Formally Guaranteed Control Adaptation for ODD-Resilient Autonomous Systems
This addresses the problem of resilience in autonomous systems for safety-critical applications, but it appears incremental as it builds on existing probabilistic models and verification methods.
The paper tackles the challenge of ensuring reliable performance for autonomous systems outside their Operational Design Domain (ODD) by introducing an approach that adapts probabilistic system models to handle out-of-ODD scenarios with quantitative guarantees, effectively increasing system reliability under unforeseen situations.
Ensuring reliable performance in situations outside the Operational Design Domain (ODD) remains a primary challenge in devising resilient autonomous systems. We explore this challenge by introducing an approach for adapting probabilistic system models to handle out-of-ODD scenarios while, in parallel, providing quantitative guarantees. Our approach dynamically extends the coverage of existing system situation capabilities, supporting the verification and adaptation of the system's behaviour under unanticipated situations. Preliminary results demonstrate that our approach effectively increases system reliability by adapting its behaviour and providing formal guarantees even under unforeseen out-of-ODD situations.