Computers

Winners of the 2018 Robot Art Competition swap pixels for paintbrushes

Winners of the 2018 Robot Art ...
The winning robot in the 2018 Robot Art Competition, CloudPainter
The winning robot in the 2018 Robot Art Competition, CloudPainter
View 33 Images
The winning robot in the 2018 Robot Art Competition, CloudPainter
1/33
The winning robot in the 2018 Robot Art Competition, CloudPainter
More original artwork by 1st-prize-winning CloudPainter
2/33
More original artwork by 1st-prize-winning CloudPainter
Reproduction of Cezanne's Houses at L'Estaque by 1st-prize-winning CloudPainter
3/33
Reproduction of Cezanne's Houses at L'Estaque by 1st-prize-winning CloudPainter
Portrait imagined by deep learning neural networks, multiple AI algorithms, and feedback loops by 1st-prize-winning CloudPainter
4/33
Portrait imagined by deep learning neural networks, multiple AI algorithms, and feedback loops by 1st-prize-winning CloudPainter
Work from the second-prize-winning robot PIX18
5/33
Work from the second-prize-winning robot PIX18
Work from the second-prize-winning robot PIX18
6/33
Work from the second-prize-winning robot PIX18
Work from the second-prize-winning robot PIX18
7/33
Work from the second-prize-winning robot PIX18
The original painting that PIX18 reinterpreted
8/33
The original painting that PIX18 reinterpreted
CMIT ReART, the third-prize-winning robot
9/33
CMIT ReART, the third-prize-winning robot
CMIT ReART works by recording the brush strokes of a human artist and replicating them robotically
10/33
CMIT ReART works by recording the brush strokes of a human artist and replicating them robotically
CMIT ReART works by recording the brush strokes of a human artist and replicating them robotically
11/33
CMIT ReART works by recording the brush strokes of a human artist and replicating them robotically
A closer look at the brush strokes of CMIT ReART
12/33
A closer look at the brush strokes of CMIT ReART
Fourth place winner is called Late Night Projects. This is a pen and water color reinterpretation of a photograph
13/33
Fourth place winner is called Late Night Projects. This is a pen and water color reinterpretation of a photograph
An original work from Late Night Projects
14/33
An original work from Late Night Projects
An ink and watercolor reinterpretation from Late Night Projects
15/33
An ink and watercolor reinterpretation from Late Night Projects
Fifth place went to Canadian artist Joanne Hastie
16/33
Fifth place went to Canadian artist Joanne Hastie
This floral still life painting was created with a robotic desktop arm programmed with Python
17/33
This floral still life painting was created with a robotic desktop arm programmed with Python
Landscape painting created using a robotic desktop arm programmed with Python
18/33
Landscape painting created using a robotic desktop arm programmed with Python
This floral still life painting was created with a robotic desktop arm programmed with Python
19/33
This floral still life painting was created with a robotic desktop arm programmed with Python
Sixth place went in independent Australian artist Jeremy Kraybill
20/33
Sixth place went in independent Australian artist Jeremy Kraybill
This painting was created in Melbourne, Australia, using a series of AI software modules and painted using an ABB IRB 120 robotic arm
21/33
This painting was created in Melbourne, Australia, using a series of AI software modules and painted using an ABB IRB 120 robotic arm
Seventh place went to a team of roboticists from MIT under the name Babot  
22/33
Seventh place went to a team of roboticists from MIT under the name Babot  
Seventh place went to a team of roboticists from MIT under the name Babot  
23/33
Seventh place went to a team of roboticists from MIT under the name Babot  
Seventh place went to a team of roboticists from MIT under the name Babot  
24/33
Seventh place went to a team of roboticists from MIT under the name Babot  
Acrylic on canvas by Ozpainter
25/33
Acrylic on canvas by Ozpainter
In this work by Ozpainter, eight colors are used, and brushstroke patterns designed prior to painting, using a program that generates brushstrokes according to predetermined rules. No feedback system is used
26/33
In this work by Ozpainter, eight colors are used, and brushstroke patterns designed prior to painting, using a program that generates brushstrokes according to predetermined rules. No feedback system is used
This robotic system called Ozpainter snagged eighth place in the competition
27/33
This robotic system called Ozpainter snagged eighth place in the competition
Ninth place went to CARP, a painting robot designed by students at the Worcester Polytechnic Institute
28/33
Ninth place went to CARP, a painting robot designed by students at the Worcester Polytechnic Institute
This is a re-interpreted artwork created by the robot CARP
29/33
This is a re-interpreted artwork created by the robot CARP
This is a re-interpreted artwork created by the robot CARP
30/33
This is a re-interpreted artwork created by the robot CARP
The Portrait Painter Robot Project from Spain took tenth place
31/33
The Portrait Painter Robot Project from Spain took tenth place
The Portrait Painter Robot paints portraits using a digital image as a source. Completely autonomous, with automatic mixing color system, the robot can generate up to 150 different colors
32/33
The Portrait Painter Robot paints portraits using a digital image as a source. Completely autonomous, with automatic mixing color system, the robot can generate up to 150 different colors
The winning robot in the 2018 Robot Art Competition, CloudPainter
33/33
The winning robot in the 2018 Robot Art Competition, CloudPainter

The Robot Art Competition is a fascinating blend of art and technology, challenging engineers to create robotic systems that can produce artworks using physical brushes and paint. The winners of the third annual competition highlight the growing sophistication and variety of machine-generated artwork.

The competition, founded by Stanford educated mechanical engineer Andrew Conru, is primarily interested in how well robotic engineers can develop new mechanical painting devices. In fact, the only real guiding limitation in the rules is that, "Paint/color must be applied with one or more physical brushes by a robotic system."

Within this constraint, the 19 teams that entered the 2018 competition all devised novel ways for their robots to create final art works. Some teams created robot arms that can mimic the movements of human artists, while others developed more complicated input processes, with their robot artists directed by various software algorithms. Some teams even went so far as to use AI systems to get their robots to generate a completely original image without a source photo or image for inspiration.

Portrait imagined by deep learning neural networks, multiple AI algorithms, and feedback loops by 1st-prize-winning CloudPainter
Portrait imagined by deep learning neural networks, multiple AI algorithms, and feedback loops by 1st-prize-winning CloudPainter

The winners were selected by a mix of public voting and professional judging. The professional art critics judging the winning entries were directed to evaluate the artworks based on various criteria: overall originality and aesthetics, "painterly" ability, and technical contribution. The top 10 entries took home a share of US$100,000.

The first-placed robot this year, taking home the $40,000 lion's share of the prize pool, is called CloudPainter. Developed by independent American roboticist Pindar Van Arman, CloudPainter came third in last year's competition and is rapidly evolving in sophistication from year to year. This is one of the more autonomous generative systems in the competition, and Van Arman notes that more teams have started incorporating AI into their robotic systems across each subsequent year of the competition.

Sixth place went in independent Australian artist Jeremy Kraybill
Sixth place went in independent Australian artist Jeremy Kraybill

"While AI was unusual when the contest began, it has since become one of the most important tools for the robots," writes Van Arman. "Many of the top entries, including mine, Hod Lipson's, and A Roboto used deep learning to create increasingly autonomous generative art systems. For some of the work it became unclear whether the system was simply being generative, or whether the robots were in fact achieving creativity."

Work from the second-prize-winning robot PIX18
Work from the second-prize-winning robot PIX18

Second place and $25,000 went to a series of works from Columbia University's Creative Machines Lab. The robot, dubbed PIX18, won the competition last year, and its efforts this year demonstrated a growing sophistication in re-interpreting existing art using impressively nuanced brushstrokes.

Take a look through our gallery for a look at all the winners in this year's Robot Art Competition.

Source: Robot Art

1 comment
Douglas Bennett Rogers
Somebody should build a "Lost in Space" robot around one of these systems and have him make comments, "These brushstrokes do not compute."