Gm Cruise Holdings LLC

Samsung Electronics Co., Ltd.

Na Yu

Clement Creusot

Jia Pu

Divya Thuremella

Seunghoon Lee

Geng Chen

Bulent Kasman

Hyungseok Yu

Jian Wang

Jia Ma

Prathyush Katukojwala

Xudong Jin

Adeel Mufti

Apparatus and methods of the present disclosure provide a solution to quickly sort through and identify relevant data sets from large amounts of data collected by numerous vehicles. This process is a form of data mining where a processor executes instructions out of a memory to evaluate sensor data collected by vehicles over time. These vehicles may be driven by person's such that data collected by those sensors would be representative of how a person drives. After data has been acquired, it may be evaluated to identify portions of data where one vehicle encounters another vehicle along a roadway. Data may be classified as being associated with particular types of driving maneuvers and organized into data sets with labels consistent with the classification or driving maneuver. Classifications could correspond to different typed of driving maneuvers, 'turning left across traffic,' “all way stop,” “merging onto a highway,” or “lane change”.

Interaction auto-labeling using spatial overlap of track footprints for mining interactions

A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Multi-modal, multi-technique vehicle signal detection

A method for providing an anti-rollback secure timer service includes determining, at a device which includes a processor providing a trusted execution environment (TEE), a trusted memory, and a real time clock (RTC) accessible through an operating system of the device, an initial reference time value, by a secure timer application running in the TEE, the initial reference time value determined based on an initial value of the RTC obtained during booting of the device and a time delta value. The method further includes determining an updated reference time value based on the initial reference time value, a second value of the RTC, and a previously stored old reference time value, determining an updated time delta value based on the second value of the RTC and the updated reference time value, and storing the updated time delta value and the updated reference time value in the trusted memory.

System and method for anti-rollback

Growing community of inventors

San Jose, CA, United States of America

Na Yu