Qualcomm Incorporated

Other

Xinzhou Wu

Junyi Li

Rajiv Laroia

Thomas J Richardson

Saurabh R Tavildar

Sundar Subramanian

Jubin Jose

Shailesh Patil

Aleksandar Jovicic

Hua Wang

Venkatesan Nallampatti Ekambaram

Arnab Das

Nilesh Nilkanth Khude

Urs Niesen

Vincent Douglas Park

Ying Wang

Sanjay Shakkottai

Prashanth Haridas Hande

Sundeep Rangan

Vikram Reddy Anreddy

Leonard Henry Grokop

Lionel Jacques Garin

Chong Li

Lei Zhang

Pramod Viswanath

Juergen Cezanne

Jay Kumar Sundararajan

Saurabha Rangrao Tavildar

Cyril Measson

Sichao Yang

Rashid Ahmed Akbar Attar

Tom Richardson

Ravi Teja Sukhavasi

Jin Won Lee

Feng Han

Hong Cheng

Ning Bi

Amin Ansari

Radhika Dilip Gowaikar

Feng Guo

Ruiduo Yang

Bence Major

Daniel Hendricus Franciscus Fontijne

Bo Tan

Rajiv Larola

Christopher S Chang

Shihuan Liu

Anand Muralidhar

Siva Theja Maguluri

Gavin Bernard Horn

Ashwin Sampath

Assaf Touboul

Jun Wang

Dilip Krishnaswamy

Shrinivas Kudekar

Pablo Alejandro Anigstein

Arthur Gubeskys

Kai Shi

Shankar Sadasivam

Jayakrishnan Unnikrishnan

Duck Hoon Kim

Jianfeng Ren

Edward Robert Hall

Young-Ki Baik

Hyun-Mook Cho

Avdhut Joshi

Michael John Hamilton

James Alan Misener

Rayadurgam Srikant

Yoga Y Nadaraajan

Gautam Sachdeva

Amir Salimi

Sree Sesha Aravind Vadrevu

Shivam Agarwal

Alberto Vigato

Teck Yian Lim

Shailesh Patel

Vasuki Narasimha Swamy

Quan Geng

Mathieu Leconte

Bikram Reddy Anreddy

Thomas Joseph Richardson

Hua Hua Wang

Thomas Richardson

Saurabh Tavildar

Vikram R Anreddy

Vincent D Park

Prashanth Hande

Nilesh Khude

Disclosed are techniques for employing deep learning to analyze radar signals. In an aspect, an on-board computer of a host vehicle receives, from a radar sensor of the vehicle, a plurality of radar frames, executes a neural network on a subset of the plurality of radar frames, and detects one or more objects in the subset of the plurality of radar frames based on execution of the neural network on the subset of the plurality of radar frames. Further, techniques for transforming polar coordinates to Cartesian coordinates in a neural network are disclosed. In an aspect, a neural network receives a plurality of radar frames in polar coordinate space, a polar-to-Cartesian transformation layer of the neural network transforms the plurality of radar frames to Cartesian coordinate space, and the neural network outputs the plurality of radar frames in the Cartesian coordinate space.

Radar deep learning

Disclosed are techniques for fusing camera and radar frames to perform object detection in one or more spatial domains. In an aspect, an on-board computer of a host vehicle receives, from a camera sensor of the host vehicle, a plurality of camera frames, receives, from a radar sensor of the host vehicle, a plurality of radar frames, performs a camera feature extraction process on a first camera frame of the plurality of camera frames to generate a first camera feature map, performs a radar feature extraction process on a first radar frame of the plurality of radar frames to generate a first radar feature map, converts the first camera feature map and/or the first radar feature map to a common spatial domain, and concatenates the first radar feature map and the first camera feature map to generate a first concatenated feature map in the common spatial domain.

Early fusion of camera and radar frames

Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.

Determining a motion state of a target object

Methods, apparatuses, and computer-readable media are described. In one example, a method of controlling a vehicle comprises: receiving, using one or more sensors, a first set of measurements of a set of physical attributes of the vehicle in a motion; determining, based on a motion data model that defines a set of relationships among the set of physical attributes of the vehicle in the motion and based on the first set of measurements, a set of expected measurements of the set of physical attributes; determining whether to use an entirety of the first set of measurements to control an operation of the vehicle based on comparing the first set of measurements and the set of expected measurements; and responsive to determining not to use the entirety of the first set of measurements, controlling the operation of the vehicle based on a second set of measurements.

Vehicle operation based on vehicular measurement data processing

Some disclosed systems may include a microphone system having two or more microphones, an interface system and a control system. In some examples, the control system may be capable of receiving, via the interface system, audio data from two or more microphones of the microphone system, of determining a gesture location based, at least in part, on the audio data and of controlling one or more settings of the system based on the gesture location.

Audio-based device control

Methods, systems, and devices are described for wireless communication. A transmitter may receive feedback that a station failed to decode a packet sent over a first channel, and the transmitter may determine to re-send the packet or to send parity bits over the first channel or over a second channel to assist in decoding the failed packet. The first channel may be in an unlicensed radio frequency spectrum, and the second channel may be in a licensed radio frequency spectrum and may have a higher reliability level compared to the first channel. The transmitter may determine a first channel degradation level, which may be based on a signal-to-noise ratio received from the station, and may determine an amount of parity bits to send based on the degradation. The transmitter may determine the reliability level of each channel, which may be based on a channel quality indicator.

Reliable channel assisted hybrid-arq

Disclosed are methods, devices, systems, apparatus, servers, computer-/processor-readable media, and other implementations, including a method of estimating a range between a first wireless device and a second wireless device that includes obtaining, at the first wireless device, first information related to a first broadcast message transmitted by the first wireless device, and obtaining, at the first wireless device, second information related to a second broadcast message transmitted by the second wireless device, with the second broadcast message including at least some of the first information. The method also includes determining the range between the first wireless device and the second wireless device based, at least in part, on the first information and the second information.

Location and range determination using broadcast messages

In some cases, V2X systems may send warning messages. The warning messages may be sent over short distances. The warning messages may be useful over wider distances. Some systems may us MBMS from a V2X proximity broadcast. Electronic communications devices, such as UEs may be unaware of the MBMS. A method, an apparatus, and a computer program product for wireless communication are provided. The apparatus may be an RSU. The RSU receive a V2X message from a UE. The RSU may broadcast information associated with the V2X message. The RSU may send the information associated with the V2X message to a network entity for a point-to-multipoint broadcast. The method, an apparatus, and a computer program product for wireless communication may also use V2X messages that include bootstrapping information to tune to an MBMS broadcast.

Point-to-multipoint broadcast assisted vehicle-to-X broadcast

A range between a first wireless device and a second wireless device is estimated using a first mechanism based on messages transmitted over a first communication channel. The first communication channel is associated with a first radio access technology capability of the wireless devices. One or more metrics indicative of an accuracy of the range estimates provided by the first mechanism are obtained. A second mechanism to estimate a range between the first wireless device and the second wireless device may be implemented in favor of the first mechanism when the metric fails to satisfy a criterion. The second mechanism is based on unicast messages transmitted over a second communication channel. The second communication channel is associated with a second radio access technology capability of the wireless devices and may be the same as, or different from, the first communication channel.

Adaptive triggering of RTT ranging for enhanced position accuracy

Aspects of the subject matter described in this disclosure can be implemented in a fall detection device and method. One or more motion sensors can access a user's acceleration data. The acceleration data can be segmented using a segmentation algorithm to identify a potential fall event. The segmentation algorithm can determine a cumulative sum of the acceleration data, where the cumulative sum is based on acceleration values being greater than or less than an acceleration threshold value, and a potential fall event can be identified where the cumulative sum is greater than a cumulative sum threshold value. Statistical features can be extracted from the segmented acceleration data and aggregated, and a determination can be made as to whether the potential fall event is a fall event based at least in part on the statistical features.

Devices and methods for fall detection based on phase segmentation

A method of determining a position of a mobile platform includes obtaining a plurality of pseudorange measurements from multiple time epochs of a satellite navigation system (SPS) and obtaining a plurality of visual-inertial odometry (VIO) velocity measurements from a VIO system. Each time epoch of the SPS includes at least one pseudorange measurement corresponding to a first satellite and at least one pseudorange measurement corresponding to a second satellite. The method also includes combining the plurality of pseudorange measurements with the plurality of VIO velocity measurements to identify one or more outlier pseudorange measurements in the plurality of pseudorange measurements. The one or more outlier pseudorange measurements are then discarded from the plurality of pseudorange measurements to generate a remaining plurality of pseudorange measurements. The position of the mobile platform is then computed based on the remaining plurality of pseudorange measurements and the plurality of VIO velocity measurements.

Outlier detection for satellite positioning system using visual inertial odometry

A method of determining a trajectory of a mobile platform includes obtaining a satellite positioning system (SPS) measurement from one or more SPS signals acquired by an SPS receiver of the mobile platform. The method also includes obtaining a visual-inertial odometry (VIO) measurement of the mobile platform from a VIO system of the mobile platform. A first position estimate of the mobile platform is determined based, at least in part, on the SPS measurement and the VIO measurement. The method then includes adjusting the first position estimate to generate a smoothed position estimate based, in part, on a smoothing parameter that controls a smoothness of the trajectory. The trajectory of the mobile platform is then determined, at least in part, using the smoothed position estimate.

Mobile platform positioning using satellite positioning system and visual-inertial odometry

Methods, systems, and devices are described for techniques for downlink (DL) scheduling and uplink (UL) scheduling in a shared radio frequency (RF)spectrum band. In some aspects, a wireless communication device may receive an UL data transmission grant associated with a channel of shared RF spectrum band. The wireless communication device may perform a channel readiness procedure associated with the channel. The wireless communication device may also transmit channel readiness information based at least in part on the channel readiness procedure to a base station. The channel readiness information may be transmitted via an uplink channel of a licensed RF spectrum band different from the shared RF band. In other aspects, a base station may schedule a data transmission on one or more channels of a shared RF spectrum band. The base station may transmit a data transmission grant for the scheduled data transmission to a wireless communication device.

Techniques for downlink scheduling and uplink scheduling in a shared radio frequency spectrum band

Methods, systems, and devices for wireless communication are described. A base station may perform a clear channel assessment (CCA) procedure on a channel that includes multiple sub-bands of a radio frequency spectrum band. The base station may determine that the channel is available based on the CCA and transmit a special header in the channel. In some examples, the special header may include multiple transmission time intervals (TTIs), where each TTI may include a header packet in each sub-band of the radio frequency spectrum band. In some cases, the header packet may include a clear to send (CTS)-to-self frame structure. The base station may transmit a first TTI across each of the sub-bands at a first power level, and transmit additional TTIs across the sub-bands at a different power level. Additional header packets may be transmitted at the boundaries of subsequent subframes.

Clear to send-to-self transmissions in an LTE-controlled Wi-Fi system

Growing community of inventors

Monmouth Junction, NJ, United States of America

Xinzhou Wu