A groundbreaking collaboration between global software company Autodesk and design engineering firm Arcadis is developing experimental technology that could transform how architects approach building renovation and adaptive reuse. The innovative system combines artificial intelligence, advanced sensors, and predictive modeling to create what researchers describe as "x-ray vision for buildings," allowing professionals to see hidden infrastructure within walls before construction begins.
The technology addresses one of the most significant challenges in adaptive reuse projects: understanding what lies behind layers of plaster, paint, and finishes. Within these hidden spaces exists an intricate network of pipes, electrical conduits, beams, and structural elements that make buildings function, yet remain invisible to the everyday eye. These layers also contain traces of different construction periods, including replaced systems, improvised adaptations, and technical solutions that once responded to specific contexts and urgent needs.
David Benjamin, Director of AEC Industry Futures at Autodesk, explains that laser scans are excellent for capturing visible aspects of existing buildings but cannot reveal invisible elements, including what's inside walls and the condition of various materials. "If we can create a kind of x-ray vision for buildings, we may be able to unlock new possibilities for material reuse, circularity, and decarbonization," Benjamin states. The research involves applying AI to multiple limited data sets rather than relying on one comprehensive data source, combining imperfect information from old floor plans, laser scans, sensors, and geographic information systems to derive better insights.
The system uses multiple information sources to create intelligent three-dimensional models of existing buildings. From these models, AI can infer and predict elements that are not directly visible, including pipe locations, material conditions, and structural health of various components. This approach represents a shift from generating new designs to teaching AI to interpret and connect what already exists, focusing on leveraging existing infrastructure rather than creating entirely new solutions.
Mansoor Kazerouni, Global Director of Architecture and Urbanism at Arcadis, emphasizes that retrofit projects represent more than technical exercises—they embody cultural and ecological responsibility. "Reusing existing structures remains one of the most effective ways to reduce carbon emissions and preserve the character of our cities," Kazerouni explains. He identifies "the unknown" as one of the main challenges in renovation projects, noting that existing conditions aren't always clearly documented, and teams don't truly know what they'll encounter until work begins.
Outdated drawings, undocumented alterations, and hidden systems frequently lead to unexpected discoveries that significantly impact project costs and schedules. Technologies capable of seeing through walls could completely transform this dynamic by providing teams with advance knowledge about structures, systems, and materials. This predictability enables more precise intervention planning, avoiding surprises and rework while building team confidence and allowing data-driven decisions rather than reactive responses to unforeseen conditions.
The implications extend far beyond improved design and construction efficiency. Early access to comprehensive structural information facilitates component reuse, reduces waste, and optimizes resource allocation. Knowing exact locations and conditions of building systems enables safer construction sites, more accurate budgeting, and more controlled project timelines. Benjamin emphasizes the urgent environmental context, noting that buildings account for 40 percent of global carbon emissions and that making existing building reuse faster and easier could create substantial impact despite the immense scale and short timeframe involved in addressing carbon problems.
Arcadis has demonstrated significant experience in this field through projects like the renovation of Castellana 66 in Madrid. The 1990 office building underwent a comprehensive sustainability transformation that converted it into one of Europe's most energy-efficient buildings. The intervention preserved the original structure while prioritizing embodied carbon retention and complete environmental performance upgrades. The project achieved a 55 percent reduction in annual energy use and prevented 10,800 tons of CO₂ emissions from entering the atmosphere.
Beyond precision, Autodesk's research explores uncertainty as an essential yet often invisible component of AI-driven decision-making. Benjamin explains that while AI predictions always include certainty or uncertainty assessments, this information rarely becomes visible to users. "We think it would be helpful for decision-making if a user could see both an AI prediction and a level of uncertainty at the same time," he notes. This approach acknowledges that reuse involves revelation and remaining open to surprises, representing both technological advancement and epistemological shifts in how architects read, interpret, and intervene in built environments.
The technology transforms uncertainty into knowledge, making invisible elements visible and enabling more informed reuse practices that bridge research and practice, precision and sensitivity, innovation and preservation. As Carl Elefante, former president of the American Institute of Architects, famously stated, "The greenest building is the one that is already built." This perspective suggests that architecture's future may depend fundamentally on how effectively professionals learn to see and understand what already exists in front of them, rather than constantly creating new structures from scratch.
