Case Study: Australian Centre for Robotic Vision 

The Australian Centre for Robotic Vision (ACRV) headquartered at Queensland University of Technology (QUT), is a research institution for tasks a robot can tackle with vision such as grasping, perception and visual servoing. It has demonstrated multiple times that challenging robotics problems have solutions, such as when a team of researchers from ACRV won the Amazon Picking Challenge.

 

'Kinova's robot is robust and easy to use (not forgetting its awesome software), making it the ideal platform to prototype from. The new Gen3 looks like it has super-sized in terms of hardware, packing an even more powerful punch as a research tool.'

Doug Morrison, PhD Researcher, Australian Centre for Robotic Vision

The Results

Significantly smaller and faster than other Convolutional Neural Networks, The Australian Centre for Robotic Vision’s GG-CNN achieved state-of-the-art results in grasping unknown, dynamic objects, including objects in cluttered and changing environments. The final GG-CNN contained 62,420 parameters, compared to CNNs used for grasp candidate classification in other works containing hundreds of thousands or millions of parameters.

Their network’s lightweight and single-pass generative nature allowed for closed-loop control at up to 50 Hz, enabling accurate grasping in non-static environments where objects move and in the presence of robot control inaccuracies.

Read the ACRV's published research paper here

83% success previously unseen objects

83% grasp success rate on a set of previously unseen objects with adversarial geometry

88% success with moving objects

88% success rate on a set of household objects moved during the grasp attempt

81% accuracy in dynamic clutter

81% accuracy when grasping in dynamic clutter