The DIPART Project: A Status Report (1994)
| Venue: | In Proceedings of the Annual ARPI Meeting |
| Citations: | 4 - 3 self |
BibTeX
@INPROCEEDINGS{Pollack94thedipart,
author = {Martha E. Pollack and Taieb Znati and Eithan Ephrati and David Joslin and Sylvain Lauzac and Arthur Nunes and Nilufer Onder and Yagil and Sigalit Ur},
title = {The DIPART Project: A Status Report},
booktitle = {In Proceedings of the Annual ARPI Meeting},
year = {1994}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Current-generation AI planning technology lacks effective, flexible techniques for managing the planning process in the presence of changing information, and for coordinating multiple, distributed planning processes. However, these issues have been the focus of theoretical work in AI over roughly the past five years, and similar issues have been studied by researchers developing distributed and real-time operating systems. The DIPART project is aimed at adapting relevant techniques developed in operating systems research, and combining them with techniques from real-time and distributed AI, to support plan generation in dynamic, multi-agent environments. Towards this end, we are building DIPART---the Distributed, Interactive Planner's Assistant for Real-time Transportation planning---a prototype simulation system that includes a network of agents, each of which assists a human planner, and a simulated dynamic environment, which implements Reece and Tate's Pacifica NEO scenario [34]. In...
