Photos: The robotic garden designed to be a programmer's playground

Shining a light

"Students can see their commands running in a physical environment, which tangibly links their coding efforts to the real world," says Lindsay Sanneman, who is lead author on the new paper. "It's meant to be a launchpad for schools to demonstrate basic concepts about algorithms and programming."

The garden features eight varieties of origami flowers - including lilies, tulips, and birds of paradise - which contain printable motors to allow them to blossom in various ways.

"Many elements of the garden can be made very quickly, including the pouch motors and the LED flowers," researcher Jospeh DelPreto, said. "We're hoping that rapid fabrication techniques will continue to improve to the point that something like this could be easily built in a standard classroom."

Image: CSAIL

Illuminating algorithms

The garden is split into 16 tiles that are connected via Arduino microcontrollers and programmed via search algorithms.

Each algorithm explores space in different ways, with the outcome   reflected in the appearance of the garden, for instance a graph-colouring algorithm that ensures no two adjacent tiles ever share the same colour.

Image: CSAIL

Controlling the garden

The system can be managed via tablet or any Bluetooth-enabled device. Users can interact using a simple "control by click" interface, where they click on individual flowers, as well as a more advanced "control by code" option, where they add their own commands and execute sequences in real-time.

Image: CSAIL

Woolly logic

As well as flora, the garden also features a series of robot animals, such as this sheep, which was created using a traditional print-and-fold origami technique.

Image: Jason Dorfman/CSAIL

Fowl play

Other creatures include these magnet-powered ducks, which started as two-dimensional paper prints before being heated in an oven to cause them to automatically fold into shape.

Image: Jason Dorfman/CSAIL

Unfolding knowledge

"The garden tests distributed algorithms for over 100 distinct robots, which gives us a very large-scale platform for experimentation," says CSAIL director Daniela Rus, the Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science and a co-author of the paper.

"At the same time, we hope that it also helps introduce students to topics like graph theory and networking in a way that's both beautiful and engaging."

Rus previously helped develop a distributed system of robots that watered, harvested, and took various metrics of an actual vegetable garden using complex motion-planning and object-recognition algorithms.

Image: CSAIL