Search Results for author:
Found 5 papers, 4 papers with code
FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs
Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also admits robustness guarantees (e. g., the certificate holds under perturbations).
Safe Drone Flight with Time-Varying Backup Controllers
TBCs reduce conservatism when compared to traditional backup controllers and can be directly applied to multi-agent coordination to guarantee safety.
LyaNet: A Lyapunov Framework for Training Neural ODEs
Our approach, called LyaNet, is based on a novel Lyapunov loss formulation that encourages the inference dynamics to converge quickly to the correct prediction.
Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning
Decision trees are ubiquitous in machine learning for their ease of use and interpretability.
Differentiable MPC for End-to-end Planning and Control
We present foundations for using Model Predictive Control (MPC) as a differentiable policy class for reinforcement learning in continuous state and action spaces.
