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.
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.
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.
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.