Augmented Environments are physical spaces where people can work and learn, collectively or individually, by using day-to-day tools such as pen and paper, or other quotidian objects. This affordable and extensible system augments the user’s capabilities without being invasive, recognising their natural language and humane behaviours.

In many scenarios, when working with computers or in computer-supported environments, such as mixed-reality ones, users must accept the machine’s abstractions and rigid interfaces, which augments our capabilities only in virtual dimensions. To cope with this issue, we design, build and test a solution to projection-based augmented reality - called the Augmented Desk: a physical space where people can work and learn, collectively or individually, by using day-to-day tools such as pen and paper.

Augmented Desk aims to leverage the power of computation using natural language and our own bodies.

Augmented desk users directly manipulate physical objects as part of the interface, this is a key feature for the interaction model, as it theoretically allows for computationally-enabled embodied knowledge.

Hand-written text is understood and interpreted using deep learning techniques. This capability boosts the flexibility of the system, since users can communicate with machines using their own language, and the work of the machine is to understand and interpret it, not the other way around.

One key aspect is the possibility of modifying a tabula rasa system (a clean, extensible projected surface) by means of QR codes, without having to touch the underlying system.

Thanks to the advances in computation and computer vision, the team is able to build a fast and accuracte object-recognition model for our system. Objects surrounding us can easily become part of the computational environment.

Multiple objects (or text) can simultaneously co-exist without interfering the attached behaviours or applications.