Abstract: Example localization systems and methods are described. In one implementation, a method receives a camera image from a vehicle camera and cleans the camera image using a VAE-GAN (variational autoencoder combined with a generative adversarial network) algorithm. The method further receives a vector map related to an area proximate the vehicle and generates a synthetic image based on the vector map. The method then localizes the vehicle based on the cleaned camera image and the synthetic image.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to simulate behavior of a vehicle suspension component based on sampling a geometry space including vehicle suspension component hard-points using Gaussian process modeling and determine one or more vehicle suspension component geometries including vehicle suspension component hard-points based on first kinematic curves corresponding to behavior of the vehicle suspension component.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to generate two or more stereo pairs of synthetic images and generate two or more stereo pairs of real images based on the two or more stereo pairs of synthetic images using a generative adversarial network (GAN), wherein the GAN is trained using a six-axis degree of freedom (DoF) pose determined based on the two or more pairs of real images. The instructions can further include instructions to train a deep neural network based on a sequence of real images and operate a vehicle using the deep neural network to process a sequence of video images acquired by a vehicle sensor.

Abstract: Various examples of hybrid metric-topological camera-based localization are described. A single image sensor captures an input image of an environment. The input image is localized to one of a plurality of topological nodes of a hybrid simultaneous localization and mapping (SLAM) metric-topological map which describes the environment as the plurality of topological nodes at a plurality of discrete locations in the environment. A metric pose of the image sensor can be determined using a Perspective-n-Point (PnP) projection algorithm. A convolutional neural network (CNN) can be trained to localize the input image to one of the plurality of topological nodes and a direction of traversal through the environment.

Abstract: Example localization systems and methods are described. In one implementation, a method receives a camera image from a vehicle camera and cleans the camera image using a VAE-GAN (variational autoencoder combined with a generative adversarial network) algorithm. The method further receives a vector map related to an area proximate the vehicle and generates a synthetic image based on the vector map. The method then localizes the vehicle based on the cleaned camera image and the synthetic image.

Abstract: A system comprising a computer that includes a processor and a memory. The memory stores instructions executable by the processor to actuate a digital display on a vehicle to display a first set of content for more than an amount of time determined to render the first set of content detectable for a human, and to actuate the digital display to display a second set of content immediately after and immediately before the first set of content for less than the amount of time.

Abstract: A computing system can be programmed to receive a spoken language command in response to emitting a spoken language cue and process the spoken language command with a generalized adversarial neural network (GAN) to determine a vehicle command. The computing system can be further programmed to operate a vehicle based on the vehicle command.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine a vehicle six degree of freedom (DoF) pose based on an image where the six DoF pose includes x, y, and z location and roll, pitch, and yaw orientation and transform the vehicle six DoF pose into global coordinates based on a camera six DoF pose. The instructions can include further instructions to communicate to the vehicle the six DoF pose in global coordinates.

Abstract: Various examples of hybrid metric-topological camera-based localization are described. A single image sensor captures an input image of an environment. The input image is localized to one of a plurality of topological nodes of a hybrid simultaneous localization and mapping (SLAM) metric-topological map which describes the environment as the plurality of topological nodes at a plurality of discrete locations in the environment. A metric pose of the image sensor can be determined using a Perspective-n-Point (PnP) projection algorithm. A convolutional neural network (CNN) can be trained to localize the input image to one of the plurality of topological nodes and a direction of traversal through the environment.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine an eccentricity map based on video image data and determine vehicle motion data by processing the eccentricity map and two red, green, blue (RGB) video images with a deep neural network trained to output vehicle motion data in global coordinates. The instructions can further include instructions to operate a vehicle based on the vehicle motion data.

Abstract: A speech conversion system is described that includes a hierarchical encoder and a decoder. The system may comprise a processor and memory storing instructions executable by the processor. The instructions may comprise to: using a second recurrent neural network (RNN) (GRU1) and a first set of encoder vectors derived from a spectrogram as input to the second RNN, determine a second concatenated sequence; determine a second set of encoder vectors by doubling a stack height and halving a length of the second concatenated sequence; using the second set of encoder vectors, determine a third set of encoder vectors; and decode the third set of encoder vectors using an attention block.

Abstract: The disclosure relates to systems, methods, and devices for determining a depth map of an environment based on a monocular image. A method for determining a depth map includes receiving a plurality of images from a monocular camera forming an image sequence. The method includes determining pose vector data for two successive images of the image sequence and providing the image sequence and the pose vector data to a generative adversarial network (GAN), wherein the GAN is trained using temporal constraints to generate a depth map for each image of the image sequence. The method includes generating a reconstructed image based on a depth map received from the GAN.

Abstract: Example localization systems and methods are described. In one implementation, a method receives a camera image from a vehicle camera and cleans the camera image using a VAE-GAN (variational autoencoder combined with a generative adversarial network) algorithm. The method further receives a vector map related to an area proximate the vehicle and generates a synthetic image based on the vector map. The method then localizes the vehicle based on the cleaned camera image and the synthetic image.

Abstract: Various examples of hybrid metric-topological camera-based localization are described. A single image sensor captures an input image of an environment. The input image is localized to one of a plurality of topological nodes of a hybrid simultaneous localization and mapping (SLAM) metric-topological map which describes the environment as the plurality of topological nodes at a plurality of discrete locations in the environment. A metric pose of the image sensor can be determined using a Perspective-n-Point (PnP) projection algorithm. A convolutional neural network (CNN) can be trained to localize the input image to one of the plurality of topological nodes and a direction of traversal through the environment.

Abstract: A computing system can be programmed to receive a spoken language command in response to emitting a spoken language cue and process the spoken language command with a generalized adversarial neural network (GAN) to determine a vehicle command. The computing system can be further programmed to operate a vehicle based on the vehicle command.

Abstract: The disclosure relates to systems, methods, and devices for simultaneous localization and mapping of a robot in an environment utilizing a variational autoencoder generative adversarial network (VAE-GAN). A method includes receiving an image from a camera of a vehicle and providing the image to a VAE-GAN. The method includes receiving from the VAE-GAN reconstructed pose vector data and a reconstructed depth map based on the image. The method includes calculating simultaneous localization and mapping for the vehicle based on the reconstructed pose vector data and the reconstructed depth map. The method is such that the VAE-GAN comprises a latent space for receiving a plurality of inputs.

Abstract: The disclosure relates to systems, methods, and devices for determining a depth map of an environment based on a monocular image. A method for determining a depth map includes receiving a plurality of images from a monocular camera forming an image sequence. The method includes determining pose vector data for two successive images of the image sequence and providing the image sequence and the pose vector data to a generative adversarial network (GAN), wherein the GAN is trained using temporal constraints to generate a depth map for each image of the image sequence. The method includes generating a reconstructed image based on a depth map received from the GAN.