Collaborative World Modeling
Abstract
The current state of the art in world modeling involves such manual effort that it is infeasible to build large models fast enough to enhance short-term decision making about issues of national and global security. We propose an effort to automate large parts of the building and running of such models, enabling an order of magnitude reduction in development time and a significant increase in the scale of problems that can be explored. The key insight is that developing large-scale world models requires a collaboration between human analysts (providing intuition, strategic thinking and thinking out of the box) and automated intelligent systems (providing large scale data search and analysis, planning and running simulations). Model development is iterative, with extensive interaction between the analyst and the system throughout. The key components of our solution are: 1) an intuitive interface for iterative model development and evaluation, using a language-driven Collaborative Problem Solving process between users and World Modeling Systems; 2) automatic and human-assisted transformation of qualitative models to executable quantitative models by means of collaborative planning; 3) capabilities for users to define novel problems, bootstrapping from a domain-independent ontology; 4) a system that learns and improves as it interacts with its users.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Feb 14, 2019
- Source ID
- W911NF1810464
Entities
People
- James F. Allen
Organizations
- Army Contracting Command
- Defense Advanced Research Projects Agency
- Florida Institute for Human and Machine Cognition