Fnu Apurva Kumar

US Patent:

20220382284, Dec 1, 2022

Filed:

May 26, 2021

Appl. No.:

17/330868

Inventors:

- Pittsburgh PA, US
FNU Ratnesh Kumar - Campbell CA, US

International Classification:

G05D 1/02
B60Q 9/00
B60W 60/00

Abstract:

Methods of determining relevance of objects that a vehicle's perception system detects are disclosed. A system on or in communication with the vehicle will identify a time horizon, and a look-ahead lane based on a lane in which the vehicle is currently traveling. The system defines a region of interest (ROI) that includes one or more lane segments within the look-ahead lane. The system identifies a first subset that includes objects located within the ROI, but not objects not located within the ROI. The system identifies a second subset that includes objects located within the ROI that may interact with the vehicle during the time horizon, but not excludes actors that may not interact with the vehicle during the time horizon. The system classifies any object that is in the first subset, the second subset or both subsets as a priority relevant object.

US Patent:

20220343101, Oct 27, 2022

Filed:

Apr 27, 2021

Appl. No.:

17/241637

Inventors:

- Pittsburgh PA, US
FNU Ratnesh Kumar - Campbell CA, US
De Wang - Pittsburgh PA, US
James Hays - Decatur GA, US

International Classification:

G06K 9/00
G06T 7/70
G01S 17/894

Abstract:

Systems and methods for operating an autonomous vehicle. The methods comprising: obtaining, by a computing device, loose-fit cuboids overlaid on 3D graphs so as to each encompass LiDAR data points associated with a given object; defining, by the computing device, an amodal cuboid based on the loose-fit cuboids; using, by the computing device, the amodal cuboid to train a machine learning algorithm to detect objects of a given class using sensor data generated by sensors of the autonomous vehicle or another vehicle; and causing, by the computing device, operations of the autonomous vehicle to be controlled using the machine learning algorithm.

US Patent:

20230004642, Jan 5, 2023

Filed:

Jun 21, 2022

Appl. No.:

17/845674

Inventors:

- South Jordan UT, US
Nagesh Ayyagari - Bangalore, IN
Fnu Pankaj Kumar - San Jose CA, US
Vinoj Ebenezer Stanley - Seattle WA, US
Praveen Kalla - Austin TX, US

Assignee:

Ivanti, Inc. - South Jordan UT

International Classification:

G06F 21/55
G06F 21/56
G06F 21/57

Abstract:

A method of application integrity verification and remediation includes scanning an appliance to identify installed program files associated with an application under analysis deployed at the appliance. The method includes computing a hash value of a first installed file of the installed program files. The method includes determining whether the first installed file exists in vendor program files of the application that are maintained separate from the installed program files. The method includes fetching a hash value of a first vendor file of the vendor program files. The first vendor file corresponds to the first installed file. Responsive to the fetched hash value differing from the computed hash value, the method includes classifying the first installed program file as a compromised file and remediating the compromised file at the network appliance.

US Patent:

20210089921, Mar 25, 2021

Filed:

Sep 23, 2020

Appl. No.:

17/029725

Inventors:

- Santa Clara CA, US
Varun Praveen - Cupertino CA, US
FNU Ratnesh Kumar - Campbell CA, US
Partha Sriram - Los Altos Hills CA, US

International Classification:

G06N 3/08
G06N 5/04

Abstract:

Transfer learning can be used to enable a user to obtain a machine learning model that is fully trained for an intended inferencing task without having to train the model from scratch. A pre-trained model can be obtained that is relevant for that inferencing task. Additional training data, as may correspond to at least one additional class of data, can be used to further train this model. This model can then be pruned and retrained in order to obtain a smaller model that retains high accuracy for the intended inferencing task.