Abstract: The present technology pertains to measuring the quality of an uncertainty prediction provided by a trajectory prediction algorithm. An AI/ML platform can receive data including predicted trajectories of objects received from the trajectory prediction algorithm and observed paths for the objects received from the plurality of sensors. The predicted trajectories indicate predicted locations of the objects at a plurality of time intervals, and uncertainty predictions reflecting an uncertainty about the location of the objects at each of the predicted time intervals. The AI/ML platform can further determine respective standard deviations of the observed paths of the objects relative to the respective uncertainty predictions and plots the respective standard deviations against an ideal distribution of path distributions relative to the predicted locations of the objects at the plurality of time intervals.

Abstract: The subject disclosure relates to techniques for detecting an object. A process of the disclosed technology can include steps for receiving three-dimensional (3D) Light Detection and Ranging (LiDAR) data of the object at a first time, generating a first point cloud based on the 3D LiDAR data at the first time, receiving 3D LiDAR data of the object at a second time, generating a second point cloud based on the 3D LiDAR data at the second time, aggregating the first point cloud and the second point cloud to form an aggregated point cloud, and placing a bounding box around the aggregated point cloud. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for improving map labeling and in particular, for automating process of semantically labeling maps used for autonomous vehicle (AV) navigation. In some aspects, a process of the disclosed technology includes steps for receiving a three-dimensional (3D) Light Detection and Ranging (LiDAR) map, processing the 3D LiDAR map to produce a 2D map, rasterizing the 2D map into a plurality of map tiles, and providing one or more of the map tiles to a machine-learning (ML) labeler, wherein the ML labeler is configured to identify and label image features in at least one of the one or more map tiles. Systems and machine-readable media are also provided.

Abstract: The present technology pertains to measuring the quality of an uncertainty prediction provided by a traj ectory prediction algorithm. An AI/ML platform can receive data including predicted trajectories of objects received from the trajectory prediction algorithm and observed paths for the objects received from the plurality of sensors. The predicted trajectories indicate predicted locations of the objects at a plurality of time intervals, and uncertainty predictions reflecting an uncertainty about the location of the objects at each of the predicted time intervals. The AI/ML platform can further determine respective standard deviations of the observed paths of the objects relative to the respective uncertainty predictions and plots the respective standard deviations against an ideal distribution of path distributions relative to the predicted locations of the objects at the plurality of time intervals.

Abstract: The present technology pertains to predicting trajectories of objects near an autonomous vehicle. The predictions may be obtained as output from a trajectory prediction machine learning model. The inputs to the trajectory prediction machine learning model may be based on a first map of an area surrounding an autonomous vehicle, and a second map of an area around an object within the first area. The second map may have a smaller area and a higher resolution relative to the first map.

Abstract: The subject disclosure relates to techniques for detecting an object. A process of the disclosed technology can include steps for receiving three-dimensional (3D) Light Detection and Ranging (LiDAR) data of the object at a first time, generating a first point cloud based on the 3D LiDAR data at the first time, receiving 3D LiDAR data of the object at a second time, generating a second point cloud based on the 3D LiDAR data at the second time, aggregating the first point cloud and the second point cloud to form an aggregated point cloud, and placing a bounding box around the aggregated point cloud. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for detecting an object. A process of the disclosed technology can include steps for receiving three-dimensional (3D) Light Detection and Ranging (LiDAR) data of the object at a first time, generating a first point cloud based on the 3D LiDAR data at the first time, receiving 3D LiDAR data of the object at a second time, generating a second point cloud based on the 3D LiDAR data at the second time, aggregating the first point cloud and the second point cloud to form an aggregated point cloud, and placing a bounding box around the aggregated point cloud. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for inserting of bounding boxes around image objects. A process of the disclosed technology can include steps for receiving, from a first data set, an image comprising a first image object, processing the image to identify a pixel region associated with the first image object, and placing a first bounding box around the first image object based on the identified pixel region. In some aspects, the process further includes steps for receiving a user input comprising an indication of whether the first bounding box is accurately placed around the first image object. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for improving map labeling and in particular, for automating process of semantically labeling maps used for autonomous vehicle (AV) navigation. In some aspects, a process of the disclosed technology includes steps for receiving a three-dimensional (3D) Light Detection and Ranging (LiDAR) map, processing the 3D LiDAR map to produce a 2D map, rasterizing the 2D map into a plurality of map tiles, and providing one or more of the map tiles to a machine-learning (ML) labeler, wherein the ML labeler is configured to identify and label image features in at least one of the one or more map tiles. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for detecting an object. A process of the disclosed technology can include steps for receiving three-dimensional (3D) Light Detection and Ranging (LiDAR) data of the object at a first time, generating a first point cloud based on the 3D LiDAR data at the first time, receiving 3D LiDAR data of the object at a second time, generating a second point cloud based on the 3D LiDAR data at the second time, aggregating the first point cloud and the second point cloud to form an aggregated point cloud, and placing a bounding box around the aggregated point cloud. Systems and machine-readable media are also provided.