Abstract: This disclosure provides systems, methods, and devices that support machine learning techniques for vehicle guidance. In one aspect, a method is provided that includes receiving an image frame from an image sensor, determining a projected image frame to correct a vertical axis of the image frame, and generating a top-down representation of the environment based on the projected image frame. The projected image frame may be aligned with the top down representation's vertical axis and may be projected using a cylindrical family projection. The top-down representation may be produced by assembling depth and context matrices from vertically aligned pixels in the projected image frame.

Abstract: An apparatus configured to perform a perception task may generate sensor features from data from one or more sensors. process the sensor features with a time-continuous recurrent neural network (RNN) to produce time-continuous features, and perform the perception task using the time-continuous features. The time-continuous features may be defined by a first feature vector value corresponding to a first observation time of the one or more sensors, a prediction of a steady state feature vector value, and estimated feature vector values between the first feature vector value and the steady state feature vector value, the estimated feature vector values being defined by a function.

Abstract: In some aspects, an apparatus may receive, from a lidar sensor, a bounding geometry in accordance with one or more data points of a point cloud representing two or more scans of a sensed object. The bounding geometry may have a bounding volume associated with the sensed object. The apparatus may extend the bounding volume of the bounding geometry to enclose at least a subset of the data points in the point cloud. The apparatus may estimate a data point displacement in accordance with two or more subsets of the data points of the point cloud. The apparatus may estimate a velocity of the sensed object in accordance with the data point displacement. Numerous other aspects are described.

Abstract: Systems and techniques are described herein for object detection. For example, a computing device can extract, by an encoder of the computing device, a plurality of features from one or more images of an environment of the computing device. The computing device can determine, based on the plurality of features, a first detection of one or more objects and three-dimensional (3D) coordinates for the one or more objects. The computing device can back-project the 3D coordinates of the one or more objects onto the one or more images. The computing device can determine one or more regions of at least one first image of the one or more images based on the back-projection of the 3D coordinates of the one or more objects. computing device determine, based on the one or more regions of the at least one first image, a second detection of the one or more objects.

Abstract: This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, a method is provided that includes a receiving sensor data from one or more sensors. The sensor data may be determined for an area surrounding a vehicle, and features may be determined based on the sensor data and projected into a top view representation of the area surrounding the vehicle. The top view representation may be defined by an inner contour and an outer contour. The inner contour may be determined based on an exterior contour of the vehicle, sensing capabilities of one or more sensors, or a combination thereof. Vehicle instructions may then be determined based on the features within the top view representation. Other aspects and features are also claimed and described.

Abstract: An apparatus comprises one or more memories, and one or more processors in communication with the one or more memories. The one or processors are configured to execute an automated driving system having a modular hybrid architecture. The modular hybrid architecture includes a plurality of task units, and the modular hybrid architecture includes one or more human-defined interfaces, and one or more AI-defined interfaces. The one or more processors are further configured to receive input data from one or more sensors process the input data using the automated driving system having the modular hybrid architecture, and control at least one operation of a vehicle according to an output of the automated driving system.

Abstract: The invention relates to a camera system (10) for a motor vehicle, wherein the camera system (10) comprises a camera (11), which is adapted to capture images, and a data processing device (12), wherein the camera (11) is adapted to capture first images (20) with a first exposure time (21) and second images (22) with a second exposure time (23) in an alternating manner or interleaved manner. The data processing device (12) is adapted to generate a first image output (13) and second image output (14) different from each other. The first image output (13) comprises the first images (20) with the first exposure time (21), and the data processing device (12) is adapted to combine the first images (20) and the second images (22) to third images (24), and to generate the second image output (14) comprising third images (24).

Abstract: This disclosure provides systems, methods, and devices that support machine learning techniques for vehicle guidance. In one aspect, a method is provided that includes receiving an image frame from an image sensor, determining a projected image frame to correct a vertical axis of the image frame, and generating a top-down representation of the environment based on the projected image frame. The projected image frame may be aligned with the top down representation's vertical axis and may be projected using a cylindrical family projection. The top-down representation may be produced by assembling depth and context matrices from vertically aligned pixels in the projected image frame.