Informed comfort: natural-language interaction with home heating and cooling

The posting

Applicants are invited for a PhD fellowship/scholarship at Graduate School of Technical Sciences, Aarhus University, Denmark, within the Civil and Architectural Engineering programme. The position is available from 01 January 2027 or later. You can submit your application via the link under 'how to apply'.

Title Informed comfort: natural-language interaction with home heating and cooling

Research area and project description Predictive control can reduce energy costs and CO2 emissions of heating and cooling homes. However, its performance depends on knowing when residents are home and what they find comfortable.

You will develop a natural-language interface, based on a large language model, between residents and a predictive controller. Residents can then tell the controller, when they are away, report how the rooms feel, or ask for a warmer bathroom etc. In return, the controller explains what it did and why, shows what the next hours cost in money and CO2, and suggests alternatives that residents can accept or decline. The comfort limits are thus set by the residents; with the information they need.

This dialogue can save energy in three ways. Knowing when people are home and which rooms they use enables occupancy-based control, heating only where and when needed. Reports on how the rooms feel train personal comfort models, so setpoints match each household. The third, and least explored, is energy sufficiency: residents knowingly accept less heating or cooling, for example 20 °C instead of 21.5 °C on an expensive evening, while remaining free to say no. A central question is whether explaining alternative control actions and their cost changes how residents judge the same indoor conditions (their thermal acceptability), and whether the change lasts. All three look the same on the energy meter, so the project must separate them.

Few people want a system that talks all the time. Residents differ in how much information they want, in what form, and whether the system should take the initiative or only respond when asked (proactive versus on-demand interaction). Engagement may also fade as the novelty wears off. The project will study these differences and design for them.

You will:

• couple the language model to the controller, so that residents' requests become control actions within safe limits
• run a climate chamber experiment on whether explanations change thermal acceptability
• carry out a field study in occupied Danish homes through a winter and a summer, covering heating and overheating

Project description For technical reasons, you must upload a project description. Please simply copy the project description above and upload it as a PDF in the application.

Qualifications and specific competences Applicants to the PhD position must hold a M.Sc. in engineering, computer science, building science or a related technical field. Applicants with a B.Sc. and at least one year of master's studies can apply through the 4+4 programme.

You should be able to program, preferably in Python, and be comfortable analysing data. Experience with one or more of the following is an advantage: model predictive control or optimisation, large language models, statistics and the design of experiments with people, and field measurements in buildings. Nobody will have all of these, and you should be willing to learn what you lack.

The field study involves installing equipment in people's homes and talking with the residents, so you should be comfortable working with people. Danish is an advantage for the field work but not a requirement.

Applicants from neighbouring fields with relevant technical skills and a clear motivation for the topic are encouraged to apply.

Place of employment and place of work The place of employment is Aarhus University, and the place of work is Department of Civil and Architectural Engineering, Inge Lehmanns Gade 10, 8000 Arhus C., Denmark.

Contacts Applicants seeking further information regarding the PhD position are invited to contact:

• Michael Dahl Knudsen, [email protected] (main supervisor)
• Massimo Fiorentini, [email protected] (co-supervisor)

For information about application requirements and mandatory attachments, please see our application guide. If answers cannot be found there, please contact:

• [email protected]

How to apply Please follow this link to submit your application.

Application deadline is 15 November 2026 at 23:59 CET.

Preferred starting date is 01 January 2027.

Please note:

• Only documents received prior to the application deadline will be evaluated. Thus, documents sent after deadline will not be considered.
• The programme committee may request further information or invite the applicant to attend an interview.
• Shortlisting will be used, which means that the evaluation committee only will evaluate the most relevant applications.

Aarhus University’s ambition is to be an attractive and inspiring workplace for all and to foster a culture in which everyone has opportunities to thrive, achieve and develop. We view equality and diversity as assets, and we welcome all applicants. All interested candidates are encouraged to apply, regardless of their personal background. Salary and terms of employment are in accordance with applicable collective agreement.