Professor · Computer Science & Engineering · University of Nevada, Reno

Sushil J. Louis

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.

Contact

📍 WPEB 409 · UNR, Reno NV 89557

📞 (775) 784-4315

✉️ sushil@cse.unr.edu


ECSL Lab

ecsl.cse.unr.edu

youtube.com/@ecsllab


Education

Ph.D., Indiana University, 1993

M.S. / B.S., Delhi University


Publications

Google Scholar ↗

Complete Publications List

Evolutionary Computing Systems Lab
Evolutionary Computing Systems Lab (ECSL)
Directed by Dr. Sushil J. Louis · Department of Computer Science & Engineering · University of Nevada, Reno
ecsl.cse.unr.edu  ·  youtube.com/@ecsllab

Evolutionary Computing Systems Lab · ECSL

Current Research Projects Adaptive training · Autonomous navigation · Game AI · Cybersecurity

Ship bridge VR simulation

Featured · ONR-Funded

Adaptive Training for Nautical Rules of the Road

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 →
Velocity obstacle cones for autonomous ship navigation

Autonomous Navigation

VORRT-COLREGs: Velocity Obstacles for Autonomous Surface Vessels

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 →
TAISER cybersecurity training game lobby

Serious Games · Cybersecurity

TAISER: Cybersecurity Training Game

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.

Target angle recognition serious game

Serious Games · Naval Training

Serious Game for Target Angle Recognition

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 →
StarCraft II RTS micro co-evolution

Game AI · Evolutionary Computing

Co-evolving RTS Micro in StarCraft II

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 →
UAV mesh network topology visualization

Evolutionary Computing · Networks

Evolving Dynamically Reconfiguring UAV Mesh 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

Latest Papers See Google Scholar for the full list

2025
Evaluating Adaptive Training for Nautical Rules of the Road
A. Dutta & S.J. Louis · Lecture Notes in Computer Science, vol. 15812 (Springer) · ONR N00014-22-1-2122
Link →
2024
A Serious Game for Target Angle Recognition
K. DiArchangel & S.J. Louis · IEEE Conference on Games (CoG 2024), pp. 1–4
IEEE →
2022
VORRT-COLREGs: A Hybrid Velocity Obstacles and RRT Based COLREGs-Compliant Path Planner for Autonomous Surface Vessels
R. Dubey & S.J. Louis · IEEE Robotics and Automation Letters
IEEE →
2020
Evolving Dynamically Reconfiguring UAV-hosted Mesh Networks
R. Dubey, S.J. Louis, et al. · IEEE Congress on Evolutionary Computation (CEC 2020)
Scholar →
2019
Comparing Three Approaches to Micro in RTS Games
R. Dubey, S.J. Louis, A. Gajurel, S. Liu · IEEE CEC 2019, pp. 777–784
Scholar →
2018
Neuroevolution for RTS Micro
A. Gajurel, S.J. Louis, D. Mendez, S. Liu · IEEE Conference on Computational Intelligence and Games (CIG)
Scholar →
2016
Evolving Effective Micro Behaviors in Real-Time Strategy Games
S. Liu, S.J. Louis, C. Ballinger · IEEE Transactions on Computational Intelligence and AI in Games
IEEE →