CAT Vehicle 2020

Real-Time Traffic Light Identification using YOLOv3 Algorithm For Autonomous Vehicles

Rachel Kozel (Purdue University)
Naeemah Robert (New York Institute of Technology)

Previous methods to detect traffic signals were not fully successful as they had limitations in detecting yellow and arrow traffic lights, in long-distance identification of a traffic light from a few pixels, and the obstruction of traffic lights from other infrastructure. This project uses a new method to identify traffic lights and their states in both urban and suburban areas by developing a deep learning model utilizing a You Only Look Once (YOLOv3) model.

Generative modeling of driving profiles

Megan Walter (University of Oregon)
Iris Jones (Washington State University)

The validity of simulation testing for autonomous vehicles depends on the ability to accurately simulate human driving behavior. This project seeks to train a model on an individual's driving data, and to test the ability of the model to predict trajectories that replicate the driver's style by using the model in a realistic simulated environment.

Hyperparameter Optimization using Grid Search for use in Monocular Depth Estimation

Calvin Barrett (Haverford College)
Tomo Bessho (University of Nebraska-Lincoln)

While an autonomous vehicle operates, it utilizes a myriad of sensors to observe its surroundings, including images that are used to train and optimize neural networks. This project explores how to set parameters for machine learning for detecting objects in these images.

Safer adaptive cruise control for traffic wave dampening

Audrey Vazzana (Rose-Hulman Institute of Technology)
Savannah Ball (Monmouth College)
Emily Baschab (University of Alabama)

Current adaptive cruise controllers can use radar sensors to follow a vehicle ahead at high speeds (40+ mph), but reach their limits if the vehicle ahead must slow down or stop, requiring the driver to resume control over the car’s speed. This project explores how to create low-speed adaptive cruise controllers that can safely operate in congested traffic.

(L) Audrey Vazzana; (C) Savannah Ball; (R) Emily Baschab

Baschab, Ball, and Vazanna publish at CPS-IoT Week

CPS-IoT Week is the premier event on Cyber-Physical Systems and Internet-of-Things Research, and three researchers from the CAT Vehicle will have their results published there in 2021. Emily Baschab (University of Alabama), Savannah Ball (Monmouth College), and Audrey Vazzana (Rose-Hulman Institute of Technology) continued work on their final paper, and submitted as a Work-In-Progress to the conference, where they will have an opportunity to present a poster on their work.