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
This communication is a first office action, non-final rejection on the merits. Claims 1-20 as filed, are currently pending and have been considered below.
Priority
Should applicant desire to obtain the benefit of foreign priority under 35 U.S.C. 119(a)-(d) prior to declaration of an interference, a certified English translation of the foreign application must be submitted in reply to this action. 37 CFR 41.154(b) and 41.202(e). Failure to provide a certified translation may result in no benefit being accorded for the non-English application.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-8 and 11-13 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Asatani (WO2021117479 A1 hereinafter “Asatani”). This office action relies on the provided Google machine translation of Asatani to provide figures, figure element numbers, and paragraph numbers. This office action relies on the translation of Asatani in the USPTO database for direct quotations of text due to minor inconsistencies in translations.
Regarding claim 1, Asatani discloses in figures 1 through 4
An information processing apparatus (40), comprising a learning model (43) that receives input of current position information (13) of a controlled device (10), target position information (50) including position information of a movement destination (41) of the controlled device, and obstacle information (61, 62) including a distance and a direction from the controlled device to a closest obstacle (61), and outputs the position information updated (S104-S106) in such a manner that the controlled device moves to the movement destination while avoiding the obstacle (q11-q19).
Asatani pertains to the control of a robotic device and employs a learning model to iteratively plan, and execute, a trajectory to a target while avoiding obstacles. The details of the processing apparatus 40, the learning model 43, and the trajectory generation unit 41 (also machine translated to orbit generation unit) begin in 0013 in addition to figure 1. The details of the controlled device 10 (there robot), target position 50, and obstacle positions 61, and 62 are found in figure 2 and 0024. The iterative process of controlling the device can be found in figure 3, particularly steps S104-S106 (detailed in 0037-0039). With the updated position at iteration q being depicted as positions q11-q19 of figure 4 (0042).
Regarding claim 2, Asatani discloses all the limitations of claim 1, and Asatani further discloses in step S104 of figure 3 wherein the learning model outputs the position information for each step in which the controlled device moves. The stepwise control of the robot is shown in figure 3, and Asatani details that the output of the trajectory generating unit 41 contains position information, stating “In step S104, the trajectory generating unit 41 includes state information and spatial information at the current position and target position of the robot arm 10 (coordinate information of the object 50 and obstacles 61 and 62, state information at the target position of the robot arm 10). , And the first trained model 43 is used to generate orbital information” (0037).
Regarding claim 3, Asatani discloses all the limitations of claim 1, and Asatani further discloses wherein the position information includes coordinate information where the controlled device is located. Asatani refers to coordinate information in terms of spatial information, specifying “the trajectory generation unit 41 inputs the state information and the spatial information at the current position and the target position of the robot arm 10 into the first trained model 43” (0037).
Regarding claim 4, Asatani discloses all the limitations of claim 1, and Asatani further discloses wherein the position information includes posture information of the controlled device. Asatani refers to posture information in terms of robot state information, specifying “the trajectory generation unit 41 inputs the state information and the spatial information at the current position and the target position of the robot arm 10 into the first trained model 43” (0037).
Regarding claim 5, Asatani discloses all the limitations of claim 1, and Asatani further discloses wherein the learning model is a neural network by detailing “The first trained model 43 can be any machine learning model capable of generating orbital information based on state information and spatial information. For example, the first trained model 43 can be realized by CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), RSTM (Long Short-Term Memory), DNN (Deep Neural Network), or a combination thereof.” (0016).
Regarding claim 6, Asatani discloses all the limitations of claim 1, and Asatani further discloses wherein the controlled device is a robot in element 10 of figure 2.
Regarding claim 7, Asatani discloses all the limitations of claim 6, and Asatani further discloses wherein the obstacle information includes a distance and a direction from each of a plurality of links included in the robot to the closest obstacle. The learning model of Asatani receives state information and spatial information as inputs when calculating a trajectory that avoids an obstacle. Asatani further details the state information as “The state information includes, but is not limited to, information indicating the joint angles of the joint 12 and the end effector 11 and the coordinates of each part of the robot arm 10 including the end effector 11” (0013). Asatani further details the spatial information as “the spatial information includes, for example, the coordinates of an obstacle included in the work space of the robot arm 10” (0016). It is understood by one of ordinary skill in the art of robotic control that the distance and direction between an obstacle and a robot link is calculated by the learning model of Asatani.
Regarding claim 8, Asatani discloses all the limitations of claim 1, and Asatani further discloses in figures 2 and 3 an obstacle information generation unit (S102) that acquires environment information (30) regarding an environment around the controlled device and generates the obstacle information. In the system of Asatani obstacle information is first generated by the trajectory generation unit, specifically “the trajectory generation unit 41 recognizes an object (object and obstacle) existing in the work space by using the RGB image and the depth image included in the first image data” (0034). Once the object is recognized as an obstacle, the obstacle information is generated, specifically “the coordinates of the object existing in the work space can be obtained. The type (spatial information) of each object is estimated. The estimated spatial information can be output as a point cloud with the type (label) of each object. In the example of FIG. 2, the object 50, the obstacle 61, and the obstacle 62 are recognized as the objects existing in the work space” (0034).
Regarding claim 11, Asatani discloses all the limitations of claim 1, and Asatani further discloses in figures 5 and 6 a storage unit (402 403) that stores the obstacle information, wherein the learning model receives input of the obstacle information stored in the storage unit (46) and outputs the position information. In the system disclosed by Asatani target and obstacle recognition is performed by the trajectory generation unit 41 at step S102 before being inputted into the learning model 43. Obstacle recognition is accomplished via “MMSS (Multi-model Sharable and Specific Feature Learning for RGB-D Object Recognition), which is a three-dimensional object recognition method using CNN, is used. In this case, by inputting the 3D data into the trained model in which the correlation between the 3D data (RGB image and depth image) and the type (label) of the object is machine-learned, the coordinates of the object existing in the work space can be obtained” (0034). It is understood by those of ordinary skill in the art of robotic control that training data for machine learning is stored in a storage unit. Asatani discloses the use of standard computer memory such as RAM, HDD, and SDD for storage units 402 and 403. Asatani further discloses the use of a trajectory storage unit 46 to store a trajectory, including obstacle position information.
Regarding claim 12, Asatani discloses in figures 1, 2, and 4 A learning model (43) that receives input of current position information (13) of a controlled device (10), target position information (50) including position information of a movement destination (41) of the controlled device, and obstacle information (61, 62) including a distance and a direction from the controlled device to a closest obstacle (61), and outputs the position information updated in such a manner that the controlled device moves to the movement destination while avoiding the obstacle (q11, q12,…q19). Claim 12 is rejected in a similar fashion to claim 1 above.
Regarding claim 13, Asatani discloses in figures 1-4, and 6 An information processing method (S101-S110) comprising learning by a computer (401) using a learning model (43), wherein the learning model receives input of current position information (13) of a controlled device (10), target position information (50) including position information of a movement destination (41) of the controlled device (10), and obstacle information (61, 62) including a distance and a direction from the controlled device to a closest obstacle (61), and outputs the position information updated in such a manner that the controlled device moves to the movement destination while avoiding the obstacle (q11, q12,…q19). Claim 13 is rejected in a similar fashion to claim 1 above.
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.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Asatani in view of Tateno et al (U.S. Patent application publication 20200073399 A1 hereinafter “Tateno”).
Regarding Claim 9, Asatani discloses all the limitations of claim 8, and Asatani further teaches various methods for obstacle information generation, stating “Various methods can be used as the object recognition method. For example, MMSS (Multi-model Sharable and Specific Feature Learning for RGB-D Object Recognition), which is a three-dimensional object recognition method using CNN, is used” (0034). Asatani fails to teach the specific use of a signed distance field. However, Tateno teaches wherein the obstacle information generation unit generates the obstacle information by using a signed distance field. Tateno pertains to a method of controlling a controlled device by determining the distance between an obstacle and the controlled device. Tateno discloses the use of signed distance fields by detailing “the determination unit 1160 may calculate the control values for avoiding an obstacle based on Euclidean Signed Distance Fields (ESDFs) storing the signed distance to the closest obstacle and perform movement control. As a control map, the determination unit 1160 stores a cost map storing values which decrease with decreasing distance to the destination. The determination unit 1160 may determine the control values by using a deep reinforcement learning machine as a neural network having learned to determine the control values by inputting the cost map and the input depth map” (0066). Therefore it would have been known to one of ordinary skill in the art of robotic control to use SDFs as disclosed by Tateno as one of the various methods of object recognition as disclosed by Asatani.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Asatani in view of Yoichi et al (Japanese Patent application publication 2013145497 A1 hereinafter “Yoichi”). This office action relies on the provided Google machine translation of Yoichi to provide figures, figure element numbers, and paragraph numbers. This office action relies on the translation of Yoichi in the USPTO database for direct quotations of text due to minor inconsistencies in translations .
Regarding Claim 10, Asatani discloses all the limitations of claim 8, and Asatani further teaches various methods for obstacle information generation, stating “Various methods can be used as the object recognition method” (0034). Asatani fails to teach the specific use of a Voronoi grid. However, Yoichi teaches wherein the obstacle information generation unit converts an occupancy grid into a Voronoi grid, and generates the obstacle information on a basis of the Voronoi grid. Yoichi pertains to a method of route planning and obstacle avoidance. Yoichi discloses the use of Voronoi grids to obtain the distance between the controlled object and an obstacle by detailing “FIG. 11 shows an example of the Voronoi space (potential field corresponding to the distance between the object 31 and the surrounding structure (30)) generated in the route planning process of S25. Reference numeral 1100 denotes an example of a point (unit for calculation, coordinates) corresponding to the current position of the workpiece (object 31). Reference numeral 1101 denotes a non-interference area, and points included in this area have no interference. Reference numeral 1102 denotes an interference area, and a point included in this area is interference. In this case, the interference state is determined based on the binary value of the presence / absence of interference” (0107). Therefore, it would have been known to one of ordinary skill in the art of robotic control to use Voronoi grids as disclosed by Yoichi as one of the various methods of object recognition as disclosed by Asatani.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nathan Daniel Neckel whose telephone number is (571)272-9537. The examiner can normally be reached M-F, 7-3.
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, Wade Miles can be reached at 571-270-7777. 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.
/NATHAN DANIEL NECKEL/Examiner, Art Unit 3656
/WADE MILES/Supervisory Patent Examiner, Art Unit 3656
Prosecution Insights