Kaiwen Chen
University of Alabama, AL·Engineering
Many American homes are old and leaky. U.S.
- Fields
Engineering
Computer Science
- Topics
building energy audit
energy retrofit
weatherization
- Grants
- 2 known grants, through Jul 2029
What they work on
- Enable real-time autonomous drone navigation around homes for thermal-imaging energy audits, studying embodied AI, edge/cloud computing and human-robot interaction methods.
- Explore two-way interaction between drones and a digital twin, an interactive 3D building model, to support precise on-site surveying and retrofit design and planning.
- Identify legal, ethical, privacy and economic barriers to deploying AI drone systems for weatherization, using co-design sessions, community focus groups and pilot demonstrations.
- Build REACT digital twin modules that manage building data, run analytics and support simulation-based retrofit modeling for residential energy retrofits.
- Develop a knowledge-driven AI agent that extracts information from audit reports and guidebooks using retrieval-augmented generation, and test it with community action agencies on an interactive retrofit design platform.
More about the research
households spend on average 5.6% of their income on energy, and about 40% of energy losses escape through the building envelope, meaning the walls, roof, windows and insulation. Fixing these homes requires energy audits that are slow, costly and often out of reach for the families who need them most. This research combines drones, thermal imaging, artificial intelligence (AI) and digital twins to make audits and retrofit planning faster and more accessible. A digital twin is an interactive 3D computer model of a real building.
Why it matters
Faster, cheaper energy audits could help lower-income households with deteriorated insulation cut high energy bills, and help weatherization agencies and community action agencies plan retrofits at scale. Open, reproducible digital twin tools could let building researchers and practitioners compare retrofit options and improve housing efficiency and resilience.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Xia Wang
Ohio State University, OH·Computer Science
Build hpcGPT, a question-answering service for academic high-performance computing centers, by combining large language model fine-tuning with retrieval augmented generation so answers reflect center-specific documentation and past support experience.
Olga Lauter
University of Texas at El Paso, TX·Engineering
Investigate how socio-cultural factors shape housing construction and energy use in two Alaska Native communities in the Bristol Bay region, using needs assessments and community workshops.
Stephen Lee
University of Pittsburgh, PA·Computer Science
Test whether inexpensive off-the-shelf sensors placed by residents can pinpoint where a specific home loses energy, without professional audit equipment.
The school
University of Alabama: 22 labs on PI Pages, $221M a year on research, 235 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.