Two teams entered the skills robotics challenge which saw teams build their own hardware and software to successfully pick and stow items in a warehouse. <\/p>\n
Amazon is known for being able to quickly package and ship millions of items daily from locations all over the world. But the company is yet to develop automated picking technology. <\/p>\n
A total of eight teams made it the finals, the Aussie team the Australian Centre for Robotic Vision, was placed fifth after the picking and stowing rounds. According to the Centres COO Dr Sue Keay, it was a tense few hours. <\/p>\n
Our team top scored early with 272 points on the final combined stowing and picking task, but 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. <\/p>\n
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. <\/p>\n
The winning robot: Cartman, was a Cartesian robot developed by the team. Cartmans movement is similar to that of a gantry crane, it can move along three axes at right angles to each other. The robot also features rotating gripper that enabled the robot to pick up items using a suction device or a simple two-finger grip. <\/p>\n
The unique design of the robot was what won the team the prize. Juxi describes the robots design: <\/p>\n
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. <\/p>\n
The team made up of people from QUT, The University of Adelaide and the Australian National University travelled all the way to Japan to compete in the event. The team spent more than 15,000 hours developing Cartman. <\/p>\n
The competition was made up of object recognition, pose recognition, grasp planning, compliant manipulation, motion planning, task planning, task execution and error detection and recovery challenges. The robots were judged on how well they picked and stowed in a set amount of time. <\/p>\n
\"We are world leaders in robotic vision, and we're pushing the boundaries of computer vision and machine learning to complete these tasks in an unstructured environment,\" says Juxi. <\/p>\n
According to Dr Anton Milan, Cartmans vision system was the result of hours of training data and training time, We had to create a robust vision system to cope with objects that we only got to see during the competition. <\/p>\n
Our vision system had the perfect trade-off of training data, training time and accuracy.....We only needed just seven images of each unseen item for us to be able to detect them. <\/p>\n
University of Adelaide team member Dr Trung Pham agrees, \"Our robot uses deep learning to see robustly and acts reliably due to smart design. The competition was a fantastic chance for us to truly test our state-of-the-art algorithms as well as opening up new real-world challenges that go beyond academic research. <\/p>\n
It feels amazing to have accomplished this, says Anton. Excellent team effort. Looking at the overall performance across all teams, we see huge advances in robotics and AI. We definitely have very exciting times ahead of us. <\/p>\n
Header:Team ACRV is ecstatic with a score of 272 points in the final round of the Amazon Robotics Challenge <\/p>\n
<\/p>\n
Visit link: <\/p>\n
Aussie Robotics Win Amazon Robotics Challenge - National Geographic Australia<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Two teams entered the skills robotics challenge which saw teams build their own hardware and software to successfully pick and stow items in a warehouse. Continue reading