IP Library › Granted Patent US 12,585,275
Granted Patent B1
US 12,585,275 · App. 16/378,188 · Granted Mar 24, 2026

Loss scaling for neural networks

Inventors: Blythe Towal (San Diego, CA); Carolina Parada (Boulder, CO); Vijay Chintalapudi (Sunnyvale, CA); Maroof Mohammed Farooq (Boulder, CO)
Assignee: NVIDIA Corporation
G05D1/0221B60W30/10B60W40/072G05D1/0088G06N3/045G06N3/048G06N5/04B60W2552/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,585,275
App. No.
16/378,188
Granted
Mar 24, 2026
Kind
B1
Abstract

A navigation path can be determined for an object using one or more neural networks. In various embodiments, image data is obtained that is representative of an environment in which the object is to be navigated. Relevant features are identified from the image, and a curve fit to those features. Loss values for the potential paths are scaled based at least in part upon the distance of those features in the real world. This can include, in at least some embodiments, performing the scaling as a function of the curvature of the curve fit to the features. Temporal smoothing can be performed with respect to prior path predictions in order to prevent sudden changes in the predicted path. The paths are analyzed to select a path with a highest confidence value that also at least satisfies a minimum confidence criterion. The path can be converted into three-dimensional navigation information.

Claims (36)

1 . One or more processors comprising: circuitry to:

identify a distribution of different geometric features of one or more paths within a plurality of images;

determine a relative frequency of the different geometric features based on the distribution;

calculate loss values based, at least in part, on one or more outputs generated by one or more neural networks using the plurality of images;

compute scaled loss values by scaling at least one of the loss values based, at least in part, on the relative frequency of the different geometric features; and

update the one or more neural networks to predict one or more additional paths of one or more vehicles based, at least in part, on the scaled loss values.

2 . The one or more processors of claim 1 , wherein the different geometric features comprise at least one of distances between objects, pixel locations of path features represented in the plurality of images, or pixel locations of lens distortions represented in the plurality of images.

3 . The one or more processors of claim 1 , wherein the scaling of the loss values is further based, at least in, part on an inverse of a frequency of a geometric feature indicated by the distribution of the different geometric features.

4 . The one or more processors of claim 1 , wherein the distribution of the different geometric features is indicated by one or more histograms.

5 . The one or more processors of claim 1 , wherein the different geometric features include one or more curvatures.

6 . The one or more processors of claim 1 , wherein the one or more additional paths are for use in navigating the one or more vehicles.

7 . The one or more processors of claim 1 , wherein the one or more additional paths correspond to a highest confidence score that at least satisfies a minimum confidence threshold.

8 . A system comprising:

one or more computers comprising one or more processors to:

identify a distribution of different geometric features of one or more paths within a plurality of images;

determine a relative frequency of the different geometric features based on the distribution;

calculate loss values based, at least in part, on one or more outputs generated by one or more neural networks using the plurality of images;

compute scaled loss values by scaling at least one of the loss values based, at least in part, on the relative frequency of the different geometric features; and

update the one or more neural networks to predict one or more additional paths of one or more vehicles based, at least in part, on the scaled loss values.

9 . The system of claim 8 , wherein the different geometric features comprise at least one of distances between objects, pixel locations of path features represented in the plurality of images, or pixel locations of lens distortions represented in the plurality of images.

10 . The system of claim 8 , wherein the scaling of the loss values is further based, at least in, part on an inverse of a frequency of a geometric feature indicated by the distribution of the different geometric features.

11 . The system of claim 8 , wherein distribution of the different geometric features is indicated by one or more histograms.

12 . The system of claim 8 , wherein the different geometric features include one or more curvatures.

13 . The system of claim 8 , wherein the one or more additional paths are for use in navigating the one or more vehicles.

14 . The system of claim 8 , wherein the one or more additional paths correspond to having a highest confidence score that at least satisfies a minimum confidence threshold.

15 . A machine-readable medium having stored thereon a set of instructions which, if performed by one or more processors, cause the one or more processors to at least:

identify a distribution of different geometric features of one or more paths within a plurality of images;

determine a relative frequency of the different geometric features based on the distribution;

calculate loss values based, at least in part, on one or more outputs generated by one or more neural networks using the plurality of images;

compute scaled loss values by scaling at least one of the loss values based, at least in part, on the relative frequency of the different geometric features; and

update the one or more neural networks to predict one or more additional paths of one or more vehicles based, at least in part, on the scaled loss values.

16 . The machine-readable medium of claim 15 , wherein the different geometric features comprise at least one of distances between objects, pixel locations of path features represented in the plurality of images, or pixel locations of lens distortions represented in the plurality of images.

17 . The machine-readable medium of claim 15 , wherein the scaling of the loss values is further based, at least in, part on an inverse of a frequency of a geometric feature indicated by the distribution of the different geometric features.

18 . The machine-readable medium of claim 15 , wherein the distribution of the different geometric features is indicated by one or more histograms.

19 . The machine-readable medium of claim 15 , wherein the different geometric features include one or more curvatures.

20 . The machine-readable medium of claim 15 , wherein the one or more additional paths correspond to a highest confidence score that at least satisfies a minimum confidence threshold.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 8, 2019
From: TOWAL, BLYTHE; PARADA, CAROLINA; CHINTALAPUDI, VIJAY; FAROOQ, MAROOF MOHAMMED
To: NVIDIA CORPORATION
Reel/Frame 048823/0135 →
Continuity (1)
Provisional Application 62684328 · Jun 13, 2018
References Cited (148)
US 9373057B1 · Erhan et al. · 2016 [cited by applicant]
US 10157331B1 · Tang et al. · 2018 [cited by applicant]
US 10768621B1 · Nix · 2020 [cited by examiner]
US 20040016870A1 · Pawlicki et al. · 2004 [cited by applicant]
US 20040252864A1 · Chang et al. · 2004 [cited by applicant]
US 20050196034A1 · Hattori et al. · 2005 [cited by applicant]
US 20060178824A1 · Ibrahim · 2006 [cited by examiner]
US 20070154068A1 · Stein et al. · 2007 [cited by applicant]
US 20080266396A1 · Stein · 2008 [cited by applicant]
US 20090088941A1 · Tsuchiya et al. · 2009 [cited by applicant]
US 20090256840A1 · Varadhan et al. · 2009 [cited by applicant]
US 20100322476A1 · Kanhere et al. · 2010 [cited by applicant]
US 20130106837A1 · Mukherjee et al. · 2013 [cited by applicant]
US 20140104424A1 · Zhang et al. · 2014 [cited by applicant]
US 20150054824A1 · Jiang · 2015 [cited by applicant]
US 20150278578A1 · Otsuka et al. · 2015 [cited by applicant]
US 20150346716A1 · Scharfe et al. · 2015 [cited by applicant]
US 20160247290A1 · Liu et al. · 2016 [cited by applicant]
US 20160321074A1 · Hung et al. · 2016 [cited by applicant]
US 20170010613A1 · Fukumoto · 2017 [cited by examiner]
US 20170061632A1 · Lindner et al. · 2017 [cited by applicant]
US 20170116781A1 · Babahajiani et al. · 2017 [cited by applicant]
US 20170124717A1 · Baruch et al. · 2017 [cited by applicant]
US 20170220876A1 · Gao et al. · 2017 [cited by applicant]
US 20170344808A1 · El-Khamy et al. · 2017 [cited by applicant]
US 20170371346A1 · Mei et al. · 2017 [cited by applicant]
US 20180089833A1 · Lewis et al. · 2018 [cited by applicant]
US 20180121273A1 · Fortino et al. · 2018 [cited by applicant]
US 20180136332A1 · Barfield, Jr. et al. · 2018 [cited by applicant]
US 20180158244A1 · Ybanez Zepeda et al. · 2018 [cited by applicant]
US 20180188059A1 · Wheeler et al. · 2018 [cited by applicant]
US 20180203959A1 · Refsnaes et al. · 2018 [cited by applicant]
US 20180232663A1 · Ross et al. · 2018 [cited by applicant]
US 20180267558A1 · Tiwari et al. · 2018 [cited by applicant]
US 20180300590A1 · Briggs et al. · 2018 [cited by applicant]
US 20180304468A1 · Holz · 2018 [cited by applicant]
US 20180348374A1 · Laddha et al. · 2018 [cited by applicant]
US 20180349746A1 · Vallespi-Gonzalez · 2018 [cited by applicant]
US 20180370540A1 · Yousuf et al. · 2018 [cited by applicant]
US 20180373980A1 · Huval · 2018 [cited by applicant]
US 20190066328A1 · Kwant et al. · 2019 [cited by applicant]
US 20190080266A1 · Zhu · 2019 [cited by examiner]
US 20190101399A1 · Sunil Kumar et al. · 2019 [cited by applicant]
US 20190102646A1 · Redmon et al. · 2019 [cited by applicant]
US 20190102668A1 · Yao et al. · 2019 [cited by applicant]
US 20190129831A1 · Goldberg · 2019 [cited by applicant]
US 20190147600A1 · Karasev et al. · 2019 [cited by applicant]
US 20190147610A1 · Frossard et al. · 2019 [cited by applicant]
US 20190171912A1 · Vallespi-Gonzalez et al. · 2019 [cited by applicant]
US 20190179979A1 · Melick · 2019 [cited by applicant]
US 20190272462A1 · Franzius · 2019 [cited by examiner]
US 20190310644A1 · Zhang · 2019 [cited by examiner]
US 20200139959A1 · Akella · 2020 [cited by examiner]
US 20200143205A1 · Yao et al. · 2020 [cited by applicant]
US 20200160559A1 · Urtasun et al. · 2020 [cited by applicant]
US 20200175311A1 · Xu et al. · 2020 [cited by applicant]
US 20200216076A1 · Otto · 2020 [cited by examiner]
US 20200257301A1 · Weiser · 2020 [cited by examiner]
US 20200257306A1 · Nisenzon · 2020 [cited by applicant]
US 20210025696A1 · Goto et al. · 2021 [cited by applicant]
US 20210089794A1 · Chen et al. · 2021 [cited by applicant]
US 20210286923A1 · Kristensen et al. · 2021 [cited by applicant]
EP 1930863A2 · 2008 [cited by applicant]
EP 1930868A1 · 2008 [cited by applicant]
KR 20120009590A · 2012 [cited by applicant]
WO 2016183074A1 · 2016 [cited by applicant]
WO 2018002910A1 · 2018 [cited by applicant]
WO WO2018083672A1 · 2018 [cited by examiner]
WO WO2018132607A2 · 2018 [cited by examiner]
Tony Lacey, “Tutorial: The Kalman Filter”, Jan. 12, 1998, Introduction (Year: 1998). [cited by examiner]
U.S. Appl. No. 62/631,781, “Methods for Accurate Real-time Object Detection and for Determining Confidence of Object Detection Suitable for Autonomous Vehicles,” filed Feb. 18, 2018. [cited by applicant]
Notice of Allowance dated Jul. 16 , 2021 in U.S. Appl. No. 16/728,598 , 9 pages. [cited by applicant]
Notice of Allowance dated Jul . 2, 2021 in U.S. Appl. No. 16/813,306 , 13 pages. [cited by applicant]
Notice of Allowance dated Oct. 7, 2021 in U.S. Appl. No. 16/813,306, 9 pages. [cited by applicant]
Preinterview First Office Action dated Jan. 26, 2021 in U.S. Appl. No. 16/355,328 , 5 pages. [cited by applicant]
Q. Wang, J. Gao and Y. Yuan, Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection, in IEEE Transactions on Intelligent Transportation Systems, vol. 19, No. 1, pp. 2… [cited by applicant]
R. Benenson, R. Timofte, and L. Gool. Stixels estimation without depth map computation. In ICCV, 2011, 8 Pages. [cited by applicant]
Rahul Mohan , “Deep deconvolutional networks for scene parsing”, CORR, abs/1411.4101, 2014. [cited by applicant]
Rothe, R. , Guillaumin, M., & Van Gool, L. (Nov. 2014). Non maximum suppression for object detection by passing messages between windows. In Asian conference on computer vision (pp. 290-306 ). [cited by applicant]
Stein , G. P. , Mano , O. , & Shashua , A. (Jun. 2003). Vision—based ACC with a single camera : bounds on range and range rate accuracy . In IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No. 03TH8683 ) (… [cited by applicant]
Suorsa, R. E. , & Sridhar , B. ( 1994 ) . A parallel implementation of a multisensor feature—based range—estimation method IEEE transactions on robotics and automation , 10 ( 6 ) , 755-768. [cited by applicant]
Szegedy et al., “Going Deeper with Convolutions,” CVPR, 2015, 9 pages. [cited by applicant]
Tao et al., “Detectnet: Deep neural network for object detection in digits,” Retrieved from, DetectNet: Deep Neural Network for Object Detection in Digits | Nvidia Technical Blog <https://developer.nvidia.com/blog/detec… [cited by applicant]
Tateno et al., “CNN-SLAM: Real-time Dense Monocular Slam with Learned Depth Prediction,” CVPR, 2017, 10 pages. [cited by applicant]
Thrun et al., “Probabilistic Robotics,” MIT Press, 2005, 492 pages. [cited by applicant]
U.S. Appl. No. 62/584,549, “Systems and Methods for Safe and Reliable Autonomous Vehicles,” Nov. 10, 2017. [cited by applicant]
U.S. Appl. No. 62/614,466, “Systems and Method for Controlling Autonomous Vehicles,” Jan. 17, 2018. [cited by applicant]
U.S. Appl. No. 62/625,351, “Systems and Method for Safe Operation of Autonomous Vehicles,” Feb. 2, 2018. [cited by applicant]
U.S. Appl. No. 62/628,831, “Conservative Control for Zone Driving of Autonomous Vehicles,” Feb. 9, 2018. [cited by applicant]
U.S. Appl. No. 62/629,822, “Systems and Methods for Sharing Camera Data Between Primary and Backup Controllers in Autonomous Vehicle Systems,” Feb. 13, 2018. [cited by applicant]
U.S. Appl. No. 62/630,445, “Pruning Convolutional Neural Networks for Autonomous Vehicles and Robotics,” Feb. 14, 2018. [cited by applicant]
U.S. Appl. No. 62/635,503, “Systems and Methods for Autonomous Shuttles, Robo-Taxis, Ride-Sharing and On-Demand Vehicles,” Feb. 26, 2018. [cited by applicant]
U.S. Appl. No. 62/636,142, “Methids for Accurate Real-time Lane and Road Boundary Detection for Autonomous Driving,” Feb. 27, 2018. [cited by applicant]
Virgo, “Lane Detection with Deep Learning (Part 1),” Retrieved from, <https://towardsdatascience.com/lane-detection-with-deep-learning-part-1-9e096f3320b7,> May 9, 2017, 16 Pages. [cited by applicant]
Weber, M., Wolf, P., & Zöllner, J. M. (Jun. 2016). DeepTLR: A single deep convolutional network for detection and classification of traffic lights. In 2016 IEEE Intelligent Vehicles Symposium (IV)(pp .342-348 ) . IEEE. [cited by applicant]
Webopedia, “What is a Polyline?,” Retrieved from, <https://www.webopedia.com/definitions/polyline/,> May 25, 2022, 3 Pages. [cited by applicant]
Wikipedia, Euler Spiral, Retrieved from, https://en.wikipedia.org/wiki/Euler_spiral ., Feb. 21, 2019, 1 Page. [cited by applicant]
Wikipedia, “F1 score,” Retrieved from, <https://en.wikipedia.org/wiki/F1_score_.,> Accessed Feb. 21, 2019, 1 Page. [cited by applicant]
A. Elfes . Sonar—based real—world mapping and navigation. Journal of Robotics and Automation, 1987. [cited by applicant]
Asvadi , A. , Garrote, L. , Premebida , C. , Peixoto , P., & Nunes, U. J. (Oct. 2017) . Depthon : vehicle detection using 3d—lidar and convnet. In 2017 IEEE 20th International Conference on Intelligent Transportation Sy… [cited by applicant]
Bach, M. , Reuter, S., & Dietmayer, K. (Jun. 2017 ) . Multi-camera traffic light recognition using a classifying labeled multi-bernoulli filter. In 2017 IEEE Intelligent Vehicles Symposium (IV) (pp . 1045-1051 ). [cited by applicant]
Bidlack, C., Hampapur, A., Katkere, A., Feng, L., Kagalwala, F., Kraljevic, T., & Weymouth, T. ( May 1994 ) . Visual robot navigation using flat earth obstacle projection . In Proceedings of the 1994 IEEE International … [cited by applicant]
C. C. T. Mendes V. Fremont D. F. Wolf . Exploiting fully convolutional neural networks for fast road detection , Proc . IEEE Int. Conf. Robot. Auto. ( ICRA ), pp. 3174-3179 May 2016. [cited by applicant]
Chilamkurthy et al., “A 2017 Guide to Semantic Segmentation with Deep Learning,” Retrieved from, <https://blog.qure.ai/notes/semantic-segmentation-deep-learning-review,> Jul. 5, 2017, 16 Pages. [cited by applicant]
Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, and Joachim Denzler “Convolutional patch networks with spatial prior for road detection and urban scene understanding”, In International Conference on Co… [cited by applicant]
D. Levi N. Garnett E. Fetaya “Stixelnet: A deep convolutional network for obstacle detection and road segmentation”, 26th British Machine Vision Conference ( BMVC ) 2015. [cited by applicant]
Data Science, What are deconvolutional layers? <https://datascience.stackexchange.com/questions/6107/what-are-deconvolutional-layers>, Retrieved from, <https://datascience.stackexchange.com/questions/6107/what-are-decon… [cited by applicant]
Deshpande, “A Beginner's Guide to Understanding Convolutional Neural Networks,” Retrieved from, <https://adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks/,> Jul. 20, 2016, 25 Pag… [cited by applicant]
Dipietro, “A Friendly Introduction to Cross-Entropy Loss,” Retrieved from, <https://rdipietro.github.io/friendly-intro-to-cross-entropy-loss/> , May 2, 2016, 10 Pages. [cited by applicant]
First Action Interview Office Action dated Mar. 1, 2021 in U.S. Appl. No. 16/355,328, 4 pages. [cited by applicant]
Gabriel L. Oliveira, Wolfram Burgard , Thomas Brox. Efficient Deep Models for Monocular Road Segmentation. IEEE / RSJ International Conference on Intelligent Robots and Systems ( IROS 2016). [cited by applicant]
Garnett, “Real-time Category-Based and General Obstacle Detection for Autonomous Driving,” ICCV, 2017, 8 Pages. [cited by applicant]
H. Badino, U. Franke, and D. Pfeiffer. The stixel world—acompact medium level representation of the 3d—world . In DAGM, 2009. [cited by applicant]
H. Badino, U. Franke, and R. Mester. Free space computation using stochastic occupancy grids and dynamic programming . In ICCV Workshop on Dynamical Vision, 2007. [cited by applicant]
H. Hirschmuller. Stereo processing by semiglobal matching and mutual information. PAMI, 2008. [cited by applicant]
Han et al., “Learning Both Weights and Connections for Efficient Neural Networks,” In Proceedings of the 28th International Conference on Neural Information Processing Systems—vol. 1, Oct. 30, 2015, pp. 1135-1143. [cited by applicant]
He et al., “Deep Residual Learning for Image Recognition,” CVPR, 2016, 9 pages. [cited by applicant]
He et al., “Learning depth from single images with deep neural network embedding focal length,” IEEE Transactions on Image Processing, 27 (9), 2018, 4676-4689. [cited by applicant]
Huval et al., “An Empirical Evaluation of Deep Learning on Highway Driving,” Apr. 17, 2015, 7 Pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Application No. PCT / US2019 / 024400 , dated Oct. 8, 2020 , 10 pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Application No. PCT / US2019 / 068764 , dated Jul . 8, 2021 , 12 pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Application No. PCT / US2019 / 068766 , dated Jul . 8, 2021 , 10 pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Application No. PCT/US2019/018348, dated Aug. 27, 2020, 16 pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Application No. PCT/US2019/019656 , dated Sep. 3, 2020, 11 pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Application No. PCT/US2019/022592, dated Sep. 24, 2020, 11 pages. [cited by applicant]
International Search Report and Written Opinion dated Apr. 22, 2020 in International Application No. PCT / US2019 / 068766. [cited by applicant]
International Search Report and Written Opinion dated Aug. 26, 2019 in International Patent Application No. PCT / US2019 / 022592, 18 Pages. [cited by applicant]
International Search Report and Written Opinion dated Jul. 25, 2019 in International Patent Application No. PCT / US 2019/018348, 22 pages. [cited by applicant]
International Search Report and Written Opinion dated Jul. 24, 2019 in International Patent Application No. PCT / US2019 / 019656, 15 pages. [cited by applicant]
Ioffe et al., “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Mar. 2, 2015, 11 Pages. [cited by applicant]
J. Franke and I. Kutzbach . Fast stereo based object detection for stop and go traffic . In IV , 1996. [cited by applicant]
J. Yao, S. Ramalingam, Y. Taguchi, Y. Miki, and R. Urtasun, “Estimating drivable collision—free space from monocular video,” in Applications of Computer Vision, 2015, pp. 420-427. [cited by applicant]
Jayaraman , A. et al . , “Creating 3D Virtual Driving Environments for Simulation—Aided Development of Autonomous Driving and Active Safety”, SAE Technical Paper Series , vol. 1 , pp. 1-3 ( Mar. 28, 2017 ) ( English Abs… [cited by applicant]
Jose M. Alvarez , Theo Gevers , Yann LeCun , and Antonio M. Lopez , “Road scene segmentation from a single image”, In Proceedings of the 12th European Conference on Computer Vision—vol. Part VII , ECCV'12 , pp. 376-389,… [cited by applicant]
Kim et al., “Depth map coding with distortion estimation of rendered view,” InVisual Information Processing and Communication ( vol. 7543, p. 75430B ). International Society for Optics and Photonics, Jan. 2010, 10 Pages. [cited by applicant]
Kingma et al. “Adam: A Method for Stochastic Optimization,” arXiv:1412.6980, dated Dec. 22, 2014, 9 pages. [cited by applicant]
Liu et al., “Neural Person Search Machines,” IEEE, 2017, 9 Pages. [cited by applicant]
Long, “Fully Convolutional Networks for Semantic Segmentation,” CVPR, 2015, 10 pages. [cited by applicant]
Marvin Teichmann , Michael Weber , Marius Zoellner , Roberto Cipolla, and Raquel Urtasun. Multinet: Real-time joint semantic reasoning for autonomous driving. arXiv preprint arXiv: 1612.07695, 2016. [cited by applicant]
Mathworks, “Polynomial Curve Fitting,” Retrieved from, <https://www.mathworks.com/help/matlab/ref/polyfit.html,> Feb. 21, 2019, 13 Pages. [cited by applicant]
Molchanov et al., Pruning Convolutional Neural Networks for Resource Efficient Inference, ICLR, 2017, 12 pages. [cited by applicant]
Neven et al., “Towards End-to-End Lane Detection: an Instance Segmentation Approach,” Feb. 15, 2018, 7 Pages. [cited by applicant]
Non- Final Office Action dated Oct. 21, 2020 in U.S. Appl. No. 16/277,895 , 13 pages. [cited by applicant]
Non Final Office Action dated Oct. 7, 2021 in U.S. Appl. No. 16/366,875 , 22 pages. [cited by applicant]
Non-Final Office action dated Jun. 2, 2020 in U.S. Appl. No. 16/286,329. [cited by applicant]
Non-Final Office Action dated May 13, 2021 in U.S. Appl. No. 16/728,595, 18 pages. [cited by applicant]
Notice of Allowance dated Aug. 31, 2021 in U.S. Appl. No. 16/728,595 , 8 pages. [cited by applicant]
Notice of Allowance dated Jan. 19, 2021 in U.S. Appl. No. 16/286,329 , 8 pages. [cited by applicant]