ADAPtive agenT Architecture

The focus of the Phase 2 effort is to expand the Intelligent Machine Learning (IML) approach taken in Phase 1 to develop a Human-Centered Intelligent Virtual Agent (IVA). IML is an approach that moves the development of machine learning models away from engineers and puts the development of the model in the hands of the end-user. A Human-Centered IVA is focused on continuously improving the Machine Learning (ML) models while also providing effective communication between the human crewmembers and the IVA. Human-centered IVA is a perspective on artificial intelligence and ML that algorithms must be designed with awareness of being part of a larger system that includes end-users. This approach allows the IVA to incorporate the knowledge, insight, and feedback of the end-users allowing for tuning and refinement of the ML models. The Human-centered IVA will assist crewmembers in various tasks e.g., crew scheduling, procedure creation, and anomaly detection and resolution during a long-duration mission. ADAPTs Human-Centered IVA will provide the computationally heavy-lifting while still receiving inputs and insights from the crewmembers. This allows for the expansion of processes and information to a larger scale without compromising data integrity or mission success due to a lack of ground assistance. To provide crewmembers with a Human-Centered IVA this effort leverages the supervised learning algorithms Decision Tree, Random Forest, Ada Boost, Gradient Boost, Extreme Gradient Boost, Categorical Boost, and Associative Rule Models which were shown in Phase I to be succesful within an IML approach. Additionally, this phase will focus on providing an explainable interface that allows the end-user to query the IVA for the reason behind its prediction. This will be accomplished using an interactive visualization Graphical User Interface. After Phase II, we will have fully defined the ADAPT architecture which leverages interactive machine learning to create Human-centered Intelligent Virtual Agents (IVA), which are capable of supporting autonomous exploration operations. The design will have been derived from Astronaut input, providing an understanding of NASA operational concepts and crewmembers' needs when working with IVAs. The IVAs developed using the ADAPT architecture will demonstrate their ability to assist crewmembers in scheduling tasks for a multi-agent team that is comprised of crewmembers, robots, and virtual assistants. The IVAs will also support crewmembers with creating task procedures for novel scenarios in which a procedure is not available. Furthermore, to enhance their adoption, the IVA’s will provide an explainable interface for understanding their decision-making process. This is accomplished through the use of interactive visualizations that provide insight into what led the IVA to make a specific recommendation. The overarching objective of the Phase 2 effort is to expand the Intelligent Machine Learning (IML) approach taken in Phase 1 to develop a Human-Centered Intelligent Virtual Agent (IVA). A Human-Centered IVA is focused on continuously improving the Machine Learning (ML) models while also providing effective communication between the human crewmembers and the IVA. Human-centered IVA is a perspective on artificial intelligence and ML that algorithms must be designed with awareness of being part of a larger system that includes humans. This approach allows the IVA to incorporate the knowledge, insight, and feedback of the human allowing for tuning and refinement of the ML models. It also allows IVAs to assist crewmembers in various tasks e.g., crew scheduling, procedure creation, and anomaly detection and resolution throughout all phases of a long-duration mission. The technical objectives are: Objective 1: Improve Performance of the ADAPT Models Objective 2: Improve Interactive Capabilities. Objective 3: Develop ADAPT Architecture Objective 4: Prototype Development Objective 5: Demonstration Objective 6: Final Report Deliverables include a kickoff meeting within 30 days of contract start; quarterly progress reports; a comprehensive final report; software implementations; and a prototype demonstration of an IVA using ADAPT's Human-Centered AI design.
Benefits: We expect the Human-centered Intelligent Virtual Agents (IVA) approach to improving model predictions throughout all phases of a long-duration mission will be of interest to several groups within NASA. The ARTEMIS program for example could make use of IVAs to assist the crew in similar scenarios used during the development. Additionally, this work will be of interest to the EVA Exploration Office, the EVA Strategic Planning and Architecture group, and the Exploration Mission Planning Office. The proposed cognitive architecture will benefit several TRACLabs commercial customers. We expect the ability of end-users to direct the adaptation of the system will be of interest. For example, Baker Hughes has already expressed interest in licensing some of the new capabilities being developed in previous cognitive agent efforts, particularly the ontology and anomaly management aspects.