Qualcomm Incorporated

General Electric Company

General Electric Renovables Espana, S.l.

Jayakrishnan Unnikrishnan

Urs Niesen

Junyi Li

Kapil Gulati

Sundar Subramanian

Avdhut Joshi

Yoga Y Nadaraajan

Amir Salimi

Gautam Sachdeva

Shivam Agarwal

Sree Sesha Aravind Vadrevu

Xinzhou Wu

Emad Andarawis Andarawis

Uwe Wiedmann

Christopher Brunner

Edward James Nieters

Ravi Teja Sukhavasi

Duck Hoon Kim

Radhika Dilip Gowaikar

Michael Joshua Shomin

Brett Alexander Matthews

Hyun-Mook Cho

Young-Ki Baik

John Anthony Dougherty

Michael John Hamilton

Dayu Huang

Liwei Hao

Lijun He

Rui Xu

Fu-Chun Yeh

Jaydeep Karandikar

Kati Illouz

Shubham Sanjeev Garg

Andrew Henderson

A processor-implemented method for radar-based tracking of an object includes transmitting radio frequency (RF) signals. In response to the transmitted RF signals, one or more return RF signals are received. Features of the one or more return RF signals are extracted. A graph comprising multiple nodes is generated. Each node of the graph corresponds to the one or more return RF signals and indicates a potential target object detection. An existence of a plurality of edges is determined. Each edge connects a pair of nodes in the graph based on features of the return RF signals. The existence of each edge indicates that the pair of nodes connected correspond to a same target object.

Radar clustering using machine learning

Systems and methods for resolving elevation ambiguity include acquiring, using a 1-D horizontal radar antenna array, a radar frame with range and azimuth information, and predicting a target elevation based on the frame by computing a depth map with a plurality of target depths assigned to corresponding azimuth-elevation pairs. Computing the depth map includes processing the radar frame with an encoder-decoder structured deep convolutional neural network (CNN). The CNN may be trained with a dataset including training radar frames acquired in a number of environments, and compensated ground truth depth maps associated with those environments. The compensated ground truth depth maps may be generated by subtracting a ground-depth from a corresponding ground truth depth map. The ground truth depth maps may be acquired with a 2-D range sensor, such as a LiDAR sensor, a 2-D radar sensor, and/or an IR sensor. The radar frame may also include Doppler data.

Resolution of elevation ambiguity in one-dimensional radar processing

Systems and techniques are described for performing object detection and tracking. For example, a tracking object can obtain an image comprising a target object at least partially in contact with a surface. The tracking object can obtain a plurality of two-dimensional (2D) keypoints based on one or more features associated with one or more portions of the target object in contact with the surface in the image. The tracking object can obtain information associated with a contour of the surface. Based on the plurality of 2D keypoints and the information associated with the contour of the surface, the tracking object can determine a three-dimensional (3D) representation associated with the plurality of 2D keypoints.

Three-dimensional target estimation using keypoints

Disclosed are techniques for radar-aided single-image three-dimensional (3D) depth reconstruction. In an aspect, at least one processor of an on-board computer of an ego vehicle receives, from a radar sensor of the ego vehicle, at least one radar image of an environment of the ego vehicle, receives, from a camera sensor of the ego vehicle, at least one camera image of the environment of the ego vehicle, receives, from a light detection and ranging (LiDAR) sensor of the ego vehicle, at least one LiDAR image of the environment of the ego vehicle, and generates a depth image of the environment of the ego vehicle based on the at least one radar image, the at least one LiDAR image, and the at least one camera image.

Radar-aided single image three-dimensional depth reconstruction

Techniques and systems are provided for determining static occupancy. For example, an apparatus can be configured to determine one or more pixels associated with one or more static objects depicted in one or more images of a three-dimensional space. The apparatus can be configured to obtain a point map including a plurality of map points, the plurality of map points corresponding to a portion of the three-dimensional space. The apparatus can be configured to determine, based on the point map and the one or more pixels associated with the one or more static objects, a probability of occupancy by the one or more static objects in the portion of the three-dimensional space. The apparatus can be configured to combine information across multiple images of the three-dimensional space, and can determine probabilities of occupancy for all cells in a static occupancy grid that is associated with the three-dimensional space.

Static occupancy tracking

Methods, systems, computer-readable media, and apparatuses for radar or LIDAR measurement are presented. Some configurations include transmitting, via a transceiver, a first beam having a first frequency characteristic; calculating a distance between the transceiver and a moving object based on information from at least one reflection of the first beam; transmitting, via the transceiver, a second beam having a second frequency characteristic that is different than the first frequency characteristic, wherein the second beam is directed such that an axis of the second beam intersects a ground plane; and calculating an ego-velocity of the transceiver based on information from at least one reflection of the second beam. Applications relating to road vehicular (e.g., automobile) use are described.

Ego-velocity estimation using radar or LIDAR beam steering

Methods, systems, and devices for wireless communications are described. In some systems, radio signals may reach a receiving antenna at a user equipment by two or more paths, which can cause interference (e.g., destructive multipath interference, constructive multipath interference, etc.). To reduce the interference, the user equipment may perform interference suppression, shaping, or both based on choosing radar waveform patterns that are varied across chirps. In one aspect, the user equipment (e.g., a vehicle) may identify waveform patterns selected by nearby vehicles based on side channel or centralized signaling and may suppress or shape interference by selecting waveform parameters based on this information. In one aspect, the pattern of waveform parameters is chosen from a codebook of patterns. The selected pattern can be broadcasted to the other vehicles using a side-communication channel.

Using a side-communication channel for exchanging radar information to improve multi-radar coexistence

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

A method and apparatus for selecting frequency modulated continuous wave waveform parameters for multiple radar coexistence by a user equipment is described. The user equipment may transmit a radar waveform consisting of a number of chirps, with each chirp having a same duration. The user equipment may vary waveform parameters of the radar waveform for at least a subset of the number of chirp, where the waveform parameters may be chosen from a codebook comprising at least one codeword of parameters. Reflected radar waveforms are received and processed where the processing includes applying a fast time discrete Fourier transform to reflected radar waveforms to produce a one dimension peak in a time delay dimension for each reflected waveform; and applying a slow time discrete Fourier transform to the reflected radar waveforms, where peaks for the reflected waveforms are added.

Methods for radar coexistence

Techniques and systems are provided for determining one or more sizes of one or more objects. For example, a bounding region identifying a first object detected in an image can be obtained. A map including map points can also be obtained. The map points correspond to one or more reference locations in a three-dimensional space. The bounding region identifying the first object can be associated with at least one map point of the map points included in the map. Using the bounding region and the at least one map point, an estimated three-dimensional position and an estimated size of the first object detected in the image can be determined. In some examples, other information can be used to estimate the estimated three-dimensional position and an estimated size of the first object, such as radar information and/or other information.

Object size estimation using camera map and/or radar information

The present disclosure provides methods and systems for radar detection. A radar device may obtain prior information about known targets including an azimuth angle of each known target. The radar device may generate an association aware transmit beam pattern toward at least a subset of the known targets based on the prior information. The radar device may detect targets from reflected beams of the association aware transmit beam pattern. Generating the association aware transmit beam pattern may include generating a partial ambiguity graph for the known targets, the graph including at least one edge connecting two known targets wherein a difficulty of disambiguating the two known targets is greater than a threshold. The graph also includes at least two known targets that are not connected by an edge.

Association aware radar beamforming

Disclosed are techniques for annotating image frames using information from a light detection and ranging (LiDAR) sensor. An exemplary method includes receiving, from the LiDAR sensor, at least one LiDAR frame, receiving, from a camera sensor, at least one image frame, removing LiDAR points that represent a ground surface of the environment, identifying LiDAR points of interest in the at least one LiDAR frame, segmenting the LiDAR points of interest to identify at least one object of interest in the at least one LiDAR frame, and annotating the at least one image frame with a three-dimensional oriented bounding box of the at least one object of interest detected in the at least one image frame by projecting the three-dimensional oriented bounding boxes from the at least one LiDAR frame to the at least one image frame using cross-calibration transforms between the LiDAR sensor and the camera.

Using light detection and ranging (LIDAR) to train camera and imaging radar deep learning networks

Methods, systems, and devices for radar signaling s are described. In some systems, devices may select radar parameters (e.g., frequency modulated continuous wave waveform parameters) to support coexistence for multiple radar sources in the system. To reduce mutual interference between radar waveforms in a system, a user equipment may detect interference from at least one interference source (e.g., another device transmitting a radar waveform) and may select waveform parameters for transmission of a radar waveform based on the detected interference. For example, the user equipment may determine slopes, frequency offsets, codewords, or a combination thereof used by nearby devices in the system (e.g., per chirp or for a waveform) and may select waveform parameters that result in low mutual interference with the determined slopes, frequency offsets, codewords, or combination thereof. The user equipment may transmit the radar waveform according to the selected waveform parameters.

Selection of frequency modulated continuous wave (FMWC) waveform parameters for multi-radar coexistence

Methods, systems, and devices for radar signaling are described. In some systems, devices may implement techniques to support coexistence for multiple radar sources using a phase-coded frequency modulated continuous wave waveform. A user equipment (e.g., a vehicle) may select a codeword (e.g., a pattern of parameters) from a codebook and may derive phase code information and waveform shape parameters from values specified in the codeword. The user equipment may apply phase modulation to at least one chirp of a waveform using the indicated phase code. In some cases, the phase-coded frequency modulated continuous wave waveform may resemble nested Zadoff-Chu sequences, where the waveform resembles a Zadoff-Chu sequence and the phase code resembles another Zadoff-Chu sequence. The phase code may support mitigating interference between radar waveforms that use the same slope and frequency offset parameters for chirps overlapping in time.

Multi-radar coexistence using phase-coded frequency modulated continuous wave waveforms

Disclosed are techniques for radar-aided single-image three-dimensional (3D) depth reconstruction. In an aspect, at least one processor of an on-board computer of an ego vehicle receives, from a radar sensor of the ego vehicle, at least one radar image of an environment of the ego vehicle, receives, from a camera sensor of the ego vehicle, at least one camera image of the environment of the ego vehicle, and generates, using a convolutional neural network (CNN), a depth image of the environment of the ego vehicle based on the at least one radar image and the at least one camera image.

Growing community of inventors

Jersey City, NJ, United States of America

Jayakrishnan Unnikrishnan