Lytx, Inc.

Brain Corporation

Andrew Tombras Smith

Syrus C Nemat-Nasser

Greg Sutton

Erwin R Boer

Tom Butch

Vadim Polonichko

A random k-nearest neighbors (RKNN) approach may be used for regression/classification model wherein the input includes the k closest training examples in the feature space. The RKNN process may utilize video images as input in order to predict motor command for controlling navigation of a robot. In some implementations of robotic vision based navigation, the input space may be highly dimensional and highly redundant. When visual inputs are augmented with data of another modality that is characterized by fewer dimensions (e.g., audio), the visual data may overwhelm lower-dimension data. The RKNN process may partition available data into subsets comprising a given number of samples from the lower-dimension data. Outputs associated with individual subsets may be combined (e.g., averaged). Selection of number of neighbors, subset size and/or number of subsets may be used to trade-off between speed and accuracy of the prediction.

Apparatus and methods for training of robots

A system for providing real-time alerts or actions comprises an image capturing device and a processor and a memory. The image capturing device is for capturing an image during vehicle operation and of an expected driver location. The processor is configured to: 1) detect a face of a driver in the image; 2) determine a set of face data from the image; and 3) determine authentication based at least in part on the set of face data. The memory is coupled to the processor and configured to provide the processor with instructions.

Using passive driver identification and other input for providing real-time alerts or actions

A system for passive driver identification comprises an input interface and a processor. The input interface is configured to receive a collection of face data from a vehicle event recorder. The processor is configured to 1) determine a set of face data of the collection of face data that is associated with a trip; 2) determine a first album associated with the trip, wherein the set of face data associated with the trip is similar to face data of other trips in the first album, and wherein the set of face data associated with the trip is dissimilar to face data of a set of trips in a second album; and 3) assign an identifier that associates the trip to the first album.

Passive driver identification

A system for driver identification comprises a processor and a memory. The processor is configured to receive a driving maneuver signature and to determine a driver identification based at least in part on the driving maneuver signature. The memory is coupled to the processor and is configured to provide the processor with instructions.

Driver identification based on driving maneuver signature

A system for identifying a driver comprises an image capturing device, a processor, and a memory. The image is captured during vehicle operation and of an expected driver location. The processor is configured to detect a face of a driver in the image, determine a set of face data from the image, and identify the driver based at least in part on the set of face data. The memory is coupled to the processor and configured to provide the processor with instructions.

Growing community of inventors

San Diego, CA, United States of America

Andrew Tombras Smith