Intel Corporation

Apple Inc.

Mobileye Vision Technologies Ltd.

Intel IP Corporation

Hassnaa Moustafa

Eve M Schooler

Katalin Klara Bartfai-Walcott

Nageen Himayat

Srikathyayani Srikanteswara

Rita H Wouhaybi

Maruti Gupta Hyde

Jeffrey Sedayao

David John Zage

Christian Maciocco

Jessica C McCarthy

Rath Vannithamby

Bahareh Sadeghi

Vallabhajosyula S Somayazulu

Dave A Cavalcanti

Sung Ho Lee

David E Cohen

Nadine L Dabby

Subramanian Anandaraj

Ned M Smith

Chittabrata Ghosh

Shilpa Talwar

Satish Chandra Jha

Kathiravetpillai Sivanesan

Shekoufeh Qawami

Ana Lucia Pinheiro

S M Iftekharul Alam

Sebastian Schoenberg

Jeffrey R Foerster

Chaitanya Sreerama

Gang Shen

Francesc Guim Bernat

Muthaiah Venkatachalam

Shao-Wen Yang

Deepak Shashidhar Vembar

Meghashree Dattatri Kedalagudde

Yen-kuang Chen

Arun Raghunath

Tianyou Li

Danny Moses

Peggy J Irelan

Jong-Kae Fwu

Debdeep Chatterjee

Kshitij Arun Doshi

Emily H Qi

Markus Dominik Mueck

Carlos Horacio Aldana

Ren Wang

Linda L Hurd

Zhibin Yu

Thorsten Clevorn

Marcio Rogerio Juliato

Bertram Gunzelmann

Harry G Skinner

Ana Lucia A Pinheiro

Debabani Choudhury

Venkatesan Nallampatti Ekambaram

Rafael Misoczki

Stephen T Palermo

Ingolf Karls

Kuilin Clark Chen

Duncan Kitchin

Javier Perez-Ramirez

Gabriel Arrobo Vidal

Stefan Fechtel

Rita Chattopadhyay

Yi Zhang

Shu Xu

Atul N Hatalkar

Cagri Tanriover

David Ott

Junyong Ding

Jonas Svennebring

Valerie J Parker

Carlos Cordeiro

Johanna M Swan

Van H Le

Candy Yiu

Alexandre Saso Stojanovski

Justin E Gottschlich

Hosein Nikopour

Richard D Roberts

Igor Tatourian

Yu Wang

Rajashree Raji Baskaran

Stanley T Mo

Oner Orhan

Vesh Raj Sharma Banjade

Yiting Liao

Ravikumar Balakrishnan

Kilian Roth

Barry A O'Mahony

Annie Foong

Shengtian Zhou

Shengbo Xu

Valerie J Young

Arvind Merwaday

Greeshma Pisharody

Sangeeta Ghangam Manepalli

Vishwanath Ramamurthi

Disclosed herein are embodiments of systems and methods for diversified imitation learning for automated machines. In an embodiment, a process-profiling system obtains sensor data captured by a plurality of sensors that are arranged to observe one or more human subjects performing one or more processes to accomplish one or more tasks. The process-profiling system clusters the sensor data based on a set of one or more process-performance criteria. The process-profiling system also performs, based on the clustered sensor data, one or both of generating and updating one or more process profiles in a plurality of process profiles. The process-profiling system selects, for one or more corresponding automated machines, one or more process profiles from among the plurality of process profiles, and the process-profiling system configures the one or more corresponding automated machines to operate according to the selected one or more process profiles.

Diversified imitation learning for automated machines

Methods, apparatus, systems, and articles of manufacture are disclosed to improve mobile edge platform resiliency. An example apparatus includes memory, instructions, and processor circuitry to execute the instructions to initiate a search for one of an access point or a cluster head at a first time, in response to detection of the cluster head, initiate an intra-cluster mobile edge platform (MEP) mutual authentication associated with the cluster head, cause transmission of historical activity data to at least one MEP associated with the cluster head, and cause storage of an authentication metric in a secure storage, the authentication metric based on historical connectivity data.

Methods, systems, articles of manufacture and apparatus to improve mobile edge platform resiliency

Methods, apparatus, systems, and articles of manufacture are disclosed for proactive data routing. An example apparatus includes at least one memory, machine-readable instructions, and processor circuitry to execute the machine-readable instructions to at least execute a machine-learning model to output a first data routing path in a network environment based on metadata associated with an event in the network environment. The processor circuitry is further to, after a detection of a change of the first data routing path to a second data routing path, retrain the machine-learning model to output a third data routing path based on the second data routing path. The processor circuitry is additionally to cause transmission of a second message to a first node based on the third data routing path after an identification of the event.

Systems, apparatus, articles of manufacture, and methods for proactive data routing

Systems and techniques for selective transport of spatially partitioned immersive media content are described herein. In an example, the system may negotiate an attribute for media content between a media producer and a media consumer. A content structure for the media content may be determined based on the negotiation of the attribute, and a network packet may be created with information corresponding to the determined content structure encoded into a transport protocol header of the network packet. The network packet may be filtered to produce filtered media content. The filtered media content may be transmitted to the media consumer.

Content partition based real time communication for immersive media

Various aspects of methods, systems, and use cases include security-based orchestration. A method may include evaluating, within a secure environment of an untrusted device, a preamble to determine a set of security requirements. The method may include, providing, to an attestation server, an indication of security parameters for services of the untrusted device corresponding to security requirements of the set of security requirements, and in response to receiving a confirmation from the attestation server, providing a request to the untrusted device outside the secure environment to generate a trusted domain including the services.

Network supported low latency security-based orchestration

A robot may include a processor, configured to operate according to a first operational mode or a second operational mode, wherein the first operational mode comprises performing an environmental perception operation using first sensor data, wherein the first sensor data comprise no camera data, and wherein the second operational mode comprises performing the environmental perception operation using second sensor data, wherein the second sensor data comprise camera data; while operating according to the first operational mode, determine a confidence factor representing a confidence of the environmental perception operation; determine whether or not the confidence factor is outside of a range; and if the confidence factor is outside of the range, operate according the second operational mode.

Robot sensor data management

The present disclosure describes mechanisms to manage session continuity for edge computing services for edge service consumers. The session management mechanisms include continuity or handing over edge service sessions between edge computing platforms in a same edge compute cluster and between edge computing platforms in different edge compute clusters. The session management mechanisms include edge computing platform switching/handover for user equipment capable of utilizing multiple access network connections and/or multiple access technologies. The described solutions can provide edge service session continuity between connected vehicles and road side units and/or edge compute nodes.

Managing session continuity for edge services in multi-access environments

System and techniques for network flow-based hardware allocation are described herein. A workload for is obtained for execution. Here, the workload includes a flow that has a processing component and a network component. Then, during execution of the workload, the flow is repeatedly profiled and assigned a network service and a processing service during a next execution based on a network metric and a processing metric obtained from the profiling.

Network flow-based hardware allocation

Various aspects of techniques, systems, and use cases include provide instructions for operating an autonomous mobile robot (AMR). A technique may include capturing audio or video data using a sensor of the AMR, performing a classification of the audio or video data using a trained classifier, and identifying a coordinate of an environmental map corresponding to a location of the audio or video data. The technique may include updating the environmental map to include the classification as metadata corresponding to the coordinate. The technique may include communicating the updated environmental map to an edge device.

Scene intelligence for collaborative semantic mapping with mobile robots

In one embodiment, a road side unit (RSU) establishes a data offload session with a vehicle in the vicinity of the RSU based on a session establishment request sent by the vehicle, and stores data received from the vehicle during the data offload session in its memory. The RSU generates storage record information (including identifying information for the RSU) for the stored data, and transmits the storage record information to the vehicle.

Data offload and time synchronization for ubiquitous visual computing witness

A compute system that includes an Internet of things (IoT) device is provided. The IoT device includes a common services interface (CSI) to create a self-managing network of devices with other nodes comprising the CSI.

Microservice provision and management

A device for a vehicle may include a first wireline interface configured to receive a first data stream from a first sensor having a first sensor type for perceiving a surrounding of the vehicle, the first data stream including raw sensor data detected by the first sensor; a second wireline interface configured to receive a second data stream from a second sensor having a second sensor type for perceiving the surrounding of the vehicle, the second data stream including raw sensor data detected by the second sensor; one or more processors configured to generate a coded packet including the received first data stream and the received second data stream by employing vector packet coding on the first data stream and the second data stream; and an output wireline interface configured to transmit the generated coded packet to one or more target units of the vehicle.

Device for a vehicle

The subject matter described herein presents various technical solutions for the technical problems facing autonomous vehicles (e.g., fully autonomous and semi-autonomous vehicles). To address technical problems facing wireless communication cost and latency, a heterogeneous roadside infrastructure can be used to improve the ability for a vehicle to communicate with a data source. To address technical problems facing interruption of vehicle services due to an abrupt loss of connection, a quality of service system provides the ability to determine and share quality of service information, such as location-based information, maps, interference data, and other quality of service information. To address technical problems facing high volume data upload and download between autonomous vehicles and cloud-based data services, optical wireless communication (OWC) provides increased data throughput and reduced complexity, and may be beneficial for short-range high-mobility wireless communications.

Systems and methods for autonomous vehicle communication

Disclosed embodiments relate to an orchestrator and arbitrator in an Internet of Things (IoT) platform. In one example, a method of servicing a plurality of data flows of a plurality of wireless devices using a plurality of protocols includes: monitoring one or more interfaces that communicate using the plurality of protocols, activating a first interface upon detecting a demand to exchange data thereon, wherein a connectivity manager performs the monitoring, and activating, extracting, by a packet analyzer, packet metadata from one or more of the plurality of data flows, determining latency encountered and bandwidth utilized by the one or more data flows based on the packet metadata, applying, by an adaptive connectivity manager (ACM), a latency reduction strategy to attempt to comply with latency criteria, and applying, by a bandwidth utilization manager (BUM), a bandwidth reduction strategy to attempt to comply with bandwidth criteria.

Connectivity service level orchestrator and arbitrator in internet of things (IoT) platforms

Technologies for managing interoperable high definition (HD) maps for autonomous vehicles includes a HD map server to distribute interoperable HD map tiles to various autonomous vehicles, each of which may be configured to utilize proprietary HD map tiles of different propriety formats. As such, each of the autonomous vehicles is configured to translate the interoperable HD map tile to the proprietary format used by that particular vehicle. Additionally, each autonomous vehicle may submit crowd-sourced sensor data to the interoperable HD map server using a universal data set by converting the sensor data to a universal data structure.

Technologies for managing interoperable high definition maps for autonomous vehicles

Growing community of inventors

Portland, OR, United States of America

Hassnaa Moustafa