collaborators

8 papers

cs.LG2026

LDLT L-Lipschitz Network Weight Parameterization Initialization

Marius F. R. Juston, Ramavarapu S. Sreenivas, Dustin Nottage +1

We analyze initialization dynamics for LDLT-based -Lipschitz layers by deriving the exact marginal output variance when the underlying parameter matrix $W_0\in \mathbb…

cs.LG2025

LDLT -Lipschitz Network: Generalized Deep End-To-End Lipschitz Network Construction

Marius F. R. Juston, Ramavarapu S. Sreenivas, Dustin Nottage +1

Deep residual networks (ResNets) have demonstrated outstanding success in computer vision tasks, attributed to their ability to maintain gradient flow through deep architectures. S…

cs.LG2025

1-Lipschitz Network Initialization for Certifiably Robust Classification Applications: A Decay Problem

Marius F. R. Juston, Ramavarapu S. Sreenivas, William R. Norris +2

This paper discusses the weight parametrization of two standard 1-Lipschitz network architectures, the Almost-Orthogonal-Layers (AOL) and the SDP-based Lipschitz Layers (SLL). It e…

eess.SY2025

Safety Monitor for Off-Road Planning with Uncertainty Bounded Bekker Costs

Akshay Naik, Ramavarapu S. Sreenivas, William R. Norris +3

Reliable off-road autonomy requires operational constraints so that behavior stays predictable and safe when soil strength is uncertain. This paper presents a runtime assurance saf…

cs.RO2025

Hybrid Terrain-Aware Path Planning: Integrating VD-RRT* Exploration and VD-D* Lite Repair

Akshay Naik, William R. Norris, Dustin Nottage +1

Autonomous ground vehicles operating off-road must plan curvature-feasible paths while accounting for spatially varying soil strength and slope hazards in real time. We present a c…

cs.RO2025

In-Situ Soil-Property Estimation and Bayesian Mapping with a Simulated Compact Track Loader

W. Jacob Wagner, Ahmet Soylemezoglu, Katherine Driggs-Campbell

Existing earthmoving autonomy is largely confined to highly controlled and well-characterized environments due to the complexity of vehicle-terrain interaction dynamics and the par…