ShardNet enforces non-convex polyhedral safety constraints in neural controllers by construction via a differentiable projection layer, achieving 100% verified safety and over 3x larger safe sets than prior methods on double integrator benchmarks.
Lyapunov-stable neural-network control
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
A co-learning approach jointly optimizes a port-Hamiltonian system model and an energy-balancing passivity-based controller from data via alternating optimization with neural networks that embed structure for guaranteed passivity and stability.
CT-BaB integrates branch-and-bound during training to tighten certified Lyapunov bounds, yielding neural controllers with 164X larger verifiable ROA and 11X faster verification than CEGIS on a 2D quadrotor.
A reinforcement learning policy learns to adaptively harvest data samples, improving empirical constraint satisfaction and training efficiency for Lyapunov NNs and PINNs.
Tutorial introducing applications of the existing α,β-CROWN verifier to scalable formal verification of neural network controllers via bound computation and domain partitioning.
citing papers explorer
-
ShardNet: Training Neural Controllers with Hard, Non-Convex Constraints
ShardNet enforces non-convex polyhedral safety constraints in neural controllers by construction via a differentiable projection layer, achieving 100% verified safety and over 3x larger safe sets than prior methods on double integrator benchmarks.
-
Co-Learning Port-Hamiltonian Systems and Optimal Energy-Shaping Control
A co-learning approach jointly optimizes a port-Hamiltonian system model and an energy-balancing passivity-based controller from data via alternating optimization with neural networks that embed structure for guaranteed passivity and stability.
-
Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control
CT-BaB integrates branch-and-bound during training to tighten certified Lyapunov bounds, yielding neural controllers with 164X larger verifiable ROA and 11X faster verification than CEGIS on a 2D quadrotor.
-
Adaptive Data Harvesting for Efficient Neural Network Learning with Universal Constraints
A reinforcement learning policy learns to adaptively harvest data samples, improving empirical constraint satisfaction and training efficiency for Lyapunov NNs and PINNs.
-
Bridging Control with Neural Network Verifier alpha-beta-CROWN: A Tutorial
Tutorial introducing applications of the existing α,β-CROWN verifier to scalable formal verification of neural network controllers via bound computation and domain partitioning.