The Peaks and Valleys of ALPS: An Adaptive Learning and Planning System for Transportation Scheduling

Randall J. Calistri-Yeh, Odyssey Research Associates, Alberto Maria Segre, University of Iowa, and David Sturgill, Cornell University

The ALPS (Adaptive Learning and Planning System) project is a three-year effort to design and prototype a next-generation adaptive planning architecture as part of the ARPA / Rome Laboratory Planning Initiative (ARPI). ALPS is being used within the Planning Initiative to perform large-scale military transportation scheduling, taking a Time-Phased Force Deployment Data (TPFDD) file with thousands of cargo requests and assigning those cargos to particular transportation resources with specific embarkation and debarkation times. This paper presents the architectural design of ALPS, discusses the innovative techniques incorporated in the system, and describes the lessons learned in applying the system to the problem of transportation scheduling.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.