Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that validates labels associated with sensor measurements of a scene in an environment. One of the methods includes receiving data representing a sensor measurement of a scene in an environment generated by one or more sensors. The sensor measurement can be associated with one or more labels, and each label can identify a portion of the sensor measurement that has been classified as measuring an object in the environment. For each of the labels, a determination can be made as to whether the label satisfies each of the validation criteria. Each validation criterion can measure whether one or more characteristics of the label are consistent with one or more characteristics of real-world objects in the environment.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for generating and editing object track labels for objects detected in video data. One of the methods includes obtaining a video segment comprising multiple image frames associated with multiple time points; obtaining object track data specifying a set of object tracks; providing, for presentation to a user, a user interface for modifying the object track data, the user interface displaying object timeline representations of the object tracks; receiving one or more user inputs that indicate one or more modifications to the object timeline representations; updating the object timeline representations displayed in the timeline display area; and updating the object track data according to the updated object timeline representations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent trajectory prediction using context-sensitive fusion.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting the future movement of agents in an environment. In particular, the future movement is predicted through occupancy flow fields that specify, for each future time point in a sequence of future time points and for each agent type in a set of one or more agent types: an occupancy prediction for the future time step that specifies, for each grid cell, an occupancy likelihood that any agent of the agent type will occupy the grid cell at the future time point, and a motion flow prediction that specifies, for each grid cell, a motion vector that represents predicted motion of agents of the agent type within the grid cell at the future time point.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating a behavior prediction system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for the generation and use of a surfel map with semantic labels. One of the methods includes receiving a surfel map that includes a plurality of surfels, wherein each surfel has associated data that includes one or more semantic labels; obtaining sensor data for one or more locations in the environment, the sensor data having been captured by one or more sensors of a first vehicle; determining one or more surfels corresponding to the one or more locations of the obtained sensor data; identifying one or more semantic labels for the one or more surfels corresponding to the one or more locations of the obtained sensor data; and performing, for each surfel corresponding to the one or more locations of the obtained sensor data, a label-specific detection process for the surfel.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating realistic full-scene point clouds. One of the methods includes obtaining an initial scene point cloud characterizing an initial scene in an environment; obtaining, for each of one or more objects, an object point cloud that characterizes the object; and processing a first input comprising the initial scene point cloud and the one or more object point clouds using a first neural network that is configured to process the first input to generate a final scene point cloud that characterizes a transformed scene that has the one or more objects added to the initial scene.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent trajectory prediction using temporal-spatial interaction predictions.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing object detection. The system obtains a respective range image corresponding to each point cloud in a set of point clouds captured by one or more sensors. The system processes each range image using a segmentation neural network to generate range image features and a segmentation output. The system generates a feature representation of the set of point clouds from only the feature representations of the foreground points. The system processes the feature representation of the set of point clouds using a prediction neural network to generate a prediction characterizing the set of point clouds.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing training of a neural network that is configured to process a network input comprising a point cloud to generate a network output for a point cloud processing task. The system obtains a set of labeled training examples and a set of unlabeled point clouds, generates a respective pseudo-label for each unlabeled point cloud, generates a plurality of pseudo-elements based on the respective pseudo-label for the unlabeled point cloud, generates augmented training data by augmenting the labeled training examples using the pseudo-elements generated for the unlabeled point clouds, and performing training of the neural network on the augmented training data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing a conditional behavior prediction for one or more agents. The system obtains context data characterizing an environment. The context data includes data characterizing a plurality of agents, including a query agent and one or more target agents, in the environment at a current time point. The system further obtains data identifying a planned future trajectory for the query agent after the current time point, and for each target agent in the set, processes the context data and the data identifying the planned future trajectory using a first neural network to generate a conditional trajectory prediction output that defines a conditional probability distribution over possible future trajectories of the target agent after the current time point given that the query agent follows the planned future trajectory for the query agent after the current time point.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating realistic full-scene point clouds. One of the methods includes obtaining an initial scene point cloud characterizing an initial scene in an environment; obtaining, for each of one or more objects, an object point cloud that characterizes the object; and processing a first input comprising the initial scene point cloud and the one or more object point clouds using a first neural network that is configured to process the first input to generate a final scene point cloud that characterizes a transformed scene that has the one or more objects added to the initial scene.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining estimated ground truth object keypoint labels for sensor readings of objects. In one aspect, a method comprises obtaining a plurality of sets of label data for a sensor reading of an object; obtaining respective quality control data corresponding to each of the plurality of sets of label data, the respective quality control data comprising: data indicating whether the labeled location of the first object keypoint in the corresponding set of label data is accurate; and determining an estimated ground truth location for the first object keypoint in the sensor data keypoint from (i) the labeled locations that were indicated as accurate by the corresponding quality control data and (ii) not from the labeled locations that were indicated as not accurate by the corresponding quality control data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for the generation and use of a surfel map with semantic labels. One of the methods includes receiving a surfel map that includes a plurality of surfels, wherein each surfel has associated data that includes one or more semantic labels; obtaining sensor data for one or more locations in the environment, the sensor data having been captured by one or more sensors of a first vehicle; determining one or more surfels corresponding to the one or more locations of the obtained sensor data; identifying one or more semantic labels for the one or more surfels corresponding to the one or more locations of the obtained sensor data; and performing, for each surfel corresponding to the one or more locations of the obtained sensor data, a label-specific detection process for the surfel.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing three-dimensional auto-labeling on sensor data. The system obtains a sensor data segment that includes a temporal sequence of three-dimensional point clouds generated from sensor readings of an environment by one or more sensors. The system identifies, from the sensor data segment, (i) a plurality of object tracks that each corresponds to a different object in the environment and (ii) for each object track, respective initial three-dimensional regions in each of one or more of the point clouds in which the corresponding object appears. The system generates, for each object track, extracted object track data that includes at least the points in the respective initial three-dimensional regions for the object track.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for processing a perspective view range image generated from sensor measurements of an environment. The perspective view range image includes a plurality of pixels arranged in a two-dimensional grid and including, for each pixel, (i) features of one or more sensor measurements at a location in the environment corresponding to the pixel and (ii) geometry information comprising range features characterizing a range of the location in the environment corresponding to the pixel relative to the one or more sensors. The system processes the perspective view range image using a first neural network to generate an output feature representation. The first neural network comprises a first perspective point-set aggregation layer comprising a geometry-dependent kernel.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a perspective computer vision model. The model is configured to receive input data characterizing an input scene in an environment from an input viewpoint and to process the input data in accordance with a set of model parameters to generate an output perspective representation of the scene from the input viewpoint. The system trains the model based on first data characterizing a scene in the environment from a first viewpoint and second data characterizing the scene in the environment from a second, different viewpoint.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.