RAYA integrates a learned recoverability margin inside an optimal controller with hard constraints and a learned scheduler that shifts task weights to enable recovery across quadrotor and autonomous vehicle platforms.
Safe control with learned certificates: A survey of neural lyapunov, barrier, and contraction methods for robotics and control
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
CA-HCBF creates a unified acceleration-level safety framework for mixed holonomic and nonholonomic robots and allocates avoidance duties proportionally to each robot's capability using a support-function metric and clipping.
LMI-Net enforces LMI constraints in neural networks by construction using a differentiable projection layer based on Douglas-Rachford splitting and implicit differentiation.
Develops sufficient conditions and sum-of-squares verification algorithms for union of control barrier functions under two switching strategies to ensure finite switches and forward invariance.
CAPE benchmark shows the proposed EPM learned dynamics model yields faster laps and lower errors than DPM and DDM across five controllers in both nominal and disturbance-aware simulations.
citing papers explorer
-
RAYA: Learning Where and When to Intervene for Robot Recovery
RAYA integrates a learned recoverability margin inside an optimal controller with hard constraints and a learned scheduler that shifts task weights to enable recovery across quadrotor and autonomous vehicle platforms.
-
Capability-Aware Heterogeneous Control Barrier Functions for Decentralized Multi-Robot Safe Navigation
CA-HCBF creates a unified acceleration-level safety framework for mixed holonomic and nonholonomic robots and allocates avoidance duties proportionally to each robot's capability using a support-function metric and clipping.
-
LMI-Net: Linear Matrix Inequality--Constrained Neural Networks via Differentiable Projection Layers
LMI-Net enforces LMI constraints in neural networks by construction using a differentiable projection layer based on Douglas-Rachford splitting and implicit differentiation.
-
Verification Framework for the Union of Control Barrier Functions
Develops sufficient conditions and sum-of-squares verification algorithms for union of control barrier functions under two switching strategies to ensure finite switches and forward invariance.
-
CAPE: Control Algorithm Performance Evaluation under Learned Vehicle Dynamics Models
CAPE benchmark shows the proposed EPM learned dynamics model yields faster laps and lower errors than DPM and DDM across five controllers in both nominal and disturbance-aware simulations.