Automating High-Level Conceptual Design Requires Machine Understanding of Cause-Effect Relations
DS 130: Proceedings of NordDesign 2024, Reykjavik, Iceland, 12th - 14th August 2024
Year: 2024
Editor: Malmqvist, J.; Candi, M.; Saemundsson, R. J.; Bystrom, F. and Isaksson, O.
Author: Schaff, Chloe; Thorisson, Kristinn R.
Series: NordDESIGN
Institution: Reykjavik University, Iceland; Reykjavik University & Icelandic Institute for Intelligent Machines
Page(s): 655-662
DOI number: 10.35199/NORDDESIGN2024.70
ISBN: 978-1-912254-21-7
Abstract
Engineering design is a problem-solving process that works from a high-level description of a problem or plan and proceeds to iteratively define an increasingly detailed solution that meets criteria required for implementation in the real world. While significant efforts have been made to automate lower- and mid-level design tasks, little work has been done on the initial high-level conceptual design stage. For producing novel solutions, engineering design must unavoidably rely on an iterative analysis-refinement process. This requires understanding of cause-effect relations and explanation.
Keywords: Artificial Intelligence (AI), Conceptual Design, Functional Reasoning, Explanation