Competitions

Amazon Robotics Challenge

The Amazon Robotics Challenge was designed to fill a gap in Amazon.com’s automated warehousing processes. In 2017 the Centre’s team took out the top prize in Nagoya, Japan. Competing as one of 16 teams from 10 countries, participants were tasked with building their own automated robot, including hardware and software, to successfully pick and stow items in a warehouse.

RoboCup@home

RoboCup@Home is a mobile manipulation and human robot interaction challenge that aims to develop service and assistive robot technology with high relevance for future domestic applications. In 2019 the Centre entered a team in the Challenge with a butler-come-garbo bot named Rocky who can take out the garbage!

RoboCup@Home is a mobile manipulation and human robot interaction challenge that aims to develop service and assistive robot technology with high relevance for future domestic applications.  Something of a Frankenstein, Rocky was built from a mish-mash of robots and technology found in the Centre’s labs and was placed sixth in our first attempt at the challenge which was a great result.

VQA 2.0 challenge

In 2017 Dr Damien Teney and Professor Anton van den Hengel of the University of Adelaide, along with Centre PhD researcher Peter Anderson from ANU and their team, placed first in the VQA 2.0 challenge. The challenge gives participants an image and an accompanying natural language question about it, which their AI system must provide an accurate natural language answer.



Comments Closed

1 Comment
Oldest
Newest Most Voted
Inline Feedbacks
View all comments
Ben Talbot
Ben Talbot
August 25, 2020 8:46 pm

Entering competitions has been both a great driver, and demonstrator, of our research. I was on the RoboCup@Home team & found it a great way to work together with people of all different skill sets / levels of experience. Sitting in a hall non-stop for days on end wouldn’t be much fun without teammates around.

The “real world problem” focus of the competitions poses a range of problems outside the typical research scope. Simply getting something to reliably work is something that can be an experience & a half in itself.