4 papers
Verification of Visual Controllers via Compositional Geometric Transformations
Alexander Estornell, Leonard Jung, Michael Everett
Perception-based neural network controllers are increasingly used in autonomous systems that rely on visual inputs to operate in the real world. Ensuring the safety of such systems…
A Hybrid Framework for Efficient Koopman Operator Learning
Alexander Estornell, Leonard Jung, Alenna Spiro +2
Koopman analysis of a general dynamics system provides a linear Koopman operator and an embedded eigenfunction space, enabling the application of standard techniques from linear an…
Learning Verifiable Control Policies Using Relaxed Verification
Puja Chaudhury, Alexander Estornell, Michael Everett
To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy…
Contingency Constrained Planning with MPPI within MPPI
Leonard Jung, Alexander Estornell, Michael Everett
For safety, autonomous systems must be able to consider sudden changes and enact contingency plans appropriately. State-of-the-art methods currently find trajectories that balance…