Vu-Anh Le (Anh)

PhD Student
Department of Computer Science
University of Virginia
mcu7uh (at) virginia [dot] edu

Research

My research centers on autonomous systems: learning algorithms that enable reliable physical decision-making, and mechanisms that help multiagent systems coordinate, divide work, and pursue shared objectives.

Research Directions

Learning algorithms for autonomous systems: I develop learning algorithms that help autonomous systems perceive uncertain environments, learn useful representations and world models, and choose safe, effective actions. My interests include learning-enabled planning and control, adaptation from limited data, decision-making under uncertainty, and reliability under physical constraints.
Incentives, coordination, and task delegation of multiagent autonomous systems: I study how teams of autonomous agents divide work, exchange information, and coordinate decisions when their goals, capabilities, and information differ. This includes incentive design, distributed coordination, dynamic task allocation and delegation, negotiation, and mechanisms that make collective behavior efficient, robust, and aligned with system-level objectives.

Six examples of sampling strategies for robot motion planning — Example of motion planning for robotics. Source: L. Zhang, K. Cai, Z. Sun, Z. Bing, C. Wang, L. Figueredo, S. Haddadin, and A. Knoll, “Motion planning for robotics: A review for sampling-based planners,” *Biomimetic Intelligence and Robotics*, vol. 5, no. 1, Art. no. 100207, 2025, doi: 10.1016/j.birob.2024.100207.

Publications

Diagram summarizing the mathematical analysis of neural operator behaviors

A Mathematical Analysis of Neural Operator Behaviors

V.-A. Le and M. Dik, “A Mathematical Analysis of Neural Operator Behaviors,” in Quantum Calculus and Functional Analysis with Applications, B. Hazarika, S. Tikare, M. Dik, and D. Chalishajar, Eds. Boca Raton, FL, USA: CRC Press, 2025, ch. 23, doi: 10.1201/9781003618751-23.