My Research
2020
EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation
Doug Morrison, Peter Corke, Juxi Leitner
IEEE Robotics and Automation Letters (RA-L). Accepted April, 2020.
We present the Evolved Grasping Analysis Dataset (EGAD), comprising over 2000 generated objects aimed at training and evaluating robotic visual grasp detection algorithms. The objects in EGAD are geometrically diverse, filling a space ranging from simple to complex shapes and from easy to difficult to grasp, compared to other datasets for robotic grasping, which may be limited in size or contain only a small number of object classes. Additionally, we specify a set of 49 diverse 3D-printable evaluation objects to encourage reproducible testing of robotic grasping systems across a range of complexity and difficulty.
2019
Doug Morrison, Peter Corke, Juxi Leitner
International Journal of Robotics Research (IJRR), June 2019
In this extended version of "Closing the Loop for Robotic Grasping" (RSS 2018), we
provide a more in-depth look at our real-time, generative grasp synthesis approach through
extended analysis, neural network design and a new multi-view approach to grasping.
Additionally, we extend our method to use the new Jacquard grasping dataset and
demonstrate the ease of transferring our platform-agnostic approach to a new robot.
Shortlist - SAGE HDR Student Publication Prize 2019
Doug Morrison, Peter Corke, Juxi Leitner
International Conference on Robotics and Automation (ICRA), 2019
Camera viewpoint selection is an important aspect of visual grasp detection, especially in clutter where many occlusions are present. Where other approaches use a static camera position or fixed data collection routines, our Multi-View Picking (MVP) controller uses an active perception approach to choose informative viewpoints based directly on a distribution of grasp pose estimates in real time, reducing uncertainty in the grasp poses caused by clutter and occlusions.
Doug Morrison, Anton Milan, Nontas Antonakos
CVPR 2019 Workshop - Robotic Vision Probabilistic Object Detection
In robotics, decisions made based on erroneous visual
detections can have disastrous consequences.
However, this uncertainty is often not captured
by classic computer vision systems or metrics.
We address the task of instance segmentation in a robotics
context, where we are concerned with uncertainty associated
with not only the class of an object (semantic uncertainty)
but also its location (spatial uncertainty).
4th Place - First ACRV Probabilistic Object Detection Challenge
2018
Doug Morrison, Peter Corke, Juxi Leitner
Robotics: Science and Systems (RSS), 2018
This paper presents a real-time, object-independent grasp synthesis method which can be used for closed-loop grasping. The lightweight and single-pass generative nature of our GG-CNN allows for closed-loop control at up to 50Hz, enabling accurate grasping in non-static environments where objects move and in the presence of robot control inaccuracies.
Doug Morrison, AW Tow, M McTaggart, R Smith, N Kelly-Boxall, S Wade-McCue, J Erskine, R Grinover, A Gurman, T Hunn, D Lee, A Milan, T Pham, G Rallos, A Razjigaev, T Rowntree, K Vijay, Z Zhuang, C Lehnert, I Reid, P Corke, J Leitner
International Conference on Robotics and Automation (ICRA), 2018
A system-level description of Cartman, our winning entry into the 2017 Amazon Robotics Challenge.
Finalist - Amazon Robotics Best Paper Awards in Manipulation 2018
A. Milan, T. Pham, K. Vijay, D. Morrison, A.W. Tow, L. Liu, J. Erskine, R. Grinover, A. Gurman, T. Hunn, N. Kelly-Boxall, D. Lee, M. McTaggart, G. Rallos, A. Razjigaev, T. Rowntree, T. Shen, R. Smith, S. Wade-McCue, Z. Zhuang, C. Lehnert, G. Lin, I. Reid, P. Corke, J. Leitner
International Conference on Robotics and Automation (ICRA), 2018
We present our approach for robotic perception in cluttered scenes that led to winning the recent Amazon Robotics Challenge (ARC) 2017. In contrast to traditional approaches which require large collections of annotated data and many hours of training, the task here was to obtain a robust perception pipeline with only few minutes of data acquisition and training time. To that end, we present two strategies that we explored.
Norton Kelly-Boxall, Doug Morrison, Sean Wade-McCue, Peter Corke, Juxi Leitner
Australasian Conference on Robotics and Automation (ACRA), 2018
We present the grasping system behind Cartman, the winning robot in the 2017 Amazon Robotics Challenge. The system was designed using an integrated design methodology and makes strong use of redundancy by implementing
complimentary tools, a suction gripper
and a parallel gripper. This multi-modal
end-effector is combined with three grasp synthesis
algorithms to accommodate the range of
objects provided by Amazon during the challenge.
2017
Doug Morrison, Peter Corke, Jürgen Leitner
"Towards robust grasping and manipulation skills for humanoids" Workshop at the IEEE-RAS International Conference on Humanoid Robots, 2017
We present a generative grasping network which encodes a one-to-one mapping from the RGB-D image space to the grasping space, rather than relying on grasp candidate sampling.
Doug Morrison, Norton Kelly-Boxall, Sean Wade-McCue, Peter Corke, Jürgen Leitner
"Towards robust grasping and manipulation skills for humanoids" Workshop at the IEEE-RAS International Conference on Humanoid Robots, 2017
We present a heuristic-based grasp detection system which uses a hierarchy of three different strategies to operate successfully under varying levels of visual uncertainty.
2014
Doug Morrison, Udantha Abeyratne
Journal of Food Engineering 141 (2014)
A publication from my undergraduate thesis, nothing to do with robots. I built a custom, hand-held ultrasound device that could evaluate the quality of oranges by relating ultrasonic surface reflections to hydration and firmness.