Part geometry
CAD models, 3D scanning and recognition of parts from a library provide a common starting point for process preparation.
Software and AI for robotic painting.
We build SCAN2SPRAY and train AI models that learn to carry out the painting process. We combine 3D geometry, motion planning and coating simulation so that robot decisions are informed by part shape, spray characteristics and process requirements.
Technologies
From geometry to a painting strategy.
In robotic painting, the path, applicator motion and quantity of deposited material form a single process. SCAN2SPRAY lets you consider them together: prepare the part, define surfaces, plan passes and evaluate the predicted coating on a 3D model.
Planning and simulation
Paths, applicator orientation, spray parameters and successive layers are evaluated in the context of the complete cell.
AI training
SI_Path focuses on learning from painting demonstrations, with model behaviour evaluated through robot motion and the predicted coating.
SI_Path. Teaching AI to paint.
We train models to make motion and spray decisions in a simulation environment. The surface state, target coating and robot constraints define the task. Each run provides data on how the selected strategy affects coverage, film thickness and motion execution.
Further SI_Path development centres on NVIDIA Isaac Lab and adapting NVIDIA Isaac GR00T models to painting tasks, with coating quality as a key evaluation criterion.
See the complete process on a specific part.
From scanning an automotive body panel, through surface reconstruction and planning, to spray simulation. Our presentation materials also show single-colour coatings, multi-stage finishes and the organisation of a robotic painting line.
Technology open to collaboration.
We are open to collaboration with manufacturers of robots, applicators, coating materials and production systems. We combine software, process models and robotic integrations in solutions tailored to a specific application.
We welcome industrial partners and investors interested in AI for painting automation.
Paint shop control. From the operator panel to process data.
PRISMATEC CONTROL Basic, CONTROL2 and SmartBooth cover booth control, recipes, installation monitoring and paint shop operations. The software can be supplied with a control cabinet and equipment integration.
News
Project updates and perspectives on robotic painting.
SI_Path: Training AI for Autonomous Robotic Painting in Scan2Spray
How SI_Path combines learning from engineering demonstrations, practice in virtual workcells and independent checks of robot motion and coating.
Read on LinkedIn ↗
Testing Industrial Software Before Commissioning: What Each Test Establishes
Configuration checks, PLC–HMI readback and communication tests in Scan2spray and CONTROL Basic, with a clear account of the verification still needed on the installation.
Read on LinkedIn ↗
Building Industrial Software: From C++ Models to Operator Interfaces
The roles of C++, Python, Qt and TypeScript in Scan2spray, from calculation and workflow to operator interfaces and checks that keep saved results tied to their inputs.
Read on LinkedIn ↗Discuss your application.
Tell us what parts you paint, what equipment you use and what result you want to achieve. We will define the scope of a technology demonstration, joint testing or integration.
contact@prismatec.app