collaborators

7 papers

cs.LO2026

Formally Guaranteed Control Adaptation for ODD-Resilient Autonomous Systems

Gricel Vázquez, Calum Imrie, Sepeedeh Shahbeigi +5

Ensuring reliable performance in situations outside the Operational Design Domain (ODD) remains a primary challenge in devising resilient autonomous systems. We explore this challe…

cs.LG2026

Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation

Daniel Bethell, Simos Gerasimou, Radu Calinescu +1

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance:…

cs.LG2025

Learning to Navigate Under Imperfect Perception: Conformalised Segmentation for Safe Reinforcement Learning

Daniel Bethell, Simos Gerasimou, Radu Calinescu +1

Reliable navigation in safety-critical environments requires both accurate hazard perception and principled uncertainty handling to strengthen downstream safety handling. Despite t…

cs.AI2025

Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding

Daniel Bethell, Simos Gerasimou, Radu Calinescu +1

Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios. When prior knowledg…

eess.SY2025

Conformal Safety Shielding for Imperfect-Perception Agents

William Scarbro, Calum Imrie, Sinem Getir Yaman +4

We consider the problem of safe control in discrete autonomous agents that use learned components for imperfect perception (or more generally, state estimation) from high-dimension…

cs.LG2025

Assuring the Safety of Reinforcement Learning Components: AMLAS-RL

Calum Corrie Imrie, Ioannis Stefanakos, Sepeedeh Shahbeigi +2

The rapid advancement of machine learning (ML) has led to its increasing integration into cyber-physical systems (CPS) across diverse domains. While CPS offer powerful capabilities…