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 .
Response to Arguments
Applicant’s arguments with respect to claim(s) 1 and 3-8 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.
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.
Claim(s) 1, 5, and 6-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Motomura et al. (US 20190347879 A1, hereinafter Motomura) in view of Chen et al. (US 20190212749 A1, hereinafter Chen).
Regarding claim 1, Motomura teaches:
A control device (Fig. 1, vehicle controller 2) comprising:
a storage that stores a plurality of trained control models (at least as in paragraph 0032, “Returning to FIG. 1, storage 7 may be a storage device such as a read only memory (ROM), a random access memory (RAM), a hard disk device, a solid state drive (SSD), or the like. Storage 7 stores various information such as detection results of operation system detector 3, input information to input unit 4, detection results of state detector 6, knowledge for behavior estimation in automatic driving control system 10 (also called machine learning data), and a neural network used for machine learning, which will be described below”), and
a controller (at least as in paragraph 0022, “As illustrated in FIG. 1, vehicle 1 includes vehicle controller 2, operation system detector 3, input unit 4, information notification unit 5, state detector 6, storage 7, automatic driving control system 10”),
wherein each of the plurality of trained control models is generated corresponding to a movement mode of a mobile body (at least as in paragraph 0034, “Learning unit 11 constructs a neural network of specific driver x of vehicle 1 from a driving history… running history of driver x”; at least as in paragraph 0035-0036, wherein the driving history and running history is constructed based on feature quantities, such as running state, and environmental parameters such as peripheral conditions; at least as in paragraph 0048, “The running scene includes elements such as running environment, weather during running, and a traffic condition of a vehicle”; see also 0048), and
wherein the controller is configured to perform:
acquiring movement condition data related to a condition of movement of the mobile body (at least as in paragraph 0049, “In step S101, during automatic driving of vehicle 1, learning unit 11 of automatic driving control system 10 acquires, from state detector 6 via storage 7, information about vehicle 1 and conditions around vehicle 1, such as position information on vehicle 1, map information on a position of vehicle 1, traffic jam information, and weather information”; see also 0025-0027 for state detector detecting the running state and peripheral condition),
determining the movement mode according to the acquired movement condition data (at least as in paragraph 0049, “Learning unit 11 specifies a running scene of vehicle 1 corresponding to this information from the acquired information”; at least as in paragraph 0048, “The running scene includes elements such as running environment, weather during running, and a traffic condition of a vehicle”),
selecting one of the plurality of trained control models according to a result of determining the movement mode (at least as in paragraph 0050, “in step S102, learning unit 11 selects a dedicated behavior estimation NN corresponding to specific driver x of vehicle 1 and corresponding to the running scene of vehicle 1 from among various dedicated behavior estimation NN stored in storage 7”),
deriving a control command for the mobile body in accordance with the calculated intensity by using the selected trained control model (at least as in paragraph 0051, “in step S103, by using the acquired dedicated behavior estimation NN, behavior estimation unit 12 performs behavior estimation, that is, prediction of a driving action, of vehicle 1 after a first predetermined time passes from a present time”; at least as in paragraph 0056, “If the behavior estimation result is valid (Yes in step S107), in step S108, automatic driving evaluation unit 13 outputs the behavior estimation result to vehicle controller 2 and notification device 5b of information notification unit 5”; at least as in paragraph 0051, 0055, & 0056, wherein “automatic driving evaluation unit 13 calculates a change amount between present behavior of vehicle 1 and the behavior estimation result output from behavior estimation unit 12, and determines validity of the behavior estimation result based on this change amount” and “If the behavior estimation result is valid (Yes in step S107), in step S108, automatic driving evaluation unit 13 outputs the behavior estimation result to vehicle controller 2 and notification device 5b of information notification unit 5”; at least as in paragraph 0062, “In step S201, learning unit 11 and behavior estimation unit 12 execute processing in steps S101 to S103 in FIG. 5, specifies a running scene of vehicle 1 from information about vehicle 1 and a condition about vehicle 1, and outputs a behavior estimation result of vehicle 1 to image display system 100 by using a dedicated behavior estimation NN corresponding to the specified running scene”), and
controlling an operation of the mobile body according to the derived control command (at least as in paragraph 0066, “If the input instructing the behavior by the driver of vehicle 1 is not executed (No in step S203), automatic driving evaluation unit 13 outputs the estimated behavior “acceleration” to vehicle controller 2, and vehicle controller 2 controls vehicle 1 according to the acquired behavior “acceleration” (step S206)”).
But Motomura does not explicitly teach calculating an intensity indicating a degree to which the movement of the mobile body is forced to be performed by the determined movement mode.
However, Chen, in the same field of endeavor of autonomous vehicle control and operation in varying environments and scenarios, specifically teaches calculating an intensity indicating a degree to which the movement of the mobile body is forced to be performed by the determined movement mode (at least as in paragraph 0036, “The trigger signal from the signal generator 102 may include data representative of the type of vehicle maneuver to be completed by the vehicle 140”; at least as in paragraph 0037, “The trigger signal may be received in response to an input received by the vehicle 140 and/or in response to a decision made by the vehicle 140”; at least as in paragraph 0140-0148, wherein the system receives a trigger signal, set a control input to an initial value based on the trigger signal, receive sensor data, apply the sensor data along with the initial control value and map data to a machine learning model, and receive control from the machine learning model; at least as in paragraph 0249-0250, wherein the autonomous vehicle may include a primary computer or first controller which determines a confidence score indicating its confidence in the chosen result and the supervisory MCU may decide whether to heed the result from a primary computer based on the confidence score received).
Therefore, it would have been obvious to one of the ordinary skill in the art at the effective filing date of the instant invention to modify the teachings of Motomura, to include Chen’s teaching of calculating a confidence score and determining control signals based on the confidence score, since Chen teaches wherein the calculation of confidence and backup computers improves the system’s accuracy in determining results by reducing false positive results.
Regarding claim 5, in view of the above combination of Motomura and Chen, Motomura further teaches:
The control device according to claim 1, wherein
an input of each of the plurality of trained control models is optimized according to the corresponding movement mode (at least as in paragraph 0038, “learning unit 11 optimizes weighting between the nodes of the neural network such that an output from the neural network corresponds to behavior which is supervised-learning data associated with the input parameters. As a result of the weighting adjustment, learning unit 11 makes the neural network learn a relation between the input parameters and the supervised-learning data, and constructs a general-purpose behavior estimation NN corresponding to the arbitrary drivers”).
Regarding claim 6, the above combination of Motomura and Chen teaches the control device according to claim 1 but does not explicitly teach wherein each of the plurality of trained control models is configured to generate a control command such that the higher the intensity, the more forcibly the movement of the mobile body is executed in the movement mode.
However, Chen, in the same field of endeavor of autonomous vehicle control and operation in varying environments and scenarios, specifically teaches wherein each of the plurality of trained control models is configured to generate a control command such that the higher the intensity, the more forcibly the movement of the mobile body is executed in the movement mode (at least as in paragraph 0250, “If the confidence score exceeds a threshold, the supervisory MCU may follow the primary computer's direction, regardless of whether the secondary computer provides a conflicting or inconsistent result”).
Therefore, it would have been obvious to one of the ordinary skill in the art at the effective filing date of the instant invention to modify the teachings of Motomura, to include Chen’s teaching of calculating a confidence score and determining control signals based on the confidence score, since Chen teaches wherein the calculation of confidence and backup computers improves the system’s accuracy in determining results by reducing false positive results.
Regarding claim 7, the above combination of Motomura and Chen teaches the control device according to claim 6 but does not explicitly teach wherein the control command is generated such that the higher the intensity, the smaller a limitation of an execution parameter of the control command.
However, Chen, in the same field of endeavor of autonomous vehicle control and operation in varying environments and scenarios, specifically teaches wherein the control command is generated such that the higher the intensity, the smaller a limitation of an execution parameter of the control command (at least as in paragraph 0250, “the primary computer may be configured to provide the supervisory MCU with a confidence score, indicating the primary computer's confidence in the chosen result. If the confidence score exceeds a threshold, the supervisory MCU may follow the primary computer's direction, regardless of whether the secondary computer provides a conflicting or inconsistent result. Where the confidence score does not meet the threshold, and where the primary and secondary computer indicate different results (e.g., the conflict), the supervisory MCU may arbitrate between the computers to determine the appropriate outcome”).
Therefore, it would have been obvious to one of the ordinary skill in the art at the effective filing date of the instant invention to modify the teachings of Motomura, to include Chen’s teaching of calculating a confidence score and determining control signals based on the confidence score, since Chen teaches wherein the calculation of confidence and backup computers improves the system’s accuracy in determining results by reducing false positive results.
Regarding claim 8, the above combination of Motomura and Chen teaches the control device according to claim 7 but does not explicitly teach wherein the movement mode is lane changing, and the control command is generated such that a degree to which a lane change is forced is increased as the intensity increases, by at least one of:
executing the lane change earlier,
executing the lane change in a narrow space, or
increasing acceleration/deceleration.
However, Chen, in the same field of endeavor of autonomous vehicle control and operation in varying environments and scenarios, specifically teaches wherein the movement mode is lane changing, and the control command is generated such that a degree to which a lane change is forced is increased as the intensity increases (at least as in paragraph 0036, “the trigger signal may include data representing or otherwise indicative of a right lane change (e.g., change lanes from current lane to adjacent lane(s) to the right of the vehicle 140), a left lane change (e.g., change lanes from current lane to adjacent lane(s) to the left of the vehicle 140), and/or other vehicle maneuver, such as a turn or lane split, as described in more detail below with respect to FIGS. 5A-5C.”; , by at least one of:
executing the lane change earlier,
executing the lane change in a narrow space, or
increasing acceleration/deceleration. (at least as in paragraph 0047, “when computing a recommended vehicle trajectory, the machine learning model(s) 118 may use the lane change parameter(s) 114 because the lane change parameter(s) 114 may indicate where along the recommended vehicle trajectory the lane change should end (e.g., based at least in part on the length of the lane change), how quickly the lane change should be completed (e.g., based at least in part on the duration of the lane change), and/or a combination thereof (e.g., based at least in part on the tempo factor). In addition, the lane change progress 122 may be affected by the lane change parameter(s) 114 (e.g., the lane change progress 122 will increase more quickly for shorter lane changes, shorter durations, etc.)”).
Therefore, it would have been obvious to one of the ordinary skill in the art at the effective filing date of the instant invention to modify the teachings of Motomura, to include Chen’s teaching of calculating a confidence score and determining control signals based on the confidence score, since Chen teaches wherein the calculation of confidence and backup computers improves the system’s accuracy in determining results by reducing false positive results.
Claim(s) 3 and 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Motomura in view of Chen, and further in view of Hatano (US 20190061745 A1).
Regarding claim 3, in view of the above combination of Motomura and Chen, Motomura further teaches:
The control device according to claim 1, wherein
the mobile body is a vehicle (at least as in paragraph 0021, “image display system 100 is mounted on vehicle 1 capable of running on a road, such as an automobile, a truck, or a bus… may be mounted to any moving body, such as an airplane, a ship, or an unmanned conveyer”),
the plurality of trained control models includes a first trained control model(at least as in paragraph 0034, “Learning unit 11 constructs a neural network of specific driver x of vehicle 1 from a driving history… running history of driver x”; at least as in paragraph 0035-0036, wherein the driving history and running history is constructed based on feature quantities, such as running state, and environmental parameters such as peripheral conditions; at least as in paragraph 0048, “The running scene includes elements such as running environment, weather during running, and a traffic condition of a vehicle”; see also 0048), and
the determining the movement mode includes selecting one of the modes of the lane change, the lane keeping, and the emergency stop (at least as in paragraph 0065-0067, wherein the behavior estimation results may include “acceleration” or “lane change”).
But Motomura does not explicitly teach:
for lane change… for lane keeping… for emergency stop.
However, Hatano, in the same field of endeavor of a vehicle control device configured to conduct an automatic driving control, specifically teaches:
for lane change… for lane keeping… for emergency stop (at least as in paragraph 0053, “The automatic driving control unit 110, for example, performs control by performing switching between a drive mode A, a drive mode B, a drive mode C, and a drive mode D in accordance with a direction from the switching control unit 140”; at least as in paragraph 0064, “The action plan, for example, is configured of a plurality of events that are sequentially executed. The events, for example, include a deceleration event of decelerating the subject vehicle M, an acceleration event of accelerating the subject vehicle M, a lane keeping event of causing the subject vehicle M to run without deviating from a running lane, a lane changing event of changing a running lane, an overtaking event of causing the subject vehicle M to outrun a vehicle running ahead, a branching event of changing a lane to a desired lane at a branching point or causing the subject vehicle M to run without deviating from a current running lane, a merging event of accelerating/decelerating the subject vehicle M and changing a running lane in a merging lane for merging into a main lane, and the like”; at least as in paragraph 0051, “The pre-operation alarm device 96 receives a control direction from the unexpected event avoiding control device 200 and performs a visible, audible, or tactile notification operation for an occupant of the subject vehicle M before execution of an emergency avoidance operation. The emergency avoidance operation includes execution of automatic drive stopping control for stopping automatic driving control when an unexpected event occurs in accordance with detection of a target or execution of avoidance control of automatically controlling one or both of acceleration/deceleration and steering of the subject vehicle M").
Therefore, it would have been obvious to one of the ordinary skill in the art at the effective filing date of the instant invention to modify the teachings of Motomura, to include Hatano's teaching of vehicle control device utilizing different action planes for various events, since Hatano teaches wherein the control device improves safety for occupants and other personnel by avoiding unexpected events appropriately.
Regarding claim 4, in view of the above combination of Motomura, Chen, and Hatano, Motomura further teaches:
The control device according to claim 3, wherein
the acquired movement condition data includes reaction data indicating a reaction of an occupant riding the vehicle (at least as in paragraph 0024, “Operation system detector 3 detects information operated by a driver of vehicle 1 and information operated by automatic driving control system 10”; at least as in paragraph 0029, “Information acquisition unit 5a may also acquire output information from operation system detector 3, output information from input unit 4, output information from state detector 6, etc. and display the acquired output information on notification device 5b”; at least as in paragraph 0035, “The driving history is constructed by associating each behavior performed by a vehicle in the past with a plurality of feature quantities… The feature quantity is, for example, a running state of the vehicle to be detected by operation system detector 3 and state detector 6”; at least as in paragraph 0040, “Note that behavior estimation unit 12 is configured to acquire detection results from operation system detector 3 and state detector 6”).
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RICARDO I VISCARRA whose telephone number is (571)270-0154. The examiner can normally be reached M-F 9-12 & 2-4 PST.
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, Adam Mott can be reached on (571) 270-5376. 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.
/RICARDO I VISCARRA/Examiner, Art Unit 3657
/ADAM R MOTT/Supervisory Patent Examiner, Art Unit 3657
Prosecution Insights