Ford Global Technolgoies, LLC

Akhil Perincherry

Nikhil Nagraj Rao

Vidya Nariyambut Murali

Nikita Jaipuria

Gautham Sholingar

Aghapi Mordovanakis

Rohan Bhasin

Arpita Chand

Kunjan Singh

Kyoung Min Lee

Ishan Patel

Christopher Cruise

Sutharsan Sivagnanam

A system includes a computer programmed to receive first sensor data from a first sensor, wherein the first sensor data is defined in part by a first data space that includes first parameters of the first sensor, and second sensor data from a second sensor, wherein the second sensor data is defined in part by a second data space that includes second parameters of the second sensor, to input the first sensor data and the second sensor data to a machine learning program to train the machine learning program to determine a domain translation of data from the first data space to the second data space, and then to input a set of training data received from the first sensor to the trained machine learning program to generate a training dataset based on the determined domain translation of data from the first data space to the second data space.

Sensor domain adaptation

Upon identifying image data associated with an object, radar data associated with the object is identified. A semantic point cloud image is generated based on the image data and the radar data. Transformed semantic point cloud image from a perspective of the object is determined with a variational auto-encoder neural network trained to accept the semantic point cloud image of the object and to generate the transformed semantic point cloud image from the perspective of the object. Physical characteristics of the object are determined based on the transformed semantic point cloud image.

Neural network object identification

A computer includes a processor and a memory, the memory storing instructions executable by the processor to collect a plurality of images of one or more targets at an intersection, input the images to a machine learning program to determine a number of the targets to which a host vehicle is predicted to yield at the intersection based on time differences between the plurality of images, and transmit a message indicating the number of the targets.

Vehicle intersection operation

A system and a method can receive a first dataset having a first label and a first context. The system and the method can also generate, at the trained deep neural network, a second dataset having the first label and a second context according to a mapping, wherein a first mapping of the plurality of mapping comprises one or more weights of the trained deep neural network that maps data having the first label and the first context to data having a second label and the first context and a second mapping of the plurality of mapping comprises one or more weights of the trained deep neural network that maps data having a second label and the first context to data having the second label and the second context, wherein the second context is different from the first context and the second label is different from the first label.

Domain generation via learned partial domain translations

The present disclosure discloses a system and a method for translating, e.g., mapping, a Red-Clear-Clear-Clear (RCCC) image to a Red-Green-Blue (RGB) image. In an example implementation, the system and the method can receive, at a deep neural network, an image having a Red-Clear-Clear-Clear (RCCC) image pattern, wherein the deep neural network includes a generator and a discriminator; generate, at the generator, a Red-Green-Blue (RGB) image based on the image having the RCCC image pattern; determine, at the discriminator, whether the RGB image is machine-generated or is sourced from the real data distribution; and update at least one weight of the generator when the discriminator determines the RGB image is machine-generated.

RCCC to RGB domain translation with deep neural networks

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to generate a synthetic image and corresponding ground truth and generate a plurality of domain adapted synthetic images by processing the synthetic image with a variational auto encoder-generative adversarial network (VAE-GAN), wherein the VAE-GAN is trained to adapt the synthetic image from a first domain to a second domain. The instructions can include further instructions to train a deep neural network (DNN) based on the domain adapted synthetic images and the corresponding ground truth and process images with the trained deep neural network to determine objects.

Growing community of inventors

Mountain View, CA, United States of America

Akhil Perincherry