Last year, Amazon kicked off its inaugural Picking Challenge to encourage teams to create robots able to perform the task of an Amazon stock picker. This year the competition was expanded to include not only picking items from a shelf and placing them in a container, but the reverse as well – and a team from the Netherlands has claimed victories in both.
This year's pick task, which carries over from last year but has been made more difficult, requires robots to grab target items from a shelf and place them in a container. Conversely, the stow task involves the robot removing items from a box and placing them back on the shelf. They sound like very simple tasks for a human, but for robot competitors it requires a sophisticated array of sensors, moving parts and artificial intelligence.
The robots have a time limit to grab as many items as they can, after which points are tallied up according to the number and value of those items retrieved, and deducted for dropped or damaged goods.
Team Delft, made up of engineers from the Delft University of Technology and the company Delft Robotics, won the stow task by a fairly large margin, gathering 214 points with the runner-up managing 186 and third place coming in at 164.
The pick task was more of a nail-biter. After drawing on 105 points with a Japanese team, the competition went into an overtime round where the fastest team to pick an item would be crowned the winner. Delft's robot completed the task about 30 seconds faster than its rival, earning itself both titles.
The winning robot is built according to industry standards, equipped with an arm allowing seven degrees of movement, 3D cameras and a specially-designed gripper. The software components used to control the robot were developed with the Robot Operating System for industry (ROS-Industrial) and will be released as open source software by the team. The team attributes the robot's success to it being robust and adaptable.
"We built a very robust system, that hardly makes any mistakes in picking the products, thanks to our expertise in 'bin picking'," says Kanter van Deurzen, of Delft Robotics. "In addition, the robot chooses the maximum of points that can be scored for each product to pick."
You can see a time-lapse video of the robot in action below.
Source: Delft University of Technology