Novateur Research Solutions

University of Texas System

Novateur Research Solution

Novateur Reserch Solutions

Bivateur Research Solutions

Zeeshan Rasheed

Khurram Hassan-Shafique

Emmanuel Tung

Nicholas Raphael Gans

Maoxu Li

Khurram Hassan-shafique

Michael Edward Araujo

Mark Tenzer

Cody Lee Lundberg

Viksit Kumar

Jonathan Jacob Amazon

Alireza Zaeemzadeh

Eric Chen

A wearable device for non-invasive monitoring of intracranial pressure includes a wearable structure configured to be secured to a head of a user; an ultrasound transducer positioned to align with an eye of the user when worn; a motorized control mechanism that dynamically adjusts a position and angulation of the ultrasound transducer; a fluid management system that maintains an acoustic coupling between the ultrasound transducer and the eye of the user; an integrated air vent system to regulate pressure, prevent condensation, and maintain imaging quality within the wearable structure; and a processor coupled to the ultrasound transducer. The processor is to employ a reinforcement learning-based control system for optimizing transducer placement; acquire ultrasound images of an optic nerve sheath; analyze the ultrasound images to measure an optic nerve sheath diameter (ONSD); and determine a likelihood of elevated intracranial pressure based on the measured ONSD.

Wearable device for non-invasive monitoring of intracranial pressure through ophthalmic biomarkers

An autonomous system for detecting, localizing, and potentially deactivating chemical threats or emissions using multiple sensing modalities and reinforcement learning techniques. The system includes visual sensors (e.g., RGB, RGBD, LIDAR), non-visual sensors (e.g., gas concentration, airflow, GPS, RADAR), a neural network architecture and processor to fuse information from different sensors, a module based on deep reinforcement learning for decision making, and a robotic interface for executing actions. The neural network extracts relevant information from sensor streams and encodes them into a joint embedding space. The module considers the current observations, historical data, and previous actions to determine the optimal action for threat localization under partially observable conditions. The system is trained in simulated environments to minimize source localization time while accounting for various constraints. The autonomous system enables effective chemical threat detection and source localization in complex, dynamic environments without endangering human operators.

Autonomous source localization

Generating trajectories from an implicit neural representation (INR) model to predict human mobility in uncertain traffic conditions includes receiving geocoordinate data representing vehicle motion observations of a traffic pattern; receiving a road network based on the geocoordinate data; training the INR model to learn continuous, latent fields of stochastic traffic properties over space and time based on the geocoordinate data; utilizing the INR model to extract spatio-temporal speed distributions from the geocoordinate data; applying a near-shortest-path, heuristic algorithm, weighted by predictions of the INR model, to produce real-world routing choices for traversing the road network; generating trajectories for transportation between an origin and destination in the road network using the algorithm and the predictions of the INR model, wherein the trajectories reflect non-deterministic and diverse route choices in the road network; and outputting generated trajectories to improve routing choices for a GPS and to provide the route choices for selection.

Generating trajectories from implicit neural models

A system for measuring surface deflection of a road includes a first stereo line-scan camera pair on a sensor rig and for capturing a first set of 3D images of a road surface; a second stereo line-scan camera pair on the sensor rig and for capturing a second set of 3D images of the road surface; at least one digital electro-optical (EO) camera rigidly attached to the sensor rig; an inertial measurement unit (IMU) detecting inertial forces acting upon the sensor rig; and a processor compensating for acceleration and vibration effects upon the sensor rig; and calculating the surface deflection of the road based on the first and second sets of 3D images. The processor utilizes imagery from the EO camera and inertial measurements from the IMU to produce 2D mosaics and 3D reconstructions of the road surface from the first and second sets of 3D images.

Camera and sensor system for measurement of road surface deflection

A feature extractor and novel training objective are provided for content-based image retrieval. For example, a computer-implemented method includes applying a query image and a search image to a neural network of a feature extraction network of a computing device, the query image indicating an object to be searched for in the search image. The feature extraction network includes the neural network, a spatial feature neural network receiving a first output of the neural network pertaining to the search image, and an embedding network receiving a second output of the neural network pertaining to the query image. The method includes generating spatial search features from the spatial feature neural network, generating a query feature from the embedding network, applying the query feature to an artificial neural network (ANN) index, and determining an optimal matching result of an object in the search image based on an operation using the ANN index.

System and method for rare object localization and search in overhead imagery

Growing community of inventors

Ashburn, VA, United States of America

Zeeshan Rasheed