公开(公告)号：US20170212223A1

公开(公告)日：2017-07-27

申请号：US15266618

申请日：2016-09-15

Applicant: QUALCOMM Incorporated

Inventor： Volodimir SLOBODYANYUK ,  Karim ARABI ,  Evgeni GOUSEV

IPC: G01S7/486 ,  G01S7/481 ,  G01S17/06

CPC classification number: G01S7/4863 ,  G01S7/4816 ,  G01S7/4817 ,  G01S7/4818 ,  G01S17/06 ,  G01S17/105 ,  G01S17/42 ,  G02B26/103

Abstract: Aspects of the disclosure are related to a Lidar device, comprising: a vibrating fiber optic cantilever system on a transmit (TX) path; and a two-dimensional (2D) light sensor array on a receive (RX) path.

公开(公告)号：US20250130329A1

公开(公告)日：2025-04-24

申请号：US18812289

申请日：2024-08-22

Applicant: QUALCOMM Incorporated

Inventor： Makesh Pravin JOHN WILSON ,  Vishnuu APPAYA DHANABALAN ,  Volodimir SLOBODYANYUK ,  Avdhut JOSHI ,  Radhika Dilip GOWAIKAR

IPC: G01S13/931 ,  G01S13/72 ,  G01S13/89

Abstract: A dynamic occupancy grid determination method includes: obtaining, at an apparatus, at least one radar-based occupancy grid based on radar sensor measurements, each of the at least one radar-based occupancy grid comprising a plurality of first cells, each cell of the plurality of first cells having a corresponding first occupancy probability and first velocity; obtaining, at the apparatus, at least one camera-based occupancy grid based on camera measurements, each of the at least one camera-based occupancy grid comprising a plurality of second cells, each cell of the plurality of second cells having a corresponding second occupancy probability and second velocity; and determining, at the apparatus, a dynamic occupancy grid by analyzing the at least one radar-based occupancy grid and the at least one camera-based occupancy grid.

公开(公告)号：US20250065905A1

公开(公告)日：2025-02-27

申请号：US18453725

申请日：2023-08-22

Applicant: QUALCOMM Incorporated

Inventor： Ali Reza ABBASPOUR ,  Volodimir SLOBODYANYUK ,  Mohammed Ataur Rahman SHUMAN

IPC: B60W60/00 ,  B60W50/02

Abstract: An environment perception method, at an ego vehicle, includes: receiving, from a device external to the ego vehicle, one or more first reliability factors associated with the device and with a first value of a parameter of an environment; determining, based on the one or more first reliability factors, a first reliability of the first value; determining, based on one or more second reliability factors associated with the ego vehicle and with a second value of the parameter of the environment provided by one or more sensors of the ego vehicle, a second reliability of the second value; and providing a reliability indication indicating which of the first value and the second value is more reliable based on which of the first reliability and the second reliability is a higher reliability.

公开(公告)号：US20240221186A1

公开(公告)日：2024-07-04

申请号：US18530660

申请日：2023-12-06

Applicant: QUALCOMM Incorporated

Inventor： Makesh Pravin JOHN WILSON ,  Radhika Dilip GOWAIKAR ,  Shantanu Chaisson SANYAL ,  Avdhut JOSHI ,  Rex JOMY JOSEPH ,  Volodimir SLOBODYANYUK

IPC: G06T7/246

CPC classification number: G06T7/251 ,  G06T2207/10028 ,  G06T2207/20084

Abstract: In some aspects, a device may obtain sensor data associated with identifying measured properties of an object in an environment. The device may detect a trigger event associated with at least one of the environment or the device. The device may modify, based on detecting the trigger event, one or more pre-processing operations associated with the sensor data for input to a neural network, and/or one or more post-processing operations associated with an object detection output of the neural network. The device may perform the one or more pre-processing operations associated with the sensor data to generate pre-processed sensor data. The device may generate the object detection output for the object based on detecting the object using the pre-processed sensor data as the input to the neural network. The device may perform the one or more post-processing operations using the object detection output. Numerous other aspects are described.

公开(公告)号：US20240144061A1

公开(公告)日：2024-05-02

申请号：US18480178

申请日：2023-10-03

Applicant: QUALCOMM Incorporated

Inventor： Makesh Pravin JOHN WILSON ,  Radhika Dilip GOWAIKAR ,  Volodimir SLOBODYANYUK ,  Avdhut JOSHI ,  James POPLAWSKI

IPC: G06N7/01

CPC classification number: G06N7/01 ,  B60W60/00

Abstract: An occupancy grid probability prediction method includes: determining a dynamic particle probability based on a first probability that a dynamic particle will move from a donor cell of an occupancy grid to a recipient cell of the occupancy grid; and determining one or more predicted probabilities of at least one of the donor cell or the recipient cell based on the dynamic particle probability.

公开(公告)号：US20230236315A1

公开(公告)日：2023-07-27

申请号：US18002992

申请日：2021-08-10

Applicant: QUALCOMM Incorporated

Inventor： Amichai SANDEROVICH ,  Eran HOF ,  Evgeny LEVITAN ,  Volodimir SLOBODYANYUK

IPC: G01S13/931 ,  G01S13/58 ,  G01S13/42

CPC classification number: G01S13/931 ,  G01S13/428 ,  G01S13/584

Abstract: Efficient super-resolution of stationary objects (e.g., objects on the roadside or above the road) can be achieved in automotive imaging radar by obtaining sensor information regarding the motion of the radar system (e.g., vehicle speed), performing analog plurality of scans of different elevations, removing motion from the data by applying the inverse of the motion of the radar system, applying a beamspace processing algorithm to achieve super resolution, and outputting a detailed high-resolution radar image of the stationary objects.

公开(公告)号：US20230092581A1

公开(公告)日：2023-03-23

申请号：US17482156

申请日：2021-09-22

Applicant: QUALCOMM Incorporated

Inventor： Arnold Jason GUM ,  Volodimir SLOBODYANYUK ,  Robert GILMORE

IPC: G01S7/4865 ,  G01S7/4863 ,  G01S7/484

Abstract: A range estimator determines an at least one code sequence, causes an at least one light source to send the at least one code sequence as an at least one coded light transmission toward one or more targets, wherein the at least one code sequence is encoded as an amplitude-based code over time, or as a wavelength-based code over time, or as a combination thereof, in the at least one coded light transmission, causes a reflected version of the at least one coded light transmission to be received at an at least one sensor from the one or more targets, as a reflected light signal, correlates the reflected light signal with the at least one code sequence, to generate a time-of-flight value for the at least one coded light transmission, and generates a range estimate for the at least one coded light transmission based on the time-of-flight value.

公开(公告)号：US20230036838A1

公开(公告)日：2023-02-02

申请号：US17443974

申请日：2021-07-29

Applicant: QUALCOMM Incorporated

Inventor： Volodimir SLOBODYANYUK ,  Avdhut JOSHI ,  Sundar SUBRAMANIAN

IPC: B60W40/08 ,  B60W60/00

Abstract: In some aspects, a device may receive point data associated with a cell of an occupancy grid for controlling a vehicle. The device may determine, based on the point data, a characteristic of the cell that is associated with an occupancy probability of the cell, wherein the occupancy probability is determined according to a first technique based on the point data. The device may configure, based on the characteristic, the occupancy probability for the cell, within the occupancy grid, according to a second technique. Numerous other aspects are described.

公开(公告)号：US20220357441A1

公开(公告)日：2022-11-10

申请号：US17316223

申请日：2021-05-10

Applicant: QUALCOMM Incorporated

Inventor： Amin ANSARI ,  Sundar SUBRAMANIAN ,  Radhika Dilip GOWAIKAR ,  Ahmed Kamel SADEK ,  Makesh Pravin JOHN WILSON ,  Volodimir SLOBODYANYUK ,  Shantanu Chaisson SANYAL ,  Michael John HAMILTON

IPC: G01S13/86 ,  G01S13/89 ,  G06T7/521 ,  G06N20/00 ,  G06T7/11

Abstract: A device for processing image data is disclosed. The device can obtain a radar point cloud and one or more frames of camera data. The device can determine depth estimates of one or more pixels of the one or more frames of camera data. The device can generate a pseudo lidar point cloud using the depth estimates of the one or more pixels of the one or more frames of camera data, wherein the pseudo lidar point cloud comprises a three-dimensional representation of at least one frame of the one or more frames of camera data. The device can determine one or more object bounding boxes based on the radar point cloud and the pseudo lidar point cloud.

公开(公告)号：US20210373127A1

公开(公告)日：2021-12-02

申请号：US16885239

申请日：2020-05-27

Applicant: QUALCOMM Incorporated

Inventor： Volodimir SLOBODYANYUK ,  Roberto RIMINI ,  Udara FERNANDO ,  Nitin Jonathan MYERS ,  Vijay VARADARAJAN

IPC: G01S7/41 ,  G01S7/35 ,  G01S13/42 ,  G06F17/14 ,  G06F17/16

Abstract: Methods, systems, computer-readable media, and apparatuses for determining one or more attributes of at least one target based on eigenspace analysis of radar signals are presented. In some embodiments, a subset of eigenvectors to use for forming a signal or noise subspace is identified based on principal component analysis. In some embodiments, the subset of eigenvectors is identified based on estimating the total number of targets using a discrete Fourier transform (DFT) or other spectral analysis technique. In some embodiments, a DFT is used to identify areas of interest in which to perform eigenspace analysis. In some embodiments, a DFT is used to estimate one attribute of a target, and eigenspace analysis is performed to estimate a different attribute of the target, with the results being combined to generate a multi-dimensional representation of a field of view.