Tasks at higher levels of the information fusion framework [e.g. the FPMFWG (Fusion Process Models and Frameworks Working Group)], such as predicting threat behavior, require reasoning about complex situations in which entities of different types are related to each other in diverse ways. This is particularly true in asymmetric warfare where the threats are elusive, secretive, and decentralized entities that often appear unconnected and exhibit stealthy behaviour that is very difficult to predict. Automated methods for reasoning about such complex situations require expressive languages that can represent and reason with uncertainty. Recent years have seen rapid advances in the expressive languages that support systems in providing the ability to represent and reason about complex situations with uncertainty.
As these technologies have become more mature, interest grew in many disciplines in which uncertainty plays a major role. Starting in the eighties in the field of artificial intelligence (AI), discussion of the suitability of each technique to address the diverse aspects in each potential application fuelled various initiatives to promote clarification on the issue. Although there is no shortage of comparisons between major approaches for representing and reasoning with uncertainty, from the standpoint of the HLIF community there are enough questions left unanswered to make it difficult for a researcher or practitioner to choose an approach best suited to his/her problem. This situation not only causes a waste of resources in various steps of the research and development processes but also fosters misconceptions that can jeopardize the advancement of the community as a whole.
A credible, unbiased framework is needed for evaluation of uncertainty management methods in information fusion. The framework must span all levels of the JDL fusion hierarchy, and must be applicable to a broad range of application areas for fusion technology. It must support fully automated as well as human-in-the-loop systems; and distributed as well as stand-alone systems. The framework must leverage the existing body of research on technologies for uncertainty representation and reasoning to produce a comprehensive, unbiased evaluation framework. A successful outcome of the ETUR WG will not only provide important insights into uncertainty management for HLIF, but will also produce a valuable tool for the community to support future comparisons.
Therefore, in order to achieve its goals, the ETUR WG will foster discussions and deliberations with the following outcomes:
- Perform an in-depth analysis of the major requirements for representing and reasoning with uncertainty from the HLIF perspective;
- Develop a set of use cases with enough complexity to cover the identified requirements;
- Define a comprehensive set of criteria to evaluate how well a given methodology addresses the representational and reasoning needs of each use case; and
- Conduct an evaluation of major uncertainty management approaches that could be used to address the use cases.
A key methodological component of this process is the design of use cases that exemplify complex situations involving difficult aspects of uncertainty representation and reasoning, especially those that any HLIF system must be capable of handling. The use cases must be derived from, and support identification of, requirements that any HLIF system ought to address. The evaluation plan must also include development of metrics to evaluate performance of the uncertainty management methods on the use case scenarios. In the schedule proposed below, the WG will follow a spiral systems engineering process to achieve its goals. Each cycle of the spiral will include all four of the above steps, which should increase in detail and complexity as the group leverages the lessons learned from previous cycles.