Robots Have Learned to Paint in Second Year of Robotic Art Contest

It was just announced that Google has developed AI that can sketch images. It should, therefore, come as no surprise that dozens of robots from around the world are now also painting with a brush, and many of them are quite skilled.

SEATTLE, April 21, 2017 /PRNewswire/ -- It was just announced that Google has developed AI that can sketch images. It should, therefore, come as no surprise that dozens of robots from around the world are now also painting with a brush, and many of them are quite skilled.


The Robot Art 2017 competition returns for a second year with over 39 painting robots, more than twice the participants it had in its inaugural year. In addition to more robots, there is more artwork. More than 200 paintings have been submitted. With regards to the quality of the artwork, the event's sponsor and organizer, Andrew Conru, sums it up best:

"The quality of the paintings for many of the teams has reached levels that are comparable with human artists. Many of this year's entries are expressive, layered, and complex."

The creativity of the teams and robots was evident not only in the artwork they produced, but also in how they went about making the art. Of the 39 painting robots, no two teams took the exact same approach. The Manibus Team captured the movements of a ballerina and painted it to canvas. HEARTalion built a robot that paints based on emotional interactions with humans. share your inner unicorn used brainwaves to control a mark-making mobile robot. Other teams built custom robots that capitalized on their innate lack of precision to make abstract work such as Anguis, a soft snake robot that slithers around its canvas. Other robots were built to collaborate with their artistic creators such as Sander Idzerda's and Christian H. Seidler's entries.

Two returning entries that were notable for their skilled approach to representational paintings in last year's contest have gone abstract. e-David submitted multiple abstract self-portraits not of a human, but of the robot itself. Each of its works was a collaboration between an artist and the machine, where most of the decisions were actually made by e-David as it continually watched and optimized its own progress on the canvas with multiple external cameras. CloudPainter also submitted multiple abstract portraits. Its subjects were taken from photo shoots performed by the robot itself. For several of CloudPainter's paintings, the only artistic decision made by an artist was to schedule the photo shoot. The robot then used artificial intelligence and deep learning to make all other "artistic" decisions, including taking the photos, making an original abstract composition from its favorite, and then executing each brushstroke until it had calculated it had done the best it could to render its original abstract composition.

The Robot Art 2017 competition will be running between now and May 15th, when more than $100,000 in awards will be given to the top painting robots. Winners will be determined based on a combination of public voting, professional judges consisting of working artists, critics, and technologists, and by how well the team met the spirit of the competition — that is, to create something beautiful using a physical brush and robotics. The public can see the artwork and vote on their favorite robotic paintings at https://robotart.org/artworks/.

Featured Product

Universal Robots - Collaborative Robot Solutions

Universal Robots - Collaborative Robot Solutions

Universal Robots is a result of many years of intensive research in robotics. The product portfolio includes the UR5 and UR10 models that handle payloads of up to 11.3 lbs. and 22.6 lbs. respectively. The six-axis robot arms weigh as little as 40 lbs. with reach capabilities of up to 51 inches. Repeatability of +/- .004" allows quick precision handling of even microscopically small parts. After initial risk assessment, the collaborative Universal Robots can operate alongside human operators without cumbersome and expensive safety guarding. This makes it simple and easy to move the light-weight robot around the production, addressing the needs of agile manufacturing even within small- and medium sized companies regarding automation as costly and complex. If the robots come into contact with an employee, the built-in force control limits the forces at contact, adhering to the current safety requirements on force and torque limitations. Intuitively programmed by non-technical users, the robot arms go from box to operation in less than an hour, and typically pay for themselves within 195 days. Since the first UR robot entered the market in 2009, the company has seen substantial growth with the robotic arms now being sold in more than 50 countries worldwide.