Skip to end of metadata
Go to start of metadata

Current Projects

 

High to Low Level Vision

 

This project aims to enable a robot to observe the world in a truly robust way. It will achieve this by using semantic knowledge of the world to inform how the image is sensed and processed while also guiding how the scene is understood with low level visual information. 

This work is part of the $26M Australian Centre for Robotic Vision. More details for this centre can be found here.


Collaborators: Michael Milford
Postdocs: Niko Suenderhauf, Sareh Shirazi, Juxi Leitner
Students and Research Assistants: Adam Tow,  Sean McMahon, Fahimeh Rezazadegan, Fangyi Zhang, James Sergeant, Peter Kujala

 

 

Place Recognition and Localisation

 

This project addresses the challenge of developing place recognition and localisation with performance exceeding that of humans and current state of the art robotic, computer vision and artificial intelligence systems. Place recognition is a well defined but extremely challenging problem to solve in the general sense; given sensory information about a place such as a photo, can a robot decide whether that place is the same as any places it has previously visited or learnt, despite the vast range of ways in which the appearance of that place can change.

This work is part of the $26M Australian Centre for Robotic Vision. More details for this centre can be found here.


Collaborators: Michael Milford, Paul Newman
Postdocs: Niko Suenderhauf, Sareh Shirazi

Some Publications

C McManus, B Upcroft, P Newman, Scene signatures: localised and point-less features for localisation, Robotics: Science and Systems 2014

N Sunderhauf et al., Place recognition with ConvNet landmarks: Viewpoint-robust, condition-robust, training-free Robotics: Science and Systems 2015

 

Watch a demo here

Farm Robotics

 

This program, funded by the Queensland State Government - Department of Agriculture, Fisheries and Forestry (DAFF), supports the Queensland Government’s 2040 Vision to Double Agriculture Production by providing new technologies and practices that directly target increased sustainable production. Australian and international reports have identified advances in technology as the key to long-term productivity gains. This Centre is developing a new farm technology to achieve these goals - intelligent lightweight farm equipment - Farm Robotics.

 More details about this project can be found here.

Collaborators: Peter Corke, Gordon WyethDavid Ball, Tristan Perez
Postdocs: Chris McCool, Chris Lehnert, Inkyu Sa, Feras Dayoub

 

Human Cues for Robot Navigation

 

The world has many navigational cues for the benefit of humans: sign posts, maps and the wealth of information on the internet. Yet, to date, robotic navigation has made little use of this abundant symbolic information as a resource. This project will develop a robot navigation system that can navigate using information beyond the robot's range sensors by incorporating knowledge gained by reading room labels, following human route directions or interpreting maps found on the web.

 More details about this project can be found here.

Collaborators: Peter Corke, Gordon Wyeth
Postdocs: Ruth Schulz
Students: Ben Talbot 

Some Publications

 

 

 

Older Projects

Click on here for some of the projects that I used to work on.

  • No labels