Ford Global Technolgoies, LLC

Samsung Display Co., Ltd.

Kaushik Balakrishnan

Praveen Narayanan

Punarjay Chakravarty

Francois Charette

Vijay K Nagasamy

Janghwan Lee

Lisa Scaria

Apurbaa Mallik

Ryan Burke

Mohsen Lakehal-ayat

Shuhui Qu

Sowndarya Sundar

Qisen Cheng

A system includes a computer including a processor and a memory, the memory storing instructions executable by the processor to generate a synthetic image by adjusting respective color values of one or more pixels of a reference image based on a specified meteorological optical range from a vehicle sensor to simulated fog, and input the synthetic image to a machine learning program to train the machine learning program to identify a meteorological optical range from the vehicle sensor to actual fog.

Enhanced vehicle operation

A method for training an autonomous vehicle to reach a target location. The method includes detecting the state of an autonomous vehicle in a simulated environment, and using a neural network to navigate the vehicle from an initial location to a target destination. During the training phase, a second neural network may reward the first neural network for a desired action taken by the autonomous vehicle, and may penalize the first neural network for an undesired action taken by the autonomous vehicle. A corresponding system and computer program product are also disclosed and claimed herein.

Automatic navigation using deep reinforcement learning

An end-to-end deep-learning-based system that can solve both ASR and TTS problems jointly using unpaired text and audio samples is disclosed herein. An adversarially-trained approach is used to generate a more robust independent TTS neural network and an ASR neural network that can be deployed individually or simultaneously. The process for training the neural networks includes generating an audio sample from a text sample using the TTS neural network, then feeding the generated audio sample into the ASR neural network to regenerate the text. The difference between the regenerated text and the original text is used as a first loss for training the neural networks. A similar process is used for an audio sample. The difference between the regenerated audio and the original audio is used as a second loss. Text and audio discriminators are similarly used on the output of the neural network to generate additional losses for training.

Joint automatic speech recognition and text to speech conversion using adversarial neural networks

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.

Vehicle language processing

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.

Simultaneous localization and mapping constraints in generative adversarial networks for monocular depth estimation

Growing community of inventors

Mountain View, CA, United States of America

Kaushik Balakrishnan