<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-07-08T08:44:08Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/2791C92C-AAEB-41C6-B0D7-2E81A4C1773C" ns1:id="2791C92C-AAEB-41C6-B0D7-2E81A4C1773C"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/5F2834D6-4497-425B-A401-A8E4B63792FE" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/8589FAD1-CE6E-4DD0-99F9-3E16ED72E7E0" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/8589FAD1-CE6E-4DD0-99F9-3E16ED72E7E0" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-04-29T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/F3F4FAA0-FB0F-4591-B95D-1F66C71F74C0" ns1:rel="FUND" ns1:start="2025-11-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10170389</ns2:identifier></ns2:identifiers><ns2:title>RetrofitAI-Sight: Drone Edge-AI to Automate PAS 2035 Home Retrofit Surveys</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Fast Start Response</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>RetrofitAI-Sight is a six-month research and development project that will demonstrate how affordable drones and artificial intelligence can revolutionise home-energy surveys in the UK. Today, a manual retrofit assessment typically costs around &amp;pound;750 and can take weeks to deliver, creating a major bottleneck in the national mission to upgrade 29 million poorly insulated homes. Our project will prove that the same insights can be captured for less than &amp;pound;100 and delivered in under two hours.

Using an off-the-shelf thermal/RGB drone, we will collect high-resolution images of roofs, walls and windows during a short, pre-authorised flight. On-board edge-computing hardware will run computer-vision models that highlight heat-loss, damp and ventilation issues in real time. Once the data land, a language model---trained on public Energy Performance Certificate datasets and retrofit best practice---will automatically generate a clear, standards-compliant report, including heat maps, recommended measures and indicative costs. The entire process will be designed to meet PAS 2035, the UK's official retrofit code of practice.

The project will culminate in three pilot surveys on social-housing estates in Stoke-on-Trent, where we will compare our AI-generated reports with traditional chartered-surveyor assessments. Success will show that local authorities, housing associations and small construction firms can cut survey costs by 85 %, speed up decision-making and unlock large-scale home decarbonisation projects earlier than planned. Deliverables will include an open demonstration dataset, a validated prototype platform at Technology Readiness Level 6, and a commercial roadmap for nationwide rollout---helping the UK move faster towards its Net-Zero 2050 target.</ns2:abstractText></ns2:project>