The summer of 2020 provided many challenges. For 9 undergraduate students across the United States, the summer also provided a research experience in autonomous driving and its many applications. In spite of the many challenges posed by the pandemic with respect to travel, networking, and person-to-person meetings, these undergraduate researchers showed tremendous resilience and perseverance in working on projects remotely and communicating largely through video conferencing and workspace text apps.

For more information on the topics and contributions of the four teams of researchers, please visit for a listing of their projects, and also links to individual videos they produced about their research experience.

“Although I wish the conference could have been in person so I could have met other researchers in Denver, I find myself very lucky to have worked with my team, and to have been able to participate in the CAT Vehicle REU program," said Christopher Kreienkamp, whose presentation was through a YouTube video due to the COVID-19 policies of the conference.  Kreienkamp and his partner Daniel Fishbein, were part of CAT Vehicle 2019.


Subscribe to CAT Vehicle RSS


The applications process is currently closed. We typically accept applications from mid-December until mid-March, for a June-August program. Check back during that time frame in order to apply for next year's program.

  • December 2020 :  Applications open
  • 1 March 2021: Applications due, to guarantee full consideration
  • 2-8 March 2021: Letters of Recommendation due, to guarantee full consideration
  • 9-20 March 2021: Selection process
  • 31 March 2021: Notification deadline
  • April-May 2021: Preparation and background reading
  • June-August 2021: 10-week program.

This REU site will support 10 students over the summer. Each student will receive:

  • Stipend of $6,000 over the summer
  • Housing and $600 travel allowance to Tucson, AZ
  • Letters of recommendation from their faculty mentors

Students will participate as researchers for the summer, working side by side with graduate researchers and faculty who are experts in cognitive radio and autonomous ground vehicles. Want to know more about what the REU is like? Check out the videos made by previous CAT Vehicle participants.

REU 2018: Lane detectives showing their pride after successful testing

Whether for business or pleasure, people come from all across the world to visit Tucson's blossoming green landscape. Found in the Sonoran Desert - dubbed "the greenest of deserts" - Tucson offers travelers clear skies, fresh air, stunning sunsets and rugged outdoor adventures.

CAT Vehicle 2020

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.

(L) Calvin Barrett; (R) Tomo Bessho

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.

Rachel Kozel and Naeemah Robert

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

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.

(L) Megan Walter; (R) Iris Jones