Contextual Anomaly Management Interface (CAMI) for Autonomous System Supervision

Unmanned systems are taking on an increasing role in the U.S. military. Monitoring unmanned vehicles, sensors, and events in dynamic environments is an intense and demanding task. Today"s unmanned systems provide limited support for detecting problems and anomalies, and deliver alerts that are generally uninformative and lack context. Given their existing limitations and shortfalls, it is unlikely that today"s technologies and display metaphors will scale to accommodate the increased demands of multi-vehicle and mission management in the future. Building on research results and lessons learned, we propose a novel approach and interface (CAMI: Contextual Anomaly Management Interface) for anomaly management to support effective unmanned systems supervision. PSE has three key elements in place to ensure successful concept development and transition: (1) task and display requirements for anomaly management, (2) an established design process to translate requirements into design, and (3) an established and viable transition plan and customer. CAMI integrates notions from ongoing efforts with innovative concepts for supporting human supervision of automation and anomaly management in a way that respects and balances the strengths and limitations of both the human operator and the inherent capabilities of automation.