arXiv AI
Aug 5
Shielding for Higher-Order Safety
arXiv:2608. 03662v1 Announce Type: new Abstract: Safety shields are runtime enforcement mechanisms that restrict the actions of a controller to guarantee safety.
Efficient Dynamic Shielding for Parametric Safety Specifications
The paper presents dynamic shields for AI-controlled autonomous systems, enabling runtime safety enforcement that adapts to changing safety specifications without recomputing from scratch. Unlike traditional static shields, these dynamic shields are pre-designed for a set of possible safety parameters and can quickly adjust as the true specification becomes known during operation. Experiments on robot navigation in unknown terrains show that dynamic shields require only a few minutes offline and a fraction of a second to a few seconds online, outperforming brute-force recomputation by up to five times.
Related stories
arXiv AI
Jun 2
Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Robotics
arXiv:2606. 02562v1 Announce Type: cross Abstract: Autonomous robots that interact with people must make safe and efficient decisions under human-induced uncertainty, such as their preferences, goals, competency, and willingness to cooperate.
arXiv AI
Jul 15
Real-Time Model Checking for Closed-Loop Robot Reactive Planning
arXiv:2508. 19186v2 Announce Type: replace-cross Abstract: Reactive obstacle avoidance methods often cause agents to become trapped in local minima, because they can often only reason one step ahead (i.
arXiv AI
Jun 12
Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks
arXiv:2606. 13621v1 Announce Type: new Abstract: Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions.
arXiv AI
Aug 25
Balancing Safety and Optimality in Robot Path Planning: Algorithm and Metric
The paper introduces the Unified Path Planner (UPP), a graph‑search algorithm that balances safety and optimality by adaptively weighting heuristics and using a local inverse‑distance safety field. UPP auto‑tunes its parameters during search, guaranteeing suboptimality bounds while improving obstacle clearance. Evaluation on ten simulated environments shows UPP achieving a 0.94 OptiSafe score—significantly higher than existing methods—while adding only 0.5–1% to path length and maintaining a 100% success rate, with hardware validation on a TurtleBot confirming practical benefits.
arXiv Machine Learning
Jul 7
CN-CBF: Composite Neural Control Barrier Function for Robot Navigation in Dynamic Environments
arXiv:2603. 06921v2 Announce Type: replace-cross Abstract: Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments.
arXiv AI
Jun 2
Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
arXiv:2606. 00090v1 Announce Type: cross Abstract: Physical AI systems increasingly map multimodal observations, language instructions, and learned world representations into physically consequential actions.
arXiv Machine Learning
Sep 24
LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials
The paper introduces LEAP-CBF, a safety filter that uses Least‑Effort Adversarial Potentials to quantify how much disturbance effort is needed to cause failure in nonlinear dynamical systems. LEAP serves as a control barrier function for the undisturbed system and can be combined with a robust safety filter that tolerates disturbances with bounded cumulative effort. The authors develop a deep reinforcement learning method to construct LEAPs and validate their effectiveness through simulations of multi‑agent systems and hardware experiments on a quadruped and quadrotors.
arXiv Machine Learning
Jun 9
Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models
arXiv:2606. 09749v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks.
Hugging Face Trending Papers
Jun 11
Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks
Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions. We argue this is the wrong product.
arXiv AI
Aug 26
Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning
arXiv:2511.02605v3 Announce Type: replace Abstract: Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specificat...
arXiv Machine Learning
Jun 25
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
arXiv:2606. 26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems.