Kyle Volle

1350 Poquito Rd N, Shalimar, FL 32579
kvolle@ufl.edu

I am an assistant research scientist for the University of Florida at the UF REEF in Shalimar, FL. As part of the Autonomous Vehicle Lab (AVL), I work with researchers from various universities, as well as the Air Force Research Lab, applying machine learning techniques to topics related to cooperative autonomy, GPS-denied navigation, and controls.

This position has given me the opportunity to work on a diverse set of projects. One of the core activities of the AVL is to host several undergraduate and graduate student interns each summer. These internships give the students experience in depolying their research on hardware, to produce proof-of-concept demos of new ideas, and to establish collaborations with students at other universities. I've mentored several students over the years that have continued to collaborate with the AVL after they returned to their home labs. These collaborations have led to one published conference paper, one submitted journal article, and two papers in progress.

While my day-to-day activities vary with the availability of funding and seasonal mentoring duties, I also have opportunities to pursue my own research questions. My primary research interest is in how neural networks encode information and how that relates to out-of-domain detection and epistemic uncertainty. Looking at the distribution of the penultimate output layers ("features") after neural collapse occurs can provide information about whether or not a given sample is meaningfully consistent with the training data. This relates to adversarial robustness, uncertainty quantification, loss function shaping, and more.

Current position

Autonomous Vehicles Lab

University of Florida REEF - Shalimar, FL
Assistant Research Scientist
Feb 2021 -    Present
National Academies of Science NRC Research Associate
Feb 2019 - Feb 2021
University of Florida Postdoc
May 2018 - Feb 2019

Education

Georgia Institute of Technology

PhD in Robotics

Thesis title: Cooperative control methods for the weapon target assignment problem

Thesis supervisor: Dr Jonathan Rogers

May 2018

Washburn University

B. Sc. Physics
Part of 3+2 Dual Degree Program with University of Kansas
August 2012

University of Kansas

B. Sc. Mechanical Engineering
May 2012

Publications

Journals

Katherine Hendrickson, Prashant Ganesh, Kyle Volle, Paul Buzaud, Kevin Brink, and Matthew Hale. Decentralized weapon–target assignment under asynchronous communications. Journal of Guidance, Control, and Dynamics, pages 1–13, 2022.

Zachary I Bell, Runhan Sun, Kyle Volle, Prashant Ganesh, Scott A Nivison, and Warren E Dixon. Target tracking subject to intermittent measurements using attention deep neural networks. IEEE Control Systems Letters, 7:379–384, 2022.

Jincheng Zhang, Prashant Ganesh, Kyle Volle, Andrew Willis, and Kevin Brink. Low-bandwidth and compute-bound rgb-d planar semantic slam. Sensors, 21(16):5400, 2021.

Andrew R Willis, Prashant Ganesh, Kyle Volle, Jincheng Zhang, and Kevin Brink. Volumetric procedural models for shape representation. Graphics and Visual Computing, 4:200018, 2021.

Kyle Volle and Jonathan Rogers. Weapon–target assignment algorithm for simultaneous and sequenced arrival. Journal of Guidance, Control, and Dynamics, 41(11):2361–2373, 2018.

Kyle Volle, Jonathan Rogers, and Kevin Brink. Decentralized cooperative control methods for the modified weapon–target assignment problem. Journal of Guidance, Control, and Dynamics, 39(9):1934–1948, 2016.


Conference Papers

J Humberto Ramos, Jaejeong Shin, Kyle Volle, Paul Buzaud, Kevin Brink, and Prashant Ganesh. Information-aware guidance for magnetic anomaly based navigation. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 6347–6354. IEEE, 2022.

Skylar E Stolte, Kyle Volle, Aprinda Indahlastari, Alejandro Albizu, Adam J Woods, Kevin Brink, Matthew Hale, and Ruogu Fang. Domino: Domain-aware model calibration in medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 454–463. Springer, Cham, 2022.

Prashant Ganesh, Kyle Volle, Paul Buzaud, Kevin Brink, and Andrew Willis. Extrinsic calibration of camera and motion capture systems. In SoutheastCon 2021, pages 01–08. IEEE, 2021.

Prashant Ganesh, Kyle Volle, Andrew R Willis, and Kevin M Brink. Three flavors of rgb-d visual odometry: Analysis of cost function compromises and covariance estimation accuracy. In 2020 IEEE/ION Position, Location and Navigation Symposium (PLANS), pages 1587–1595. IEEE, 2020.

Kyle Volle, Prashant Ganesh, Thomas F Burks, and Siddhartha S Mehta. Semi-self-supervised segmentation of oranges with small sample sizes. In 2020 ASABE Annual International Virtual Meeting, page 1. American Society of Agricultural and Biological Engineers, 2020.

J Humberto Ramos, Prashant Ganesh, William Warke, Kyle Volle, and Kevin Brink. Reef estimator: A simplified open source estimator and controller for multirotors. In 2019 IEEE National Aerospace and Electronics Conference (NAECON), pages 606–613. IEEE, 2019.

Prashant Ganesh, Kyle Volle, Thomas F Burks, and Siddhartha S Mehta. Deep orange: Mask r-cnn based orange detection and segmentation. IFAC-PapersOnLine, 52(30):70–75, 2019.

Kyle Volle and Jonathan D Rogers. Simultaneous arrival control algorithms for weapon target assignment. In AIAA Guidance, Navigation, and Control Conference, page 1739, 2017.

Kyle Volle, Jonathan D Rogers, and Kevin Brink. Scalable cooperative control algorithms for the weapon target assignment problem. In AIAA Guidance, Navigation, and Control Conference, page 2106, 2016.