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 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis 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.
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.
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 05/19/2026 has been entered.
Status of Claims
This action is in response to Applicant’s Request for Continued Examination filed on 05/19/2026. Claims 1-20 are pending and examined below.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1-12, 14-17, and 19-20 are rejected under 35 U.S.C. 103 as being obvious over Nie et al., US 20240319750 A1, herein referred to as Nie, and in view of Sykora et al., US 20210248460 A1, herein referred to as Sykora.
Regarding claim 1, Nie discloses deploying a plurality of nodes over a predetermined space, wherein each of the plurality of nodes is associated with a corresponding one or more regions of the predetermined space, and wherein each of the plurality of nodes is trained based on a predetermined set of traffic rules (Figs. 3A-3B, Paragraphs 0051, 0089-0091; multiple vertices (nodes) may be established in a predetermined space; of the multiple vertices (nodes) in the predetermined space, a portion are established for each corresponding floor, where each floor may be considered as one or more regions of the predetermined space; a global critic may be established for all floors and vertices (nodes) within the predetermined space; the global critic may be trained which includes a training of the vertices (nodes) based on rewards for plan or task execution; the planning may be considered a predetermined set of traffic rules as it includes searching of vertices (nodes) based on breadth-first or depth-first for optimized path planning of the autonomous robots; examiner notes that “traffic rules” under BRI can include any set of rules or parameters related to movement of traffic (the autonomous robots of Nie) and the search planning disclosed above satisfies this set of rules as it is related to movement of the autonomous robots (which vertices are most optimal for movement to achieve the task); examiner also notes that the task parameters may also be considered as traffic rules as they indicate target times for pickup and drop-off, as well as energy efficiency, all of which are related to movement of the autonomous robots), deploying a plurality of agents in the predetermined space, wherein each of the plurality of agents is associated with a starting location (Figs. 1A-1C, Paragraph 0028; the predetermined space may have multiple autonomous robots present, each with its own starting position), determining a destination for each of the plurality of agents (Fig. 3A, Paragraph 0051; each autonomous robot may have a corresponding target location (delivery vertex for transportation task) based on the current task), determining, by each of the plurality of agents, a path to the destination corresponding to that agent (Fig. 3A, Paragraphs 0068-0069; a path may be established for traveling from a current location to the target location), querying, by each agent, at least one of the plurality of nodes associated with the corresponding region encompassing a current position of the agent, to determine a direction of travel (Fig. 3A, Paragraphs 0068-0069, 0086; a robot may plan a path for transportation; the robot may utilize a local critic and a global critic for evaluation of the path; this evaluation of the path determines which vertices (nodes) the robot must pass through in order to reach the target location (delivery vertex); this can be considered as querying at least one of the nodes associated with a corresponding region to determine directions for travel as the selection of vertices (nodes) for planning will dictate the direction the robot will go; this process may be performed for multiple robots that are performing a given transportation task; the queried nodes may be within a given floor which may encompass the autonomous robot’s current position/vertex), determining, by at least one of the queried nodes, a preferred direction of travel for the querying agent based on the predetermined set of traffic rules (Paragraphs 0086-0087; preferred directions of travel for a robot are dictated by which vertices (nodes) are selected for the optimized task plan (best rewards); the vertices (nodes) that are best for the task are based on a global critic and an associated reward; as stated above, the global critic includes a vertex (node) search method for optimization (breadth and depth searches) which can be considered the predetermined set of rules), sending the preferred direction of travel from the queried node to the querying agent (Paragraph 0042; control signals may be transmitted to each of the autonomous robots; control signals may be based on the optimized path determined by the global critic evaluation of the nodes within the predetermined space), and travelling, by the querying agent, in the preferred direction from the current position of the agent (Figs. 2 step 206, 3A, Paragraph 0048; a transportation task may be executed by one of the autonomous robots in accordance with the determined optimal path which indicates a preferred direction (at least the first trajectory between the current vertex and the next optimized vertex)), but fails to disclose determining, by at least one of the queried nodes, a preferred direction of travel for the querying agent based on an internal state of the at least one of the nodes and the predetermined set of traffic rules.
However, Sykora, in an analogous field of endeavor, teaches determining, by at least one of the queried nodes, a preferred direction of travel for the querying agent based on an internal state of the at least one of the nodes and the predetermined set of traffic rules (Paragraphs 0035-0037, 0083; nodes may have given values, features, etc.; these can be considered internal states of the nodes; the next node for traversal (preferred direction) may be based on the node values; the vehicles may determine the node values and next node based on inputting data into the graph neural network (can be considered as a querying process) which results in the graph neural network outputting node values). Therefore, from the teaching of Sykora, it would have been obvious to one of ordinary skill in the art to have modified, with a reasonable expectation for success, the robotic system of Nie to include determining, by at least one of the queried nodes, a preferred direction of travel for the querying agent based on an internal state of the at least one of the nodes and the predetermined set of traffic rules, as taught/suggested by Sykora. The motivation to do so would be to ensure that node selection is based on current values of the node. This can lead to better traversal of an environment as node values/states may indicate faster and/or safer traversal for a given node.
Regarding claim 2, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses the predetermined set of traffic rules are generated based on a machine learning model (Paragraphs 0051, 0092; task parameters and/or task planning (vertex search based on breadth/depth) may be used for task optimization and are generated based on the global critic; these parameters and search rules are based off the global critic which is trained utilizing a machine learning model).
Regarding claim 3, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses one or more of the regions are non-overlapping in the predetermined space (Fig. 1E, Paragraph 0046; as stated above, each floor is considered its own region within the predetermined space; a multi-floor model may be used for multi-floor factories, warehouses, etc.; each floor is separate from each other and do not overlap one another).
Regarding claim 4, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses each of the plurality of agents lacks computational resources to determine the preferred direction of travel within a predetermined time interval (Fig. 1E; as explained above in the rationale for claim 1, the preferred direction for each of the autonomous robots is performed through a global critic which searches the vertices (nodes) for an optimal plan for task execution; this preferred direction as determined through the global critic is performed on an edge server; this can be considered as each of the autonomous robots lacking computational resources to determine the preferred direction).
Regarding claim 5, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses the starting location associated with each of the plurality of agents is different from other starting locations of all other agents (Figs. 1A-1C, 3A, Paragraph 0036 at least; path planning may be optimized towards resolving competitive collisions during task execution; this allows for collisions to be optimized around such that no two autonomous robots encounter a collision; this means that no two autonomous vehicles will have the same starting location as this would cause a collision; examiner also notes that from a physical standpoint, no two autonomous robots can occupy a single location (x, y coordinate as seen in Fig. 3A) as this would either be a collision (system is optimized to avoid) or an impossibility (physical constraint)).
Regarding claim 6, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses the at least one of the nodes is queried by more than one of the plurality of agents (Paragraphs 0052, 0073; a delivery vertex (destination/delivery node) may be determined for each transportation task that is assigned to a given autonomous robot; in a multi-floor model, robots performing a transportation task may have different delivery vertices (destination/delivery node); some vertices may be queried by multiple robots (same delivery vertex)).
Regarding claim 7, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses the same predetermined set of traffic rules is used for training each of the plurality of nodes (Figs. 3A-3B, 9A-9H, Paragraphs 0051, 0089-0091; the global critic may be trained which includes a training of the vertices (nodes) based on rewards for plan or task execution; the planning may be considered a predetermined set of traffic rules as it includes searching of vertices (nodes) based on breadth-first or depth-first for optimized path planning of the autonomous robots; examiner notes that “traffic rules” under BRI can include any set of rules or parameters related to movement of traffic (the autonomous robots of Nie) and the search planning disclosed above satisfies this set of rules as it is related to movement of the autonomous robots (which vertices are most optimal for movement to achieve the task); examiner also notes that the task parameters may also be considered as traffic rules as they indicate target times for pickup and drop-off, as well as energy efficiency, all of which are related to movement of the autonomous robots; Figs. 9A-9H show training of both the global and local critics over time, indicating that the traffic rules as explained above are continuously used for training the global critic).
Regarding claim 8, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses each of the plurality of agents comprise a physical vehicle (Fig. 2, Paragraph 0042; each of the autonomous robots may be a physical entity).
Regarding claim 9, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses each of the plurality of agents comprise a virtual agent in a simulated environment (Paragraph 0115; experiments may be run to simulate tasks for a multitude of robots, the robots in these simulated tasks may be considered as simulated agents).
Regarding claim 10, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses the direction of travel comprises a speed component (Paragraph 0047; the optimized path for a task includes an optimized speed).
Regarding claim 11, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses the path determined by each of the plurality of agents is a shortest path from the current position of the corresponding one of the plurality of agents to the determined destination, wherein determining, by the at least one of the nodes, the preferred direction of travel for the corresponding one of the plurality of agents is based on the shortest path (Paragraph 0104, 0124; optimization of the path for a robot task may be one in which a shortest path is selected; an optimized shortest path indicates directions from vertex to vertex that results in a shortest path based on the task).
Regarding claim 12, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses further repeating steps of querying the at least one of the nodes associated with at least one of the corresponding regions encompass a current position of the querying agent, determining, by the at least one of the nodes, the preferred direction of travel for the querying agent based on the predetermined set of traffic rules, sending the preferred direction of travel from the at least one of the nodes to the querying agent, and enabling the querying agent to travel in the preferred direction from a current location to the destination until the current position of the querying agent is equal to the determined destination (Figs. 3A-3B, Paragraphs 0042, 0051, 0086-0091 0068-0069, 0114-0118, at least; examiner notes that the claim is a repeat of steps as disclosed in claim 1, and as such, the rational for each of the respective parts can be found in the rationale of claim 1 above; additionally, Nie discloses that an experiment may be run utilizing 31 robots over a multi-floor scenario to simulate non-stationary tasks (delivery/transportation) at specific timesteps, wherein the system is reconfigured at each timestep; the reconfiguration at given timesteps may be considered a repeat of the prior steps of querying nodes, determining the preferred direction, etc.), but fails to disclose determining, by the at least one of the nodes, the preferred direction of travel for the querying agent based on the internal state of the at least one of the nodes and the predetermined set of traffic rules. However, the obviousness of determining a preferred direction based on an internal state of the nodes is shown in the rationale for claim 1 and would be applicable here as well.
Regarding claim 14, a portion of the claim limitations are similar to those of claim 1 and are rejected using the same rationale as seen above in claim 1. Nie additionally discloses determine the current position of the corresponding one or more agents is equal to the assigned destination or not (Paragraph 0054; system may determine if a robot has executed delivery within a given time frame; this would require the system to determine the robot’s current position as being that of the delivery vertex).
Regarding claims 15-17 and 19, the claim limitations are similar to those in claims 2, 4, 11, and 10, respectively, and are rejected using the same rationale as seen above in claims 2, 4, 11, and 10.
Regarding claim 20, the claim limitations are similar to those in claim 14 and are rejected using the same rationale as seen above in claim 14.
Claims 13 and 18 are rejected under 35 U.S.C. 103 as being obvious over Nie, in view of Sykora, and further in view of Anand et al., US 20230266766 A1, herein referred to as Anand.
Regarding claim 13, Nie in view of Sykora renders obvious all the limitations of claim 1. Nie further discloses the one or more nodes are Graph Convolutional Neural Network (GCNN) nodes (Paragraphs 0037, 0060; neural networks may include GCNNs which comprise neurons (nodes) for use in a graph format data structure), but fails to disclose the one or more nodes are Graph Recurrent Neural Network (GRNN) nodes. However, Anand, in an analogous field of endeavor, teaches the one or more nodes are Graph Recurrent Neural Network (GRNN) nodes (Paragraph 0035; spatial representation of nodes may be represented through a Recurrent Graph Neural Network). Therefore, from the teaching of Anand, it would have been obvious to one of ordinary skill in the art before the effective filing date to have modified, with a reasonable expectation for success, the multi-robot system of Nie to include the one or more nodes are Graph Recurrent Neural Network (GRNN) nodes, as taught/suggested by Anand. The motivation to do so would be to utilize a well-known alternative neural network for robot tasking. This can lead to potentially higher efficiency when allocating tasks for each robot or generating the most optimized path, etc. when utilizing a node representation.
Regarding claim 18, the claim limitations are similar to those in claim 13 and are rejected using the same rationale as seen above in claim 13.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1, 12, 14, and 18 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.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTOPHER ALLEN BUKSA whose telephone number is (571)272-5346. The examiner can normally be reached M-F 7:30 AM-4:30 PM.
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.
/CHRISTOPHER A BUKSA/Examiner, Art Unit 3658
Prosecution Insights