New design Employ our graduates
Avatar Image

Associate Professor Ben Upcroft

Science and Engineering Faculty,
Electrical Engineering, Computer Science,
Robotics and Aerospace Systems

Personal

Name
Associate Professor Ben Upcroft
Position(s)
Associate Professor
Science and Engineering Faculty,
Electrical Engineering, Computer Science,
Robotics and Aerospace Systems
Discipline *
Artificial Intelligence and Image Processing, Electrical and Electronic Engineering
Phone
+61 7 3138 7158
Email
Location
View location details (QUT staff and student access only)
Qualifications

Phd (Physics) (University of Queensland)

Professional memberships
and associations

For more information please see my group research page http://wiki.qut.edu.au/display/cyphy/Ben+Upcroft

* Field of Research code, Australian and New Zealand Standard Research Classification (ANZSRC), 2008

Biography

My interests lie in the development of vision systems for long term robotic applications ranging from underwater and ground to airborne autonomous platforms. The overarching theme of my work is in robust visual perception for robotics and the major areas I have contributed to include:

1.      Multiple robotic platforms that communicate visual maps to other robots and humans building a consolidated representation of a large scale outdoor environment. Vision was the primary sensor for perceiving the world with a focus on representations that could be communicated efficiently, fused with other information consistently, in a decentralised manner.
2.      A full-sized commercial vehicle able to navigate and localise in urban environments. The vehicle was able to obey traffic rules and drive within lanes, strongly aided by visual information. This was the only Australian entrant to the USA Urban DARPA Grand Challenge which was a major demonstrator for the capabilities of robotics in civilian spaces.
3.     Dragline payload density estimation for optimising mining production. Robotics and automation play a major role in mining and perception in unstructured environments is not only crucial for robust operation but also for streamlining the entire productivity pipeline. This work demonstrated real-time estimation of payload density, enabling accurate calculations of total mined product and illustrated how to improve production capacity.
4.     Robust multiview vision algorithms for robots in harsh and challenging environments. I have developed short baseline stereo algorithms that are robust to vibrations and pressure changes between stereo cameras with views of environments at long ranges. This work is particularly suited to vision only pose estimation and 3D reconstructions of visual observations from Unmanned Aerial Vehicles and autonomous submersibles.
This work falls under the research area of the CyPhy lab which focuses on robotics in general.
For more information please see my group research page http://wiki.qut.edu.au/display/cyphy/Ben+Upcroft
CAREER HISTORY
Senior Lecturer, Queensland University of Technology, 2011-present
Senior Lecturer, University of Queensland, 2007-2011
Postdoctoral Fellow (Robotics), University of Sydney, 2004-2007
PhD (Physics), University of Queensland, 2004
COMPETITIVE GRANTS
1.      QLD Smart Futures Co-Investment Fund, Creating a more RESilient QUeensland – Unmanned aircraft for emergency response and biosecurity, $7million
2.      ARC Linkage, Robotics for Zero-Tillage Agriculture, 2011, Funding = $389,000
3.      ARC Discovery, Lifelong Robotic Navigation Using Visual Perception, 2010, Funding = $445,000
4.      Q Early Career Researcher’s Fund, Natural Environment Mapping for Emergency Services Robotics, 2010. Funding = $35,000.
5.      ACARP Grant, Real Time Continuous Measurement of Blasted Dragline Overburden Bulk Density, 2009. Funding = $377,800.
6.      UQ New Staff Research Fund, Visual Perception and Outdoor Navigation for Robust Autonomous Vehicles, 2008. Funding = $12,000
CONSULTANCIES
1.      Structural Complexity of the Great Barrier Reef, Global Change Institute, 2013
2.      Automated Bin Detection for Waste Management, J.J. Richards, 2012,
3.      Sensor Evaluation Study for Mapping and Obstacle Detection, 2007-2008.
4.      Decentralised Simultaneous Localisation and Mapping, L3 Communications, 2007.
5.      Decentralised Data Fusion for Surveillance, BAE Systems, 2004.
PATENTS
Inventors: A. Bewley, P. Lever, R. Shekhar and B. Upcroft. “Measurement of Bulk Density of the Payload in a Dragline Bucket.” Pub. Number: AU-A-2010236018, This system enables consistent monitoring of suspended bucket payload volumes from a commercial laser scanner with zero impact on mining productivity.
This information has been contributed by Associate Professor Ben Upcroft.

Teaching

  • Advanced Robotics and Control
  • Mechatronics Team Project I
  • Microprocessors and Digital Systems
  • Sensors and Actuators
For more information please see my group research page http://wiki.qut.edu.au/display/cyphy/Ben+Upcroft
This information has been contributed by Associate Professor Ben Upcroft.

Experience

I have spent the last 9 years working on perception systems for field robotics. Robots that I have had experience with include commercial passenger vehicles, all-terrain vehicles, haul trucks, and unmanned aerial vehicles. For more information, please see my webpage on robots. Some of the projects I have been involved in are listed below:

  • Robotic networks (UAVs and ground vehicles) for large scale mapping
  • Urban DARPA Grand Challenge
  • Haul truck obstacle detection and mapping
  • Sparse landmark SLAM for mining excavators
  • UAV visual egomotion
I have more recently focussed on navigation and classification using visual egomotion for mobile robotics.
For more information please see my group research page http://wiki.qut.edu.au/display/cyphy/Ben+Upcroft
EXTERNAL COLLABORATIONS
Mobile Robotics Group, Oxford University
ICT, CSIRO
Australian Centre for Field Robotics, University of Sydney

PROFESSIONAL ACTIVITIES I have been program chair for robotics conferences, have held technical program roles and have reviewed journal and conference publications in the field of robotics: -       Treasurer for the Australasian Robotics and Automation Association, 2011-present -       Reviewer for the International Conference on Robotics and Automation, 2007,2008, 2010,2013 -       Reviewer for the Robotics: Science and Systems International Conference, 2012 -       Associate Editor for the International Conference on Robotics and Automation, 2011 -       Program Chair for the Australian Conference on Robotics and Automation, 2010 -       Program Committee Member for the Robotics: Science and Systems conference, 2008 -       Reviewer for Journal of Field Robotics 2008-present, IF=2.684 -       Reviewer for International Symposium on Unmanned Aerial Vehicles, 2010 -       Reviewer for the Third International Symposium on Unmanned Aerial Vehicles, 2010 -       Associate Editor for the International Conference in Intelligent Robots and Systems, 2008-2009 INVITED TALKS 2013: Structure from Motion for Aerial, Underwater, and Ground Robots; Mobile Robotics Group, Oxford University 2009:  Physics Colloquium; University of Queensland COMPETITIONS 2007: Quarter Finalist in DARPA Grand Challenge ($US 2 million prize purse). I led the only Australian team to enter this competition.

This information has been contributed by Associate Professor Ben Upcroft.

Publications

For publications by this staff member, visit QUT ePrints, the University's research repository.

Research projects

Grants and projects (Category 1: Australian Competitive Grants only)

Title
Lifelong Robotic Navigation Using Visual Perception
Primary fund type
CAT 1 - Australian Competitive Grant
Project ID
DP110103006
Start year
2011
Keywords
Robotics, Computer Vision, Visual Mapping, Visual Navigation
Title
Robotics for zero-tillage agriculture
Primary fund type
CAT 1 - Australian Competitive Grant
Project ID
LP110200375
Start year
2012
Keywords
Robotics, Broad Acre Agriculture, Zero Tillage, Weed Control