Dominance functions from a small number of trajectories serve as dissipative and expressive building blocks for formal safety certificates in monotone discrete-time systems.
hub
Control barrier functions: Theory and ap- plications
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SafeDojo is a new world model-based safe RL framework for VLA that outperforms baselines on SafeLIBERO and real robot tasks.
Internal attention heads in VLA policies localize targets for a CBF safety filter that enables real-time collision avoidance with dynamic obstacles and outperforms init-time oracle identification by 43% on average.
A post-hoc predictive safety filter adjusts RL policy contact locations for quadruped robots via sampling-based optimization on a full-physics model, reducing safety violations in cluttered environments with minimal performance deviation.
A scalable verification framework for neural control barrier functions uses linear bound propagation on network gradients combined with McCormick relaxations to certify safety conditions for control-affine systems.
Case study verifying a neural network drug-dosing controller for infinite-horizon safety using Rocq and the Vehicle theorem prover.
MARCH combines simplified-model trajectory generation with CLF-guided teacher RL and vision-policy distillation to enable stable humanoid locomotion over sparse terrain with better sample efficiency than pure model-free methods.
Robot middleware is the harness for Physical AI and should implement Projection, Isolation, and Transfer to enforce AI model outputs across control, computation, and communication.
ConstrainedMimic integrates operational space control and control barrier functions into RL tracking policies to enforce arbitrary runtime constraints on humanoid kinematics and dynamics while preserving contact modes and tracking goals.
A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.
A filter line search SQP algorithm reduces iterations and computation time for nonconvex SOS programs compared to prior methods.
A literature review that defines silent physical-action failures in Physical AI and identifies the lack of complete runtime authorization boundaries across surveyed technical streams.
Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention of invalid actions in interventions.
Replicates SPARK humanoid safety filters and stress-tests them under crowding, noise, and delays, showing trade-offs in goal tracking versus collision reduction.
citing papers explorer
-
Trajectory-based Safety of Monotone Systems: Verification and Control Synthesis
Dominance functions from a small number of trajectories serve as dissipative and expressive building blocks for formal safety certificates in monotone discrete-time systems.
-
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
SafeDojo is a new world model-based safe RL framework for VLA that outperforms baselines on SafeLIBERO and real robot tasks.
-
Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models
Internal attention heads in VLA policies localize targets for a CBF safety filter that enables real-time collision avoidance with dynamic obstacles and outperforms init-time oracle identification by 43% on average.
-
Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering
A post-hoc predictive safety filter adjusts RL policy contact locations for quadruped robots via sampling-based optimization on a full-physics model, reducing safety violations in cluttered environments with minimal performance deviation.
-
Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
A scalable verification framework for neural control barrier functions uses linear bound propagation on network gradients combined with McCormick relaxations to certify safety conditions for control-affine systems.
-
Vancomycert: A Certified Neuro-Symbolic Drug Delivery System (Case Study)
Case study verifying a neural network drug-dosing controller for infinite-horizon safety using Rocq and the Vehicle theorem prover.
-
MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds
MARCH combines simplified-model trajectory generation with CLF-guided teacher RL and vision-policy distillation to enable stable humanoid locomotion over sparse terrain with better sample efficiency than pure model-free methods.
-
Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer
Robot middleware is the harness for Physical AI and should implement Projection, Isolation, and Transfer to enforce AI model outputs across control, computation, and communication.
-
Constrained Whole-Body Tracking for Humanoid Robots
ConstrainedMimic integrates operational space control and control barrier functions into RL tracking policies to enforce arbitrary runtime constraints on humanoid kinematics and dynamics while preserving contact modes and tracking goals.
-
Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study
A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.
-
On the Practical Implementation of a Sequential Quadratic Programming Algorithm for Nonconvex Sum-of-squares Problems
A filter line search SQP algorithm reduces iterations and computation time for nonconvex SOS programs compared to prior methods.
-
Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
A literature review that defines silent physical-action failures in Physical AI and identifies the lack of complete runtime authorization boundaries across surveyed technical streams.
-
Can Predicted Dynamics Exist in the Physical World?
Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention of invalid actions in interventions.
-
Adversarial Stress Testing of SPARK Humanoid Safety Filters
Replicates SPARK humanoid safety filters and stress-tests them under crowding, noise, and delays, showing trade-offs in goal tracking versus collision reduction.