News

Designers find better solutions with computer assistance, but sacrifice creative touch

From building software to designing cars, engineers grapple with complex design situations every day. 'Optimizing a technical system, whether it’s making it more usable or energy-efficient, is a very hard problem!' says Antti Oulasvirta, professor of electrical engineering at Aalto University and the Finnish Center for Artificial Intelligence. Designers often rely on a mix of intuition, experience and trial and error to guide them. Besides being inefficient, this process can lead to ‘design fixation’, homing in on familiar solutions while new avenues go unexplored. A ‘manual’ approach also won’t scale to larger design problems and relies a lot on individual skill.
The design space in the virtual reality task
The design space in the virtual reality task. From Figure 2 in Chan et al. (2022).
Participants in the study moved their hand to find targets in the virtual reality space.
Participants in the study moved their hand to find targets in the virtual reality space. From Figure 2 in Chan et al. (2022).

Oulasvirta and colleagues tested an alternative, computer-assisted method that uses an algorithm to search through a design space, the set of possible solutions given multi-dimensional inputs and constraints for a particular design issue. They hypothesized that a guided approach could yield better designs by scanning a broader swath of solutions and balancing out human inexperience and design fixation. 

Along with collaborators from the University of Cambridge, the researchers set out to compare the traditional and assisted approaches to design, using virtual reality as their laboratory. They employed Bayesian optimization, a machine learning technique that both explores the design space and steers towards promising solutions. ‘We put a Bayesian optimizer in the loop with a human, who would try a combination of parameters. The optimizer then suggests some other values, and they proceed in a feedback loop. This is great for designing virtual reality interaction techniques,’ explains Oulasvirta. ‘What we didn’t know until now is how the user experiences this kind of optimization-driven design approach.’

To find out, Oulasvirta’s team asked 40 novice designers to take part in their virtual reality experiment. The subjects had to find the best settings for mapping the location of their real hand holding a vibrating controller to the virtual hand seen in the headset. Half of these designers were free to follow their own instincts in the process, and the other half were given optimizer-selected designs to evaluate. Both groups had to choose three final designs that would best capture accuracy and speed in the 3D virtual reality interaction task. Finally, subjects reported how confident and satisfied they were with the experience and how in control they felt over the process and the final designs. 

The results were clear-cut: ‘Objectively, the optimizer helped designers find better solutions, but designers did not like being hand-held and commanded. It destroyed their creativity and sense of agency,’ reports Oulasvirta. The optimizer-led process allowed designers to explore more of the design space compared with the manual approach, leading to more diverse design solutions. The designers who worked with the optimizer also reported less mental demand and effort in the experiment. By contrast, this group also scored lower on expressiveness, agency and ownership, compared with the designers who did the experiment without a computer assistant.  

‘There is definitely a trade-off,’ says Oulasvirta. ‘With the optimizer, designers came up with better designs and covered a more extensive set of solutions with less effort. On the other hand, their creativity and sense of ownership of the outcomes was reduced.’ These results are instructive for the development of AI that assists humans in decision-making. Oulasvirta suggests that people need to be engaged in tasks such as assisted design so they retain a sense of control, don’t get bored, and receive more insight into how a Bayesian optimizer or other AI is actually working. ‘We’ve seen that inexperienced designers especially can benefit from an AI boost when engaging in our design experiment,’ says Oulasvirta. ‘Our goal is that optimization becomes truly interactive without compromising human agency.’

 

This paper was selected for an honourable mention at the ACM CHI Conference on Human Factors in Computing Systems in May 2022.  

Reference: Chan, L., Liao, Y.C., Mo, G.B., Dudley, J.J., Cheng, C.L., Kristensson, P.O. and Oulasvirta, A., 2022. Investigating Positive and Negative Qualities of Human-in-the-Loop Optimization for Designing Interaction Techniques. doi: 10.1145/3491102.3501850 

FCAI

Finnish Center for Artificial Intelligence (external link)

The Finnish Center for Artificial Intelligence FCAI is a research hub initiated by Aalto University, the University of Helsinki, and the Technical Research Centre of Finland VTT. The goal of FCAI is to develop new types of artificial intelligence that can work with humans in complex environments, and help modernize Finnish industry. FCAI is one of the national flagships of the Academy of Finland.

  • Published:
  • Updated:
Share
URL copied!

Read more news

Koeputkia, joissa on eri värisiä nesteitä.
Press releases Published:

A greener route to blue – a new method drastically reduces the amount of solvent needed to produce widely used organic dyes

Phthalocyanines dyes can be produced with solid-state synthesis instead of high-boiling organic solvents.
Havainnekuva rintasyöpäsoluista mikroskoopissa
Press releases Published:

Breast cancer cells use forces to open up channels through tissue

A new method reveals that cancer cells can spread by rapidly applying forces to tissue material.
Tuoleja ravintolatilassa, taustalla asiakaspalvelutilanne
Press releases Published:

New technologies can help people make sustainable dietary decisions

Blockchain-backed app provides information about food impacts and combined customer choice
An illustration with a graph on the left and a molecular structure inset in a cube on the right. Each curve on the graph is a different colour, and each is connected by a line to an inset circle with a specific molecular feature corresponding to that curve. Above the cube with the molecular structure is a squigly arrow coming in, labelled "hv", and a straight arrow going out, labelled "e-". The entire figure (graph and inset cube) is labelled "XPS".
Press releases Published:

Machine learning gives material science researchers a peek at the answer key

A model trained to predict spectroscopic profiles helps to decipher the structure of materials