ForesightSafety-VLA creates a diagnostic benchmark for VLA safety with taxonomy across physical, language, and visual risks, showing perception and structure variations cause more safety degradation than language changes in tested models.
Safe learning in robotics: From learning-based control to safe reinforcement learning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
A dual-pathway Neural-ESO uses a Lipschitz-bounded neural network for feedforward disturbance prediction and a conventional ESO for online correction, guaranteeing uniform ultimate boundedness of the closed-loop system.
CVaR-constrained TD3 policies for robot navigation show larger safety margins and higher post-training reachability verification rates than average-cost baselines across simulated scenarios and real-robot tests.
Energy-based regularization on residual dynamics learning improves neural MPC for aerial robots, cutting positional error 23% versus analytical models and boosting stability over unregularized neural MPC in real flights.
Goal-conditioned neural ODEs built from bi-Lipschitz diffeomorphisms deliver global exponential stability and safe-set invariance for all-pairs motion planning with explicit convergence bounds.
Integrates RL with a differentiable CVaR quadratic-program safety layer to jointly learn nominal controls, risk levels, and margins for adaptive safe navigation under motion uncertainty.
COOPO is a cyclic offline-online RL algorithm that repeatedly anchors the policy to a dataset via KL-regularized updates then fine-tunes online, claiming better sample efficiency and monotonic improvement under coverage assumptions.
citing papers explorer
-
ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
ForesightSafety-VLA creates a diagnostic benchmark for VLA safety with taxonomy across physical, language, and visual risks, showing perception and structure variations cause more safety degradation than language changes in tested models.
-
Neural-ESO: A Dual-Pathway Architecture for Provably Robust Learning-Based Control
A dual-pathway Neural-ESO uses a Lipschitz-bounded neural network for feedforward disturbance prediction and a conventional ESO for online correction, guaranteeing uniform ultimate boundedness of the closed-loop system.
-
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
CVaR-constrained TD3 policies for robot navigation show larger safety margins and higher post-training reachability verification rates than average-cost baselines across simulated scenarios and real-robot tests.
-
Energy-based Regularization for Learning Residual Dynamics in Neural MPC for Omnidirectional Aerial Robots
Energy-based regularization on residual dynamics learning improves neural MPC for aerial robots, cutting positional error 23% versus analytical models and boosting stability over unregularized neural MPC in real flights.
-
Goal-Conditioned Neural ODEs with Guaranteed Safety and Stability for Learning-Based All-Pairs Motion Planning
Goal-conditioned neural ODEs built from bi-Lipschitz diffeomorphisms deliver global exponential stability and safe-set invariance for all-pairs motion planning with explicit convergence bounds.
-
Reinforcement Learning for Risk Adaptation via Differentiable CVaR Barrier Functions
Integrates RL with a differentiable CVaR quadratic-program safety layer to jointly learn nominal controls, risk levels, and margins for adaptive safe navigation under motion uncertainty.
-
COOPO: Cyclic Offline-Online Policy Optimization Algorithm
COOPO is a cyclic offline-online RL algorithm that repeatedly anchors the policy to a dataset via KL-regularized updates then fine-tunes online, claiming better sample efficiency and monotonic improvement under coverage assumptions.