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 .
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-3, 5-6, 9-10, 11-13, 15-16, 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL “Rosinol” , in view of NPL “RoboExp”.
Claim 1 and 11
Updating a dynamic scene graph by adding, to the dynamic scene graph, object-level history information corresponding to a target object, of which a state changes according to an interaction with a robot that occurs through an execution of an instruction for a task of a target robot;
Rosinol teaches a dynamic scene graph by stating that "Dynamic scene graphs (DSGs) extend this notion to represent dynamic scenes with moving agents (e.g., humans, robots), and to include actionable information that supports planning and decision-making (e.g., spatio-temporal relations, topology at different levels of abstraction)." Rosinol further teaches that "a DSG is a layered directed graph where nodes represent spatial concepts (e.g., objects, rooms, agents) and edges represent pairwise spatio-temporal relations" and that DSGs are "an actionable representation for navigation and planning." RoboEXP teaches updating the scene graph based on robot interaction by stating that the robot "reasons about what and how to explore an object, accumulating new information through the interaction process and incrementally constructing the ACSG." RoboEXP further teaches that "our agent takes an action...receives a new observation...used to update its current inferred graph Gt. This update might include adding new nodes to the graph or updating the state of an existing node." RoboEXP additionally explains that the memory module updates the graph across time because "objects may change positions or states across different time steps" and updates the graph by "adding, deleting, or modifying nodes and edges within our graph." Collectively, Rosinol and RoboEXP teach updating a dynamic scene graph as object states change due to robot interaction. However, neither reference expressly teaches adding object-level history information corresponding to the target object, wherein the history information itself is stored as historical information associated with the object node after execution of a task instruction.
Controlling the target robot based on the updated dynamic scene graph, in response to receiving a target instruction corresponding to the target object.
RoboEXP teaches controlling the robot using the updated scene graph by stating that "given our scene graph and a target object, an agent merely needs to sequentially execute all the actions on the paths from the root to the object node in a topological order to retrieve the object." RoboEXP further teaches that the decision-making module "identify[ies] the appropriate object and corresponding skill" and selects actions "based on information from our ACSG." These disclosures teach controlling the robot using the updated scene graph in response to a target object.
Claim 2 and 12,
Wherein the history information comprises any one or any combination of any two or more of: a previous state of the target object, comprising any one or any combination of any two or more of a previous position coordinate of the target object, a previous direction of the target object, and a positional relationship with one or more other objects located in a same space as the target object; a first instruction previously performed in response to the target object; time information corresponding to the first instruction; and a previous user that issued the first instruction.
RoboEXP teaches maintaining historical object state information by explaining that its memory module "handles merging across different viewpoints and time steps" and that "objects may change positions or states across different time steps." RoboEXP further teaches maintaining "relationships between objects and the logical associations between actions and objects" and updating graph nodes and edges accordingly. Rosinol likewise teaches that each object node contains "a 3D object pose, ... a bounding box, and ... semantic class" and that "edges between objects describe relations, such as co-visibility, relative size, distance, or contact ('the cup is on the desk')." These disclosures teach previous object position and positional relationships. However, neither Rosinol nor RoboEXP expressly teaches storing, as part of the object's history information, a previously executed instruction, time information corresponding to that instruction, or the identity of the previous user issuing the instruction.
Claim 3 and 13
Wherein the updating of the dynamic scene graph comprises updating the dynamic scene graph by adding, to an object node, history information of one or more other objects, of which a state changes together with the target object due to the interaction, in a form of an attribute, wherein the object node corresponds to the target object.
RoboEXP teaches that an "action-conditioned 3D scene graph (ACSG) is an actionable, spatial-topological representation that models objects and their interactive and spatial relations" and that "each node represents either an object or an action" while edges encode interaction relationships. RoboEXP further teaches examples in which interaction with one object affects another object, such as "the cabinet can be opened only if we move away the condiment" and "a banana can be reached if we open the cabinet." The RoboEXP memory module further analyzes "relationships between objects" and updates nodes and edges when those relationships change. Rosinol similarly teaches that object nodes are connected through spatial relationships such as contact and distance. Although these references teach object relationships and updating those relationships after interaction, neither reference expressly teaches adding the history information of another object as an attribute within the target object's node. Instead, the relationships are represented through graph nodes and edges rather than embedding another object's history within an object node. Therefore, this limitation is within the knowledge of ordinary skilled artisan.
Claim 5
Wherein the updating of the dynamic scene graph comprises storing the history information in a plurality of slots of an object node corresponding to the target object in the dynamic scene graph in a form of a stack data structure.
RoboEXP teaches maintaining information across multiple time steps by explaining that its memory module "handles merging across different viewpoints and time steps" and updates memory whenever "objects may change positions or states across different time steps." Rosinol likewise teaches maintaining temporal information for dynamic entities through "a collection of time-stamped 3D poses" describing trajectories over time. These references therefore teach maintaining temporal information and updating scene graph information over time. However, storing history information in a plurality of slots of an object node using a stack (LIFO) data structure would have within the knowledge ordinary skilled artisan
Claim 9 and 19
Wherein the controlling of the target robot comprises supplementing a missing information item that is missing from the target instruction, based on the updated dynamic scene graph;
RoboEXP teaches using the action-conditioned scene graph to infer the actions necessary to retrieve a desired object. Specifically, RoboEXP states that "given our scene graph and a target object, an agent merely needs to sequentially execute all the actions on the paths from the root to the object node in a topological order to retrieve the object." RoboEXP further teaches that GPT-4V "select[s] the appropriate skill" using information contained within the ACSG and verifies actions "based on information from our ACSG." These disclosures teach using information stored within the scene graph to determine robot actions.
Controlling the target robot according to the target instruction with the information item supplemented.
RoboEXP teaches controlling the robot after determining the required action sequence through the ACSG and executing those actions using the action module.
Claim 10 and 20
Wherein the target instruction comprises either one or both of an instruction in a form of text and an instruction in a form of voice, for a task of the target robot.
Rosinol is directed to visual-inertial perception and construction of dynamic scene graphs for planning and navigation. RoboEXP employs GPT-4V internally within its decision-making module to propose and verify robot actions based upon the current scene graph; therefore voice, text for a task target would have been obvious and within the knowledge or ordinary skilled artisan.
Allowable Subject Matter
Claims 4 and 14, 7 and 17, 8 and 18 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MASUD AHMED whose telephone number is (571)270-1315. The examiner can normally be reached M-F 9:00-8:30 PM PST with IFP.
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, Abby Lin can be reached at 571 270 3976. 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.
MASUD . AHMED
Primary Examiner
Art Unit 3657A
/MASUD AHMED/Primary Examiner, Art Unit 3657
Prosecution Insights