Qualcomm Incorporated

Amazon Technologies, Inc.

Onkar Jayant Dabeer

Aleksandar Damnjanovic

Wanshi Chen

Hao Xu

Yongbin Wei

Kiran Kumar Somasundaram

Durga Prasad Malladi

Madhavan Srinivasan Vajapeyam

Peter S Gaal

Xiaoxia Zhang

Naga Bhushan

Srinivas Yerramalli

Shimman Arvind Patel

Ravi Teja Sukhavasi

Jelena Damnjanovic

Taesang Yoo

Tao Luo

Alberto Rico Alvarino

Ozcan Ozturk

Siddhartha Mallik

Radhika Dilip Gowaikar

Jing X Sun

Anastasios Stamoulis

Makesh Pravin John Wilson

Jun Wang

Miguel Griot

Ravindra Manohar Patwardhan

Tingfang Ji

Gavin Bernard Horn

Maarten Menzo Wentink

Ajay Gupta

Marco Papaleo

Gerhard Reitmayr

Dexu Lin

Zhengwei Liu

Sean C Murphy

Qingsi Wang

Zachary Tokarczyk

Jesse Norman Clark

Taewan Kim

Jing Sun

Techniques for training a machine-learning model are described. In an example, a computer generates a first pseudo-label indicating a first mask associated with a first object detected by a first machine-learning model in a first training image. A transformed image of the first training image can be generated using a transformation. Based on the transformation, a second pseudo-label indicating a second mask detected in the transformed image and corresponding to the first mask can be determined. A second machine-learning model can be trained using the second pseudo-label. The trained, second machine-learning model can detect a third mask associated with a second object based on a second image.

Training and using computer vision model for item segmentations in images

A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.

Systems and methods for mapping based on multi-journey data

According to the present disclosure, CSI and/or a plurality of ACKs related to a group of DL data transmissions may be buffered at the UE as a GACK until a DCI trigger is received from the eNB. Once the trigger is received, the UE may transmit the CSI and/or GACK to the eNB. In this way HARQ feedback and/or CSI may be reliably communicated while reducing payload. In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus send, to a UE, data transmissions associated with a first plurality of downlink subframes. In an aspect, the apparatus increments a counter for each data transmission sent to the UE. In a further aspect, the apparatus transmits, to the UE, a first trigger for a first GACK when a counter is greater than or equal to a threshold.

Group acknowledgement/negative acknowledgement and triggering GACK/channel state information

Techniques for synchronization across transmitting nodes of a same public land mobile network (PLMN) operator using a shared radio frequency spectrum band may include initiating, at a first wireless node, a listen-before-talk (LBT) procedure for access to the shared radio frequency spectrum band, and identifying that a second wireless node associated with a same PLMN operator as the first wireless node has won contention for the shared radio frequency spectrum band. The first wireless node may discontinue the LBT procedure and initiate an auxiliary transmission using the shared radio frequency spectrum band concurrently with a primary transmission of the second wireless node.

Synchronization across transmitting nodes using shared radio frequency spectrum

A method performed by an apparatus is described. The method includes receiving a first set of object data corresponding to a first journey. The method also includes receiving a second set of object data corresponding to a second journey. The method further includes determining a similarity metric between the first set of object data and the second set of object data. The similarity metric indicates a distance between the first set of object data and the second set of object data for at least one object. The method additionally includes clustering the first set of object data and the second set of object data for the at least one object based on the similarity metric to produce at least one object cluster. The method also includes producing map data based on the at least one object cluster.

Certain aspects relate to methods and apparatus for latency reduction for UEs in a RRC connected mode. During contention-based uplink access by groups of UEs within a subframe, an eNB may decode the received uplink transmission based, at least in part, on the assigned group of resources assigned to the UE and used for transmission. Additional orthogonalization techniques such as reduced TTI size can be used to reduce collisions among different users performing contention-based transmissions. Furthermore, when the eNB fails to successfully decode the uplink transmission, the eNB may identify the UE that sent the uplink transmission based on a detected reference signal and may transmit an uplink assignment to the identified UE.

Low latency physical layer design for contention-based uplink channels

An end-of-arm-tool (EOAT) can elongate from a retracted position into an extend position to be configured to fit within a space available for contacting and grasping an object. The EOAT includes arrays of linkage elements having corresponding arrays of suction cups attached to linkage element of the linkage element array. In the retracted position, the arrays are pulled away from the distal end of the EOAT to be alongside of a longitudinal rail. In the extended position, a proximal end of the array is moved toward the distal end of the EOAT such that the linkages glide outwardly and linearly to deploy additional suction cups of the suction cup array against the object-to-be-lifted.

Flexible end of arm tool

Certain aspects relate to methods and apparatus for discovering whether one or more enhanced capabilities are supported by devices (e.g., user equipment (UE), base station (BS), etc.) in a network. The enhanced capabilities may include, for example, the ability to support certain low latency procedures, enhanced component carrier (eCC) capability, and the like. The devices in the network may perform one or more handover-related procedures (e.g., cell selection/reselection, make-before-break handover, etc.) and/or other procedures (e.g., QoS negotiation, etc.) based, at least in part, on support for the one or more enhanced capabilities.

Low latency and/or enhanced component carrier discovery for services and handover

Various aspects described herein relate to communicating a scheduling request (SR) in a wireless network. A frame structure that allows dynamic switching of transmission time intervals (TTI) between uplink and downlink communications may be used to communicate with a network entity. At least one SR mode can be selected for SR transmission to the network entity in one or more of the TTIs configured for uplink communications based at least in part on the frame structure. The SR can be transmitted to the network entity in at least one uplink TTI of the one or more TTIs configured for uplink communications based at least in part on the at least one SR mode.

Scheduling request modes for enhanced component carriers

Techniques are described for wireless communication. A first method may include inserting, in a first transmission using a first radio access technology (RAT), a channel occupancy identifier for a second transmission using a second RAT. The first method may also include transmitting the first transmission having the channel occupancy identifier over an unlicensed radio frequency spectrum band. A second method may include receiving, at a receiver operated using a first RAT, a channel occupancy identifier for a transmission using a second RAT. The channel occupancy identifier may be received over an unlicensed radio frequency spectrum band. The second method may also include decoding the channel occupancy identifier to identify a backoff period, and refraining from accessing the unlicensed radio frequency spectrum band using the first RAT based at least in part on the identified backoff period.

Techniques for transmitting and receiving channel occupancy identifiers over an unlicensed radio frequency spectrum band

A method performed by an apparatus is described. The method includes receiving a set of image frames including at least one object. The method also includes receiving a camera position for each image frame. The method further includes associating the at least one object between image frames based on one or more object points and the received camera position for each image frame to produce two-dimensional (2D) object location data. The method additionally includes estimating three-dimensional (3D) pose data of the at least one object based on the 2D object location data. The method also includes refining the 3D pose data based on a shape constraint.

Systems and methods for object location

The present disclosure, for example, relates to one or more techniques for scaling the bandwidth of a carrier. Available sub-channels of an unlicensed radio frequency spectrum band may be determined, and the available sub-channels may be included in the carrier. The available sub-channels may be adjacent or non-adjacent sub-channels. The bandwidth of the carrier may be determined according to which sub-channels are included in the carrier. In this way, the bandwidth of the carrier may be scaled according to the available sub-channels in the unlicensed radio frequency spectrum band.

Techniques for scaling bandwidth of an unlicensed radio frequency spectrum band

Growing community of inventors

San Diego, CA, United States of America

Onkar Jayant Dabeer