Flexible Agent-based Communications for Exploration

Because close collaboration between the crew and mission control will not be practical for inter-planetary exploration, NASA envisions the need for an intelligent autonomous agent that can continually integrate data from the spacecraft or lunar/planetary base to advise the crew during their mission. TRACLabs has designed and prototyped such an agent called a cognitive architecture for space exploration (CASE) that incorporates a procedure development system known as PRIDE that allows for variably autonomous execution of both crew and robotic procedures, an automated planner that plans and re-plans the execution of procedures to achieve overall mission goals, an ontology data management system that makes system states available to all the components, a process manager to manage the use of distributed computing resources that support the CASE components, and a natural language dialog system to allow the crew access to any part of the architecture.However, past and current work in NASA space analogs, such as NEEMO and HERA has shown that the usefulness of any automation supporting human activity is only as good as its user interfaces and interaction. The agent must have a suite displays and interaction modes that can update the users’ situation awareness and recommend courses of action without undue cognitive load on the users, particularly the intra-vehicular activity user, or IVA. Therefore, this proposal seeks to investigate, design and test a canonical interaction protocol for CASE, called a flexible agent-based communication for exploration (FACE) that will include natural language dialog and active graphics, provide a consistent presentation of the current situation to the IVA, rapidly assess anomalous situations so as to focus the users’ attention on the key facts of the situation, recommend courses of action for correcting anomalous situations and provide for variable autonomy and user override of any autonomous operation.