a command to a robot when an actual state does not match the commanded state. Therefore, it is respectfully submitted that claim 1 is allowable over the cited art.
The examiner considers Brisson’s updating of the commanded state to be filtering based on the current joint state and based on state constraints of the robot, as required by claim 1. Brisson states, at paragraphs [0086-0087]:
[0086] In Step 906, the difference between the commanded state and the actual state is compared against an error threshold to determine whether the difference exceeds the error threshold. The absolute difference may be used to make the determination regardless of whether the difference is positive or negative. The error threshold may have been previously established. A reduced error threshold may be preferred for scenarios in which less energy buildup can be accepted, whereas an increased error threshold may be used in scenarios in which more energy buildup can be accepted. An increased error threshold may also be used in scenarios where it is less desirable to alter the commanded state. If the difference reaches or exceeds the error threshold, the execution of the method may proceed with Step 908. If the difference is below the error threshold, the execution of the method may bypass Step 908 to proceed directly with Step 910.
[0087] In Step 908, an updated offset is obtained, and the commanded state is updated using the updated offset. In one or more embodiments, the updated offset is an offset that reduces the difference between the commanded state and the actual state, thereby reducing the energy buildup in the servo loop, associated with the proportional control gain KP operating on the difference between the commanded state and the actual state. More specifically, the updated offset may be computed to accomplish an adjustment of the commanded state toward the actual state, while not completely reaching it. The commanded state may, thus, end up in close proximity to the actual state. The resulting difference between the commanded state and the actual state may be barely sufficient to reach the saturation limit of the associated actuator, based on the proportional control gain (KP) selected for the actuator, i.e., the commanded state may be set to the minimum distance (or a small multiple of the minimum distance) from the actual state required to obtain saturation. In other words, a barely sufficient difference between the commanded state and the actual state is a difference that drives the servo loop into saturation without the difference being significantly larger than necessary to reach the saturation limit. The updating of the commanded state may be performed in a single time instant or more gradually over time (e.g. over a fraction of a second or multiple seconds, etc.) in a single step or over multiple steps. A multi-step or more gradual updating may be more likely used with algorithms that check the commanded state for unexpected jumps (e.g. seemingly implausible jumps, such as jumps beyond what the system can achieve or an expected maximum for the operating condition). In such cases, a multi-step or more gradual updating would help avoid incorrectly triggering such algorithms. Multi-step or more gradual updating may also be more likely used in scenarios where a larger discrepancy between actual and commanded state has built up, such as may be more common during particular mode switches.
[Emphasis added. The original Step numbers have been kept intact, however, the corresponding step numbers used in Fig. 9 are two less than those in paragraphs [0086-0087], i.e. Step 906 in the text corresponds to Step 904 in Fig. 9, Step 908 in the text corresponds to Step 906 in Fig. 9.]
As indicated at Brisson paragraphs [0086-0087], the commanded state is left unmodified if the difference between the commanded state and the actual state is less than an error threshold (Step 904, Fig. 9 / Step 906, [0086]). If the difference exceeds the error threshold, the commanded state is filtered to exclude the portion of the commanded state beyond what would cause the actuator to be saturated (Step 906, Fig. 9 / Step 908, [0087]). This saturation limit is a state constraint of the actuator of the robot - the actuator cannot provide predictable control beyond these performance limits. The Examiner considers this to be filtering as the commanded state is allowed to pass unchanged if the difference between the commanded state and the actual state is less than an error threshold, and the commanded state is modified or altered if the difference between the commanded state and the actual state is greater than an error threshold.
Allowable Subject Matter
Claim 16 would be allowable if rewritten to include all of the limitations of the base claim and any intervening claims.
Conclusion
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 SPENCER D PATTON whose telephone number is (571)270-5771. The examiner can normally be reached Monday to Friday 9:00-5:00 ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Khoi Tran can be reached at (571)272-6919. 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.
/SPENCER D PATTON/Primary Examiner, Art Unit 3656
Prosecution Insights