The Australian Centre for Robotic Vision Team (ACRV) has won the 2017 Amazon Robotics Challenge at RoboCup in Nagoya Japan.
And for winning the finals, ACRV, headquartered at Queensland University of Technology (QUT), will take home US$80,000 for their efforts.
The skills challenge attracted 16 teams of researchers from 10 countries – including two teams from Australia.
The teams were tasked with building their own hardware and software to successfully pick and stow items in a warehouse.
While Amazon can quickly package and ship millions of items to customers from its network of fulfillment centres, the commercial technologies to solve automated picking in unstructured environments are yet to be developed.
Eight teams made it through to the finals, with the Australian Centre for Robotic Vision placing fifth after the picking and stowing rounds.
Reassembled out of suitcases
“It was a tense few hours,” said Dr Sue Keay, the Centre’s Chief Operating Officer after the team top scored early with 272 points on the final combined stowing and picking task.
“We then had to wait on the results for five other teams, many of whom had outperformed us in the rounds, before it became clear that we had won.
“Not bad for a robot that was only unpacked and reassembled out of suitcases a few days before the event, with at least one key component held together with cable ties.”
The Australian Centre for Robotic Vision developed their own Cartesian robot “Cartman” for the challenge – the only team with a Cartesian robot at the event.
Team leader Dr Juxi Leitner from QUT said the victory could be largely attributed to the custom made Cartman.
“Cartman can move along three axes at right angles to each other, like a gantry crane,” he explained.
The robot features a rotating gripper enabling it to pick up items using either suction or a simple two-finger grip.
More flexibility
“With six degrees of articulation and both a claw and suction gripper, Cartman gives us more flexibility to complete the tasks than most robots can offer, Dr Leitner said. “Cartman is robust and tackles the task in an innovative way and is also cost effective. We learnt from our experience last year when we used an off-the-shelf robot. I think we had the lowest cost robot at the event!"
Fifteen members of the Centre’s 27-strong team of researchers, sourced from QUT, the University of Adelaide and the Australian National University, were in Japan for the event.
“We feel brilliant, we say thank you very much for all the support we’ve received. The competition was a lot of work but really rewarding and a lot of fun,” says Adam Tow, a PhD researcher with the Centre, based at QUT. The team invested more than 15,000 hours into the project.
Improbable scenarios
The time and effort paid off according to Dr Chris Lehnert, a roboticist at QUT.
“Everything from the robot design, vision systems and grasping system worked flawlessly in the finals, he said.
“The competition was tough – so many of the improbable scenarios that we thought would never occur did occur.”
The Challenge combined object recognition, pose recognition, grasp planning, compliant manipulation, motion planning, task planning, task execution, and error detection and recovery. The robots were scored by how many items they successfully picked and stowed in a fixed amount of time.
The Australian Centre for Robotic Vision is an ARC Centre of Excellence that leads the world in robotic vision, applying computer vision to robotics.
“We're pushing the boundaries of computer vision and machine learning to complete these tasks in an unstructured environment," said Dr Leitner.
