Abstract: In various examples, systems and methods are disclosed relating to neural networks for realistic and controllable agent simulation using guided trajectories. The neural networks can be configured using training data including trajectories and other state data associated with subjects or agents and remote or neighboring subjects or agents, as well as context data representative of an environment in which the subjects are present. The trajectories can be determining using the neural networks and using various forms of guidance for controllability, such as for waypoint navigation, obstacle avoidance, and group movement.

Abstract: In various examples, systems and methods are presented for model-based trajectory simulation of agents in a simulated environment. Traffic simulators mimic reality so that autonomous or semi-autonomous vehicle design teams can validate driving models in environments that have diversity and complexity. In some embodiments, for a model-controlled agent of a simulation environment, a plurality of navigation probability distributions are generated, each of the plurality of navigation probability distributions defining a candidate trajectory for the agent to follow. A trajectory is selected for the agent based at least on at least one of the plurality of navigation probability distributions, and the agent is moved within the simulation environment based at least on the selected trajectory. In some embodiments, a search algorithm may be applied across multiple time-steps of a simulation, for example, to identify the occurrence of collision-free sequences of navigation probability distributions.

Abstract: Approaches for training data set size estimation for machine learning model systems and applications are described. Examples include a machine learning model training system that estimates target data requirements for training a machine learning model, given an approximate relationship between training data set size and model performance using one or more validation score estimation functions. To derive a validation score estimation function, a regression data set is generated from training data, and subsets of the regression data set are used to train the machine learning model. A validation score is computed for the subsets and used to compute regression function parameters to curve fit the selected regression function to the training data set. The validation score estimation function is then solved for and provides an output of an estimate of the number additional training samples needed for the validation score estimation function to meet or exceed a target validation score.

Abstract: A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.

Abstract: A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.

Abstract: In various examples, systems and methods are disclosed that use a domain-adaptation theory to minimize the reality gap between simulated and real-world domains for training machine learning models. For example, sampling of spatial priors may be used to generate synthetic data that that more closely matches the diversity of data from the real-world. To train models using this synthetic data that still perform well in the real-world, the systems and methods of the present disclosure may use a discriminator that allows a model to learn domain-invariant representations to minimize the divergence between the virtual world and the real-world in a latent space. As such, the techniques described herein allow for a principled approach to learn neural-invariant representations and a theoretically inspired approach on how to sample data from a simulator that, in combination, allow for training of machine learning models using synthetic data.

Abstract: Apparatuses, systems, and techniques to use one or more neural networks to generate one or more images based, at least in part, on one or more spatially-independent features within the one or more images. In at least one embodiment, the one or more neural networks determine spatially-independent information and spatially-dependent information of the one or more images and process the spatially-independent information and the spatially-dependent information to generate the one or more spatially-independent features and one or more spatially-dependent features within the one or more images.

Abstract: Apparatuses, systems, and techniques are presented to generate view-specific representations of an object or environment. In at least one embodiment, one or more neural networks are used to generate one or more images based, at least in part, on two or more two-dimensional (2D) images having different frames of reference.

Abstract: Apparatuses, systems, and techniques are presented to generate a simulated environment. In at least one embodiment, one or more neural networks are used to generate a simulated environment based, at least in part, on stored information associated with objects within the simulated environment.

Abstract: A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.