Abstract: Aspects presented herein relate to perception data collection and curation. In one aspect, a network entity receives, from a first set of user equipments (UEs), a first set of perception data collected by the first set of UEs. The network entity configures, for a second set of UEs based on the first set of perception data, at least one of: a set of planned routes and time plans for collecting a second set of perception data or a set of embeddings centroids. The network entity receives, from the second set of UEs, the second set of perception data based on at least one of the configured set of planned routes and time plans or the configured set of embeddings centroids.

Abstract: Aspects presented herein relate to perception data collection and curation. In one aspect, a network entity receives, from a first set of user equipments (UEs), a first set of perception data collected by the first set of UEs. The network entity configures, for a second set of UEs based on the first set of perception data, at least one of: a set of planned routes and time plans for collecting a second set of perception data or a set of embeddings centroids. The network entity receives, from the second set of UEs, the second set of perception data based on at least one of the configured set of planned routes and time plans or the configured set of embeddings centroids.

Abstract: Trajectory planning techniques for high-definition (HD) mapping platforms are disclosed. The techniques can include obtaining multi-agent vehicle trajectory data associated with a map segment of an HD map, constructing, by a neural network, a trajectory value-based flow field for the map segment based on the multi-agent vehicle trajectory data, and configuring, for the map segment, trajectory planning parameters of a driving policy layer of the HD mapping platform based on the trajectory value-based flow field.

Abstract: A device for processing sensor data is configured to receive the first frames from a first sensor; receive the second frames from a second sensor; perform a first feature extraction on the first frames using a first dynamic neural network to determine first features; perform a second feature extraction on the second frames using a second dynamic neural network to determine second features; determine a first delay associated with the first features; determine a second delay associated with the second features; modify a topology of the second dynamic neural network based on the first delay and the second delay; and use the second dynamic neural network with the modified topology to generate an output.

Abstract: Systems and techniques are described herein for processing data. For instance, a method for processing data is provided. The method may include obtaining source features generated based on first sensor data captured using a first set of sensors; obtaining source semantic attributes related to the source features; obtaining target features generated based on second sensor data captured using a second set of sensors; obtaining map information; obtaining location information of a device comprising the second set of sensors; obtaining target semantic attributes from the map information based on the location information; aligning the target features with a set of the source features, based on the source semantic attributes and the target semantic attributes, to generate aligned target features; and processing the aligned target features to generate an output.

Abstract: A method for selecting one or more Regions of Interest (RoIs) for human annotations includes obtaining sensor data generated by one or more sensors of a vehicle; applying at least one class-agnostic heuristic function to the sensor data to determine a presence and an approximate position of one or more objects in an RoI of the sensor data; selecting one or more RoIs having proposed annotations for the one or more objects for refinement by an annotator; and outputting the one or more selected RoIs.

Abstract: This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, a method of image processing includes receiving first kinematic information associated with a camera image sensor; receiving, by the processor, point cloud data from a light detection and ranging (LiDAR) sensor; generating, by the processor, first image data that is time-synchronized with the point cloud data based on the first kinematic information and a neural radiance fields (NeRF) model; and generating, by the processor, fused data that combines the first image data and the point cloud data. Other aspects and features are also claimed and described.