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 . In the event the determination of the status of the application as subject to 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.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 27 January 2026 has been entered.
Status of Claims
Claims 1-7, 10-17, and 20 are currently pending and are being hereby examined herein. Claims 1 and 11 are currently amended.
Response to Amendment / Remarks
Any reference to the prior office action refers to the final rejection dated 15 December 2025.
Applicant’s arguments with respect to the prior art of record from the prior office action have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Joint Inventors
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Information Disclosure Statement
The information disclosure statement submitted on 27 January 2026 was considered by the examiner.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 1-7, 10-17, and 20 are rejected under 35 U.S.C. 112(a) as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, at the time the application was filed, had possession of the claimed invention. Claim 1 has been amended to recite “for the object recognition error being detected, performing, by the processor, a recovery process to address the object recognition error by automatically detecting existence of a falsely divided object or a falsely undivided object based on comparing current object recognition results against prior object recognition results, and responsively adjusting the weights assigned to the first probability images and the second probability images without human intervention to improve the object recognition”. No support was found for this limitation in the original disclosure. As can be seen in FIG. 8, the RGB/depth weights are updated based on a human user completing the remote recovery request (S818/S820/S284). Therefore, there is no support for “responsively adjusting the weights assigned to the first probability images and the second probability images without human intervention to improve the object recognition”. Additionally, there is no support for “responsively adjusting the weights” at all “based on comparing current object recognition results against prior object recognition results”, all embodiments show that sending a request to the human operator is the embodiment that results in adjusting weights. The historical results (see, for example, paragraph [0031] and FIG. 5) are an alternate solution and not disclosed as being part of the training to update weights. Claim 11 has been similarly amended and is therefore rejected for the same reasons as Claim 1. Claims 2-7, 10, 12-17, and 20 are dependent on Claim 1 or Claim 11 and are therefore rejected for the same reasons as Claim 1.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 3, 6, 13, and 16 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, regards as the invention. One of ordinary skill in the art would not be able to determine the metes and bounds of these claims because Claims 1 and 11 recite “without human intervention” but Claims 3 and 13 claim user intervention for the same process. Claims 6 and 16 are rejected for being dependent on a rejected claim. Appropriate corrections are required.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claims 3, 6, 13, and 16 are rejected 35 U.S.C. 112(d) as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. These claims either do not contain “without human intervention” (in which case they fail to include all the limitations from which they depend) or do include “without human intervention” (in which case they aren’t actually claiming anything because the limitations would not exist). Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements. Appropriate corrections are required.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-2, 4-5, 10-12, 14-15, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Pub. No. 2021/0122586 (Sun et al., hereinafter, Sun) in view of IEEE Article Adaptive Fusion for RGB-D Salient Object Detection (Wang et al., hereinafter, Wang) in further view of IEEE Article Multi-view Self-supervised Object Segmentation (Ma et al., hereinafter, Ma).
Regarding Claim 1, Sun discloses A method for recognizing and unloading a plurality of objects (see at least FIG. 7A), the method comprising:
until the plurality of objects has been unloaded (see at least [0107] and FIG. 7A: “if more items remain to be singulated (714), a further iteration of steps 702, 704, 706, 708, and 710 is performed”), iteratively performing
collecting, by a processor, object data through a vision sensor comprising red, green and blue (RGB) images and depth images (see at least [0049], [0107], and Fig 7A: “image data is received at 702”; “Computer vision information is generated by merging data from multiple sensors, including one or more of 2D cameras, 3D (e.g., RGBD) cameras, infrared, and other sensors to generate a three-dimensional view of a workspace that includes one or more sorting stations”);
performing, by the processor, object recognition by determining object orientation and object location based on the object data by performing object edge detection… determining the object orientation and the object location… (see at least [0071]-[0072], [0107], and FIG. 7A: “at 302 items to be picked from a chute or other source or receptacle via which items are received at a singulation station are identified. In some embodiments, image data from one or more cameras is used, e.g., by a vision system or module comprising a control computer, to generate a 3D view of the pile or flow of items. Segmentation processing is performed to determine item boundaries and orientation”; “In various embodiments, the plan/strategy is determined based at least in part on one or more of image data, e.g., indicating the size, extent, and orientation of an item, and attributes that may be known, determined, and/or inferred about the item, such as by classifying the item by size and/or item type.”; “At 704, segmentation and item (e.g., type) identification are performed”);
for an object of the plurality of objects being recognized and determined as available for picking, picking up and unloading the object using a robotic device (see at least [0107] and FIG. 7A: “At 708, the model is used to determine grasp strategies and a plan to grasp the next n items from the pile/flow. At 710, the plan is executed”); and
for no object being determined as available for picking (see at least [0113] and FIG. 7C: “at 742 a condition in which no item can currently be grasped is detected. For example, the system may have attempted to determine grasp strategies for items in the pile, but determined that due to flow speed, clutter, orientation, overlap, etc., there is no item for which a grasp strategy having a probability of success greater than a prescribed minimum threshold is currently available”), performing:
determining, by the processor, occurrence of an object recognition error (see at least [0059], [0113], and FIG. 7C: “at 742 a condition in which no item can currently be grasped is detected. For example, the system may have attempted to determine grasp strategies for items in the pile, but determined that due to flow speed, clutter, orientation, overlap, etc., there is no item for which a grasp strategy having a probability of success greater than a prescribed minimum threshold is currently available”; “In various embodiments, an arbitrary mix of items to be singulated may include parcels, packages, and/or letters of a variety of shapes and sizes. Some may be standard packages one or more attributes of which may be known, others may be unknown. Image data is used, in various embodiments, to discern individual items (e.g., via image segmentation). The boundaries of partially occluded items may be estimated, e.g., by recognizing an item as a standard or known type and/or extending visible item boundaries to logical estimated extents (e.g., two edges extrapolated to meet at an occluded corner). In some embodiments, a degree of overlap (i.e., occlusion by other items) is estimated for each item, and the degree of overlap is taken into consideration in selecting a next item to attempt to grasp. For example, for each item a score may be computed to estimate the probability of grasp success, and in some embodiments the score is determined at least in part by the degree of overlap/occlusion by other items. Less occluded items may be more likely to be selected, for example, other considerations being equal.”);
for the object recognition error being detected, performing, by the processor, a recovery process to address the object recognition error…. (see at least [0113] and FIG. 7C: “At 744, in response to the determination at 742, the system uses the robotic arm to attempt to change the state of the pile/flow in a way that makes a grasp strategy available. For example, the robotic arm may be used to gently nudge, pull, push, etc. an item or multiple items into different positions in the pile. After each nudge, the system may reevaluate, e.g., by re-computing the 3D view of the scene to determine if a viable grasp strategy has become available. If it is determined at 746 that a grasp (or multiple grasps each for a different item) has become available, then autonomous operation is resumed at 750. Otherwise, if after a prescribed number of attempts to change the pile/flow state a viable grasp strategy has not become available, then at 748 the system obtains assistance, e.g., from another robot and/or a human worker, the latter via teleoperation and/or manual intervention such as shuffling items in the pile and/or manually picking/placing items until the system determines that autonomous operation can be resumed.”), and
for the object recognition error not being detected, recognizing, by the processor, completion in unloading of the plurality of objects (see at least [0107]: “If at 712 it is determined the attempt is not fully successful (e.g., one or more items failed to be grasped, item not in expected location, flow disrupted or otherwise not as expected) or if more items remain to be singulated (714), a further iteration of steps 702, 704, 706, 708, and 710 is performed, and successive iterations are performed until it is determined at 714 that no more items remain to be singulated”).
Sun does not explicitly disclose determining object orientation and object location based on the object data by performing object edge detection using the RGB images to detect first object boundaries and using the depth images to detect second object boundaries, generating first probability images using the RGB images as input to a first trained machine learning model, generating second probability images using the depth images as input to a second trained machine learning model, assigning weights to the first probability images and the second probability images, combining the first probability images and the second probability images based on the weights to generate a binarized edge map of the plurality of objects, and determining the object orientation and the object location using the binarized edge map and address the object recognition error by automatically detecting existence of a falsely divided object or a falsely undivided object based on comparing current object recognition results against prior object recognition results, and responsively adjusting the weights assigned to the first probability images and the second probability images without human intervention to improve the object recognition.
Wang, in the same field of detecting objects using sensors, and therefore analogous art, teaches determining object orientation and object location based on the object data by performing object edge detection using the RGB images to detect first object boundaries and using the depth images to detect second object boundaries (see at least Figure 2: “A color image and an aligned depth image are, respectively, fed into the RGB saliency prediction stream and the depth saliency prediction stream to get the uni-modal saliency prediction map Srgb and Sd. They are further fused by the saliency fusion module to output the final saliency map Sfused.”), generating first probability images using the RGB images as input to a first machine learning model (see at least Figure 1: (d)), generating second probability images using depth images as input to a second machine learning model (see at least Figure 1: (e)), assigning weights to the first probability images and the second probability images, combining the first probability images and the second probability images based on the weights to generate a binarized edge map of the plurality of objects (see at least Section IV Experimental Results 1) THE EFFECTIVENESS OF THE SALIENCY FUSION MODULE and Figure 5: “When Srgb correctly detects the salient objects, as the scenarios shown in the first two rows, our approach fuses more information from the RGB predictions by highlighting most regions in the switch maps. When objects share similar color appearances with back-grounds but have different depth values, as shown in the third row, our approach suppresses unreliable predictions in Srgb by assigning low weights for these regions in the switch map. Thus, more information from Sd are fused.”), and determining the object orientation and the object location using the binarized edge map (see at least Figure 5: (d)) and address the object recognition error by automatically detecting existence of a falsely divided object or a falsely undivided object… and responsively adjusting the weights assigned to the first probability images and the second probability images to improve the object recognition…. (see at least Section III. THE PROPOSED METHOD: the switch map which is the combination of the RGB prediction map and depth prediction map is trained based on the truth to better find the edges, an edge placement that makes the object too large is a “falsely undivided object” and an edge placement that makes the object too small is “a falsely divided object”).
It would have been obvious, before the effective filing date of the invention, with a reasonable expectation of success, to one having ordinary skill in the art, to substitute the specific object detection of Wang into the Sun because Wang teaches object detection that outperforms other known object detection (see at least Wang abstract).
The Wang and Sun combination does not explicitly teach automatically detecting existence of a falsely divided object or a falsely undivided object based on comparing current object recognition results against prior object recognition results and adjusting the weights …without human intervention to improve the object recognition. Alternatives to human labeled ground truth are well-known in the art. Online training is well-known in the art (Sun discloses online training). Ma, in the same fields of robotics and computer vision, and therefore analogous art, teaches automatically detecting existence of a falsely divided object or a falsely undivided object based on comparing current object recognition results against prior object recognition results (see at least Fig. 2: unsupervised training based on iterative results from multiple views).
Substituting a ground truth determined by the self-supervision of Ma into Wang would result in adjusting the weights …without human intervention to improve the object recognition.
The substitution of a ground truth determined through self-supervision of Ma into Wang would have been obvious, before the effective filing date of the invention, with a reasonable expectation of success, to one having ordinary skill in the art, with the motivation of reducing reliance on labeled data (see at least Ma Introduction).
Regarding Claim 2, the Sun, Wang, and Ma combination teaches the limitations of Claim 1. Furthermore, Sun further discloses wherein the object orientation comprises object dimensions (see at least [0072]: “In addition, in some embodiments, strategies to grasp items may be learned over time, e.g., by the system noting and recording the success or failure of prior attempts to grasp a similar item (e.g., same standard item/packaging type; similar shape, rigidity, dimensions; same or similar shape; same or similar material; position and orientation relative to other items in pile; the extent of item overlap; etc.)”.
Regarding Claim 4, the Sun, Wang, and Ma combination teaches the limitations of Claim 1. Furthermore, Wang teaches (with the same motivation to combine as Claim 1 as this is part of the same substitution) wherein the object recognition is performed using at least one learnable object recognition function (see at least Figure 2).
Regarding Claim 5, the Sun, Wang, and Ma combination teaches the limitations of Claim 4. Furthermore, Wang teaches (with the same motivation to combine as Claim 1 as this is part of the same substitution) wherein training of the at least one learnable object recognition function is performed online or offline (see at least section III. THE PROPOSED METHOD: offline training is described).
Regarding Claim 10, the Sun, Wang, and Ma combination teaches the limitations of Claim 1. Furthermore, Wang teaches (with the same motivation to combine as Claim 1 as this is part of the same substitution) further comprising adjusting the weights assigned to the first probability images and the second probability images by:
for a failed object division being detected, increasing a first weight of the weights or decreasing a second weight of the weights, wherein the first weight is associated with the first probability images and the second weight is associated with the second probability images (see at least section III. THE PROPOSED METHOD: “good detection results are achieved in most scenarios if the algorithm can automatically choose the complimentary predictions from RGB and depth modality”; the ground truth matching RGB makes the weighting increase to RGB, “a failed object division” has edges that do not match the truth and the weights would be adjusted to bring it towards truth in machine learning once the ground truth is provided in the training); and
for a falsely divided object being detected, decreasing the first weight or increasing the second weight (see at least section III. THE PROPOSED METHOD: “good detection results are achieved in most scenarios if the algorithm can automatically choose the complimentary predictions from RGB and depth modality”; the ground truth not matching RGB changes the weight to increase the depth component, “a falsely divided object” has edges that do not match the truth and the weights would be adjusted to bring it towards truth in machine learning once the ground truth is provided in the training).
Regarding Claim 11, this claim is substantially similar to Claim 1 and rejected for the same reasons as Claim 1. However, there are several additional limitations also disclosed by Sun A system for recognizing and unloading a plurality of objects (see at least [0034]: “A robotic system to perform singulation and/or sortation is disclosed”); a robotic device (see at least FIG. 2A: robotic arm 202); and a processor in communication with the robotic device (see at least [0032] and FIG. 2A: control computer 212).
Regarding Claim 12, this claim is substantially similar to Claim 2 and rejected for the same reasons as Claim 2.
Regarding Claim 14, this claim is substantially similar to Claim 4 and rejected for the same reasons as Claim 4.
Regarding Claim 15, this claim is substantially similar to Claim 5 and rejected for the same reasons as Claim 5.
Regarding Claim 20, this claim is substantially similar to Claim 10 and rejected for the same reasons as Claim 10.
Claims 3, 6-7, 13, and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Wang in further view of Ma in further view of U.S. Patent No. 9,486,921 (Straszheim et al., hereinafter, Straszheim).
Regarding Claim 3, the Sun, Wang, and Ma combination teaches the limitations of Claim 1. Furthermore, Sun further discloses wherein performing the recovery process comprises:
sending a recovery request containing the object data to a user (see at least [0063] and [0113]: “control computer 212 sends an alert to obtain assistance from a human operator via teleoperation, e.g., by human operator 220 using teleoperation device 218. In various embodiments, control computer 212 uses image data from cameras such as cameras 214 and 216 to provide a visual display of the scene to human worker 220 to facilitate teleoperation”);
receiving, in response to the recovery request, a correction response from the user… (see at least [0063], [0113], and [0143]-[0145]: “The operator 220 may use the visual display of the scene to identify the item(s) to be grasped and use teleoperation device 218 to control the robotic arm 202 and end effector 204 to pick the item(s) from chute 206 and place each in a corresponding location on conveyor 208.”), and
updating data…based on the correction response… (see at least [0063], [0090], [0113], and FIG. 5A: “In various embodiments, in the event of human intervention, the robotic system observes the human worker (e.g., manual task completion, task completion using a robotic arm and end effector via teleoperation) and attempts to learn a strategy to (better) complete the task in an autonomous mode in future”; “In various embodiments, the process 500 of FIG. 5 is a continuous and ongoing process. As items are picked and placed from the pile, subsequently received image data is processed to identify and determine strategies to grasp more items (502, 504, and 506), and a plan to pick/place items is updated based on the grasp strategies and probabilities (508)”).
The Sun, Wang, and Ma combination does not explicitly teach wherein the correction response comprises at least one selected recognition error area and at least one category of recognition error and updating data for the object recognition based on the correction response and reperforming the object recognition.
Straszheim, in the same field of robotic picking, and therefore analogous art, teaches wherein the correction response comprises at least one selected recognition error area and at least one category of recognition error (see at least column 26 lines 30-45, column 26 lines 55-65, column 27 lines 1-10, and FIG. 3: “Adjustable elements may include, for instance, one or more virtual boundary lines (e.g., corners, edges) of box hypotheses that the control system may have determined with a low confidence level. For example, the control system may have correctly determined the locations of three edges of a box hypothesis, but may have incorrectly determined the fourth edge of the box hypothesis. As such, each of the determined edges may be visually presented to the human user as graphical elements on the remote assistor device and the human user may be able to move the fourth edge to the correct corresponding location in the region and “snap” the fourth edge to one of the correctly-determined edges.”; “Within additional examples, the human user may be able to create new graphical elements and/or delete graphical elements in addition to or alternative to adjusting elements. For instance, the human user may be able to use a touchscreen of the remote assistor device to “draw” a box hypothesis around a box or other object that the control system did not detect”; “Referring back to FIG. 3, at block 308, the control system receives, from the at least one remote assistor device, a plurality of responses to the requesting, where each response includes information indicative of how to perform the manipulation of the respective subset of objects”) and updating data for the object recognition based on the correction response and reperforming the object recognition (see at least column 22 lines 15-25 and column 30 lines 55-65: “a predetermined confidence threshold may dynamically decrease as the control system has been trained to perform tasks with higher confidence and greater precision and accuracy, based on repeated interaction between the control system and the remote assistor devices”; “Further, the GUI includes an option for the human user to either “Accept” the box hypotheses determined by the control system for region 406 or instruct the control system to “Rescan” and thereby determine new box hypotheses”).
Combining providing error information with the response as taught by Straszheim with the Sun, Wang, and Ma combination, would have been obvious, before the effective filing date of the invention, with a reasonable expectation of success, to one having ordinary skill in the art, with the motivation of providing additional truth information that could be used for machine learning.
Regarding Claim 6, the Sun, Wang, Ma, and Straszheim combination teaches the limitations of Claim 3. Furthermore, Straszheim further teaches (with the same motivation to combine as Claim 3) wherein sending the recovery request containing the object data to the user comprises sending the recovery request to a graphic user interface (GUI) for the user to review (see at least FIG. 5 and FIG. 6: GUI 500, GUI 600).
Regarding Claim 7, the Sun, Wang, and Ma combination teaches the limitations of Claim 1. The Sun, Wang, and Ma combination teaches does not explicitly teach Claim 7. Straszheim, in the same field of robotic picking, and therefore analogous art, teaches wherein performing the object recognition comprises performing object confidence calculation on the plurality of objects to generate confidence values, and each confidence value of the confidence values is associated with a corresponding object of the plurality of objects (see at least column 5 lines 20-35, column 30 lines 1-5, and FIG. 5: “As an example task, the control system may attempt to determine, from a model of various boxes present in the robotic manipulator's workspace, various “box hypotheses” (e.g., hypothesized edges, corners, borders, etc. of the boxes that correspond to the actual edges, corners, borders, etc. of the boxes in the workspace) so as to segment the model. If the control system is not confident that a particular box hypothesis is accurate, the control system may request remote assistance with confirming, rejecting, or adjusting the particular box hypothesis.”; “The GUI 500 also includes a visual representation of region 404, box hypotheses that the control system determined for region 404, and confidence “scores” associated with various box hypotheses (e.g., “HIGH”)”);
wherein recognition of an object of the plurality of objects is performed by:
comparing the confidence value of the object against a confidence threshold (see at least column 21 lines 30-67: “Within examples, based on the associated region and task, the confidence score may indicate a level of confidence in how to determine a segmentation that distinguishes boundaries of the subset of objects of the respective region (e.g., a confidence score value of a determined box hypothesis, as described above)”; the confidence scores are described relative to a region, however, it is obvious a region may include only one object and that this could be applied to just one box based on the description in the specification),
for the confidence value of the object being equal to or exceeding the confidence threshold, determining the object as recognized (see at least column 5 lines 30-40 and column 21 lines 55-65: “when the control system's confidence level for a particular box hypothesis is high, the control system may determine that no remote assistance is necessary.”; “On the other hand, if the control system determines that a confidence score associated to a given region is greater than the predetermined confidence threshold, the control system may not request remote assistance with the respective task for the given region”), and
for the confidence value of the object being less than the confidence threshold, determining the object as not being recognized (see at least column 5 lines 20-25 and column 21 lines 50-60: “when the control system has a low confidence level in being able to correctly perform a given task, the control system may identify the given task as a task for which the control system should request remote assistance”; “Within examples, if the control system determines that a confidence score associated to a given region is lower than a predetermined confidence threshold, the control system may identify that the respective task for the given region is a task for which the control system will request remote assistance.”); and
wherein the recovery process further comprises adjusting the confidence threshold (see at least column 22 lines 15-25: “Furthermore, each predetermined confidence threshold may be adjusted automatically or manually. For instance, a predetermined confidence threshold may dynamically decrease as the control system has been trained to perform tasks with higher confidence and greater precision and accuracy, based on repeated interaction between the control system and the remote assistor devices. Additionally or alternatively, a human user may provide instructions for the control system to adjust a predetermined confidence score.”).
Combining confidence threshold adjustment as taught by Straszheim with the Sun, Wang, and Ma combination, would have been obvious, before the effective filing date of the invention, with a reasonable expectation of success, to one having ordinary skill in the art, with the motivation of reducing unnecessary time for additional processing.
Regarding Claim 13, this claim is substantially similar to Claim 3 and rejected for the same reasons as Claim 3.
Regarding Claim 16, this claim is substantially similar to Claim 6 and rejected for the same reasons as Claim 6.
Regarding Claim 17, this claim is substantially similar to Claim 7 and rejected for the same reasons as Claim 7.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXANDRA ROBYN MORFORD whose telephone number is (571)272-6109. The examiner can normally be reached Monday - Friday 8:00 AM - 4:00 PM 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, Thomas Worden can be reached at (571) 272-4876. 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.
/A.R.M./Examiner, Art Unit 3658
/JASON HOLLOWAY/Primary Examiner, Art Unit 3658
Prosecution Insights