CMU Robotics Institute
Summer Scholar
2024
Ethan Villalovoz
Sacramento, California, United States
I work on robot learning at Georgia Tech and multi-agent systems at Microsoft. I'm interested in how robots learn from imperfect human feedback, reason under uncertainty, and align their behavior with human intent.
You can reach me at .
Previously
Selected work
ScenarioLens (2026)
An autonomy-evaluation tool for ranking and inspecting long-tail driving scenarios with interpretable risk and baseline-failure metrics.
BODE-GEN (arXiv 2025)
Bayesian prompt optimization for test-driven code generation, evaluated across 164 HumanEval+ tasks and three code models.
Social Triangles (IROS 2023)
How multi-robot formation geometry shapes human navigation and approach behavior.