Enabling & Support

APSI - Advanced Planning and Scheduling Initiative

2483 views 4 likes

ESA / Enabling & Support / Space Engineering & Technology

SW003 - Abstract:

The offered tool (APSI) was developed by ESA with the aim of to creating a software framework to improve the cost-effectiveness and flexibility of the development of planning support tools. It strives initially to bridge the gap between advanced Artificial Intelligence (AI) planning and scheduling technology and the world of space mission planning. The final output of the project was a software framework for developing planning solutions and three different case studies to demonstrate the validity of the proposed approach, i.e. using AI technologies for space mission planning and scheduling. License agreements are sought.

Description of the offer:

The objective of the APSI project was to investigate the use of an experimental framework for the development of AI-based planning modules, in order to increase the automation and the efficiency of the planning process. This ultimate goal was achieved by:

trying to bridge the gap between advanced AI planning and scheduling techniques and the world of space mission planning and operations, by identifying typical operational planning problems that can be resolved by these techniques;
designing and implementing a prototype framework for supporting the development of space-oriented AI-based planning applications;
demonstrating the resolution of planning problems using AI-based techniques within the framework in three case studies.

The results of the project were:

A library of techniques and a set of functional AI modules applicable to the modelling and resolution of these problems;
A general architecture for the development of experimental planning tools;
Three prototype planning systems or part of planning systems built using the experimental framework.

Innovations and advantages:

The implementation of the prototypes demonstrates two key points.

First, the advantage of employing an AI model-based approach, in which the relevant features of the domain are described in a high-level declarative language allowing harnessing the versatility of general modelling and solving capabilities.

The second feature, which enables fast prototyping, is the capability of designing ad-hoc components and including them in the domain specification.

Domain of application:

The objective of the APSI was to investigate the use of an experimental framework for the development of AI-based planning modules, in order to increase the automation and the efficiency of the planning process. This objective might be supplemented by similar problem statements from related industries developing AI and AI-like software.