13 citations · 18 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
eess.SY2026
Interleaved Projected Gradient Descent for Safe Imitation Learning
Shengfan Cao, Francesco Borrelli
We propose an imitation-learning design for neural-network control policies under state and input constraints. Training alternates a standard imitation gradient step with a block o…
cs.RO2026
SHIELD: Scalable Optimal Control with Certification using Duality and Convexity
Hansung Kim, Siddharth H. Nair, Francesco Borrelli
We present SHIELD, a hierarchical algorithm that reduces both the decision-variable dimension and the constraint set in -regularized convex programs. From strong convexity…