Intelligent, Collaborative Management of Autonomous Vehicle Anomalies

This project will advance the state of art in two areas necessary for effective exploitation of intelligent diagnosis, planning, and execution technologies within autonomous vehicles. First, it will create and demonstrate the effectiveness of a software framework that specifies how these automation technologies can work together. Second, it will create an intelligent collaborative anomaly management system that enables operators and vehicles to work together as a team, so the benefits of automation can be enjoyed while minimizing the errors that might otherwise result from automation biases. During this Phase 1 project, we will develop a concept of operations and a high-level user interface design; design scenarios describing situations and events that benefit from collaborative anomaly management for autonomous vehicles; design a software framework that specifies the capabilities, algorithms, knowledge requirements, and interfaces of each software module; develop a limited software prototype that illustrates key elements of our approach, and specify metrics for evaluating the utility and efficiency of collaborative anomaly management.