Cisco Technology, Inc.

Other

New York University

Sateesh Kumar Addepalli

Raghuram S Sudhaakar

Lillian Lei Dai

Flavio Giovanni Bonomi

Jean-Philippe Vasseur

Pere Monclus

Preethi Natarajan

Vina Ermagan

Kevin C Lee

Fabio Rodolfo Maino

Rong Pan

Xiaoqing Zhu

Ashok Krishnaji Moghe

Rodolfo Alberto Milito

Alexander Loukissas

Christian Ibars Casas

Robert Edward Somers

Pascal Thubert

Vijaynarayanan Subramanian

Chin-Ju Chen

Erick D Lee

Marc Jean-Philippe Girardot

David A Maluf

Chiu Ngok Eric Wong

Ramesh Karri

Landon Curt Noll

James D Stanley, Iii

Vinayaka Jyothi

Mohammand H Falaki

An artificial intelligence (AI) system is disclosed. The AI system provides an AI system lane processing chain, at least one AI processing block, a local memory, a hardware sequencer, and a lane composer. Each of the at least one AI processing block, the local memory coupled to the AI system lane processing chain, the hardware sequencer coupled to the AI system lane processing chain, and the lane composer is coupled to the AI system lane processing chain. The AI system lane processing chain is dynamically created by the lane composer.

Systems and methods for artificial intelligence with a flexible hardware processing framework

Aspects of the present disclosure are presented for an AI system featuring specially designed AI hardware that incorporates security features to provide iron clad trust and security to run AI applications/solution models. Presented herein are various security features for AI processing, including: a trust and integrity verifier of data during operation of an AI solution model; identity and trust establishment between an entity and the AI solution model; secure isolation for a virtual AI multilane system; a real-time attack detection and prevention mechanism; and built in detection mechanisms related to rogue security attack elements insertion during manufacturing. Aspects also include security to implement an AI network interconnecting multiple user devices in an AI environment.

Systems and methods of security for trusted artificial intelligence hardware processing

Aspects of the present disclosure provide for a novel system and method where users can promote, subscribe, license, train collaboratively, and/or trade AI models in real-time over an AI trusted model network that represents a group of trusted users across platform agnostic ways. The system and methods described herein may effectively provide a marketplace to collaboratively develop and reliably disseminate developed AI models to other users who may have similar needs. The system may include an AI user device server (AI-UDS), an AI trusted model network (AI-TMN), an AI secure marketplace system (AI-SMPS), an AI collaborative training platform (AI-CTP), an AI secure transaction fulfillment system (AI-STFS), and an AI model license subscription management platform (AI-LSMP).

Real-time customizable AI model collaboration and marketplace service over a trusted AI model network

Aspects of the present disclosure are presented for a power management system of a multilane AI system architecture. The system may include an orchestrator configured to control power and other operations of a lane. An uber orchestrator manages the overall system, and may know all of the multilane systems within the AI virtual multilane system that need to be active at a given frequency and power envelope for given price, and performance constraints. The orchestrator of each lane knows the compute/logic blocks that need to be active for a given AI app model AI processing chain execution. The orchestrator may be configured to send commands to turn off power to certain components that are not utilized in performing an AI execution sequence, deactivate operation to the lane when its functions are completed, and also modulate the clock frequency of a lane to fit the computation demands while minimizing power usage.

Systems and methods for power management of hardware utilizing virtual multilane architecture

A method in one embodiment includes intercepting a message in an on-board unit (OBU) of a vehicular network environment between a source and a receiver in the vehicular network environment, verifying the message is sent from the source, verifying the message is not altered, evaluating a set of source flow control policies associated with the source, and blocking the message if the set of source flow control policies indicate the message is not permitted. In specific embodiments, the message is not permitted if a level of access assigned to the source in the set of source flow control policies does not match a level of access tagged on the message. In further embodiments, the method includes evaluating a set of receiver flow control policies associated with the receiver, and blocking the message if the set of receiver flow control policies indicates the message is not permitted.

System and method for wireless interface selection and for communication and access control of subsystems, devices, and data in a vehicular environment

An exemplary system, method and computer-accessible medium for determining a starting point of a header field(s) in a network packet(s) can be provided, which can include, for example receiving the network(s) packet, determining a header location of the header field(s) in the network packet(s), determining a delimiter location of a delimiter(s) in the network packet(s), and determining the starting point of the header field(s) based on the header and delimiter locations. The header location can be determined using a header finder module. The delimiter location can be determined using a delimiter finder module. The header and delimiter locations can be determined using a plurality of comparators arranged into a plurality of sets.

System, method and computer-accessible medium for network intrusion detection

A method includes receiving, by a processor of a data collector, a request for sensor data related to an event. The method also includes sending a plurality of requests for the sensor data to a plurality of on-board units (OBUs), respectively, where the plurality of OBUs is associated with a plurality of vehicles, respectively. The method further includes receiving a plurality of responses from the plurality of OBUs, respectively, wherein each response of the plurality of responses includes a sensor data item related to the event. In more specific embodiments the plurality of requests are sent to the plurality of OBUs based on the plurality of OBUs being located within a certain proximity to the event. In yet further embodiments, each sensor data item of the plurality of responses is encapsulated with a respective tag.

System and method for routing, mobility, application services, discovery, and sensing in a vehicular network environment

In one embodiment, a router operating in a hierarchically routed computer network may receive collected data from one or more hierarchically lower devices in the network (e.g., hierarchically lower sensors or routers). The collected data may then be converted to aggregated metadata according to a dynamic schema, and the aggregated metadata is stored at the router. The aggregated metadata may also be transmitted to one or more hierarchically higher routers in the network. Queries may then be served by the router based on the aggregated metadata, accordingly.

Network-based dynamic data management

A method in one example embodiment includes identifying a power state and a battery level of a vehicle. The method also includes allocating power to critical applications (for example) in response to determining that the battery level is above a reserve threshold while the power state of the vehicle is engine-off. The method also includes allocating remaining power in excess of the reserve threshold to non-critical applications according to a power management policy. The power management policy may comprise at least one of a user power preference index and an application power preference index.

System and method for applications management in a networked vehicular environment

A method includes establishing communication channels between an on-board unit (OBU) of a vehicle and a plurality of nodes, tagging each of a plurality of data from the plurality of nodes with a priority level, storing the plurality of data in a priority queue according to respective priority levels, selecting a medium to present a first data of the plurality of data to a user, and presenting the first data to the user via the medium. In the method, the plurality of nodes includes a remote node and an in-vehicle device. Another method includes receiving a data from a remote node, generating a plurality of data streams from the data and transmitting the plurality of data streams across a plurality of wireless interfaces. Another method includes enhancing audio signals from a plurality of microphones and speakers. Yet another method includes various gesture based user interfaces coupled to the OBU.

System and method for real-time synthesis and performance enhancement of audio/video data, noise cancellation, and gesture based user interfaces in a vehicular environment

A method includes selecting a path for routing a data packet from a source node to a destination node in a vehicular ad hoc network, storing the data packet if the selected path is identified as a dead end, and establishing a communication link with a first node. The method also includes forwarding the data packet to the first node if a first distance between the first node and the destination node is less than a second distance between the source node and the destination node. More specific embodiments include sending a query for location information of the destination node, receiving the location information including two or more available paths from the source node to the destination node, and determining the path for routing the data packet is an optimal path of the two or more available paths.

In one embodiment, a stream of data packets originated by a visual data source is received at an edge device in a network. The data packets include at least one of video data, image data, and geo spatial data. Next, a visual data attribute is extracted at the edge device from the stream of data packets according to an edge-based extraction algorithm. The extracted visual data attribute is vectorized at the edge device via quantization vectors. The vectorized visual data attribute is then indexed at the edge device in a schema-less database that stores indexed visual data attributes.

Line rate visual analytics on edge devices

In one embodiment, a universal programming module on a first device collects context and state information from a local application executing on the first device, and provides the context and state information to a context mobility agent on the first device. The context mobility agent establishes a peer-to-peer connection with a second device, and transfers the context and state information to the second device, such that a remote application may be configured to execute according to the transferred context and state information from the first device. In another embodiment, the context mobility agent receives remote context and remote state information from the second device, wherein the remote application had been executing according to the remote context and remote state information, and provides the remote context and remote state information to the universal programming module to configure the local application to execute according to the remote context and remote state information.

Growing community of inventors

San Jose, CA, United States of America

Sateesh Kumar Addepalli