Detecting and Mitigating System-Level Anomalies of Vision-Based Controllers

arXiv:2309.13475v3 Announce Type: replace-cross
Abstract: Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these vision-based controllers can make erroneous predictions when faced with novel or out-of-distribution inputs. Such errors can cascade to catastrophic system failures and compromise system safety. In this work, we introduce a run-time anomaly monitor to detect and mitigate such closed-loop, system-level failures. Specifically, we …

abstract arxiv autonomous autonomous systems cars control cs.cv cs.lg cs.ro cs.sy decision distribution driving drones eess.sy errors inputs machine machine learning making novel performance predictions self-driving systems type vision visual