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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 04/15/2026 has been entered.
Response to Arguments
Applicant’s arguments, see Remarks page 7, filed 04/15/2026, with respect to the rejections of claims 1-12 and 14-15 under 35 U.S.C. 101 have been fully considered and are persuasive. The rejections of claims 1-12 and 14-15 have been withdrawn.
Applicant's arguments, see Remarks pages 7-11, filed 04/15/2026, with respect to the rejections of claims 1 and 14-15 under 35 U.S.C. 103 have been fully considered but they are not persuasive.
On pages 8-9 of Remarks, Applicant argues:
PNG
media_image1.png
940
757
media_image1.png
Greyscale
Examiner respectfully disagrees.
In response to applicant's argument that “Amano' s distance-based algorithm switching is motivated by computational efficiency considerations, not by the physical/spatial problem of partial target capture at close range”, a recitation of the intended use of the claimed invention must result in a structural difference between the claimed invention and the prior art in order to patentably distinguish the claimed invention from the prior art. If the prior art structure is capable of performing the intended use, then it meets the claim.
In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
The Abstract of Lee discloses “The proposed framework integrates deep learning methods for perception and variational Bayesian techniques for trajectory prediction. Deep learning modules enable robots to accompany a person by detecting the target, learning the target and following while avoiding collision within the dynamic home environment”. Wherein the human following system disclosed by Lee discloses a camera which follows a specific target and a robot which attempts to maintain a following relationship with a target person.
Paragraph 0197 of Amano discloses “Furthermore, in the tracking process of the object recognition device 1 according to this embodiment, the matching process method is switched depending on the distance to the object. That is, when the object is close, the number of pixels in the detection area is large, so rough matching processing is performed to perform template matching using a thinned prediction area and a thinned template in which pixels are significantly thinned out. Furthermore, when the object is far away, a part matching process is performed in which template matching is performed using a thinned prediction region and a thinned template in the same manner as in the rough matching process to identify the rough position of the object, and template matching is performed using a part template”. Wherein the object recognition algorithm is modified based on the vehicle’s distance from the object being tracked.
In addition, as discussed further below in the rejection of claim 1 under 35 U.S.C. 103, Figures 9 & 10, and paragraphs 0057 & 0063-0064 of prior art Kunihiro disclose the claim limitations “in a case where it is determined that recognition of the follow-up target will be obstructed by an obstacle, control the movable device based on a position of the follow-up target so that the distance to the follow-up target becomes shorter”.
Therefore, as further disclosed in the rejection of claim 1 under 35 U.S.C. 103 below, Lee in view of Kunihiro and Amano discloses the claim 1 limitations “change a recognition algorithm for recognizing the follow-up target based on a distance to the follow-up target…
in a case where it is determined that recognition of the follow-up target will be obstructed by an obstacle, control the movable device based on a position of the follow-up target so that the distance to the follow-up target becomes shorter, and
in a case where the distance to the follow-up target becomes shorter than a predetermined distance threshold as a result of controlling the movable device, change the recognition algorithm for recognizing the follow-up target”.
On page 9 of Remarks, Applicant argues:
PNG
media_image2.png
413
719
media_image2.png
Greyscale
Examiner respectfully disagrees.
In response to applicant's argument that Lee's person re-identification algorithm and Amano's distance-based image matching algorithms are fundamentally different architectures, the test for obviousness is not whether the features of a secondary reference may be bodily incorporated into the structure of the primary reference; nor is it that the claimed invention must be expressly suggested in any one or all of the references. Rather, the test is what the combined teachings of the references would have suggested to those of ordinary skill in the art. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981).
Section III. A. 2.) Person Re-identification of Lee discloses “The ability to identify the correct target is essential for home service robots to follow the target person and provide proper service to the correct person. Therefore, we investigated using a re-identification (one-to-one correspondence of database and the current image) algorithm with the detected bounding box of the person from the person detection module. We adopted the [15] re-identification algorithm which uses the Siamese network and combines the matching layers to achieve state-of-the- art performance”. Wherein the reidentification algorithm disclosed by Lee serves to investigate the one-to-one correspondence between database images and a detected bounding box of a person from the person detection module.
Paragraph 0197 of Amano discloses “when the object is close, the number of pixels in the detection area is large, so rough matching processing is performed to perform template matching using a thinned prediction area and a thinned template in which pixels are significantly thinned out. Furthermore, when the object is far away, a part matching process is performed in which template matching is performed using a thinned prediction region and a thinned template in the same manner as in the rough matching process to identify the rough position of the object, and template matching is performed using a part template”. Wherein the object matching process disclosed by Amano serves to investigate the one-to-one correspondence between a template image and a current image based on the vehicle’s distance to the object.
Thus, it would have been obvious for one of ordinary skill in the art, prior to the effective filing date of the claimed invention, to substitute the person reidentification algorithm disclosed by Lee in view of Kunihiro with the distance based image matching algorithms taught by Amano in order to modify the recognition algorithm based on the robot’s distance to its target.
Therefore, as further disclosed in the arguments above and in the rejection of claim 1 under 35 U.S.C. 103 below, Lee in view of Kunihiro and Amano discloses the limitations of claim 1.
As per claim(s) 14 & 15, arguments made in rejecting claim(s) 1 are analogous.
On pages 9-10 of Remarks, Applicant argues:
PNG
media_image3.png
1083
731
media_image3.png
Greyscale
Applicant’s arguments, with respect to the rejection of claim(s) 1 and 14-15 under 35 U.S.C. 103, specifically in regards to prior art Nishimura, have been fully considered and are moot in view of the new grounds of rejection (detailed in the rejections below).
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.
Claim(s) 1-4, 8, and 11-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al. (Robust Human Following by Deep Bayesian Trajectory Prediction for Home Service Robots) hereinafter referenced as Lee, in view of Kunihiro et al. (JP2010015194A) hereinafter referenced as Kunihiro, and Amano et al. (JP2017151535A) hereinafter referenced as Amano.
Regarding claim 1, Lee discloses: An information processing device comprising: circuitry configured to drive a movable device including one or more actuators for following a follow-up target (Lee: Figure 4; SECTION IV. A. Infrastructure Setting: “The used laptop was the Asus EeePC 1215N laptop (Intel AtomTM D525 Dual Core Processor) to execute the Turtlebot2.”; Wherein the robots are controlled using the laptop processor),
recognize the follow-up target (Lee: Figure 4; SECTION III. A. Detecting and Learning to Follow a Person: Perception and Learning: “To detect people in a real-time manner, we employed the YOLOv2 [13] algorithm.”; SECTION IV. A. Infrastructure Setting: “For deep learning modules, we prepared a GPU server, Ubuntu 14.04 (ROS Indigo) based 12GB memory PASCAL GPU slotted computer.”), and
determine a trajectory of the follow-up target (Lee: Abstract: “The variational Bayesian techniques robustly predict the trajectory of the target by empowering the following ability of the robot when target is lost. We experimentally demonstrate the capability of the deep Bayesian trajectory prediction method on real-time usage”).
Lee does not disclose expressly: in a case where it is determined that recognition of the follow-up target will be obstructed by an obstacle, control the movable device based on a position of the follow-up target so that the distance to the follow-up target becomes shorter.
Kunihiro discloses: in a case where it is determined that recognition of a follow-up target will be obstructed by an obstacle, control a movable device based on a position of the follow-up target so that the distance to the follow-up target becomes shorter (Kunihiro: Figures 9 & 10;
0057: “when there is a risk that the field of view to the target 101 will be obstructed by an obstacle 201, or when it is obstructed, this autonomous mobile robot device controls the driving unit 1 to move in a direction that increases the field of view margin, thereby ensuring a clear view to the target 101”;
0063-0064: “As shown in Figure 9, the autonomous mobile robot device according to the present invention, when moving in the direction of arrow a (the opposite direction to the direction of the field of view margin), moves to point b, the intersection of the perpendicular line of arrow a and the furthest point of the reachable range, thereby widening the field of view margin while preventing the distance to the tracking target 101 from increasing, and enabling tracking of the tracking target 101. Figure 10 is a plan view showing the operation of the third field of view securing algorithm in the autonomous mobile robot device according to the present invention.”;
Wherein the robot decreases its distance from the target as it widens its field of view, as illustrated in figures 9 & 10.).
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to incorporate the field of view securing algorithm taught by Kunihiro into the trajectory prediction and following robot disclosed by Lee. The suggestion/motivation for doing so would have been “when there is a risk that the field of view to the target 101 will be obstructed by an obstacle 201, or when it is obstructed, this autonomous mobile robot device controls the driving unit 1 to move in a direction that increases the field of view margin, thereby ensuring a clear view to the target 101” (Kunihiro: 0057). Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Lee in view of Kunihiro does not disclose expressly: change a recognition algorithm for recognizing the follow-up target based on a distance to the follow-up target, and in a case where the distance to the follow-up target becomes shorter than a predetermined distance threshold as a result of controlling the movable device, change the recognition algorithm for recognizing the follow-up target.
Amano discloses: change a recognition algorithm for recognizing the follow-up target based on a distance to the follow-up target, and in a case where the distance to the follow-up target becomes shorter than a predetermined distance threshold as a result of controlling the movable device, change the recognition algorithm for recognizing the follow-up target (Amano: 0197: “in the tracking process of the object recognition device 1 according to this embodiment, the matching process method is switched depending on the distance to the object. That is, when the object is close, the number of pixels in the detection area is large, so rough matching processing is performed to perform template matching using a thinned prediction area and a thinned template in which pixels are significantly thinned out. Furthermore, when the object is far away, a part matching process is performed in which template matching is performed using a thinned prediction region and a thinned template in the same manner as in the rough matching process to identify the rough position of the object, and template matching is performed using a part template.”).
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to substitute the person reidentification algorithm disclosed by Lee in view of Kunihiro with the distance-based image matching algorithms taught by Amano. The suggestion/motivation for doing so would have been “in the case of short distances, rough matching processing is adopted, which increases the detection accuracy of the detection area by frame correction processing… in the case of long distances…part matching processing is adopted, which improves the detection accuracy of the detection area by correction processing using template matching that uses part templates” (Amano: 0197). Further, one skilled in the art could have substituted one known element for another, and the substitution would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Lee in view of Kunihiro with Amano to obtain the invention as specified in claim 1.
Regarding claim 2, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 1, wherein the processing circuitry is further configured to set, in a case where the distance to the follow-up target is a distance equal to or longer than the predetermined distance threshold, the recognition algorithm to a recognition algorithm for normal distance, and set, in a case where the distance to the follow-up target is shorter than the distance threshold, the recognition algorithm to a recognition algorithm for short distance (Amano: 0197: “in the tracking process of the object recognition device 1 according to this embodiment, the matching process method is switched depending on the distance to the object. That is, when the object is close…so rough matching processing is performed to perform template matching using a thinned prediction area and a thinned template in which pixels are significantly thinned out. Furthermore, when the object is far away, a part matching process is performed in which template matching is performed using a thinned prediction region and a thinned template in the same manner as in the rough matching process to identify the rough position of the object, and template matching is performed using a part template.”).
Regarding claim 3, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2, wherein the processing circuitry is further configured to detect a region matching an entire feature of the follow-up target from an image imaged by a camera as the recognition algorithm for normal distance (Amano: 0192: “The third template matching unit 617 of the matching unit 610 performs template matching based on the two part templates updated by the third updating unit 636 for the previous frame, within the detection area 860 detected by template matching by the second template matching unit 616 in the current frame…That is, the third template matching unit 617 detects images within the detection area 860 that match or can be considered to match (hereinafter simply referred to as "matching") the part templates 870 and 871 (or part templates 870a and 871a)...The third template matching unit 617 calculates the SAD based on each of the part templates 870 and 871 (or part templates 870a and 871a) while raster scanning the detection area 860, and finds the position of the image where the SAD is smallest.”; Wherein the matching of part template images constitutes the detection of a region matching an entire feature.).
Regarding claim 4, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2, wherein the processing circuitry is further configured to detect a region of a mobile body as a region of the follow-up target from an image imaged by a camera as the recognition algorithm for normal distance (Amano: 0192: “The third template matching unit 617 of the matching unit 610 performs template matching based on the two part templates updated by the third updating unit 636 for the previous frame, within the detection area 860 detected by template matching by the second template matching unit 616 in the current frame…That is, the third template matching unit 617 detects images within the detection area 860 that match or can be considered to match (hereinafter simply referred to as "matching") the part templates 870 and 871 (or part templates 870a and 871a)...The third template matching unit 617 calculates the SAD based on each of the part templates 870 and 871 (or part templates 870a and 871a) while raster scanning the detection area 860, and finds the position of the image where the SAD is smallest.”).
Regarding claim 8, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2, wherein the processing circuitry is further configured to detect a region matching a feature amount corresponding to the follow-up target from an image imaged by a camera as the recognition algorithm for short distance (Amano: 0160: “The first template matching unit 613 of the matching unit 610 performs template matching based on the thinning template updated by the first updating unit 632 for the previous frame within the thinning prediction region 801 (802) that has been thinned by the first thinning processing unit 612 in the current frame…That is, the first template matching unit 613 detects an image that matches or can be considered to match the thinned template 811 (812) within the thinned prediction region 801 (802)…The first template matching unit 613 calculates the SAD based on the thinning template 811 (812) while raster scanning the thinning prediction region 801 (802), and determines the position of the image with the smallest SAD.”; Wherein the object recognition based on the calculation of image similarity constitutes the detection of a region matching a feature amount.).
Regarding claim 11, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2, wherein the processing circuitry is further configured to predict a trajectory of the follow-up target (Lee: Abstract: “The variational Bayesian techniques robustly predict the trajectory of the target by empowering the following ability of the robot when target is lost. We experimentally demonstrate the capability of the deep Bayesian trajectory prediction method on real-time usage”),
and in a case where it is predicted that the follow-up target that moves along the predicted trajectory deviates from a capturing range in which the follow-up target is recognized, control the movable device so that a distance to the follow-up target becomes shorter than the distance threshold (Kunihiro: Figures 9 & 10; 0057: “when there is a risk that the field of view to the target 101 will be obstructed by an obstacle 201, or when it is obstructed, this autonomous mobile robot device controls the driving unit 1 to move in a direction that increases the field of view margin, thereby ensuring a clear view to the target 101”;
0063-0064: “As shown in Figure 9, the autonomous mobile robot device according to the present invention, when moving in the direction of arrow a (the opposite direction to the direction of the field of view margin), moves to point b, the intersection of the perpendicular line of arrow a and the furthest point of the reachable range, thereby widening the field of view margin while preventing the distance to the tracking target 101 from increasing, and enabling tracking of the tracking target 101. Figure 10 is a plan view showing the operation of the third field of view securing algorithm in the autonomous mobile robot device according to the present invention.”;
Wherein the robot decreases its distance from the target as it widens its field of view, as illustrated in figures 9 & 10. Also, wherein the target being obstructed, or blocked, constitutes a deviation from the capturing range.).
Regarding claim 12, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2, wherein the normal distance is a distance at which an entire follow-up target is recognized (Amano: 0141-0144: “and if the estimated distance is a long distance equal to or greater than a predetermined distance (step S121: long distance), the process proceeds to step S123…<Step S123> The third thinning unit 615, second template matching unit 616, and third template matching unit 617 of the matching unit 610 perform part matching processing using a template based on the detection region detected in the previous frame…Through the processes of steps S121 to S123 described above, the matching process (matching process of tracking process) is performed by the matching unit 610 of the tracking processing unit 520.”; Wherein the matching, and thus tracking of an object, constitutes the entire follow-up target being recognized).
Regarding claim 13, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 1, wherein the follow-up target is a person (Lee: Abstract).
As per claim(s) 14, arguments made in rejecting claim(s) 1 are analogous.
As per claim(s) 15, arguments made in rejecting claim(s) 1 are analogous. In addition, the laptop disclosed in Section: IV. A. Infrastructure Setting of Lee implies the presence of “A non-transitory computer-readable storage medium storing computer-readable instructions.”
Claim(s) 5-7, and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee in view of Kunihiro, and Amano, and further in view of Basso et al. (Fast and Robust Multi-people Tracking from RGB-D Data for a Mobile Robot) hereinafter referenced as Basso.
Regarding claim 5, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2.
Lee in view of Kunihiro, and Amano does not disclose expressly: wherein the processing circuitry is further configured to detect a region of a mobile body as a region of the follow-up target from a measurement range measured by a ranging sensor as the recognition algorithm for normal distance.
Basso discloses: the detection of a target person as a mobile body using a ranging sensor for detection (Basso: 1 Introduction and Related Work: “The track initialization procedure, which relies on a HOG people detector, allows to minimize the number of false positives and the online learning person classifier is used every time a person is lost, in order to recover the correct person ID even after a full occlusion.”; 2 System Overview: “As reported in Fig. 2, the RGB-D data are processed by three main software blocks: filtering, detection and tracking. The filtering block consists in a smart down-sampling of the 3D point cloud…The detection block performs the necessary operations for clustering the remaining points and selecting the clusters of points containing people, that are subsequently passed to the tracking module.”).
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to supplement the person detection and tracking methods for normal and short distances disclosed by Lee in view of Kunihiro, and Amano with the methods for point cloud clustering and people detection and tracking as taught by Basso. The suggestion/motivation for doing so would have been “With the advent of reliable and affordable RGB-D sensors a rapid boosting of robots capabilities can be envisioned…it constitutes a very rich source of information that can be simply used on a mobile platform” (Basso: 1 Introduction and Related Work; Wherein the addition of point cloud data increases the accuracy of the methods.). Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Lee in view of Kunihiro, and Amano with Basso to obtain the invention as specified in claim 5.
Regarding claim 6, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2.
Lee in view of Kunihiro, and Amano does not disclose expressly: wherein the processing circuitry is further configured to detect a region matching a shape of the follow-up target from a measurement range measured by a ranging sensor as the recognition algorithm for normal distance.
Thus, Lee in view of Kunihiro, and Amano does not disclose expressly the detection of the target person by matching the shape of the target with a region of radar sensor data for detection at the normal distance.
Basso discloses: the detection of a target person by matching the shape of the target with a region of radar sensor data (Basso: 4 Detection: “In order to divide the scene into different clusters, our algorithm remove all 3D points belonging to the floor from the output of the previous software block…the different clusters are no longer connected through the floor, so they can be easily calculated by labeling neighboring 3D points on the basis of their Euclidean distances…For each cluster, we estimate: the height from the ground plane, the centroid, the distance from the sensor and the corresponding blob in the RGB image. Clusters with height out of a plausible range for an adult person are discarded before computing the subsequent features and do not pass to the tracking phase.”; Wherein the extraction of cluster points based on human features constitutes the matching of a target’s shape.)
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to supplement the person detection and tracking methods for normal and short distances disclosed by Lee in view of Kunihiro, and Amano with the methods for point cloud clustering and people detection and tracking as taught by Basso. The suggestion/motivation for doing so would have been “With the advent of reliable and affordable RGB-D sensors a rapid boosting of robots capabilities can be envisioned…it constitutes a very rich source of information that can be simply used on a mobile platform” (Basso: 1 Introduction and Related Work; Wherein the addition of point cloud data increases the accuracy of the methods.). Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Lee in view of Kunihiro, and Amano with Basso to obtain the invention as specified in claim 6.
Regarding claim 7, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2.
Lee in view of Kunihiro, and Amano does not disclose expressly: wherein the processing circuitry is further configured to detect a region matching a representative color of the follow-up target from an image imaged by a camera as the recognition algorithm for short distance.
Thus, Lee in view of Kunihiro, and Amano does not disclose expressly the detection of the target person by detecting a region matching a representative color of the target for detection at the short distance.
Basso discloses: the detection of the target person by detecting a region matching a representative color of the target (Basso: 5.2 Online Classifier: “we maintain for each track an online classifier based on Adaboost...we select the image pixels belonging to the person by exploiting the blob mask given by the detector; 2. we compute the 3D color histogram of these points on the three RGB channels; 3. we select a set of randomized parallelepipeds (one for each weak classifier) inside the histogram. The feature value is given by the sum of histogram elements that fall inside a given parallelepiped.
For the training phase, since the approach introduced by [10] gave us poor performances, we use as positive sample the color histogram of the target, while as negative samples we consider the histograms calculated on the detections not associated to the current track.”; Wherein a target is detected based on a model trained using the target’s corresponding colors).
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify the person reidentification algorithm for normal and short distances disclosed by Lee in view of Kunihiro, and Amano with the inclusion of the trained online classifier disclosed Basso. The suggestion/motivation for doing so would have been “This approach has the advantage to select only the colors that really characterize the target and distinguish it from all the others.” (Basso: 5.2 Online Classifier). Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Lee in view of Kunihiro, and Amano with Basso to obtain the invention as specified in claim 7.
Regarding claim 9, Lee in view of Kunihiro, and Amano discloses: The information processing device according to claim 2.
Lee in view of Kunihiro, and Amano does not disclose expressly: wherein the processing circuitry is further configured to detect a region of a mobile body as a region of the follow-up target from a measurement range measured by a ranging sensor as the recognition algorithm for short distance.
Thus, Lee in view of Kunihiro, and Amano does not disclose expressly the detection of the target person as a mobile body using a ranging sensor for detection at the short distance.
Basso discloses: the detection of a target person as a mobile body using a ranging sensor for detection (Basso: 1 Introduction and Related Work: “The track initialization procedure, which relies on a HOG people detector, allows to minimize the number of false positives and the online learning person classifier is used every time a person is lost, in order to recover the correct person ID even after a full occlusion.”; 2 System Overview: “As reported in Fig. 2, the RGB-D data are processed by three main software blocks: filtering, detection and tracking. The filtering block consists in a smart down-sampling of the 3D point cloud…The detection block performs the necessary operations for clustering the remaining points and selecting the clusters of points containing people, that are subsequently passed to the tracking module.”).
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to supplement the person detection and tracking methods for normal and short distances disclosed by Lee in view of Kunihiro, and Amano with the methods for point cloud clustering and people detection and tracking as taught by Basso. The suggestion/motivation for doing so would have been “With the advent of reliable and affordable RGB-D sensors a rapid boosting of robots capabilities can be envisioned…it constitutes a very rich source of information that can be simply used on a mobile platform” (Basso: 1 Introduction and Related Work; Wherein the addition of point cloud data increases the accuracy of the methods.). Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine Lee in view of Kunihiro, and Amano with Basso to obtain the invention as specified in claim 9.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANTHONY J RODRIGUEZ whose telephone number is (703)756-5821. The examiner can normally be reached Monday-Friday 10am-7pm.
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, Sumati Lefkowitz can be reached at (571) 272-3638. 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.
/ANTHONY J RODRIGUEZ/Examiner, Art Unit 2672
/SUMATI LEFKOWITZ/Supervisory Patent Examiner, Art Unit 2672
Prosecution Insights