Probabilistic Safety

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 48

All topics

Finite-Data Safety Informativity Under Dynamic Asymmetric Actuation
Oct 1, 2026Abhinav Sinha, Praveen Kumar Ranjan, Yongcan CaoProbabilistic Safety Finite-Sample Certificates
GALACxIS Lab, Department of Aerospace Engineering, University of Cincinnati, Cincinnati, OH 45221, USA · Unmanned Systems Lab (USL), Department of Electrical Engineering, The University of Texas at San Antonio, TX 78249, USA
A Reachability-based Safety Certificate for Dynamical System Motion Policies
Sep 29, 2026Aditya Vats, Tianyi Xia, Nadia FigueroaProbabilistic Safety Control Barrier Functions
The authors are with the University of Pennsylvania, Philadelphia, PA, USA.
Safe-by-Design Learning via Energy-based Neural Networks
Sep 29, 2026Simone Betteti, Morteza Lahijanian, Luca LaurentiProbabilistic Safety Learning-Based Control
RIAS Lab The Italian Institute of Artificial Intelligence for Industry Torino, 10129, ITA · RECUV University of Colorado Boulder Boulder, CO 80303, USA · Delft Center for Systems and Control, TU Delft, Delft, 2600 AA, The Netherlands
Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination
Sep 23, 2026Yihong Zhou, Hanbin Yang, Thomas MorstynProbabilistic Safety Artificial Intelligence Safety
Department of Engineering Science, University of Oxford, U.K.
MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs
Sep 16, 2026Albert Wu, Nicholas Roberts, Tzu-Heng Huang +5Probabilistic Safety Model-Based Multi-Agent Systems
University of Wisconsin-Madison · Princeton University
Conformal Policy Learning with Distribution-Free Safety Guarantees
Sep 15, 2026Ying Jin, Naoki EgamiLearning Policy Probabilistic Safety
Department of Statistics and Data Science, University of Pennsylvania · Department of Political Science & Statistics and Data Science Center, Massachusetts Institute of Technology
When Information is Worth the Risk: Behavioral Valuation for Hazardous Robotic Exploration
Sep 11, 2026Alkesh K. Srivastava, Aamodh Suresh, Carlos Nieto-Granda +1Risk Exploration
Department of Mechanical Engineering, Temple University, Philadelphia, PA 19122, USA · U.S. DEVCOM Army Research Laboratory, Adelphi, MD 20783, USA · Lobster Robotics, The Hague, South Holland, Netherlands
SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
Aug 4, 2026Mayur Akewar, Ravi RanjanProbabilistic Safety Safer
Florida International University
Risk-Aware Motion Planning with Learned Trajectory Primitives and Probabilistic Safety Assessment
Jul 29, 2026Marc Kaufeld, Dian Zhuang, Johannes BetzMotion Planning Path Planning
Professorship of Autonomous Vehicle Systems, Technical University of Munich, 85748 Garching, Germany; Munich Institute of Robotics and Machine Intelligence (MIRMI) · School of Engineering and Design, Technical University of Munich, 85748 Garching, Germany
Sound Probabilistic Safety Bounds for Large Language Models
Jul 22, 2026Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani +1Large Language Model Safety Probabilistic Safety
Department of Computer Science, University of Oxford, UK · Max Planck Institute for Software Systems, Germany · School of Computer Science, University of Birmingham, UK
Formal Foundations for Known Good Reliable Die Screening in Chiplet-Based AI Systems-on-Chip
Jul 22, 2026Prashanthi Metku, Chandra GanduSemiconductor Manufacturing Probabilistic Safety
Qualcomm Technologies, Inc., USA
Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RL
Jul 18, 2026Zhaohui WangModel-Based Reinforcement Learning Probabilistic Safety
Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA.
SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction
Jul 17, 2026Xue Yu, Bo Yuan, Kailin Zhao +3Graphical User Interface Agents Probabilistic Safety
JIUTIAN Research
SMC-ES: Automated synthesis of formally verified control policies
Jul 16, 2026Riccardo Curcio, Toni Mancini, Enrico TronciProbabilistic Safety Cyber-Physical System
Department of Computer Science, Sapienza University of Rome, via Salaria 113, 00198 Rome, Italy
Detecting Ladder Logic Bombs in IEC 61131-3 PLC Programs using ESBMC-PLC+: A Formal Verification Approach with Trigger Synthesis
Jul 9, 2026Pierre Dantas, Lucas Cordeiro, Waldir JuniorFormal Verification Ladder
Electrical Engineering Federal University of Amazonas (UFAM) Manaus, AM, Brazil
HJ-SafeDMP: Hamilton-Jacobi Reachability-Guided Dynamic Movement Primitives for Provably Safe Robot Motion
Jun 27, 2026Siddhanth Ramesh, Ravi PrakashHamilton-Jacobi Reachability Probabilistic Safety
Cyber-Physical Systems, Indian Institute of Science (IISc), Bengaluru.
Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems
Jun 26, 2026Jose Pascual Gumbau MezquitaArtificial Intelligence Safety Probabilistic Safety
University Jaume I de Castell´o, Spain
Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion
Jun 23, 2026Sahil KadadekarSpeculative Decoding Large Language Model Safety
Independent Researcher
Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications
Jun 22, 2026Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris +1Neural Network Verification Certification
Foundation for Reasearch and Technology - Hellas, Heraklion, Greece · University of Crete, Heraklion, Greece · Catalan Institution for Research and Advanced Studies, Barcelona, Spain +1
Verifiable Foundation Models for Robot Safety
Jun 22, 2026Davide Corsi, Kyungmin Kim, Roy FoxProbabilistic Safety Scalable Robot Learning
University of California, Irvine
Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation
Jun 17, 2026Ahmad Farooq, Kamran IqbalMulti-Agent Reinforcement Learning Probabilistic Safety
Department of Electrical and Computer Engineering, University of Arkansas at Little Rock, Little Rock, AR 72204 USA
pdSTL: Probabilistic Differentiable Signal Temporal Logic for Stochastic Systems
Jun 17, 2026Bennett Dogbey, Hemanth ManjunathaSignal Temporal Logic Probabilistic Safety
Dept. of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK USA
TNODEV: Toolbox for Neural ODE Verification
Jun 15, 2026Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Mohamed GhazelNeural Network Verification Neural Ordinary Differential Equations
Univ Gustave Eiffel, COSYS-ESTAS, F-59657 Villeneuve d’Ascq, France
Shielded Analysis: Certification and Characterization of Defensibility in Systems under Adversarial Interaction
Jun 11, 2026Achraf Hsain, Sultan AlmuhammadiLLM Defense Mechanisms Probabilistic Safety
Information and Computer Science Department King Fahd University of Petroleum and Minerals Dhahran, Saudi Arabia
Distribution-Free Risk-Aware Planning and Control Under Uncertainty Using Conformal Spectral Risk Control
Jun 2, 2026Junsik Eom, Tulga ErsalModel Predictive Control Conformal Risk Control
Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI 48109
Chance-Constrained MPPI under State and Dynamic Object Prediction Uncertainty and the Evaluation of Collision Risk Calibration
May 27, 2026Benjamin Serfling, Konrad Doll, Kati Radkhah-LensModel Predictive Path Integral Collision Prediction
University of Applied Sciences Aschaffenburg, Aschaffenburg, Germany
Provably Safe Motion Planning Under Unknown Disturbances
May 26, 2026Ibon Gracia, Qi Heng Ho, Luca Laurenti +1Probabilistic Safety Planning
Department of Aerospace Engineering Sciences at the University of Colorado Boulder, CO, USA · Department of Aerospace and Ocean Engineering, Virginia Tech, VA, USA · Delft University of Technology, the Netherlands, and the Italian Institute of Artificial Intelligence, Italy
A Subjective Logic-based method for runtime confidence updates in safety arguments
May 21, 2026Benjamin Herd, Jessica Kelly, Clarissa Heinemann +1Probabilistic Safety Safety Claims
Fraunhofer Institute for Cognitive Systems (IKS) Munich, Germany
Kernel-Based Safe Exploration in Deep Reinforcement Learning
May 21, 2026Rupak Majumdar, Nikhil Singh, Sadegh SoudjaniProbabilistic Safety Barriers
Max Planck Institute for Software Systems, Germany
Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning
May 14, 2026Debraj Chakraborty, Anirban Majumdar, Prince Mathew +2Partially Observable Markov Decision Process Markov Decision Processes
Nanyang Technological University, Singapore · Tata Institute of Fundamental Research, Mumbai, India · Université Libre de Bruxelles, Brussels, Belgium +1
Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach
May 13, 2026Daniel M. Cherenson, Haejoon Lee, Taekyung Kim +1Probabilistic Safety Safety Filters
Department of Robotics, University of Michigan, Ann Arbor, MI, USA
Shields to Guarantee Probabilistic Safety in MDPs
May 11, 2026Linus Heck, Filip Macák, Roman Andriushchenko +2Probabilistic Safety Kernel-Resident Tool Governance Gateway
Radboud University, Nijmegen, the Netherlands · Brno University of Technology, Czechia
GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic
May 11, 2026Tianyuan Zhang, Peng Yue, Zihao Peng +8Autonomous Driving Probabilistic Safety
Beihang University · Zhongguancun Laboratory · Peking University
Robust Probabilistic Shielding for Safe Offline Reinforcement Learning
May 11, 2026Maris F. L. Galesloot, Thomas Rhemrev, Nils JansenOffline Reinforcement Learning Probabilistic Safety
Radboud University · Nijmegen, The Netherlands · Ruhr University & Radboud University +1
Containment Verification: AI Safety Guarantees Independent of Alignment
May 9, 2026Royce Moon, Lav R. VarshneyArtificial Intelligence Safety Agentic Framework
Enclave Intelligence · AI Innovation Institute, Stony Brook University
Safety Certification is Classification
May 7, 2026Oliver Schön, Licio Romao, Sadegh SoudjaniProbabilistic Safety Certification
ETH Zürich · Zürich, Switzerland · Technical University of Denmark +3
Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents
Apr 27, 2026German Marin, Jatin ChaudharyProbabilistic Safety Governance
Department of Computing, University of Turku, Turku, Finland
Information-Geometric First-Passage Monitoring of Distributional Stability in Stochastic Systems
Apr 27, 2026Hikmat Karimov, Rahid Zahid AlekberliArtificial Intelligence Safety Probabilistic Safety
Institute of Defense Technologies and Cybersecurity„ Azerbaijan Technical University, Azerbaijan
Cooptimizing Safety and Performance Using Safety Value-Constrained Model Predictive Control
Apr 26, 2026Hao Wang, Nam Nguyen, Armand Jordana +2Model Predictive Control Safety Constraints
Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California · Department of Aeronautics and Astronautics, Stanford University · Electrical and Computer Engineering Department, New York University
Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture
Apr 26, 2026Rong XiangArtificial Intelligence Alignment Authorization
Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation
Apr 23, 2026Jingyang Li, Xin Chen, Hongfei Fu +1Neural Network Verification Probabilistic Safety
Shanghai Jiao Tong University, Shanghai 200240, China · University of New Mexico, Albuquerque, NM 87106, USA
Interval POMDP Shielding for Imperfect-Perception Agents
Apr 22, 2026William Scarbro, Ravi MangalProbabilistic Safety Partially Observable Markov Decision Process
Department of Computer Science Colorado State University Fort Collins, USA
Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives
Apr 18, 2026Daeyeon SonKernel-Resident Tool Governance Gateway Model Context Protocol
Independent Researcher · Republic of Korea
CBCL: Safe Self-Extending Agent Communication
Apr 16, 2026Hugo O'ConnorMultilingual Agents Probabilistic Safety
Anuna Research
Algorithms for Deciding the Safety of States in Fully Observable Non-deterministic Problems: Technical Report
Mar 16, 2026Johannes Schmalz, Chaahat JainProbabilistic Safety Worst-Case
Saarland University, Germany
PB-OEL: A Performance-Bounded Online Ensemble Learning Framework With Mixed Feedback for Real-Time Safety Assessment
Mar 19, 2025Songqiao Hu, Zeyi Liu, Lufeng Hao +2Probabilistic Safety Safety-Critical Scenarios
Department of Automation, and the Institute for Embodied Intelligence and Robotics, Tsinghua University, Beijing 100084, China · China Ship Research and Development Academy, Beijing 100192, China
Real-Time Safety Evaluation of Human Arm Operations Using a Wrist-Mounted IMU with PSM System
Feb 13, 2025Musab Zubair Inamdar, Alhusain Al Hadrami, Seyed Amir TafrishiHuman-Robot Collaboration Wrist
Geometric Mechanics and Mechatronics in Robotics (gm2R) Lab, School of Engineering, Cardiff University, Cardiff CF24 3AA, United Kingdom
Training Verifiably Robust Agents Using Set-Based Reinforcement Learning
Aug 17, 2024Manuel Wendl, Lukas Koller, Tobias Ladner +1Reinforcement Learning With Verifiable Reward Adversarial Training
Technical University of Munich, Germany

Oct 1, 2026, eess.SYJ/K move · Enter open · S save

Finite-Data Safety Informativity Under Dynamic Asymmetric Actuation

Abhinav Sinha, Praveen Kumar Ranjan, Yongcan Cao

GALACxIS Lab, Department of Aerospace Engineering, University of Cincinnati, Cincinnati, OH 45221, USA · Unmanned Systems Lab (USL), Department of Electrical Engineering, The University of Texas at San Antonio, TX 78249, USA

Probabilistic Safety Finite-Sample Certificates Robust Control Actuator Upper Bounds Continuation

Open paper AskPDF arXiv

When the system model is not fully known, measurement error and limited excitation can leave several models consistent with the same finite data. A command judged safe for one model may fail for another, while limited control authority can prevent the corrective action needed to preserve safety. To ensure safety under model uncertainty and asymmetric input limits, we develop a finite-data certificate that determines whether a command can enforce a prescribed safety inequality. For a linearly parameterized safety channel with exactly known regressors and bounded aggregate residual error, we derive a support formula for the worst-case safety contribution of all data-consistent models. The formula identifies the regressor directions that admit a finite bound, allowing rank-deficient records to contribute to safety certification. Using certified componentwise bounds on actuator tracking error yields an affine inequality with a necessary and sufficient test for pointwise command feasibility. The affine inequality reduces computation of the closest certified command to a scalar root-finding problem. It also yields a closed-form gate that selects the largest certified fraction of a prescribed command segment. The proposed certificate guarantees output safety within its operating domain, provided the feedback is locally Lipschitz and the uncertainty bounds remain valid. Domain retention and full-state continuation extend this guarantee to all time. A vehicle study demonstrates that output safety can be certified from finite measurements in a safety-critical setting with model and actuator uncertainty.

Momentum

Related topics

Latest papers 48