Professor · Computer Science & Engineering · University of Nevada, Reno
Director, Evolutionary Computing Systems Lab (ECSL)
I work in Genetic Algorithms, Evolutionary Computing and their applications to AI, Machine Learning, and Optimization. My lab builds simulation-based adaptive training systems for naval operators, autonomous surface vessel path planners, cybersecurity training games, and evolves AI for real-time strategy games. We investigate interaction design for controlling large numbers of heterogeneous, semi-autonomous agents.
📍 WPEB 409 · UNR, Reno NV 89557
Ph.D., Indiana University, 1993
M.S. / B.S., Delhi University
Evolutionary Computing Systems Lab · ECSL
Featured · ONR-Funded
We designed and built a ship driving simulation trainer that uses knowledge tracing to adapt scenario difficulty in real time. A comparative study showed adaptive training is statistically significantly more effective (p < 0.0001), with 73% of students preferring it. The system trains naval officers on COLREGs — the international rules governing ship encounters — with scenarios set in Singapore and San Diego.
Read the paper →
Autonomous Navigation
VORRT-COLREGs combines velocity obstacles (VO) with rapidly-exploring random trees (RRT) to plan COLREGs-compliant trajectories for autonomous surface vessels in dynamic multi-ship environments. Published in IEEE Robotics and Automation Letters.
IEEE paper →
Serious Games · Cybersecurity
TAISER is a multiplayer Unity-based cybersecurity training game where human and AI players take WHITEHAT or BLACKHAT roles defending or attacking a city network. A CyberAI teammate provides real-time firewall rule recommendations to guide player learning.
Serious Games · Naval Training
A simulation-based game for training Naval Surface Warfare Officers to rapidly identify target angle — the bearing of a ship relative to an observer. Combines realistic 3D ship rendering with adaptive difficulty. Presented at IEEE CoG 2024.
IEEE paper →
Game AI · Evolutionary Computing
Using potential field-based co-evolutionary algorithms to develop sophisticated unit micro for StarCraft II. Recent work investigates NEAT-based neuroevolution and multi-objective approaches for generalizable, emergent combat tactics.
More ECSL projects →
Evolutionary Computing · Networks
Genetic algorithms evolve dynamic topologies for UAV-hosted mesh networks, optimizing communication coverage and reliability under changing conditions. Presented at IEEE Congress on Evolutionary Computation, 2020.
See publication →Ph.D. students interested in game AI, adaptive training, or autonomous systems: contact me · ecsl.cse.unr.edu
Selected Recent Publications