Imagen de Portada

Conformal Safety Shielding for Imperfect-Perception Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Scarbro, William, Imrie, Calum, Yaman, Sinem Getir, Fatehi, Kavan, Pasareanu, Corina S., Calinescu, Radu, Mangal, Ravi
Formato:	Preprint
Publicado:	2025
Materias:	Systems and Control Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Interval POMDP Shielding for Imperfect-Perception Agents
por: Scarbro, William, et al.
Publicado: (2026)

Interpretable Attention-Based Multi-Agent PPO for Latency Spike Resolution in 6G RAN Slicing
por: Fatehi, Kavan, et al.
Publicado: (2026)

Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding
por: Bethell, Daniel, et al.
Publicado: (2024)

Tool for Supporting Debugging and Understanding of Normative Requirements Using LLMs
por: Kleijwegt, Alex, et al.
Publicado: (2025)

Learning to Navigate Under Imperfect Perception: Conformalised Segmentation for Safe Reinforcement Learning
por: Bethell, Daniel, et al.
Publicado: (2025)

Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
por: Canizales, Ronaldo, et al.
Publicado: (2026)

Safety Controller Synthesis for Collaborative Robots
por: Gleirscher, Mario, et al.
Publicado: (2020)

Control Analysis and Design for Autonomous Vehicles Subject to Imperfect AI-Based Perception
por: Yan, Tao, et al.
Publicado: (2025)

A Mixture of Linear Corrections Generates Secure Code
por: Yu, Weichen, et al.
Publicado: (2025)

Safe and Efficient CAV Lane Changing using Decentralised Safety Shields
por: Hegde, Bharathkumar, et al.
Publicado: (2025)

A Collaborative Safety Shield for Safe and Efficient CAV Lane Changes in Congested On-Ramp Merging
por: Hegde, Bharathkumar, et al.
Publicado: (2026)

Predictive Safety Shield for Dyna-Q Reinforcement Learning
por: Pin, Jin, et al.
Publicado: (2025)

Differentiable Optimization Layered Safety-Critical Control for Risk-Aware Navigation via Conformal Prediction
por: Dong, Jinyang, et al.
Publicado: (2026)

GANs for EVT Based Model Parameter Estimation in Real-time Ultra-Reliable Communication
por: Valiahdi, Parmida, et al.
Publicado: (2024)

Diffusion Model Based Resource Allocation Strategy in Ultra-Reliable Wireless Networked Control Systems
por: Darabi, Amirhassan Babazadeh, et al.
Publicado: (2024)

Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators
por: Badithela, Apurva, et al.
Publicado: (2025)

Secure Hierarchical Federated Learning in Vehicular Networks Using Dynamic Client Selection and Anomaly Detection
por: HaghighiFard, M. Saeid, et al.
Publicado: (2024)

Statistically Assuring Safety of Control Systems using Ensembles of Safety Filters and Conformal Prediction
por: Tabbara, Ihab, et al.
Publicado: (2025)

Verification and External Parameter Inference for Stochastic World Models
por: Calinescu, Radu, et al.
Publicado: (2025)

Efficient Dynamic Shielding for Parametric Safety Specifications
por: Corsi, Davide, et al.
Publicado: (2025)

Safe Adaptive Cruise Control Under Perception Uncertainty: A Deep Ensemble and Conformal Tube Model Predictive Control Approach
por: Li, Xiao, et al.
Publicado: (2024)

Fighting AI with AI: Leveraging Foundation Models for Assuring AI-Enabled Safety-Critical Systems
por: Mavridou, Anastasia, et al.
Publicado: (2025)

EVT-Based Generative AI for Tail-Aware Channel Estimation
por: Valiahdi, Parmida, et al.
Publicado: (2026)

Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation
por: Bethell, Daniel, et al.
Publicado: (2025)

$α^3$-Bench: A Unified Benchmark of Safety, Robustness, and Efficiency for LLM-Based UAV Agents over 6G Networks
por: Ferrag, Mohamed Amine, et al.
Publicado: (2026)

Safety Certification is Classification
por: Schön, Oliver, et al.
Publicado: (2026)

From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration
por: Wen, Shuide, et al.
Publicado: (2025)

Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)
por: Hu, Boyue Caroline, et al.
Publicado: (2025)

Approximate Model-Based Shielding for Safe Reinforcement Learning
por: Goodall, Alexander W., et al.
Publicado: (2023)

Maintaining driver attentiveness in shared-control autonomous driving
por: Calinescu, Radu, et al.
Publicado: (2021)

DualShield: Safe Model Predictive Diffusion via Reachability Analysis for Interactive Autonomous Driving
por: Yang, Rui, et al.
Publicado: (2026)

PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation
por: Cao, Haofan, et al.
Publicado: (2026)

Point-Based Value Iteration for POMDPs with Neural Perception Mechanisms
por: Yan, Rui, et al.
Publicado: (2023)

Towards Deductive Verification of Control Algorithms for Autonomous Marine Vehicles
por: Foster, Simon, et al.
Publicado: (2020)

BarrierBench: Evaluating Large Language Models for Safety Verification in Dynamical Systems
por: Taheri, Ali, et al.
Publicado: (2025)

The Use of the Simplex Architecture to Enhance Safety in Deep-Learning-Powered Autonomous Systems
por: Nesti, Federico, et al.
Publicado: (2025)

Safety-Critical Contextual Control via Online Riemannian Optimization with World Models
por: Li, Tongxin
Publicado: (2026)

Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems
por: Kranzlmüller, Miriam, et al.
Publicado: (2026)

Safety-Aware Reinforcement Learning for Electric Vehicle Charging Station Management in Distribution Network
por: Fan, Jiarong, et al.
Publicado: (2024)

Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair
por: Puranic, Aniruddh G., et al.
Publicado: (2026)