From Waste to Value:
Digital & automated solutions for circular construction
A collection of takeaways from the final RECONMATIC Conference
Prague, 27-29 May 2026
Digital and automated solutions for circular construction, the key outcomes from the Reconmatic conference.
Material databanks & digital passports
Waste prediction using data and AI
Standardisation via data dictionaries (WASTEie)
Blockchain-enabled logistics
Generative design to minimise waste
Speakers: Petr Vokoun, Owen Ashton, Vitalij Tetervov, Kostas Choumas, Pavel Švejda
Converting drawings and scans into BIM models
Automating pre-demolition audits (PDAs)
Decision-support tools for deconstruction
Speakers: Omer Muhammad, Slávek Zbirovský, Abel Capelastegui Lasso, Jan Pesta
AI-driven waste recognition
Robotic sorting systems
IoT-enabled waste tracking
Quality assurance and traceability systems
Speakers: Inés Díez Ortiz, Václav Nežerka, Damien Sallé, Pavel Trávníček
Key issues include:
The Earth’s resources are finite, yet construction relies heavily on non-renewable materials
The sector consumes over 60% of natural aggregates (stone, sand)
Concrete production alone contributes ~7% of global CO₂e emissions
Over 10 billion tonnes of construction and demolition waste (CDW) are generated globally each year
CDW accounts for 35–65% of landfill, despite reported high recycling rates
Current “recycling” often equates to downcycling (low-value reuse - backfilling)
While reuse is widely discussed, regulatory frameworks and standards are still lacking.
The core message to take forward was the industry must move from volume-based waste handling to high-value circularity.
1 - Earth's resources
2 - Consumption
3 - Concrete production
4 - Demolition waste
5 - CDW
6 - Recycling challenges
7 - Reuse challenges
They provide end-to-end traceability across the asset lifecycle
They enable standardised, machine-readable product data
Include key documents (performance, environmental data, installation guidance)
Allow access via APIs, QR codes, and unique identifiers
But what is the value that can be unlocked with material passports?
Accurate material quantities and lifecycle data
Ability to compare design options based on cost and environmental performance
Long-term tracking—even for discontinued products
In summary, the key takeaway from the discussion was that data transparency enables better design decisions and future reuse potential.
1 - Accurate material quantities and lifecycle data
2 - Ability to compare design options based on cost and environmental performance
3 - Long-term tracking—even for discontinued products
Historically, waste forecasting has been unreliable. The introduction of machine learning models now enables:
Predictive analysis based on project metadata and BIM (IFC) files
Automated extraction of material quantities and building elements
Forecasting of waste volumes at different stages (design to execution)
Impact:
Provides early-stage insight into waste generation
Supports decision-making before waste occurs
The output established that predictive waste analytics shifts waste management from reactive to proactive.
WASTEie provides a common data structure for construction waste information.
Standardises terminology and classifications
Enables interoperability across systems and stakeholders
Supports consistent data exchange within circular workflows
Key takeaway: Data standardisation is essential to scale digital waste solutions.
Read more about WASTEie
IoT-enabled concrete delivery systems combined with blockchain create:
Real-time tracking of quantity, quality, and location
Tamper-proof records of delivery stages
Transparent validation of orders and responsibilities
Benefits:
Eliminates disputes
Improves efficiency and compliance
Enhances traceability and accountability
Key takeaway: Trusted data infrastructure improves supply chain efficiency and reduces waste/error.
Generative design introduces automated optimisation of building layouts:
Traditional focus of construction considers – Cost, performance and speed. But excitingly emerging focus considers:
Material efficiency
Carbon reduction
Constructability & logistics
Where do these emerging focus add value?
Early design decisions strongly influence waste generation
Optimised design ≠ lowest cost solution
Requires integration with manufacturing and prefabrication systems
Key takeaway: Waste reduction must be embedded at design stage, not addressed later.
A hybrid workflow converts 2D drawings into 3D BIM models:
Steps in the process include:
Scan drawings
Convert to CAD
Generate 3D model
Validate and correct
Benefits of a drawing to BIM automation:
Reduces reliance on outdated drawings
Cuts time and manual effort
Enables accurate pre-demolition audits (PDA)
Key takeaway: Automating legacy data conversion is critical for end-of-life building planning.
Using LiDAR and drones, buildings can be digitised via point clouds:
Processes large, unstructured datasets
Generates accurate BIM models quickly
Uses open standards (OpenBIM / IFC)
Value:
Enables precise mapping of existing assets
Supports reuse and demolition planning
Key takeaway: Reality capture technologies provide high-fidelity digital twins for circular workflows.
Tools support material recovery decisions by answering:
Where are materials located?
What are they used for?
Are they reusable?
Is recovery economically viable?
Critical requirement:
High-quality, standardised BIM data (property sets, correct naming, volume data).
Key takeaway: Decision automation depends on data quality and standardisation.
Advanced robotic systems improve waste processing:
~23 picks per minute
~97% sorting purity
Workflow includes:
Pre-processing (air, magnetic separation)
AI classification
Robotic picking
Real-time monitoring and QA
Higher-quality recycled materials
Reduced contamination
Full traceability
Key takeaway: Automation significantly improves recycling quality and efficiency.
Digital image processing enables accurate waste identification:
Uses AI (CNNs, hyperspectral imaging)
Supports classification of materials during processing
Enhances separation efficiency
Supporting processes:
Crushing, screening, and sorting remain core
AI enhances precision within these steps
Key takeaway: AI enables smarter, more precise material recovery.
An advanced robotic sorting system combining:
Multi-sensor perception (RGB, NIR, depth)
Hybrid grippers (suction + mechanical)
Performance insights:
Strong results in positive sorting (~97% purity)
Limitations in throughput and negative sorting
Performance constrained by hardware speed and AI accuracy
Key takeaway: Robotics is viable but requires continued optimisation (AI + hardware).
Integration of IoT with BIM creates live digital twins:
Tracks container location, fill levels, and material types
Uses sensors for environmental and structural data
Feeds real-time data into BIM models
Outcome:
Improved waste logistics
Better operational decisions
Live monitoring of assets
Key takeaway: IoT bridges the gap between digital models and real-world operations.
