Expert Critics in Engineering Design: Lessons Learned and Research Needs
An engineer who creates a design needs to determine whether the design is free of errors that can lead to high manufacturing costs, tragic accidents because of design defects, low use because of poor product quality, and a host of other downstream concerns. The domain of engineering design is much harder than other domains, and errors are more likely to arise and remain undetected until it is too late to do something about them. One way to reduce these errors is to introduce the use of expert critics into the designer's electronic support environment. Critics are a promising approach for organizing a next-generation design support environment (DSE). Unfortunately, expert-critiquing theory offers inaccurate but widely followed guidance for helping builders create usable critic programs. Existing critics rely on batch, after-task, debiasing of experts. This form of criticism turns out to be overly limited and too often leads to user frustration. As a step toward correcting this deficiency, this article presents lessons learned from following the incorrect theory along with guidance for a more robust approach to criticism system construction. Future research needs are also identified that should help builders realize the full potential of critics in engineering DSEs.
Copyright © 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.