Abstract: A computer-implemented method for determining scene-consistent motion forecasts from sensor data can include obtaining scene data including one or more actor features. The computer-implemented method can include providing the scene data to a latent prior model, the latent prior model configured to generate scene latent data in response to receipt of scene data, the scene latent data including one or more latent variables. The computer-implemented method can include obtaining the scene latent data from the latent prior model. The computer-implemented method can include sampling latent sample data from the scene latent data. The computer-implemented method can include providing the latent sample data to a decoder model, the decoder model configured to decode the latent sample data into a motion forecast including one or more predicted trajectories of the one or more actor features.

Abstract: The present disclosure provides systems and methods for training probabilistic object motion prediction models using non-differentiable representations of prior knowledge. As one example, object motion prediction models can be used by autonomous vehicles to probabilistically predict the future location(s) of observed objects (e.g., other vehicles, bicyclists, pedestrians, etc.). For example, such models can output a probability distribution that provides a distribution of probabilities for the future location(s) of each object at one or more future times. Aspects of the present disclosure enable these models to be trained using non-differentiable prior knowledge about motion of objects within the autonomous vehicle's environment such as, for example, prior knowledge about lane or road geometry or topology and/or traffic information such as current traffic control states (e.g., traffic light status).

Abstract: Systems and methods are provided for detecting objects of interest. A computing system can input sensor data to one or more first machine-learned models associated with detecting objects external to an autonomous vehicle. The computing system can obtain as an output of the first machine-learned models, data indicative of one or more detected objects. The computing system can determine data indicative of at least one uncertainty associated with the one or more detected objects and input the data indicative of the one or more detected objects and the data indicative of the at least one uncertainty to one or more second machine-learned models. The computing system can obtain as an output of the second machine-learned models, data indicative of at least one prediction associated with the one or more detected objects. The at least one prediction can be based at least in part on the detected objects and the uncertainty.

Abstract: A computer-implemented method for determining scene-consistent motion forecasts from sensor data can include obtaining scene data including one or more actor features. The computer-implemented method can include providing the scene data to a latent prior model, the latent prior model configured to generate scene latent data in response to receipt of scene data, the scene latent data including one or more latent variables. The computer-implemented method can include obtaining the scene latent data from the latent prior model. The computer-implemented method can include sampling latent sample data from the scene latent data. The computer-implemented method can include providing the latent sample data to a decoder model, the decoder model configured to decode the latent sample data into a motion forecast including one or more predicted trajectories of the one or more actor features.

Abstract: The present disclosure provides systems and methods for training probabilistic object motion prediction models using non-differentiable representations of prior knowledge. As one example, object motion prediction models can be used by autonomous vehicles to probabilistically predict the future location(s) of observed objects (e.g., other vehicles, bicyclists, pedestrians, etc.). For example, such models can output a probability distribution that provides a distribution of probabilities for the future location(s) of each object at one or more future times. Aspects of the present disclosure enable these models to be trained using non-differentiable prior knowledge about motion of objects within the autonomous vehicle's environment such as, for example, prior knowledge about lane or road geometry or topology and/or traffic information such as current traffic control states (e.g., traffic light status).

Abstract: Systems and methods for generating motion forecast data for actors with respect to an autonomous vehicle and training a machine learned model for the same are disclosed. The computing system can include an object detection model and a graph neural network including a plurality of nodes and a plurality of edges. The computing system can be configured to input sensor data into the object detection model; receive object detection data describing the location of the plurality of the actors relative to the autonomous vehicle as an output of the object detection model; input the object detection data into the graph neural network; iteratively update a plurality of node states respectively associated with the plurality of nodes; and receive, as an output of the graph neural network, the motion forecast data with respect to the plurality of actors.

Abstract: Systems and methods for generating motion forecast data for actors with respect to an autonomous vehicle and training a machine learned model for the same are disclosed. The computing system can include an object detection model and a graph neural network including a plurality of nodes and a plurality of edges. The computing system can be configured to input sensor data into the object detection model; receive object detection data describing the location of the plurality of the actors relative to the autonomous vehicle as an output of the object detection model; input the object detection data into the graph neural network; iteratively update a plurality of node states respectively associated with the plurality of nodes; and receive, as an output of the graph neural network, the motion forecast data with respect to the plurality of actors.

Abstract: Systems and methods are provided for detecting objects of interest. A computing system can input sensor data to one or more first machine-learned models associated with detecting objects external to an autonomous vehicle. The computing system can obtain as an output of the first machine-learned models, data indicative of one or more detected objects. The computing system can determine data indicative of at least one uncertainty associated with the one or more detected objects and input the data indicative of the one or more detected objects and the data indicative of the at least one uncertainty to one or more second machine-learned models. The computing system can obtain as an output of the second machine-learned models, data indicative of at least one prediction associated with the one or more detected objects. The at least one prediction can be based at least in part on the detected objects and the uncertainty.

Abstract: Systems and methods are provided for detecting objects of interest. A computing system can input sensor data to one or more first machine-learned models associated with detecting objects external to an autonomous vehicle. The computing system can obtain as an output of the first machine-learned models, data indicative of one or more detected objects. The computing system can determine data indicative of at least one uncertainty associated with the one or more detected objects and input the data indicative of the one or more detected objects and the data indicative of the at least one uncertainty to one or more second machine-learned models. The computing system can obtain as an output of the second machine-learned models, data indicative of at least one prediction associated with the one or more detected objects. The at least one prediction can be based at least in part on the detected objects and the uncertainty.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with object association and tracking are provided. Input data can be obtained. The input data can be indicative of a detected object within a surrounding environment of an autonomous vehicle and an initial object classification of the detected object at an initial time interval and object tracks at time intervals preceding the initial time interval. Association data can be generated based on the input data and a machine-learned model. The association data can indicate whether the detected object is associated with at least one of the object tracks. An object classification probability distribution can be determined based on the association data. The object classification probability distribution can indicate a probability that the detected object is associated with each respective object classification. The association data and the object classification probability distribution for the detected object can be outputted.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with object association and tracking are provided. Input data can be obtained. The input data can be indicative of a detected object within a surrounding environment of an autonomous vehicle and an initial object classification of the detected object at an initial time interval and object tracks at time intervals preceding the initial time interval. Association data can be generated based on the input data and a machine-learned model. The association data can indicate whether the detected object is associated with at least one of the object tracks. An object classification probability distribution can be determined based on the association data. The object classification probability distribution can indicate a probability that the detected object is associated with each respective object classification. The association data and the object classification probability distribution for the detected object can be outputted.

Abstract: The present disclosure provides systems and methods for training probabilistic object motion prediction models using non-differentiable representations of prior knowledge. As one example, object motion prediction models can be used by autonomous vehicles to probabilistically predict the future location(s) of observed objects (e.g., other vehicles, bicyclists, pedestrians, etc.). For example, such models can output a probability distribution that provides a distribution of probabilities for the future location(s) of each object at one or more future times. Aspects of the present disclosure enable these models to be trained using non-differentiable prior knowledge about motion of objects within the autonomous vehicle's environment such as, for example, prior knowledge about lane or road geometry or topology and/or traffic information such as current traffic control states (e.g., traffic light status).

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with object association and tracking are provided. Input data can be obtained. The input data can be indicative of a detected object within a surrounding environment of an autonomous vehicle and an initial object classification of the detected object at an initial time interval and object tracks at time intervals preceding the initial time interval. Association data can be generated based on the input data and a machine-learned model. The association data can indicate whether the detected object is associated with at least one of the object tracks. An object classification probability distribution can be determined based on the association data. The object classification probability distribution can indicate a probability that the detected object is associated with each respective object classification. The association data and the object classification probability distribution for the detected object can be outputted.

Abstract: Systems and methods for generating motion forecast data for actors with respect to an autonomous vehicle and training a machine learned model for the same are disclosed. The computing system can include an object detection model and a graph neural network including a plurality of nodes and a plurality of edges. The computing system can be configured to input sensor data into the object detection model; receive object detection data describing the location of the plurality of the actors relative to the autonomous vehicle as an output of the object detection model; input the object detection data into the graph neural network; iteratively update a plurality of node states respectively associated with the plurality of nodes; and receive, as an output of the graph neural network, the motion forecast data with respect to the plurality of actors.

Abstract: Systems and methods are provided for detecting objects of interest. A computing system can input sensor data to one or more first machine-learned models associated with detecting objects external to an autonomous vehicle. The computing system can obtain as an output of the first machine-learned models, data indicative of one or more detected objects. The computing system can determine data indicative of at least one uncertainty associated with the one or more detected objects and input the data indicative of the one or more detected objects and the data indicative of the at least one uncertainty to one or more second machine-learned models. The computing system can obtain as an output of the second machine-learned models, data indicative of at least one prediction associated with the one or more detected objects. The at least one prediction can be based at least in part on the detected objects and the uncertainty.