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 .
Status of Claims
Pending
1-16
Rejected – 35 U.S.C. 103
1-16
Response to Amendment
This office action is in response to applicant’s arguments and amendments filed 07/11/2025, which are in response to USPTO Office Action mailed 04/11/2025. Applicant’s arguments and amendments have been considered with the results that follow: THIS ACTION IS MADE FINAL.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claim(s) 1-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hayashi et al. (US 2021/0252714 A1, hereinafter “Hayashi”) and further in view of El Khadir et al. (US 2022/0040861 A1, hereinafter “Khadir”).
Regarding claim 1: Hayashi teaches: A control device comprising ([0009] control device): a memory storing instructions ([0092] memory and instructions); and one or more processors configured to execute the instructions to ([0100] processors):
set an abstract state […] which abstractly represents a state of each object in a workspace where each robot works ([0071] sensors observe object present in environment and calculates relationship amounts between objects, including relative coordinates, forces, states; Fig. 1: state of objects in workspace; [0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount);
generate an environment map which is a map representing accuracy of information in the workspace ([0123] acquires environment information regarding each object present in the environment where operation is executed; create map indicating arrangement space based on environment info; [0141] each node Nd corresponds to one state of the relative relationship between objects, and indicates the relative relationship amount in the one state; each node Nd may be set by as random sampling or operator’s designation; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; this match may include an approximation based on a threshold (an allowable error) as well as an exact match; when there is a match, determine that relative relationship amount between objects has transitioned to the target state; if no match, determines that the relative relationship amount between objects has not transitioned to target state);
generate an abstract model which represents dynamics of the abstract state and a time change of the environment map ([0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount; “starting time point” is the starting point of the plan, and is the state before starting the control of the operation of the robot device in relation to the execution of the operation; “final target” is the ending point of the plan, and is realized when execution of the operation is completed and is set according to the given operation; [0075] FIG. 1, a scene in which the series of relative relationship amounts is determined so that the operation of transporting the parts from the starting time point to the final target is executed in n steps); and
generate a control input with respect to each robot based on the abstract model ([0072] sets relative relationship amount between objects serving as a final target; final target based on operation to be performed by manipulator; [0073] determines series of relative relationship amounts in target state of objects until the relative relationship amount of the final target set from relative relationship amount between objects realized; [0074] outputs the determined control command to manipulator; control command controls robot and includes target control amount, operation amount).
However, Hayashi does not explicitly teach, but Khadir teaches: [set an abstract state] while leaving the abstract state unset with respect to an unset object to which the abstract state cannot be set, in a case of setting the abstract state [which abstractly represents a state of each object in a workspace where each robot works] ([0004] real-time adaptation to dynamic obstacles during execution; [0041] picking and placing task dynamically shifts to configurations unseen during training and dynamic obstacles encountered during execution (i.e. unset abstract state for unset object); when faced with an obstacle (i.e. unset object), robot can no longer follow the demonstration path anymore and should re-compute a new motion trajectory in real-time to avoid collision and still attempt to accomplish the desired task; [0042] vector field defines a closed-loop velocity dynamical systems control policy; from any state that the robot finds itself in, the vector field used to steer robot back towards desired imitation behavior, without need for path re-planning; learned vector field modulated in real-time to avoid collisions with obstacles; [0076] CVF-P generalizes to a wider region in state space; [0084] robot arm operated to follow demonstrated trajectories while avoiding obstacles unseen during training (i.e. unset abstract state for unset object); [0094] generate a workspace Cartesian to joint space mapping for robot, using mapping to update contracting vector fields on the fly to avoid dynamic obstacles).
Hayashi and Khadir are analogous art to the claimed invention since they are from the similar field of robot controls and path planning. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Hayashi with the aspects of Khadir to create, with a reasonable expectation for success, a control device that sets an abstract state while leaving the abstract state unset with respect to an unset object to which the abstract state cannot be set, in a case of setting the abstract state which abstractly represents a state of each object in a workspace where each robot works. The motivation for modification would have been to control a robot while avoiding obstacles unseen during training, perform space mapping for the robot, use the mapping on-the-fly to avoid dynamic obstacles, which overall improve the robot control system by avoiding collisions against any part of the robot body (Khadir, [0084], [0094]).
Regarding claim 2: Hayashi-Khadir further teach: The control device according to claim 1, wherein the processor is further configured to determine whether or not to re-generate the abstract model based on a change of the abstract state during an operation of each robot by the control input (Hayashi: [0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount; [0073] determines the series of relative relationship amounts in a target state of a plurality of objects until the relative relationship amount of the final target set from the relative relationship amount between the plurality of objects at the starting time point of the operation control is realized; controller repeatedly determines the control command to be provided to the manipulator so that the relative relationship amount in the current state calculated from the latest observation data acquired from the sensors is changed to the relative relationship amount in the state of the next transition target of the current state, included in the series of relative relationship amounts until the relative relationship amount of the final target is realized; [0074] outputs the determined control command to the manipulator; control command controls robot and includes target control amount, operation amount).
Regarding claim 3: Hayashi-Khadir further teach: The control device according to claim 2, wherein the processor determines whether or not to re-generate the abstract model based on at least one of a number and each position of objects during the operation of each robot by the control input (Hayashi: [0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; [0073] controller repeatedly determines the control command to be provided to the manipulator so that the relative relationship amount in the current state calculated from the latest observation data acquired from the sensors is changed to the relative relationship amount in the state of the next transition target of the current state, included in the series of relative relationship amounts until the relative relationship amount of the final target is realized; see also [0084]; [0110] matches the model of each object indicated by the CAD data with respect to the image data obtained by the camera (i.e. model adjusted or not adjusted based on location of objects and robot during operation)).
Regarding claim 4: Hayashi-Khadir further teach: The control device according to claim 2, wherein each robot is provided with a measurement device (Hayashi: [0018] sensor includes camera and image data),
a measurement range of the measurement device changes in accordance with the operation of each robot (Hayashi: [0025] arrangement space includes free region and restricted region; [0070] FIG. 1, computer that generates a control command for controlling the operation of a robot device operating under an environment in which a plurality of objects is present; environment is an area where an object is present and a robot device operates; [0084] control device repeatedly determines the control command to be provided to the manipulator so that relative relationship amount in the current state calculated from the latest image data from camera is changed to the relative relationship amount in the state of the next transition target of the current state included in the series of relative relationship amounts until relative relationship amount of the final target is realized; [0110] matches the model of each object indicated by the CAD data with respect to the image data obtained by the camera (i.e. sensor adjusts range/measurement area based on location of objects and robot during operation)), and
the processor specifies the change of the abstract state based on a measurement signal which the measurement device generates during the operation of each robot (Hayashi: [0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; [0073] controller repeatedly determines the control command to be provided to the manipulator so that the relative relationship amount in the current state calculated from the latest observation data acquired from the sensors is changed to the relative relationship amount in the state of the next transition target of the current state, included in the series of relative relationship amounts until the relative relationship amount of the final target is realized; see also [0084]).
Regarding claim 5: Hayashi-Khadir further teach: The control device according to claim 4, wherein the processor determines whether or not to re-generate the abstract model, based on a difference between the abstract state currently set based on the measurement signal and the abstract state currently predicted based on the control input (Hayashi: [0084] controller repeatedly determines the control command to be provided to the manipulator so that the relative relationship amount in the current state calculated from the latest image data acquired from the camera is changed to the relative relationship amount in the state of the next transition target of the current state included in the series of relative relationship amounts until the relative relationship amount of the final target is realized; in first step of this repetition, the initial state at the starting time point is the current state; that is, the relative relationship amount in the current state calculated from the latest image data is the same as the relative relationship amount at the starting time point; the “latest” is when the operation is controlled by the control command and is a time point immediately before the control command is determined; [0110] matches the model of each object indicated by the CAD data with respect to the image data obtained by the camera; [0111] determines the series of relative relationship amounts in the state of the target of the objects until the relative relationship amount of the set final target is realized from the relative relationship amount at the starting time point of the operation control; the relative relationship amount at the starting time point is calculated from the image data acquired at the time point immediately before starting the control of the operation of the manipulator in relation to the execution of the operation; retains the map information for use in determining the series of relative relationship amounts; searches for a route from a node corresponding to the relative relationship amount in the state of the starting time point to a node corresponding to the relative relationship amount in the state of the final target by selecting a waypoint node from a plurality of nodes in the arrangement space indicated by the map information; generates the series of relative relationship amounts by the relative relationship amount corresponding to the node included in the searched route; [0193] calculates the operation amount of each of the joint from the difference (deviation) between the target value of the control amount of each of the joint portions indicated by the control command and the measured value acquired from the encoder).
Regarding claim 6: Hayashi-Khadir further teach: The control device according to claim 1, wherein the processor generates the control input based on the abstract model and an environment evaluation value in which accuracy represented by the environment map is evaluated (Hayashi: [0193] calculates the operation amount of each of the joint from the difference (deviation) between the target value of the control amount of each of the joint portions indicated by the control command and the measured value acquired from the encoder; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; this match may include an approximation based on a threshold (an allowable error) as well as an exact match; when there is a match, determine that relative relationship amount between objects has transitioned to the target state; if no match, determines that the relative relationship amount between objects has not transitioned to target state).
Regarding claim 7: Hayashi-Khadir further teach: The control device according to claim 6, wherein the processor sets an evaluation function including the control input and the environment evaluation value and a constraint condition to be satisfied in an execution of an objective task which is a task for each robot to work, and generates the control input using an optimization based on the evaluation function and the constraint condition (Hayashi: [0161] controller: inputs the relative relationship amount and the relative relationship amount to the input layer for each of the learning data sets; performs the firing judgment of each neuron included in each layer in order from the input side; acquires, from the output layer, an output value corresponding to the result of determining the control command to be provided to the manipulator in order to change the relative relationship amount to the relative relationship amount; calculates an error between the acquired output value and the corresponding control command; calculates the error of the coupling weight between neurons and the error of the threshold of each neuron using the error of the output value calculated by the error back propagation method; updates the coupling weight between neurons and the threshold of each neuron on the basis of the calculated errors; [0179] constraint conditions may be imposed on the route search such that a route from the node Ns to the node Ng must satisfy the constraint conditions; [0180] as constraint conditions, a weight may be set for each edge;. This weight may be appropriately set or changed according to the prioritizing item in the route search, such as shortest route, or passing through all nodes; control unit may use this weight to search for a route (i.e. optimization based on constraints; see also [0111]; [0193] calculates the operation amount of each of the joint from the difference (deviation) between the target value of the control amount of each of the joint portions indicated by the control command and the measured value acquired from the encoder).
Regarding claim 8: Hayashi-Khadir further teach: The control device according to claim 1, wherein the processor is further configured to generate a target logical formula which is a logical formula of a temporal logic representing a final target (Hayashi: [0161] controller: inputs the relative relationship amount and the relative relationship amount to the input layer for each of the learning data sets; performs the firing judgment of each neuron included in each layer in order from the input side; acquires, from the output layer, an output value corresponding to the result of determining the control command to be provided to the manipulator in order to change the relative relationship amount to the relative relationship amount; calculates an error between the acquired output value and the corresponding control command; calculates the error of the coupling weight between neurons and the error of the threshold of each neuron using the error of the output value calculated by the error back propagation method; updates the coupling weight between neurons and the threshold of each neuron on the basis of the calculated errors; [0100] control device may be programmable logic controller (PLC); [0020] when reinforcement learning is employed as the machine learning, the learning model may be configured as a value function such as a state value function or an action value function; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; this match may include an approximation based on a threshold (an allowable error) as well as an exact match; when there is a match, determine that relative relationship amount between objects has transitioned to the target state; if no match, determines that the relative relationship amount between objects has not transitioned to target state); and
generate, from the logical formula, time step logical formula which is a logical formula representing a state for each time step for executing a certain objective task which is a task for each robot to work (Hayashi: [0084] controller repeatedly determines the control command to be provided to the manipulator so that the relative relationship amount in the current state calculated from the latest image data acquired from the camera is changed to the relative relationship amount in the state of the next transition target of the current state included in the series of relative relationship amounts until the relative relationship amount of the final target is realized; [0111] determines the series of relative relationship amounts in the state of the target of the objects until the relative relationship amount of the set final target is realized from the relative relationship amount at the starting time point of the operation control; the relative relationship amount at the starting time point is calculated from the image data acquired at the time point immediately before starting the control of the operation of the manipulator in relation to the execution of the operation; retains the map information for use in determining the series of relative relationship amounts; searches for a route from a node corresponding to the relative relationship amount in the state of the starting time point to a node corresponding to the relative relationship amount in the state of the final target by selecting a waypoint node from a plurality of nodes in the arrangement space indicated by the map information; generates the series of relative relationship amounts by the relative relationship amount corresponding to the node included in the searched route),
wherein the processor generates the control input based on the abstract model and the time step logical formula (Hayashi: [0161] time step control logic and machine learning; see also [0100]; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; [0074] outputs the determined control command to manipulator; control command controls robot and includes target control amount, operation amount).
Regarding claim 9: Hayashi-Khadir further teach: The control device according to claim 8, wherein the processor generates the target logical formula including a logical sum of a logical formula corresponding the objective task and an environment evaluation value in which accuracy represented by the environment map is evaluated (Hayashi: [0161] controller: inputs the relative relationship amount and the relative relationship amount to the input layer for each of the learning data sets; performs the firing judgment of each neuron included in each layer in order from the input side; acquires, from the output layer, an output value corresponding to the result of determining the control command to be provided to the manipulator in order to change the relative relationship amount to the relative relationship amount; calculates an error between the acquired output value and the corresponding control command; calculates the error of the coupling weight between neurons and the error of the threshold of each neuron using the error of the output value calculated by the error back propagation method; updates the coupling weight between neurons and the threshold of each neuron on the basis of the calculated errors; [0100] control device may be programmable logic controller (PLC); [0020] when reinforcement learning is employed as the machine learning, the learning model may be configured as a value function such as a state value function or an action value function; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; this match may include an approximation based on a threshold (an allowable error) as well as an exact match; when there is a match, determine that relative relationship amount between objects has transitioned to the target state; if no match, determines that the relative relationship amount between objects has not transitioned to target state).
Regarding claim 10: Hayashi-Khadir further teach: The control device according to claim 1, wherein the processor is further configured to supply a subtask sequence in which the control input is converted into a sequence of subtasks executable for each robot, to a corresponding robot (Hayashi: [0072] sets the relative relationship amount between a plurality of objects serving as a final target; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount; [0073] determines the series of relative relationship amounts in a target state of a plurality of objects until the relative relationship amount of the final target set from the relative relationship amount between the plurality of objects at the starting time point of the operation control is realized; controller repeatedly determines the control command to be provided to the manipulator; [0015] “target” includes final target and set as appropriate to achieve the execution of the operation; targets other than final target are waypoints that are passed until reaching an ending point after starting from a starting point; final target may be simply “target (goal)”, and a target other than the final target may be “subordinate target (sub-goal)”; see also [0081]).
Regarding claim 11: Hayashi-Khadir further teach: The control device according to claim 1, wherein the processor updates the environment map to attenuate the accuracy in a space based on passage of time after measurement in the space where the measurement has performed (Hayashi: [0111] determines the series of relative relationship amounts in the state of the target of the objects until the relative relationship amount of the set final target is realized from the relative relationship amount at the starting time point of the operation control; the relative relationship amount at the starting time point is calculated from the image data acquired at the time point immediately before starting the control of the operation of the manipulator in relation to the execution of the operation; retains the map information for use in determining the series of relative relationship amounts; searches for a route from a node corresponding to the relative relationship amount in the state of the starting time point to a node corresponding to the relative relationship amount in the state of the final target by selecting a waypoint node from a plurality of nodes in the arrangement space indicated by the map information; generates the series of relative relationship amounts by the relative relationship amount corresponding to the node included in the searched route; [0123] acquires environment information regarding each object present in the environment where operation is executed; create map indicating arrangement space based on environment info; [0141] each node Nd corresponds to one state of the relative relationship between objects, and indicates the relative relationship amount in the one state; each node Nd may be set by as random sampling or operator’s designation; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; this match may include an approximation based on a threshold (an allowable error) as well as an exact match; when there is a match, determine that relative relationship amount between objects has transitioned to the target state; if no match, determines that the relative relationship amount between objects has not transitioned to target state).
Regarding claim 12: Hayashi teaches: A control method comprising ([0005] control method of the robot device):
setting an abstract state […] which abstractly represents a state of each object in a workspace where each robot works ([0071] sensors observe object present in environment and calculates relationship amounts between objects, including relative coordinates, forces, states; Fig. 1: state of objects in workspace; [0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount);
generating an environment map which is a map representing accuracy of information in the workspace ([0123] acquires environment information regarding each object present in the environment where operation is executed; create map indicating arrangement space based on environment info; [0141] each node Nd corresponds to one state of the relative relationship between objects, and indicates the relative relationship amount in the one state; each node Nd may be set by as random sampling or operator’s designation; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; this match may include an approximation based on a threshold (an allowable error) as well as an exact match; when there is a match, determine that relative relationship amount between objects has transitioned to the target state; if no match, determines that the relative relationship amount between objects has not transitioned to target state);
generating an abstract model which represents dynamics of the abstract state and a time change of the environment map ([0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount; “starting time point” is the starting point of the plan, and is the state before starting the control of the operation of the robot device in relation to the execution of the operation; “final target” is the ending point of the plan, and is realized when execution of the operation is completed and is set according to the given operation; [0075] FIG. 1, a scene in which the series of relative relationship amounts is determined so that the operation of transporting the parts from the starting time point to the final target is executed in n steps); and
generating a control input with respect to each robot based on the abstract model ([0072] sets relative relationship amount between objects serving as a final target; final target based on operation to be performed by manipulator; [0073] determines series of relative relationship amounts in target state of objects until the relative relationship amount of the final target set from relative relationship amount between objects realized; [0074] outputs the determined control command to manipulator; control command controls robot and includes target control amount, operation amount).
However, Hayashi does not explicitly teach, but Khadir teaches: [setting an abstract state] while leaving the abstract state unset with respect to an unset object to which the abstract state cannot be set, in a case of setting the abstract state [which abstractly represents a state of each object in a workspace where each robot works] ([0004] real-time adaptation to dynamic obstacles during execution; [0041] picking and placing task dynamically shifts to configurations unseen during training and dynamic obstacles encountered during execution (i.e. unset abstract state for unset object); when faced with an obstacle (i.e. unset object), robot can no longer follow the demonstration path anymore and should re-compute a new motion trajectory in real-time to avoid collision and still attempt to accomplish the desired task; [0042] vector field defines a closed-loop velocity dynamical systems control policy; from any state that the robot finds itself in, the vector field used to steer robot back towards desired imitation behavior, without need for path re-planning; learned vector field modulated in real-time to avoid collisions with obstacles; [0076] CVF-P generalizes to a wider region in state space; [0084] robot arm operated to follow demonstrated trajectories while avoiding obstacles unseen during training (i.e. unset abstract state for unset object); [0094] generate a workspace Cartesian to joint space mapping for robot, using mapping to update contracting vector fields on the fly to avoid dynamic obstacles).
Hayashi and Khadir are analogous art to the claimed invention since they are from the similar field of robot controls and path planning. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Hayashi with the aspects of Khadir to create, with a reasonable expectation for success, a control device that sets an abstract state while leaving the abstract state unset with respect to an unset object to which the abstract state cannot be set, in a case of setting the abstract state which abstractly represents a state of each object in a workspace where each robot works. The motivation for modification would have been to control a robot while avoiding obstacles unseen during training, perform space mapping for the robot, use the mapping on-the-fly to avoid dynamic obstacles, which overall improve the robot control system by avoiding collisions against any part of the robot body (Khadir, [0084], [0094]).
Regarding claim 13: Hayashi teaches: A non-transitory computer-readable recording medium storing a program, the program causing a computer to perform a process comprising ([0100] computer, RAM, controller, processor, storage with instructions; see also [0092]):
setting an abstract state […] which abstractly represents a state of each object in a workspace where each robot works ([0071] sensors observe object present in environment and calculates relationship amounts between objects, including relative coordinates, forces, states; Fig. 1: state of objects in workspace; [0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount);
generating an environment map which is a map representing accuracy of information in the workspace ([0123] acquires environment information regarding each object present in the environment where operation is executed; create map indicating arrangement space based on environment info; [0141] each node Nd corresponds to one state of the relative relationship between objects, and indicates the relative relationship amount in the one state; each node Nd may be set by as random sampling or operator’s designation; [0200] determine whether the relative relationship amount calculated matches the relative relationship amount in the target state; this match may include an approximation based on a threshold (an allowable error) as well as an exact match; when there is a match, determine that relative relationship amount between objects has transitioned to the target state; if no match, determines that the relative relationship amount between objects has not transitioned to target state);
generating an abstract model which represents dynamics of the abstract state and a time change of the environment map ([0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount; “starting time point” is the starting point of the plan, and is the state before starting the control of the operation of the robot device in relation to the execution of the operation; “final target” is the ending point of the plan, and is realized when execution of the operation is completed and is set according to the given operation; [0075] FIG. 1, a scene in which the series of relative relationship amounts is determined so that the operation of transporting the parts from the starting time point to the final target is executed in n steps); and
generating a control input with respect to each robot based on the abstract model ([0072] sets relative relationship amount between objects serving as a final target; final target based on operation to be performed by manipulator; [0073] determines series of relative relationship amounts in target state of objects until the relative relationship amount of the final target set from relative relationship amount between objects realized; [0074] outputs the determined control command to manipulator; control command controls robot and includes target control amount, operation amount).
However, Hayashi does not explicitly teach, but Khadir teaches: [setting an abstract state] while leaving the abstract state unset with respect to an unset object to which the abstract state cannot be set, in a case of setting the abstract state [which abstractly represents a state of each object in a workspace where each robot works] ([0004] real-time adaptation to dynamic obstacles during execution; [0041] picking and placing task dynamically shifts to configurations unseen during training and dynamic obstacles encountered during execution (i.e. unset abstract state for unset object); when faced with an obstacle (i.e. unset object), robot can no longer follow the demonstration path anymore and should re-compute a new motion trajectory in real-time to avoid collision and still attempt to accomplish the desired task; [0042] vector field defines a closed-loop velocity dynamical systems control policy; from any state that the robot finds itself in, the vector field used to steer robot back towards desired imitation behavior, without need for path re-planning; learned vector field modulated in real-time to avoid collisions with obstacles; [0076] CVF-P generalizes to a wider region in state space; [0084] robot arm operated to follow demonstrated trajectories while avoiding obstacles unseen during training (i.e. unset abstract state for unset object); [0094] generate a workspace Cartesian to joint space mapping for robot, using mapping to update contracting vector fields on the fly to avoid dynamic obstacles).
Hayashi and Khadir are analogous art to the claimed invention since they are from the similar field of robot controls and path planning. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Hayashi with the aspects of Khadir to create, with a reasonable expectation for success, a control device that sets an abstract state while leaving the abstract state unset with respect to an unset object to which the abstract state cannot be set, in a case of setting the abstract state which abstractly represents a state of each object in a workspace where each robot works. The motivation for modification would have been to control a robot while avoiding obstacles unseen during training, perform space mapping for the robot, use the mapping on-the-fly to avoid dynamic obstacles, which overall improve the robot control system by avoiding collisions against any part of the robot body (Khadir, [0084], [0094]).
Regarding claim 14 : Hayashi-Khadir further teach: The control device according to claim 1, wherein the processor recognizes a state of each object in the workspace which are necessary to be considered at a time of executing an objective task, and represents, as a state vector, the state which is recognized, while setting the abstract state while leaving the abstract state unset with respect to the unset object (Hayashi: [0071] sensors observe object present in environment and calculates relationship amounts between objects, including relative coordinates, forces, states; Fig. 1: state of objects in workspace; [0072] sets the relative relationship amount between a plurality of objects serving as a final target; final target is determined according to operation to be performed by the manipulator; plans the transition of the relative relationship amount until the final target is achieved from the starting time point of the operation control, and determines the control command to be provided to the manipulator according to the planned transition of the relative relationship amount; Khadir: [0004] real-time adaptation to dynamic obstacles during execution; [0041] picking and placing task dynamically shifts to configurations unseen during training and dynamic obstacles encountered during execution (i.e. unset abstract state for unset object); when faced with an obstacle (i.e. unset object), robot can no longer follow the demonstration path anymore and should re-compute a new motion trajectory in real-time to avoid collision and still attempt to accomplish the desired task; [0042] vector field defines a closed-loop velocity dynamical systems control policy; from any state that the robot finds itself in, the vector field used to steer robot back towards desired imitation behavior, without need for path re-planning; learned vector field modulated in real-time to avoid collisions with obstacles; [0076] CVF-P generalizes to a wider region in state space; [0084] robot arm operated to follow demonstrated trajectories while avoiding obstacles unseen during training (i.e. unset abstract state for unset object); [0094] generate a workspace Cartesian to joint space mapping for robot, using mapping to update contracting vector fields on the fly to avoid dynamic obstacles).
The motivation for modification would have been to control a robot while avoiding obstacles unseen during training, perform space mapping for the robot, use the mapping on-the-fly to avoid dynamic obstacles, which overall improve the robot control system by avoiding collisions against any part of the robot body (Khadir, [0084], [0094]).
Regarding claim 15: Hayashi-Khadir further teach: The control device according to claim 1, further comprising one or more measurement devices configured to detect the state in the workspace where the objective task is executed, wherein the unset object is an object which the one or more measurement devices cannot measure (Hayashi: [0018] sensor includes camera and image data; Khadir: [0004] real-time adaptation to dynamic obstacles during execution; [0041] picking and placing task dynamically shifts to configurations unseen during training and dynamic obstacles encountered during execution (i.e. unset abstract state for unset object); when faced with an obstacle (i.e. unset object), robot can no longer follow the demonstration path anymore and should re-compute a new motion trajectory in real-time to avoid collision and still attempt to accomplish the desired task; [0042] vector field defines a closed-loop velocity dynamical systems control policy; from any state that the robot finds itself in, the vector field used to steer robot back towards desired imitation behavior, without need for path re-planning; learned vector field modulated in real-time to avoid collisions with obstacles; [0076] CVF-P generalizes to a wider region in state space; [0084] robot arm operated to follow demonstrated trajectories while avoiding obstacles unseen during training (i.e. unset abstract state for unset object); [0094] generate a workspace Cartesian to joint space mapping for robot, using mapping to update contracting vector fields on the fly to avoid dynamic obstacles).
The motivation for modification would have been to control a robot while avoiding obstacles unseen during training, perform space mapping for the robot, use the mapping on-the-fly to avoid dynamic obstacles, which overall improve the robot control system by avoiding collisions against any part of the robot body (Khadir, [0084], [0094]).
Regarding claim 16: Hayashi-Khadir further teach: The control device according to claim 1, wherein the unset object is any one of an object existing in a blind spot of a measurement device, an object which exists farther than a measurable distance of each of one or more measurement devices, and an object which is accommodated in a housing (Khadir: [0004] real-time adaptation to dynamic obstacles during execution; [0041] picking and placing task dynamically shifts to configurations unseen during training and dynamic obstacles encountered during execution (i.e. unset abstract state for unset object); when faced with an obstacle (i.e. unset object), robot can no longer follow the demonstration path anymore and should re-compute a new motion trajectory in real-time to avoid collision and still attempt to accomplish the desired task; [0042] vector field defines a closed-loop velocity dynamical systems control policy; from any state that the robot finds itself in, the vector field used to steer robot back towards desired imitation behavior, without need for path re-planning; learned vector field modulated in real-time to avoid collisions with obstacles; [0076] CVF-P generalizes to a wider region in state space; [0084] robot arm operated to follow demonstrated trajectories while avoiding obstacles unseen during training (i.e. unset abstract state for unset object); [0094] generate a workspace Cartesian to joint space mapping for robot, using mapping to update contracting vector fields on the fly to avoid dynamic obstacles).
The motivation for modification would have been to control a robot while avoiding obstacles unseen during training, perform space mapping for the robot, use the mapping on-the-fly to avoid dynamic obstacles, which overall improve the robot control system by avoiding collisions against any part of the robot body (Khadir, [0084], [0094]).
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-16 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
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
An