Intel Corporation

Patrick Mead

Ignacio Javier Alvarez

David Arditti Ilitzky

David Israel Gonzalez Aguirre

Justin E Gottschlich

Kathiravetpillai Sivanesan

Liuyang L Yang

Javier Felip Leon

Sridhar G Sharma

Daniel S Lake

Victor Palacios Rivera

Alexander F Heinecke

Sara S Baghsorkhi

Jason Martin

Rafael De La Guardia Gonzalez

Paul H Dormitzer

Shengtian Zhou

Mohammad Mejbah Ul Alam

Jeffrey Ota

Shahab Layeghi

Carlos Ornelas

Yassir Mosleh

John Tell

Miryam Lomeli Barajas

Apparatuses, methods and storage medium associated with compensating for a sensor deficiency in a heterogeneous sensor array are disclosed herein. In embodiments, an apparatus may include a compute device to aggregate perception data from individual perception pipelines, each of which is associated with respective one of different types of sensors of a heterogeneous sensor set, to identify a characteristic associated with a space to be monitored by the heterogeneous sensor set; detect a sensor deficiency associated with a first sensor of the sensors; and in response to a detection of the sensor deficiency, derive next perception data for more than one of the individual perception pipelines from sensor data originating from at least one second sensor of the sensors. Other embodiments may be disclosed or claimed.

Compensating for a sensor deficiency in a heterogeneous sensor array

Methods and apparatus to generate vehicle warnings are disclosed. An example apparatus includes a sensor to detect a vehicle, where the sensor is associated with an observer of the vehicle, an object tracker to determine a motion of the vehicle, an accident estimator to calculate a likelihood of a collision of the vehicle based on the determined motion, and a transceiver to transmit a message to the vehicle upon the likelihood of the collision exceeding a threshold, where the message includes information pertaining to the collision.

Methods and apparatus to generate vehicle warnings

Methods, apparatus, systems and articles of manufacture are disclosed that provide an apparatus to analyze vehicle perspectives, the apparatus comprising a profile generator to generate a first profile of an environment based on a profile template and first data generated by a first vehicle; a data analyzer to: determine a difference between the first profile and a second profile obtained from a first one of one or more nodes in the environment; and in response to a trigger event, update the first profile based on the difference; and a vehicle control system to: in response to the trigger event, update a first perspective of the environment based on one or more of second data from the first one of the one or more nodes or the updated first profile; update a path plan for the first vehicle based on the updated first perspective; and execute the updated path plan.

Methods and apparatus to update autonomous vehicle perspectives

Methods and apparatus relating to heterogeneous compute architecture hardware/software co-design for autonomous driving are described. In one embodiment, a heterogeneous compute architecture for autonomous driving systems (also interchangeably referred to herein as Heterogeneous Compute Architecture or 'HCA' for short) integrates scalable heterogeneous processors, flexible networking, benchmarking tools, etc. to enable (e.g., system-level) designers to perform hardware and software co-design. With HCA system engineers can rapidly architect, benchmark, and/or evolve vehicle system architectures for autonomous driving. Other embodiments are also disclosed and claimed.

Heterogeneous compute architecture hardware/software co-design for autonomous driving

Systems and methods for detecting rogue vehicles within a plurality of vehicles connected via a vehicular ad-hoc network (VANET) are provided. Sensors on each VANET vehicle provide host vehicle data and data associated with other nearby vehicles. Each VANET vehicle multicasts information that includes location, velocity, and preferred future travel path to the other VANET vehicles. Using data from sensors and data received from other VANET vehicles the host vehicle generates a dynamic set of safe vehicle operating behaviors. Nearby vehicles that do not comply with the determined safe vehicle operating behaviors or perform illegal/unsafe acts are identified as rogue vehicles. Data associated with identified rogue vehicles is transmitted to all VANET vehicles. Each VANET vehicle determines a preferred future travel path based on the received information associated with rogue vehicles, the preferred future travel path information received from other VANET vehicles, and the host vehicle's safe vehicle operating behaviors.

Rogue vehicle detection and avoidance

Growing community of inventors

Portland, OR, United States of America

Patrick Mead