Venkatesh S Rao

US Patent:

8320272, Nov 27, 2012

Filed:

Feb 12, 2010

Appl. No.:

12/705212

Inventors:

Colin Kahn - Morris Plains NJ, US
Alistair Urie - Issy-les-Moulineaux, FR
Venkatesh Rao - Naperville IL, US
Harish Viswanathan - Morristown NJ, US

Assignee:

Alcatel Lucent - Paris

International Classification:

H04L 12/56
H04J 1/16

US Classification:

370252, 370278, 370329

Abstract:

A method and system for selecting at a terminal at least one of a plurality of available access networks for use with a wireless application invoked at the terminal according preferences associated with the wireless application, the network service provider, the subscriber, the subscriber subscription and application content provider. The selection may be constrained by an Application Policy received from a network service provider.

US Patent:

20120300706, Nov 29, 2012

Filed:

Aug 7, 2012

Appl. No.:

13/568305

Inventors:

Colin Kahn - Morris Plains NJ, US
Alistair Urie - Issy-les-Moulineaux, FR
Venkatesh Rao - Naperville IL, US
Harish Viswanathan - Morristown NJ, US

International Classification:

H04W 8/00

US Classification:

370328

Abstract:

A method and system for selecting at a terminal at least one of a plurality of available access networks for use with a wireless application invoked at the terminal according preferences associated with the wireless application, the network service provider, the subscriber, the subscriber subscription and application content provider. The selection may be constrained by an Application Policy received from a network service provider.

US Patent:

20200372809, Nov 26, 2020

Filed:

May 21, 2019

Appl. No.:

16/417960

Inventors:

- Armonk NY, US
Mudhakar Srivasta - White Plains NY, US
Venkatesh Ashok Rao Rao - Natick MA, US
Linsong Chu - White Plains NY, US

International Classification:

G08G 5/00
G06N 20/00
G06N 5/04
G08G 5/04

Abstract:

An action recommendation system uses reinforcement learning that provides a next action recommendation to a traffic controller to give to a vehicle pilot such as an aircraft pilot. The action recommendation system uses data of past human actions to create a reinforcement learning model and then uses the reinforcement learning model with current ABS-B data to provide the next action recommendation to the traffic controller. The action recommendation system may use an anisotropic reward function and may also include an expanding state space module that uses a non-uniform granularity of the state space.