Skip to main content

2019 Spring

Semester Short

Machine Learning Bug Prediction Using Simulation Attributes

The goal of this project is to predict which design Verilog simulation fails are from an actual design bug vs. an invalid simulation artifact or bad checking assumption. The sponsor will provide the complete historic data set of Verilog simulation results from a recent x86 Core design project, consisting of possibly millions of design simulations and the simulation attributes and their results and log data.

Stereo Camera-based Localization and Obstacle Detection for Unmanned Aerial Vehicles

The goal of this project is to develop software modules for an autonomous drone navigation system. Our modules determine the location of the drone in a flight space relative to a map of the space, and detect obstacles and their positions within the environment. These modules function using only inputs from a stereo camera and a given map of the flight space. These modules are intended to be combined and extended for a complete autonomous drone navigation system. The application for this system is in a WiFi and GPS denied indoor environment.

Cradl: A Smart Baby Wearable

Currently, 3,500 babies are lost to SIDS and other sleep related deaths in the U.S. alone. The stress associated with infant deaths causes parents to lose 1,000 hours of sleep each year, which leads to inactive, stressed, and less-effective parenting. To solve for this we offer a wearable that provides real-time insights about baby health, in order to reduce the anxiety that parents experience. Through an easy to use mobile application paired with our hardware, we hope to transform distressed parents into more informed, more effective, and ultimately happier parents.

Traffic Controller for UAVs

Unmanned Aerial Vehicles have the potential to be used in large-scale applications of delivery or automation. Because of this, there may be a large amount of air traffic with the potential for crashes. This creates the need for a traffic controller. Our team’s solution is a scaled-down prototype of a larger system’s traffic control framework. Our design solution is to schedule and control two drones at once with the ability for an individual drone to land when a rogue object such as a drone has potential to collide with it.

Automatic Computer Generated Dull Bit Grading

Currently, oilfield personnel analyze and dull grade drill bits through visual inspection which can be subjective. The goal of this project is to build a web application that automates drill bit dull grading in order to improve consistency and accuracy. To perform the dull grading, the system calculates the damage of individual drill bit cutters using digital images as input. By performing an automated process, the system will provide a higher level of reliability, consistency, and accuracy.

Automated Data Collection for Mobile Network Traffic Data Classification

We are creating an updated dataset mapping mobile network packet metadata to applications, application activities, and application activity types in order to address the problem of mobile network data classification. For example, the dataset we create might contain packet length and proportion of inbound vs outbound packets mapped to instances of streaming videos on Netflix.


The Pulse-T looks to deliver on an athletic shirt that looks and feels like athletic wear while having the same biometric capability as the newest smartwatches and heart monitors. Using advancements in fabric sensor technology, we have combined conductive fabric to function as both a lead and a sensor.

National Instruments SourceAdapt

National Instruments has developed numerous LabVIEW Virtual Instrument (VI) and documents to assist test engineers to use this technology. However, it still demands a test engineer to have an unreasonably high minimum understanding of the system and control theory for effective use. This becomes an issue because there are many test engineers who do not have such background. Therefore, there is a need for automation the SourceAdapt technology.

Team Members: 

Ashton Broussard

Brent Devere

Riley Green

Sara Pham

Subscribe to 2019 Spring