A Dialogue-Based Approach to Mixed-Initiative Plan Management

• Main Authors: Allen, James F, Ferguson, George M, Schubert, Lenhart K
• Format: Report
• Language: English
• Subjects: COMMAND AND CONTROL SYSTEMS; Computer Programming and Software; DATA MINING; INFORMATION RETRIEVAL; MAN COMPUTER INTERFACE; MANAGEMENT INFORMATION SYSTEMS; MIXED INITIATIVE PLANNING; NATURAL LANGUAGE; PARSERS; PE62301E; PE63760E; PLANNING; SPEECH RECOGNITION; Voice Communications; WUAFRLC6428800

This research investigates ways to augment human plan reasoning capabilities in command and control tasks, such as logistics planning, crisis management and situation assessment. The goal was to avoid making the simplifying assumptions made in traditional research in planning that prevented effective human-computer collaborative planning. Specifically, no assumptions were made relative to goals being well specified in the beginning, or that the evaluation criteria can be precisely defined in a quantitative manner. The groundwork was laid for research in mixed-initiative planning through development of TRIPS (The Rochester Interactive Planning System), a robust speech-driven mixed initiative planning system, which has been installed at Global Infotech in Washington DC for the Command Post of the Future (CPOF) jumpstart demonstration as well as at the Air Force Research Lab in Rome, New York. TRIPS runs stand-alone without Rochester researchers present. New Theoretical techniques for speeding up well-founded domain-independent planners were also developed. In addition, simulation and data mining techniques to find improvements to large-scale plans that could not be reasoned about using traditional techniques were developed and demonstrated.