Abstract: Certain aspects of the present disclosure provide a method for generating a map. A method generally includes obtaining sensor data from one or more sensors, the sensor data corresponding to an environment comprising one or more features including a first feature having one or more changes in curvature; inputting the sensor data to a map generation model; and obtaining as output from the map generation model a vectorized map of the one or more features of the environment, wherein the vectorized map represents the first feature as a polyline comprising a plurality of line segments, wherein a comparison of changes of slope between consecutive line segments of the polyline to slopes of the plurality of line segments of the polyline satisfies a threshold.

Abstract: Systems and techniques are described herein for generating map information. For instance, a method for generating map information is provided. The method may include obtaining points representative of objects in an environment based on a feature map, wherein the feature map is based on perception data representative of the environment; encoding the points to generate encoded points; encoding vectors of the feature map that correspond to the points to generate encoded vectors; combining the encoded points and the encoded vectors to generate combined features; determining a plurality of representative points based on the combined features; and generating map data based on the plurality of representative points.

Abstract: A computing system may determine, for a plurality of polylines associated with one or more pictures of a video, a plurality of pair-wise distance measures for pairs of polylines from the plurality of polylines. The computing system may cluster, based on the plurality of pair-wise distance measures, a subset of polylines from the plurality of polylines to generate a polyline cluster. The computing system may determine a lane boundary or a road boundary that corresponds to the polyline cluster and may output information indicative of the lane boundary or the road boundary.

Abstract: Certain aspects of the present disclosure provide techniques for representing polylines and polygons. A method generally includes obtaining a ordered set of points that represent a polyline or a polygon in a multidimensional space; forming two or more channels from the ordered set of points, each channel has a respective set of coordinate values that corresponds to a respective coordinate direction in the multidimensional space; inputting the two or more channels into a one-dimensional convolutional neural network (1D CNN); and obtaining, as output from the 1D CNN, a feature vector representation of the polyline or polygon.

Abstract: Certain aspects of the present disclosure provide a method for generating a map. A method generally includes obtaining sensor data from one or more sensors, the sensor data corresponding to an environment comprising one or more features including a first feature having one or more changes in curvature; inputting the sensor data to a map generation model; and obtaining as output from the map generation model a vectorized map of the one or more features of the environment, wherein the vectorized map represents the first feature as a polyline comprising a plurality of line segments, wherein a comparison of changes of slope between consecutive line segments of the polyline to slopes of the plurality of line segments of the polyline satisfies a threshold.

Abstract: A method for generating predictions for vectorized High Definition (HD) map elements includes obtaining sensor data generated by sensors of a vehicle; extracting feature maps from the sensor data; identifying anchor regions based on the feature maps, wherein the anchor regions represent potential locations for vectorized HD map elements, and wherein the vectorized HD map represents an environment surrounding the vehicle; generating initial object queries in the anchor regions, wherein the initial object queries are associated with a specific vectorized HD map element; refining, by a transformer decoder, the initial object queries based on the feature maps to generate refined object queries; and generating predictions for the vectorized HD map elements based on the refined object queries.

Abstract: Certain aspects of the present disclosure provide a method for generating a map. A method generally includes obtaining sensor data corresponding to one or more sensors. The method includes inputting the sensor data to a map generation model. The method obtains as output from the map generation model a vectorized map of one or more features of an environment. The vectorized map represents the first feature as a convex polygon, such that all internal angles of the convex polygon are less than or equal to 180 degrees.

Abstract: Systems and techniques are described herein for determining object-location information. For instance, a method for determining object-location information is provided. The method may include: generating, using an encoder machine-learning model, a latent-space representation of objects based on a representation of the objects in a scene; clustering points of the latent-space representation of the objects, to generate clusters of points; determining representative values of the clusters of points; and generating, using a decoder machine-learning model, a reconstructed representation of the objects in the scene based on the representative values of the clusters of points.

Abstract: In some aspects, a device may receive sensor data associated with a vehicle and a set of frames. The device may aggregate, using a first pose, the sensor data associated with the set of frames to generate an aggregated frame, wherein the aggregated frame is associated with a set of cells. The device may obtain an indication of a respective occupancy label for each cell from the set of cells, wherein the respective occupancy label includes a first occupancy label or a second occupancy label, and wherein a subset of cells from the set of cells are associated with the first occupancy label. The device may train, using data associated with the aggregated frame, a machine learning model to generate an occupancy grid, based on a loss function that only calculates a loss for respective cells from the subset of cells. Numerous other aspects are described.

Abstract: Certain aspects are directed to an apparatus for lane estimation. The apparatus generally includes: at least one memory; and at least one processor coupled to the at least one memory and configured to receive a first input associated with a three-dimensional (3D) space, extract, from the first input, a first set of points associated with a ground plane of the 3D space, map each of the first set of points to a region of a plurality of regions of a two-dimensional (2D) frame, determine one or more attributes associated with each region of the plurality of regions based on one or more of the first set of points mapped to the region, and identify one or more road lanes based on the one or more attributes.

Abstract: In some aspects of the disclosure, an apparatus includes a processing system that includes one or more processors and one or more memories coupled to the one or more processors. The processing system is configured to receive sensor data associated with a scene and to generate a cylindrical representation associated with the scene. The processing system is further configured to modify the cylindrical representation based on detecting a feature of the cylindrical representation being included in a first region of the cylindrical representation. Modifying the cylindrical representation includes relocating the feature from the first region to a second region that is different than the first region. The processing system is further configured to perform, based on the modified cylindrical representation, one or more three-dimensional (3D) perception operations associated with the scene.

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 image data from an image sensor; extracting point features from light detection and ranging (LiDAR) data; partitioning the point features; performing BEV-feature pooling based on the partitioned point features; determining lane-boundary heads based on the BEV-feature pooling, wherein the determining comprises row-wise classification with at least one of: offset correction regression processing; or vertex-wise height regression processing. Other aspects and features are also claimed and described.

Abstract: In some aspects, a device may receive sensor data associated with a vehicle and a set of frames. The device may aggregate, using a first pose, the sensor data associated with the set of frames to generate an aggregated frame, wherein the aggregated frame is associated with a set of cells. The device may obtain an indication of a respective occupancy label for each cell from the set of cells, wherein the respective occupancy label includes a first occupancy label or a second occupancy label, and wherein a subset of cells from the set of cells are associated with the first occupancy label. The device may train, using data associated with the aggregated frame, a machine learning model to generate an occupancy grid, based on a loss function that only calculates a loss for respective cells from the subset of cells. Numerous other aspects are described.

Abstract: Certain aspects are directed to an apparatus for lane estimation. The apparatus generally includes: at least one memory; and at least one processor coupled to the at least one memory and configured to receive a first input associated with a three-dimensional (3D) space, extract, from the first input, a first set of points associated with a ground plane of the 3D space, map each of the first set of points to a region of a plurality of regions of a two-dimensional (2D) frame, determine one or more attributes associated with each region of the plurality of regions based on one or more of the first set of points mapped to the region, and identify one or more road lanes based on the one or more attributes.