Welcome to the Center for Autonomy
The Center for Autonomy brings together several research groups that address fundamental challenges in developing autonomous systems through contributions in controls, machine learning, game theory, information theory, and formal methods. Its primary objective is to create a unified front in attracting the best researchers to UT Austin and empowering them to solve the pressing problems toward developing autonomous systems that can make a net positive impact.
Upcoming Events
News
Research Projects
Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
Researchers introduce Simulation Distillation (SimDist), a new framework for real-world robot adaptation based on world models. SimDist uses planning and lightweight dynamics adaptation instead of direct policy finetuning to improve sim-to-real policies that fail after deployment.
Neural Solvers for Hamilton-Jacobi Equations
By aligning neural network training objectives with the theoretical requirements of Hamilton–Jacobi equations, the approach offers a path toward stable and accurate computation in settings where classical methods alone become prohibitively expensive.
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
MEMO introduces a self-play framework that stabilizes and improves LLM evaluation in multi-agent settings by using persistent memory and prompt exploration to reduce variance and produce more reliable performance outcomes.
Outreach Events
Center for Autonomy Strengthens Outreach Initiatives
Robotics, AI and Programming: The Center for Autonomy Summer Research Internship Programs
Local High School Students Gain Hands-On Experience Through Robotics Tour
Learning Together: Del Valle Juniors and Seniors Visit UT
